ArticlePDF Available

A Survey on Cloud Gaming: Future of Computer Games

January 2016
IEEE Access 4:1-1

DOI:10.1109/ACCESS.2016.2590500

License
CC BY-NC-ND 4.0

Authors:

Wei Cai

The Chinese University of Hong Kong, Shenzhen

Chun-Ying Huang

National Yang Ming Chiao Tung University

Kuan-Ta Chen

Academia Sinica

Show all 7 authorsHide

Cloud gaming is a new way to deliver high-quality gaming experience to gamers anywhere and anytime. In cloud gaming, sophisticated game software runs on powerful servers in data centers, rendered game scenes are streamed to gamers over the Internet in real time, and the gamers use light-weight software executed on heterogeneous devices to interact with the games. Due to the proliferation of high-speed networks and cloud computing, cloud gaming has attracted tremendous attentions in both the academia and industry since late 2000's. In this paper, we survey the latest cloud gaming research from different aspects, spanning over cloud gaming platforms, optimization techniques, and commercial cloud gaming services. The readers will gain the overview of cloud gaming research and get familiar with the recent developments in this area.

Typical cloud gaming services.

…

Our proposed classification system of cloud gaming papers.

…

Figures - uploaded by Wei Cai

Content may be subject to copyright.

Content uploaded by Wei Cai

Content may be subject to copyright.

Available via license: CC BY-NC-ND 4.0

Content may be subject to copyright.

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2016.2590500, IEEE Access

A Survey on Cloud Gaming: Future of Computer

Games

Wei Cai, Member, IEEE, Ryan Shea, Member, IEEE, Chun-Ying Huang, Member, IEEE, Kuan-Ta Chen, Senior

Member, IEEE, Jiangchuan Liu, Senior Member, IEEE, Victor C. M. Leung, Fellow, IEEE,

and Cheng-Hsin Hsu, Senior Member, IEEE,

Abstract—Cloud gaming is a new way to deliver high-quality

gaming experience to gamers anywhere and anytime. In cloud

gaming, sophisticated game software runs on powerful servers

in data centers, rendered game scenes are streamed to gamers

over the Internet in real-time, and gamers use light-weight

software executed on heterogeneous devices to interact with the

games. Due to the proliferation of high-speed networks and cloud

computing, cloud gaming has attracted tremendous attentions in

both the academia and industry since late 2000’s. In this article,

we survey the latest cloud gaming research from different aspects,

spanning over cloud gaming platforms, optimization techniques,

and commercial cloud gaming services. The readers will gain

the overview of cloud gaming research and get familiar with the

recent developments in this area.

Index Terms—Clouds, distributed computing, video coding,

quality of service, computer graphics

I. INT ROD UC TI ON

Cloud gaming refers to a new way to deliver computer

games to users, where computationally complex games are

executed on powerful cloud servers, the rendered game scenes

are streamed over the Internet to gamers with thin clients

on heterogeneous devices, and the control events from input

devices are sent back to cloud servers for interactions. Figure 1

presents how cloud gaming services work. In the cloud, a

cloud gaming platform is hosted on cloud servers in one

or multiple data centers. The cloud gaming platform runs

computer game programs, which can be roughly divided into

two major components: (i) game logic that is responsible

to convert gamer commands into in-game interactions, and

(ii) scene renderer that generates game scenes in real-time.

The gamer commands come from the command interpreter,

and the game scenes are captured by video capturer into

videos, which are then compressed by video encoder. The

command interpreter, video capturer, and video encoder are

all implemented as parts of the cloud gaming platform. As

shown in this ﬁgure, the cloud gaming platform sends the

video frames to, and receives user inputs from thin clients used

by gamers for playing games. It is a thin client, because only

W. Cai and V. Leung are with the Department of Electrical and Computer

Engineering, University of British Columbia, Vancouver, Canada.

R. Shea and J. Liu are with the School of Computing Science, Simon Fraser

University, Burnaby, Canada.

C. Huang is with the Department of Computer Science, National Chiao

Tung University, Hsin-Chu, Taiwan.

K. Chen is with the Institute of Information Science, Academia Sinica,

Taipei, Taiwan.

C. Hsu is with the Department of Computer Science, National Tsing Hua

University, Hsin-Chu, Taiwan.

two low-complexity components are required: (i) command

receiver, which connects to the game controllers, such as

gampads, joysticks, keyboards, and mouses, and (ii) video

decoder, which can be realized using massively produced

(inexpensive) decoder chips. The communications between the

cloud game platform and thin clients are over the best-effort

Internet, which in turn makes supporting real-time computer

games quite challenging.

In late 2000’s, we started to see cloud gaming services

offered by startups, such as OnLive [67], Gaikai [27], G-

cluster [26], and Ubitus [93]. We also witnessed that Gaikai

was acquired by SONY, which is a major game console

developer [86]. This was followed by the competition between

Sony’s PlayStation Now (PS Now) [68] and Nvidia’s Grid

Game Streaming Service [65], which further heats up the

cloud gaming market. In fact, a 2014 report from Strategy

Analytics [75] indicates that the number of cloud gaming users

increases from 30 millions in 2014 to 150 millions in 2015.

The same report also predicts that other leading game console

manufactures will soon join the cloud gaming market.

The tremendous popularity of cloud gaming may be at-

tributed to several potential advantages to gamers, game de-

velopers, and service providers. For gamers, cloud gaming

enables them to: (i) have access to their games anywhere and

anytime, (ii) purchase or rent games on-demand, (iii) avoid

regularly upgrading their hardware, and (iv) enjoy unique

features such as migrating across client computers during

game sessions, observing ongoing tournaments, and sharing

game replays with friends. For game developers, cloud gaming

allows them to: (i) concentrate on a single platform, which in

turn reduces the porting and testing costs, (ii) bypass retailers

for higher proﬁt margins, (iii) reach out to more gamers, and

(iv) avoid piracy as the game software is never downloaded

to client computers. For service providers, cloud gaming: (i)

leads to new business models, (ii) creates more demands on

already-deployed cloud resources, and (iii) demonstrates the

potential of other/new remote execution applications, since

cloud gaming imposes the strictest constraints on various

computing and networking resources.

Despite the great opportunities of cloud gaming, several cru-

cial challenges must be addressed by the research community

before it reaches its full potentials to attract more gamers,

game developers, and service providers. We summarize the

most important aspect as follows. First, cloud gaming plat-

forms and testbeds must be built up for comprehensive perfor-

mance evaluations. The evaluations include measurements on

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

Fig. 1. Typical cloud gaming services.

Quality of Service (QoS) metrics, such as energy consumption

and network metrics, and Quality of Experience (QoE) met-

rics, such as gamer perceived experience. Building platforms

and testbeds, designing the test scenarios, and carrying out

the evaluations, require signiﬁcant efforts, while analyzing the

complex interplay between QoS and QoE metrics is even more

difﬁcult.

Second, the resulting platforms and evaluation procedures

allow the research community to optimize various components,

such as cloud servers and communication channels. More

speciﬁcally, optimization techniques for: (i) better resource

allocation and distributed architecture are possible at cloud

servers, and (ii) optimal content coding and adaptive trans-

missions are possible in communication channels.

Third, computer games are of various game genres [19].

These genres can be categorized on the basis of two elements:

viewpoint and theme.Viewpoint is how a gamer observe the

game scene. It determines the variability of rendered video

on the screen. Most commonly seen viewpoints include ﬁrst-

person, second-person, third-person, and omnipresent. First-

person games adopt graphical perspectives rendered from the

viewpoint of the in-game characters, such as in Counter-Strike.

Second-person games are rendered from the back of the in-

game characters, so that gamers can see the characters on

the screen, like in Grand Theft Auto. Third-person games

ﬁx the gamers’ views on 3D scenes, projected onto 2D

spaces. Modern third-person games usually adopts the sky

view, also known as God view. Classic third-person games

include Diablo, Command & Conquer, FreeStyle, and etc.

Last, omnipresent enables gamers to fully control views on

the region of interest (RoI) from different angels and dis-

tances. Many recent war games, e.g., Age of Empires 3,

Stronghold 2, and Warcraft III, fall into this category. Game

theme determines how gamers interact with game content.

Common themes include shooting, ﬁghting, sports, turn-based

role-playing (RPG), action role-playing (ARPG), turn-based

strategy, real-time strategy (RTS), and management simulation.

Although the viewpoint may be restricted by game theme,

but generally a game genre can be describe by a pair of

viewpoint and theme, such as ﬁrst-person shooting, third-

person ARPG, omnipresent RTS, and etc. Among them, fast-

paced ﬁrst-person shooting games impose the highest scene

complexity, which are the most challenging games for cloud

gaming service providers. In contrast, third-person turn-based

RPG games are least sensitive to delays and thus more suitable

for cloud gaming.

Cloud gaming is an exciting research area and the existing

literature aims to address several aforementioned challenges.

Nonetheless, to the best of our knowledge, there is no com-

prehensive survey on cloud gaming research. The lack of a

central survey of existing literature may delay or even prevent

researchers, who are interested in cloud gaming or other

remote execution applications, from joining the community. A

thorough understanding and exploration of existing academic

and industrial research and development can help lead to the

building of future cloud gaming platforms. One such advance

might come from future games being designed speciﬁcally

with cloud gaming functionalities and supports in mind. How

we accomplish this is still an open question, for example

game developers could create cloud gaming aware contexts

or even whole new programing paradigms. With this in mind,

we carefully connect existing research on solving current

challenges together, and come up with a classiﬁcation system

described below.

A. Scope and Classiﬁcations

In the current article, we survey the cloud gaming literature.

We ﬁrst collect representative cloud gaming papers, and group

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

them into several classiﬁcations. We emphasize that only a

selective set of papers are surveyed, in order to give the readers

better understanding on the landscape of the cloud gaming

research. Upon selecting the representative papers, we propose

a classiﬁcation system as summarized in Figure 2. More details

on the classiﬁcation system follow.

1) Cloud Gaming Overview (Section II): We survey the

overview, introductory, and positioning papers on either

general cloud gaming, or specialized topics, such as

mobile cloud gaming and Game-as-a-Service (GaaS).

2) Cloud Gaming Platforms (Section III): We consider

papers that construct basic cloud gaming platforms,

which support different performance evaluation method-

ologies. These studies can be further categorized into

three groups: system integration, QoS evaluations, and

QoE evaluations.

a) System Integration (Section III-A): The funda-

mental step of cloud gaming research, like many

other systems areas, is to put up basic platforms,

based on existing tools. We summarize such system

integration efforts, which serve as cornerstones of

related research.

b) Quality of Service Evaluations (Section III-B):

We survey the studies on objective metric evalu-

ations, which algorithmically quantify the system

performance, i.e., without subject assessments. Ex-

isting papers focus on two types of objective met-

rics, Energy Consumption and Network Metrics.

The energy consumption is critical to mobile cloud

gaming clients, in order to prolong the precious

battery life. There are several network metrics

affecting the gamer experience, and interaction

latency is a representative network metric. The

interaction latency refers to the time difference

between a gamer input and the corresponding

game scene update on the client computer. Be-

cause gamers are highly sensitive to interaction

latency [19], its measurement methodologies draw

a lot of attentions in the literature.

c) Quality of Experience Evaluations

(Section III-C): We discuss the papers on

subjective metric evaluations, which are based

on user studies, where subject gamers give

opinion scores to their cloud gaming experience.

Conducting user studies is inherently expensive

and tedious, and thus most QoE studies attempt

to analyze the relationship between the QoS and

QoE metrics. The resulting models may in turn be

used to optimize cloud gaming platforms.

3) Optimizing Cloud Gaming Platforms (Section IV):

We consider papers that optimize cloud gaming plat-

forms from speciﬁc aspects; usually each work focuses

on optimizing one or a few components. Such studies

can be further categorized into two groups: cloud server

infrastructure and communications.

a) Cloud Server Infrastructure (Section IV-A):

The existing studies on optimizing cloud server

infrastructure are surveyed. Several papers study

the Resource Allocation problem of server and

network resources among multiple data centers,

server nodes, and game clients to optimize the

overall cloud gaming experience, where diverse

criteria are considered. Other papers optimize the

Distributed Architectures of cloud gaming plat-

forms, e.g., using Peer-to-Peer (P2P) overlays or

multi-tier clouds for better performance and scala-

bility.

b) Communications (Section IV-B): We survey

the existing work on optimizing the efﬁciency of

content streaming over the dynamic and heteroge-

neous communication channels. These studies are

further classiﬁed into two groups. First, several pa-

pers consider the problem of Data Compression,

e.g., layered coding and graphics compression are

proposed, which may outperform the conventional

2D image compression in certain environments.

Second, there are papers on Adaptive Transmis-

sion, which cope with the network dynamics by

continuously changing various parameters, such as

encoding bitrate, frame rate, and image resolution.

The same adaptive transmissions may also be used

to absorb the negative impacts due to insufﬁcient

resources on cloud servers and game clients.

4) Commercial Cloud Gaming Services (Section V):

We survey the representative commercial cloud gaming

services, and classify them along different aspects. We

also discuss the advantages and disadvantage of different

cloud gaming services.

In the rest of this article, we survey the four classes of

papers in Sections II–V. They are followed by Section VI,

which concludes the survey.

II. CL OU D GAM IN G OVE RVIEW PAP ER S

As a promising cloud service provisioning paradigm, cloud

gaming has attracted interests from prominent research teams

all over the world. These teams have shared their thoughts

and ideas on cloud gaming from their viewpoints in several

high-level overview papers. In this section, we survey and

summarize the representative papers along this direction. Our

concise summary puts readers into the context of cloud gaming

research, while interested readers may ﬁnd new research

directions in the surveyed overview papers.

Ross [74] is the ﬁrst literature that introduces the cloud

gaming model to the academia in 2009, nine years after the

G-cluster’s demonstration of cloud gaming technology at E3.

The author describes gaming as cloud computing’s killer app

and depicts the blueprint of novel gaming delivery paradigm,

proposed by Advanced Micro Devices (AMD), which renders

games’ scene videos, compresses them, and transmit them to

the gamers through the Internet. This approach enables online

gamers to ofﬂoad their graphic rendering tasks to the cloud,

thus, eliminates the computational workload on gamers’ local

platforms. This is the most popular deﬁnition of cloud gaming

adopted by most of the research work in this area. However,

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

Fig. 2. Our proposed classiﬁcation system of cloud gaming papers.

a recent publication [59] provides a more general deﬁnition,

by envisioning the cloud gaming system as a novel computer

architecture that leverages cloud resources to improve gaming

performance, such as rendering, response time, precision and

fairness. The authors distribute system workload to multiple

cloud servers and game clients to enable this vision. For a

further step, Cai et al. [4] explore the essence of cloud games

as inter-dependent components, thus, deﬁne cloud gaming as

utilizing cloud resources to host gaming components, thereby

reducing workload at gamers’ local platforms and increasing

the overall system performance. According to different inte-

gration approach of the cloud, the authors identify and discuss

the research directions of three cloud gaming architectures,

which are Remote Rendering,Local Rendering, and Cognitive

Resource Allocation.

After the ofﬁcial launch of OnLive in March 2010, the

business model for cloud gaming becomes a hot topic in

research society. Riungu-kalliosaari et al. [73] conduct in-

terviews in small and medium size gaming companies to

qualitatively study the adoption dynamics of cloud computing

. With grounded theory method, the authors observe that the

concept of cloud gaming are relatively well-known in the

industry, while gaming organizations still hesitate in adopting

cloud computing services and technologies due to the lack of

clear business models and success stories. To this end, Ojala

and Tyrvainen [66] start their investigations on developing

business models for cloud gaming services. As a case study

for Software as a Service (SaaS), the authors select G-cluster,

one of famous cloud gaming companies, and study its business

model over ﬁve years from 2005 to 2010. They conclude

that, over time, the business model in cloud gaming becomes

simpler and has fewer actors, which increases the revenue

per gamer. In addition, they also expect the cloud gaming

solution will make illegal copying practically impossible.

Another work [61] considers the convergence of mobile cloud

in gaming industry from a business model proposition. The

authors discuss the ﬁrst sketch of a possible business model of

Kusanagi project, a proposed end-to-end infrastructure, from

domains of service, technology, organization, and ﬁnancial,

while compare these domains of three cloud examples, i.e.,

G-cluster, Gaikai, and OnLive.

During the decade of development, there have been cloud

gaming systems and services in the market. A number of

positioning papers consider these systems and envision the

opportunities, challenges, and directions in this area. The lit-

erature, e.g., [23], [85], [100], [4], [59], [11], [17], covers both

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

the commercial and academic platforms, while their concerns

of open issues are greatly overlapped in the topics of response

time minimization, graphical video encoding, network aware

adaption, QoE optimization, and cloud resource management.

Besides of these common focuses, each research team has

particular interests and directions. Dey et al. [23] concentrate

on developing device aware scalable applications, which in-

volve open issues of extending cloud to wireless networks.

Soliman et al. [85] brieﬂy discuss related legal issues, in-

cluding patents, ownership concerns, guaranteed service levels,

and pricing schemes. In contrast, piracy and hacking may no

long be an issue, since the executable game program will

not be delivered to the gamers. Wu [100] explores cloud

gaming architecture from the aspect of cloud computing’s

three layers, i.e., IaaS, SaaS and PaaS. The author identiﬁes

security as a potential challenge in cloud gaming, especially

data protection and location. Cai et al. [4] investigate the

features of different game genres and identify their impact

on cloud gaming system design. In addition, they provide

a vision on GaaS provisioning for mobile devices. Mishra

et al. [59] explain how to enhance the quality of online

gaming by integrating techniques from cloud gaming research

communities. Featured topics include the interplay between

QoS and QoE metrics, game models, and cloud expansion.

Chen et al. [11] point out some unique research directions in

cloud gaming, such as game integration, visualization, user

interface, server selection, and resource scheduling. Chuan et

al. [17] study cloud gaming from a green media perspective.

They discuss the major cloud gaming subsystems with green

designs, which include a cloud data centre, graphics rendering

modules, video compression techniques, and network delivery

methods.

In addition to these high-level studies, more cloud gaming

papers focus on individual research problems. We divide them

into several classiﬁcations and survey them in the following

sections.

III. CLO UD GA MI NG PL ATFO RM S

This section presents the work related to cloud gaming

platforms in three steps: (i) integrated cloud gaming platforms

for complete prototype systems, (ii) measurement studies on

QoS metrics, and (iii) measurement studies on QoE metrics.

A. System Integration

Providing an easy-to-use platform for (cloud) game devel-

opers is very challenging. This is because of the complex,

distributed, and heterogeneous nature of the cloud gaming plat-

forms. In fact, there is a clear tradeoff between development

complexity and optimization room. Platforms opt for very low

(or even no) additional development complexity may suffer

from limited room for optimization, which are referred to as

transparent platforms that run unmodiﬁed games. In contrast,

other platforms opt for more optimized performance at the

expense of requiring additional development complexity, such

as code augmentation and recompilation, which are called

non-transparent platforms. These two classes of cloud gaming

platforms have advantages and disadvantages, and we describe

representative studies in individual classes below.

The transparent platforms ease the burden of deploying new

games on cloud gaming platforms, at the expense of potentially

suboptimal performance. Depasquale et al. [22] present a

cloud gaming platform based on the RemoteFX extension of

Windows remote desktop protocol. Modern Windows servers

leverage GPUs and Hyper-V virtual machines to enable vari-

ous remote applications, including cloud games. Their experi-

ments reveal that RemoteFX allows Windows servers to better

adapt to network dynamics, but still suffers from high frame

loss rate and inferior responsiveness. Kim et al. [44] propose

another cloud gaming platform, which consists of a distributed

service platform, a distributed rendering system, and an en-

coding/streaming system. Their platform supports isolated

audio/video capturing, multiple clients, and browser-based

clients. Real experiments with 40 subjects have been done,

showing high responsiveness. Both Depasquale et al. [22] and

Kim et al. [44] are proprietary platforms, and are less suitable

for cloud gaming research. GamingAnywhere [40], [38] is

the ﬁrst open source transparent cloud gaming platform. Its

design principles can be summarized as extensive, portable,

conﬁgurable, and open. The GamingAnywhere server supports

Windows and Linux, and the GamingAnywhere client runs

on Windows, Linux, Mac OS, and Android. It is shown that

GamingAnywhere outperforms several commercial/proprietary

cloud gaming platforms, and has been used and enhanced in

several cloud gaming studies in the literature. For example,

Hong et al. [35] develop adaptation algorithms for multiple

gamers, to maximize the gamer experience. In addition to: (i)

a user study to map cloud gaming parameters to gamer expe-

rience and (ii) optimization algorithms for resource allocation,

they also enhance GamingAnywhere [40], [38] to support on-

the-ﬂy adaption of frame rate and bitrate.

The non-transparent platforms require augmenting and re-

compiling existing games to leverage unique features for better

gaming experience, which may potentially be time-consuming,

expensive, and error-prone. For example, current games can be

ported to Google’s Native Client technology [63], [62] or to

Mozilla’s asm.js language [1], [24]. Several other studies focus

on integrating new techniques with cloud gaming platforms for

better gaming experience. Nan et al. [64] propose a joint video

and graphics streaming system for higher coding efﬁciency as

well. Moreover, they present a rate adaptation algorithm to

further minimize the bandwidth consumption. Lee et al. [49],

[48] present a system to improve the responsiveness of mobile

cloud gaming by compensating network delay. In particular,

their system pre-renders potential future frames based on

some prediction algorithm and delivers the rendered frames to

mobile clients when the network conditions are good. These

frames are then used to compensate late video frames due to

unstable networks. They integrate the proposed system with

two open source games, and conduct a user study of 23

subjects. The subjects report good gaming experience under

nontrivial network delay, as high as 250 ms. Cai et al. [3]

build a prototype platform for decomposed cloud gaming,

and rigorously address several system issues, which were

not thoroughly investigated in their earlier work [4]. Their

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

main contribution is the very ﬁrst cognitive cloud gaming

platform that automatically adapts to distributive workload in

run-time, in order to optimally utilize distributed resources

(on different entities, like cloud servers, in-network computing

nodes, and gamers’ local platforms) for the best gamer experi-

ence. On the resulting platform, several games are developed

and empirically evaluated, demonstrating the potentials of

cognitive cloud gaming platforms. Several enhancements on

such a platform are still possible, such as implementing more

sophisticated games, supporting more gamers, and providing

more completed SDK (Software Development Kit) to cloud

game developers.

B. Quality of Service Evaluations

Performing QoS measurements is crucial for quantifying the

performance of the cloud gaming platforms. Moreover, doing

so in real-time allows us to effectively troubleshoot and even

to dynamically optimize the cloud gaming platforms. The QoS

related cloud gaming papers are roughly categorized into two

classes: (i) energy consumption and (ii) network metrics. They

are surveyed in the following.

1) Energy Consumption: Games have been known to push

consumer computing platforms to their maximum capacity.

In traditional systems such as desktop computers, it is often

expected and accepted that Game software will push a system

to its limits. However, mobile environments are in a strikingly

different scenario as they have limited power reserves. A

fully utilized mobile device may have a greatly reduced

running time, thus it is important to reduce the complexity

of these game software for mobile devices. Luckily, cloud

gaming systems provide a potential way forward by ofﬂoading

complicated processing tasks such as 3D rendering and physics

calculations to powerful cloud servers. However, cares must be

taken because the decoding of video, especially high deﬁnition

video is far from a trivial task. We will cover some pioneering

work [29], [91], [39] that has been done on this important

subject.

Hans et al. [29] systematically test the energy performance

of their in-house cloud gaming server MCGS.KOM on real

world tablets. They ﬁnd that when WLAN was used as the

access network, cloud game software could save between 12%

and 38% of energy use, depending on the types of games

and tablets. Explorations on important energy saving coding

parameters for H.264/AVC are reported in Taher et al. [91].

Further, Huang et al. [39] explore the energy consumption

of the cloud gaming video decoders. The researchers found

that frame rate has the largest impact on the decoders energy

consumption, with bit rate and resolution also being major

contributors. Moreover, Shea et al. [79] explore the perfor-

mance and energy implications of combing cloud gaming

systems with live broadcasting systems such as Twitch.

2) Network Metrics: Like many other distributed multime-

dia applications, user experience highly depends on network

conditions. Therefore, evaluating different network metrics in

cloud gaming is crucial, and we present detailed survey below.

Claypool [18] measures the contents variety of different

game genres in details. 28 games from 4 perspectives, includ-

ing First-Person Linear,Third-Person Linear,Third-Person

Isometric, and Omnipresent, are selected to analyze their

scene complexity and motion, indicated by average Intra-coded

Block Size (IBS) and Percentage of Forward/backward or

Intra-coded Macroblocks (PFIM), respectively. Measurements

conducted by the author suggest that Microsoft’s remote

desktop achieves better bitrate than NoMachine’s NX client,

while NX client has higher frame rate. A following work

[21] investigates OnLive’s network characteristics, such as the

data size and frequency being sent and the overall downlink

and uplink bitrates. The authors reveal that the high downlink

bitrates of OnLive games are very similar to those of live

videos, nevertheless, OnLive’s uplink bitrates are much more

moderate, which are comparable to traditional game uplink

trafﬁc. They also indicate that the game trafﬁc features are

similar for three types of game genres, including First-Person,

Third-Person, and Omnipresent, while the total bitrates can

vary by as much as 50%. Another important ﬁnding is that

OnLive does not demonstrate its ability in adapting bitrate

and frame rates to network latency.

Chen et al. [10] analyze a cloud gaming system’s re-

sponse delays and segment it into three components, including

network delay, processing delay, and playout delay. With

this decomposition, the authors propose a methodology to

measure the latency components and apply the methodology

on OnLive and StreamMyGame, two of the popular cloud

gaming platforms. The authors identify that OnLive system

outperforming StreamMyGame in terms of latency, due to the

different resource provisioning strategy based on game genres.

A following work [9] by the same group extend the model by

adding game delay, which represents the latency introduced

by the game program to process commands and render the

next video frame of the game scene. They also study how

system design and selective parameters affect responsiveness,

including scene complexity, updated region sizes, screen reso-

lutions, and computation power. Their observation in network

trafﬁcs are inline with previous work conducted by Claypool

et al. [21]. Lower network quality, including the higher packet

loss rate and insufﬁcient bandwidth, will impose negative

impacts on both of OnLive and StreamMyGame, resulting

lower frame rates and worse graphic quality. Moreover, by

quantifying the streaming quality, the authors further reveal

that OnLive implements an algorithm to adapt its frame rate

to the network delay, while StreamMyGame doesn’t.

Manzano et al. [55] collect and compare network trafﬁc

traces of OnLive and Gaikai, including packet inter-arrival

times, packet size, and packet inter-departure time, to observe

the difference between cloud gaming and traditional online

gaming from the perspectives of network load and trafﬁc

characteristics. The authors reveal that the package size dis-

tributions between the two platforms are similar, while the

packet inter-arrival times are distinct. Afterwards, Manzano et

al. [56] claim to be the ﬁrst research work on speciﬁc network

protocols used by cloud gaming platforms. They focus on

conducting a reverse engineering study on OnLive, based on

extensive trafﬁc traces of several games. The authors further

propose a per-ﬂow trafﬁc model for OnLive, which can be

used for network dimensioning, planning optimization, and

other studies.

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

Shea et al. [81] measure the interaction delay and image

quality of OnLive system, under diverse games, computers,

and network conﬁgurations. The authors conclude that cloud

procedure introduces 100 to 120 ms latency to the overall

system, which requires further developments in both video

encoders and streaming software. Meanwhile, the impacts of

compression mechanism on video quality are quite notice-

able, especially under the circumstances with lower available

bandwidth. They later present an experimental study [80]

on the performance of existing commercial games and ray-

tracing applications with graphical processing units (GPUs).

According to their analysis, gaming applications in virtual-

ized environments demonstrate poorer performance than the

instances executing in non-virtualized bare-metal baseline.

Detailed hardware proﬁling further reveals that the pass-

through access introduces memory bottleneck, especially for

those games with real-time interactions. Another work [36],

however, observes more advanced virtualization technologies

such as mediated pass-through maintain high performance in

virtualized environments. In the authors’ measurement work,

rendering with virtualized GPUs may achieves better perfor-

mance than direct pass-through ones. In addition, if the system

adopts software video coding, the CPU may became the

bottleneck, while hypervisor will no longer be the constraint of

the system performance. Based on these analysis, the authors

conclude that current virtualization techniques are already

good enough for cloud gaming.

Suznjevic et al. [89] measure 18 games on GamingAny-

where [38] to analyze the correlation between the charac-

teristics of the games played and their network trafﬁc. The

authors observe the highest values for motion, action game

and shooter games, while the majority of strategy games are

relatively low. In contrast, for spatial metrics the situation is

reversed. They also conclude that the bandwidth usage for

most games are within the range of 3 and 4 Mbit/s, except the

strategy games that consume less network resources. Another

notable ﬁnding is that, gamers’ action rate will introduce a

slight packet rate increase, but will not affect the generated

network trafﬁc volume.

Lampe et al. [46] conduct experimental evaluations of user-

perceived latency in cloud games and locally executed video

games. Their results, produced by a semi-automatic mea-

surement tool called GALAMETO.KOM, indicate that cloud

gaming introduces additional latency to game programs, which

is approximately 85% to 800% higher than local executions.

This work also features the signiﬁcant impact of round-trip

time. The measurement results conﬁrm the hypothesis that the

geographical placement of cloud data centres is an important

element in determining response delay, speciﬁcally when the

cloud gaming services are accessed through cellular networks.

Xue et al. [102] conduct a passive and active measurement

study for CloudUnion, a Chinese cloud gaming system. The

authors characterize the platform from the aspects of archi-

tecture, trafﬁc pattern, user behaviour, frame rate and gaming

latency. Observations include: (i) CloudUnion adopts a geo-

distributed infrastructure; (ii) CloudUnion suffers from a queu-

ing problem with different locations from time to time; (iii) the

User Datagram Protocol (UDP) outperforms the Transmission

Control Protocol (TCP) in terms of response delay while

sacriﬁcing the video quality; and (iv) CloudUnion adopts con-

servative video rate recommendation strategy. By comparing

CloudUnion and GamingAnywhere [38], the authors observe

four common problems. First, the uplink and downlink data

rates are asymmetric. Second, low-motion games perceive a

periodical jitter at the interval of 10 seconds. Third, audio

and video streams are suffering from synchronization problem.

Fourth, packet loss in network transmission degrades gaming

experiences signiﬁcantly.

C. Quality of Experience Evaluations

Measuring and modeling cloud gaming QoE are no easy

tasks because QoE metrics are subjective. In particular, enough

subjects need to be recruited, and time-consuming, tedious,

and expensive user studies need to be carried out. After that,

practical models to relate the QoS and QoE metrics need to

be proposed, trained, and evaluated. Only when the resulting

models are validated with large datasets, they can be employed

in actual cloud gaming platforms. Cloud gaming QoE has

been studied in the literature and can be categorized into two

classes: (i) general cloud gaming QoE evaluations, and (ii)

mobile cloud gaming QoE evaluations, which are tailored for

mobile cloud games, where mobile devices are resource con-

strained and vulnerable to inferior wireless network conditions.

We survey the related work in these two classes below.

Chang et al. [8] present a measurement and modeling

methodology on cloud gaming QoE using three popular remote

desktop systems. Their experiment results reveal that the

QoE (in gamer performance) is a function of frame rate and

graphics quality, and the actual functions are derived using

regression. They also show that different remote desktop sys-

tems lead to quite diverse QoE levels under the same network

conditions. Jarschel et al. [42] present a testbed for a user study

on cloud gaming services. Mean Opinion Score (MOS) values

are used as the QoE metrics, and the resulting MOS values are

found to depend on QoS parameters, such as network delay

and packet loss, and context, such as game genres and gamer

skills. Their survey also indicates that very few gamers are

willing to commit themselves in a monthly fee plan for cloud

gaming. Hence, better business models are critical to long-

term success of cloud gaming. Moller et al. [60] also conduct

a subjective test in the labs, and consider 7 different MOS

values: input sensitivity, video quality, audio quality, overall

quality, complexity, pleasantness, and perceived value. They

observe complex interplays among QoE metrics, QoS metrics,

testbed setup, and software implementation. For example, the

rate control algorithm implemented in cloud gaming client is

found to interfere with the bandwidth throttled by a trafﬁc

shaper. Several open issues are raised after analyzing the

results of the user study, partially due to the limited number

of participants. Slivar et al. [84] carry out a user study of in-

home cloud gaming, i.e., the cloud gaming servers and clients

are connected over a LAN. Several insights are revealed, e.g.,

switching from a standard game client to in-home cloud gam-

ing client leads to QoE degradation, measured in MOS values.

Moreover, more skilled gamers are less satisﬁed with in-home

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

cloud gaming. Hossain et al. [37] adopt gamer emotion as a

QoE metric and study how several screen effects affect gamer

emotion. Sample screen effects include adjusting: (i) redness,

(ii) blueness, (iii) greenness, (iv) brightness, and (v) contrast;

and the goal of applying these screen effects is to mitigate

negative gamer emotion. They then perform QoE optimization

after deriving an empirical model between screen effects and

gamer emotion.

Some other QoE studies focus on the response delay, which

is probably the most crucial performance metric in cloud

gaming, where servers may be geographically far away from

clients. Lee et al. [50] ﬁnd that response delay imposes

different levels of implications on QoE with different game

genres. They also develop a model to capture this implication

as a function of gamer inputs and game scene dynamics. Quax

et al. [71] make similar conclusions after conducting extensive

experiments, e.g., gamers playing action games are more

sensitive to high responsive delay. Claypool and Finkel [20]

perform user studies to understand the objective and subjective

effects of network latency on cloud gaming. They ﬁnd that

both MOS values and gamer performance degrade linearly

with network latency. Moreover, cloud gaming is very sensitive

to network latency, similar to the traditional ﬁrst-person avatar

games. Raaen [72] designs a user study to quantify the smallest

response delay that can be detected by gamers. It is observed

that some gamers can perceive <40 ms response delay, and

half of the gamers cannot tolerate ≥100 ms response delay.

Haung et al. [41] perform extensive cloud gaming exper-

iments using both mobile and desktop clients. Their work

reveals several interesting insights. For example, gamers’

satisfaction on mobile clients are more related to graphics

quality, while the case on desktop clients is more correlated to

control quality. Furthermore, graphics and smoothness qual-

ity are signiﬁcantly affected by the bitrate, frame rate, and

network latency, while the control quality is determined only

by the client types (mobile or desktop). Wang and Dey [94],

[97] build a mobile cloud gaming testbed in their lab for

subjective tests. They propose a Game Mean Opinion Score

(GMOS) model, which is a function of game genre, streaming

conﬁguration, measured Peak Signal-to-Noise Ratio (PSNR),

network latency, and packet loss. The derivations of model

parameters are done via ofﬂine regression, and the resulting

models can be used for optimizing mobile cloud gaming

experience. Along this line, Liu et al. [54] propose a Cloud

Mobile Rendering–Mean Opinion Score (CMR-MOS) model,

which is a variation of GMOS. CMR-MOS has been used in

selecting detail levels of remote rendering applications, like

cloud games.

IV. OPT IM IZ IN G CLO UD GA MI NG PL ATFORM S

This section surveys optimization studies on cloud gaming

platforms, which are further divided into two classes: (i) cloud

server infrastructure and (ii) communications.

A. Cloud Server Infrastructure

To cope with the staggering demands from the massive

number of cloud gaming users, carefully-designed cloud server

infrastructures are required for high-quality, robust, and sus-

tainable cloud gaming services. Cloud server infrastructures

can be optimized by: (i) intelligently allocating resources

among servers or (ii) creating innovative distributed structures.

We detail these two types of work in the following.

1) Resource Allocation: The amount of resources allocated

to high performance multimedia applications such as cloud

gaming continues to grow in both public and private data

centers. The high demand and utilization patterns of these plat-

forms make the smart allocation of these resources paramount

to the efﬁciency of both public and private clouds. From

Virtual Machine (VM) placement to shared GPUs, researchers

from many areas have been exploring how to efﬁciently use

the cloud to host cloud gaming platforms. We now explore

the important work done in this area to facilitate efﬁcient

deployment of cloud gaming platforms.

Critical work has been done on both VM placement and

cloud scheduling to facilitate better quality of cloud gaming

services. For example, Wang et al. [98] show that, with

proper scheduling of cloud instances, cloud gaming servers

could be made wireless networking aware. Simulations of

their proposed scheduler show the potential of increased

performance and decreased costs for cloud gaming platforms.

Researchers also explore making resource provisioning cloud

gaming aware. For example, a novel QoE aware VM place-

ment strategy for cloud gaming is developed [33]. Further,

research has been done to increase the efﬁciency of re-

source provisioning for massively multi-player online games

(MMOG) [57]. The researchers develop greedy heuristics to

allocate the minimum number of computing nodes required

to meet the MMOG service needs. Researchers also study the

popularity of games on the cloud gaming service OnLive and

propose methods to improve performance of these systems

based on game popularity [25]. Later, a resource allocation

strategy [51] based on the expected ending time of each

play session is proposed. The strategy can reduce the cost of

operation to cloud gaming providers by reducing the number

of purchased nodes required to meet their clients needs. They

note that classical placement algorithms such as First Fit and

Best Fit, are not effective for cloud gaming. After extensive

experiments, the authors show an algorithm leveraging on

neural-network-based predictions, which could improve VM

deployment, and potentially decreases operating costs.

Although many cloud computing workloads do not require

a dedicated GPU, cloud gaming servers require access to a

rendering device to provide 3D graphics. As such VM and

workload placements have been researched to ensure cloud

gaming servers have access to adequate GPU resources. Kim et

al. [45] propose a novel architecture to support multiple-view

cloud gaming servers, which share a single GPU. This archi-

tecture provides multi-focal points inside a shared cloud game,

allowing multiple gamers to potentially share a game world,

which is rendered on a single GPU. Zhao et al. [104] perform

an analysis of the performance of combined CPU/GPU servers

for game cloud deployments. They try ofﬂoading different

aspects of game processing to these cloud servers, while

maintaining some local processing at the client side. They

conclude that keeping some processing at the client side may

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

lead to an increase in QoS of cloud gaming platforms.

Pioneering research has also been done on GPU sharing and

resource isolation for cloud gaming servers [70], [103]. These

works show that with proper scheduling and allocation of re-

sources we can maximize GPUs utilization, while maintaining

high performance for the gamers sharing a single GPU. Shea

and Liu [80] show that direct GPU assignment to a virtualized

gaming instance can lead to frame rate degradation of over

50% in some gaming applications. They ﬁnd that the GPU

device pass-through severely diminishes the data transfer rate

between the main memory and the GPU. Their follow-up work

using more advanced platforms [78] reveals that although the

memory transfer degradation still exists, it no longer affects

the frame rate of current generation games. Hong et al. [34]

perform a parallel work, where they discover that the frame

rate issue presents in virtualized clouds may be mitigated by

using mediated pass-through, instead of direct assignment.

In addition, work has been done to augment existing clouds

and games to improve cloud gaming efﬁciency. It has been

shown that using game engine information can greatly re-

duce the resources needed to calculate the motion estimation

(ME) needed for conventional compression algorithms such as

H.264/AVC [76]. Research into these technique shows that we

can accelerate the motion estimation phase by over 14% if we

use in-game information for encoding. Others have proposed

using reusable modules for cloud gaming servers [30]. They

refer to these reusable modules as substrates and test the

latency between the different components. All these data

compression studies affect resource allocation; we provide a

comprehensive survey on data compression for cloud gaming

in Section IV-B1.

2) Distributed Architectures: Due to the vast geographic

distribution of the cloud gaming clients the design of dis-

tributed architectures is of critical importance to the deploy-

ment of cloud gaming systems. The design of these systems

must be carefully optimized to ensure that a cloud gaming

system can sufﬁciently cover its target audience. Further,

to maintain the extremely low delay tolerance required for

high QoE even the placement of different server components

must be optimized for the lowest possible latency. These

innovative distributed architectures have been investigated in

the literature, and we detail them below.

Suselbeck et al. [90] discover that running a cloud gaming

based massively multi-player online game (MMOG) may

suffer from increased latency. These issues are aggravated

in a cloud gaming context because MMOG are already ex-

tremely latency sensitive applications. The increased latency

introduced by a cloud gaming may vastly decrease the playa-

bility of these games. To deal with this increased latency,

they propose a P2P based solution. Similarly, Prabu and

Purushotham [69] propose a P2P system based on Windows

Azure to support online games.

Research has also been done on issues created by the

geographical distance between the end user of cloud gaming

and a cloud gaming data center. Choy et al. [13] show that

the current geographical deployments of public data centers

leave a large fraction of the USA with an unacceptable

RTT for low latency applications such as cloud gaming.

To help mitigate this issue, they propose deploying edge

servers near some users for cloud gaming; a follow up work

further explores this architecture and shows that hybrid edge-

cloud architectures could indeed expand the reach of cloud

gaming data centers [14]. Similarly, Siekkinen and Xiao [83]

propose a distributed cloud gaming architecture with servers

deployed near local gamers when necessary. The researchers

prototype the system and show that if being deployed widely

enough, for example at the ISP level, cloud gaming could

reach an even larger audience. Tian et al. [92] perform an

extensive investigation into issues of deploying cloud gaming

architecture with distributed data centers. They focus on a

scenario where adaptive streaming technology is available to

the cloud provider. The authors give an optimization algorithm,

which can improve gamer QoE as well as reducing operating

costs of the cloud gaming provider. The algorithm is evaluated

using trace driven simulations, and the results show a potential

cost savings of 25% to the cloud gaming provider.

B. Communications

Due to the distributed nature of cloud gaming services,

the efﬁciency and robustness of the communication channels

between cloud gaming servers and clients are crucial and have

been studied. These studies can be classiﬁed into two groups:

(i) the data compression algorithms to reduce the network

trafﬁc amount and (ii) the transmission adaptation algorithms

to cope with network dynamics. We survey the work in these

two groups in the following.

1) Data Compression: After game scenes are computed on

cloud servers, they have to be captured in proper representa-

tions and compressed before being streamed over networks.

This can be done in one of the three data compression

schemes: (i) video compression, which encodes 2D rendered

videos and potentially auxiliary videos (such as depth videos)

for client side post-rendering operations, (ii) graphics com-

pression, which encodes 3D structures and 2D textures, and

(iii) hybrid compression, which combines both video and

graphics compression. Upon cloud gaming servers produce

compressed data streams, the servers send the streams to client

computers over communication channels. We survey each of

the three schemes below.

Video compression is the most widely-used data compres-

sion schemes for cloud gaming probably because 2D video

codecs are quite mature. These proposals strive to improve the

coding efﬁciency in cloud gaming, and can be further classiﬁed

into groups depending on whether in-game graphics contexts,

such as camera locations and orientations, are leveraged for

higher coding efﬁciency. We ﬁrst survey the proposals that

do not leverage graphics contexts. Cai et al. [6] propose to

cooperatively encode cloud gaming videos of different gamers

in the same game session, in order to leverage inter-gamer

redundancy. This is based on an observation that game scenes

of close-by gamers have non-trivial overlapping areas, and thus

adding inter-gamer predictive video frames may improve the

coding efﬁciency. The high-level idea is similar to multiview

video codecs, such as H.264/MVC, and the video packets

shared by multiple gamers are exchanged over an auxiliary

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

short-range ad-hoc network in a P2P fashion. Cai et al. [5]

improve upon the earlier work [6] by addressing three more

research problems: (i) uncertainty due to mobility, (ii) diversity

of network conditions, and (iii) model of QoE. These problems

are solved by a suite of optimization algorithms proposed in

their work. Sun and Wu [88] solve the video rate control

problem in cloud gaming in two steps. First, they adopt

the concept of RoI, and deﬁne heterogeneous importance

weights for different regions of game scenes. Next, they

propose a macroblock-level rate control scheme to optimize

the RoI-weighted video quality. Cheung et al. [12] propose

to concatenate the graphic renderer with a customized video

coder on servers in cellular networks and multicast the coded

video stream to a gamer and multiple observers. Their key

innovation is to leverage the depth information used in 3D

rendering process to locate the RoI and then allocate more

bits to that region. The resulting video coder is customized for

cloud gaming, yet produces standard compliant video streams

for mobile devices. Lui et al. [53] also leverage rendering

information to improve video encoding in cloud gaming for

better perceived video quality and shorter encoding time.

In particular, they ﬁrst analyze the rendering information to

identify RoI and allocate more bits on more important regions,

which leads to better perceived video quality. In addition,

they use this information to accelerate the encoding process,

especially the time used in motion estimation and macroblock

mode selection. Experiments reveal that their proposed video

coder saves 42% of encoding time and achieves perceived

video quality similar to the unmodiﬁed video coder. Similarly,

Semsarzadeh et al. [76] study the feasibility of using rendering

information to accelerate the computationally-intensive motion

estimation and demonstrate that it is possible to save 14.32%

of the motion estimation time and 8.86% of the total encoding

time. The same authors [77] then concertize and enhance their

proposed method, in which they present the general method,

well-designed programming interface, and detailed motion

estimation optimization. Both subjective and objective tests

show that their method suffers from very little quality drop

compared to the unmodiﬁed video coder. It is reported that

they achieve 24% and 39% speedups on the whole encoding

process and motion estimation, respectively.

Next, we survey the proposals that utilize graphics con-

texts [82], [101]. Shi et al. [82] propose a video compression

scheme for cloud gaming, which consists of two unique

techniques: (i) 3D warping-assisted coding and (ii) dynamic

auxiliary frames. 3D warping is a light-weight 2D post-

rendering process, which takes one or multiple reference view

(with image and depth videos) to generate a virtual view

at a different camera location/orientation. Using 3D warping

allows video coders to skip some video frames, which are

then wrapped at client computers. Dynamic auxiliary frames

refer to those video frames rendered with intelligently-chosen

camera location/orientations that are not part of the game

plays. They show that the auxiliary frames help to improve

3D warping performance. Xu et al. [101] also propose two

techniques to improve the coding efﬁciency in cloud gam-

ing. First, the camera rotation is rectiﬁed to produce video

frames that are more motion estimation friendly. On client

computers, the rectiﬁed videos are compensated with some

camera parameters using a light-weight 2D process. Second,

a new interpolation algorithm is designed to preserve sharp

edges, which are common in-game scenes. Last, we notice

that the video compression schemes are mostly orthogonal

to the underneath video coding standards, and can be readily

integrated with the recent (or future) video codecs for further

performance improvement.

Graphics compression is proposed for better scalability,

because 3D rendering is done at individual client computers.

Compressing graphics data, however, is quite challenging and

may consume excessive network bandwidth [52], [58]. Lin et

al. [52] design a cloud gaming platform based on graphics

compression. Their platform has three graphics compression

tools: (i) intra-frame compression, (ii) inter-frame compres-

sion, and (iii) caching. These tools are applied to graphics

commands, 3D structures, and 2D textures. Meilander et

al. [58] also develop a similar platform for mobile devices,

where the graphics are sent from cloud servers to proxy clients,

which then render game scenes for mobile devices. They also

propose three graphics compression tools: (i) caching, (ii)

lossy compression, and (iii) multi-layer compression. Gener-

ally speaking, tuning cloud gaming platforms based on graph-

ics compression for heterogeneous client computers is non-

trivial, because mobile (or even some stationary) computers

may not have enough computational power to locally render

game scenes.

Hybrid compression [15], [16] attempts to fully utilize

the available computational power on client computers to

maximize the coding efﬁciency. For example, Chuah and

Cheung [15] propose to apply graphics compression on sim-

pliﬁed 3D structures and 2D textures, and send them to client

computers. The simpliﬁed scenes are then rendered on client

computers, which is called the base layer. Both the full-

quality video and the base-layer video are rendered on cloud

servers, and the residue video is compressed using video

compression and sent to client computers. This is called the

enhancement layer. Since the base layer is compressed as

graphics and the enhancement layer is compressed as videos,

the proposed approach is a hybrid scheme. Based on the

layered coding proposal, Chuah et al. [16] further propose

a complexity-scalable base-layer rendering pipeline suitable

for heterogeneous mobile receivers. In particular, they employ

scalable Blinn-Phong lighting for rendering the base-layer,

which achieves maximum bandwidth saving under the comput-

ing constraints of mobile receivers. Their experiments demon-

strate that their hybrid compression solution, customized for

cloud gaming, outperforms single-layer general-purpose video

codecs.

2) Adaptive Transmission: Even though data compression

techniques have been applied to reduce the network trans-

mission rate, the ﬂuctuating network provisioning still results

in unstable service quality to the gamers in cloud gaming

system. These unpredictable factors include bandwidth, round-

trip time, jitter, and etc. Under this circumstance, adaptive

transmission is introduced to further optimize gamers’ QoE.

The foundation of these studies is based on a common sense:

gamers would prefer to scarify video quality to gain smoother

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

playing experience in insufﬁcient network QoS supplement.

Jarvinen et al. [43] explore the approach to adapt the

gaming video transmission to available bandwidth. This is

accomplished by integrating a video adaptation module into

the system, which estimates the network status from network

monitor in real-time and dynamically manipulates the encod-

ing parameters, such as frame rate and quantization, to produce

speciﬁc adaptive bit rate video stream. The authors utilize RTT

jitter value to detect the network congestion, in order to decide

if the bit rate adaptation should be triggered. To evaluate

this proposal, a following work [47] conducts experiments on

a normal television with an IPTV set-top-box. The authors

simulate the network scenarios in homes and hotels to verify

that the proposed adaptation performed notably better.

Adaptive transmission has also been studied in mobile

scenarios. Wang and Dey [95] ﬁrst decompose the cloud

gaming system’s response time into sub-components: server

delay, network uplink/downlink delay, and client delay. Among

the optimization techniques applied, rate-selection algorithm

provides a dynamic solution that determine the time and the

way to switch the bit rate according to the network delay.

As a further step, Wang and Dey [96] study the potential of

rendering adaptation. They identify the rendering parameters

that affect a particular game, including realistic effect (e.g.,

colour depth, multi-sample, texture-ﬁlter, and lighting mode),

texture detail, view distance and enabling grass. Afterwards,

they analyze these parameters’ characteristics of communi-

cations and computation costs and propose their rendering

adaptation scheme, which is consisted of optimal adaptive

rendering settings and level-selection algorithm. With the

experiments conducted on commercial wireless networks, the

authors demonstrate that acceptable mobile gaming user expe-

rience can be ensured by their rendering adaption technique.

Thus, they claim that their proposal is able to facilitate cloud

gaming over mobile networks.

Other aspects of transmission adaptation have also been

investigated in the literature. He et al. [31] consider the

adaptive transmission from the perspective of multi-player.

The authors calculate the packet urgency based on buffer status

estimation and propose a scheduling algorithm. In addition,

they also suggest an adaptive video segment request scheme,

which estimates media access control (MAC) queue as an

additional information to determine the request time interval

for each gamer, on the purpose of improving the playback

experience. Bujari et al. [2] provides a VoAP algorithm to

address the ﬂow coexistence issue in wireless cloud gam-

ing service delivery. This research problem is introduced by

the concurrent transmissions of TCP-based and UDP-based

streams in home scenario, where the downlink requirement

of gaming video exacerbate the operation of above mentioned

transport protocols. The authors’ solution is to dynamically

modify the advertised window, in such way the system can

limit the growth of the TCP ﬂow’s sending rate. Wu et al. [99]

present a novel transmission scheduling framework dubbed

AdaPtive HFR vIdeo Streaming (APHIS) to address the issue

in the cloud gaming video delivery through wireless networks.

The authors ﬁrst propose an online video frame selection

algorithm to minimize the total distortion based on network

status, input video data, and delay constraint. Afterwards, they

introduce an unequal forward error correction (FEC) coding

scheme to provide differentiated protection for Intra (I) and

Predicted (P) frames with low-latency cost. The proposed

APHIS framework is able to appropriately ﬁlter video frames

and adjust data protection levels to optimize the quality of

HFR video streaming. Hemmati et al. [32] propose an object

selection algorithm to provide an adaptive scene rendering

solution. The basic idea is to exclude less important objects

from the ﬁnal output, thus to reduce less processing time

for the server to render and encode the frames. In such a

way, the cloud gaming system is able to achieve a lower bit

rate to stream the resulting video. The proposed algorithm

evaluates the importance of objects from the game scene based

on the analysis of gamers’ activities and do the selection work.

Experiments demonstrate that this approach reduces streaming

bit rate by up to 8.8%.

V. CO MM ER CI AL CL OU D GAM IN G SERVICES

In addition to the technical problems discussed in prior

sections, commercialization and business models of cloud

gaming services are critical to their success. We survey the

commercialization efforts starting from a short history on

cloud gaming services. G-cluster [26] starts building cloud

gaming services since early 2000’s. In particular, G-cluster

publicly demonstrated live game streaming1over WiFi to a

PDA in 2001, and a commercial game-on-demand service

in 2004. G-cluster’s service is tightly coupled with several

third-party companies, including game developers, network

operators, and game portals. This can be partially attributed to

the less mature Internet connectivity and data centers, which

force G-cluster to rely on network QoS supports from network

operators. Ojala and Tyrvainen [66] presents the evolution of

G-cluster’s business model, and observe that the number of

G-cluster’s third-party companies is reduced over years. The

number of households having access to G-cluster’s IPTV-based

cloud gaming service increased from 15,000 to 3,000,000

between 2005 and 2010.

In late 2000’s, emerging cloud computing companies start

offering Over-The-Top (OTT) cloud gaming services, repre-

sented by OnLive [67], Gaikai [27], and GameNow [28].

OTT refers to delivering multimedia content over the Inter-

net above arbitrary network operators to end users, which

trades QoS supports for ubiquitous access to cloud games.

OnLive [67] was made public in 2009, and was a well-

known cloud gaming service, probably because of its investors

including Warner Bros, AT&T, Ubisoft, and Atrari. OnLive

provided subscription based service, and hosted its servers

in several States within the US, to control the latency due

to geographical distances. OnLive ran into ﬁnancial difﬁculty

in 2012, and ceased operations in 2015 after selling their

patents to Sony [87]. Gaikai [27] offered cloud gaming service

using a different business model. Gaikai adopt cloud gaming

to allow gamers to try new games without purchasing and

installing software on their own machines. At the end of

each gameplay, gamers are given options to buy the game

1At that time, the term cloud was not yet popular.

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

if they like it. That is, Gaikai is more like an advertisement

service for game developers to boost their sales. Gaikai was

acquired by Sony [86] in 2012, which leads to a new cloud

gaming service from Sony, called PS Now [68] launched in

2014. PS Now allows gamers to play PlayStation games as

cloud games, and adopts two charging models: per-game and

monthly subscription.

The aforementioned cloud gaming services can be classiﬁed

in groups from two aspects. We discuss the advantages and

disadvantages of different groups in the following. First, cloud

gaming services are either: (i) integrated with underlaying

networks or (ii) provided as OTT services. Tighter integration

provides better QoS guarantees which potentially lead to better

user experience, while OTT reduces the expenses on cloud

gaming services at a possible risk of unstable and worse user

experience. Second, cloud gaming services adopt one of the

three charging models: (i) subscription, (ii) per-game, and (iii)

free to gamers. More speciﬁcally, cloud gaming users pay

for services in the ﬁrst two charging models, while third-

party companies, which can be game developers or network

operators, pay for services in the third charging model. In the

future, there may be innovative ways to offer cloud gaming

services to general publics in a commercially-viable manner.

VI. CO NC LU SI ON A ND OU TL OO K

In this article, we grouped the existing cloud gaming

research into four classiﬁcations: (i) overview, (ii) platform,

(iii) optimization, and (iv) commercialization. In Section II

(overview), we included papers that introducing general and

specialized (such as mobile) cloud gaming. In Section III

(platform), we presented the basic cloud gaming platforms that

support quantitative performance measurements. More speciﬁ-

cally, we considered: (i) QoS evaluations, such as energy con-

sumption and network metrics, and (ii) QoE evaluations, such

as gamer experience. In Section IV (optimization), we pre-

sented the two major optimization directions: (i) cloud server

infrastructure, such as resource allocation and distributed ar-

chitecture, and (ii) communications, such as data compression

and adaptive transmission. In Section V (commercialization),

we gave a brief history of cloud gaming services, followed by

the design decisions made by representative commercial cloud

gaming services.

Cloud gaming is not a panacea and incurs non-trivial

costs to service providers. Minimizing the cost on cloud and

networking resources while achieving high gamer experience

requires careful optimization like the approaches explored

in this survey. Without these optimizations, service provider

cannot consolidate enough cloud gaming users to each phys-

ical machine. This in turn leads to much lower proﬁts, and

may drive the service provider out of business. Some early

industrial pioneers such as OnLive [67] have unfortunately

exited the market. More recent cloud gaming services such

as PS Now [68] and GameNow [28] are better optimized

and will be more competitive in the current gaming industry.

As commercial cloud gaming services become ﬁnancially

sustainable, the new cloud gaming ecosystem will continue

to expand, leading to more investments and technologies to

improve these services. Much of the innovation needed to push

cloud gaming to the next level may reside in creating new

programing paradigms to support the unique needs of these

complex systems. Most current cloud gaming platforms work

as a ”black box” simply wrapping a traditionally programed

game in a support system to enable cloud gaming. Although,

the original black box model of cloud gaming has led to

many practical real world implementations a more integrated

approach may be necessary. It is likely that using in-game

contexts or whole new programing paradigms may solve some

of cloud gaming shortcomings [7]. Future cloud gaming aware

programing paradigms will help facilitate both better user

experience and resource utilization. This will allow more

innovative, yet demanding ideas to be implemented, which

in turn results in critical momentum towards building the next

generation cloud gaming services.

In summary, the advances of technologies turn playable

cloud gaming services into reality; more optimization tech-

niques gradually make cloud gaming services proﬁtable;

hence, we believe that we are on the edge of a new era of

a whole new cloud gaming ecosystem, which will eventually

leads to the next generation cloud gaming services.

ACK NOW LE DG EM EN TS

This work was supported in part by a UBC Four Year

Doctoral Fellowship, by the Canadian Natural Sciences and

Engineering Research (Grant STPGP 447524), and by the Na-

tional Natural Science Foundation of China (Grant 61271182).

This work was partially supported by the Ministry of Science

and Technology (MOST) of Taiwan under the grants: 102-

2221-E-007-062-MY3, 103-2221-E-009-230-MY2, 104-2221-

E-009-200-MY3, 103-2221-E-001-023-MY2.

REF ER EN CE S

[1] asm.js web page, March 2013. http://asmjs.org/.

[2] A. Bujari, M. Massaro, and C. Palazzi. Vegas over access point:

Making room for thin client game systems in a wireless home.

IEEE Transactions on Circuits and Systems for Video Technology,

25(12):2002–2012, December 2015.

[3] W. Cai, H. Chan, X. Wang, and V. Leung. Cognitive resource optimiza-

tion for the decomposed cloud gaming platform. IEEE Transactions

on Circuits and Systems for Video Technology, 25(12):2038–2051,

December 2015.

[4] W. Cai, M. Chen, and V. Leung. Toward gaming as a service. IEEE

Internet Computing, 18(3):12–18, May 2014.

[5] W. Cai, Z. Hong, X. Wang, H. Chan, and V. Leung. Quality-of-

experience optimization for a cloud gaming system with ad hoc cloudlet

assistance. IEEE Transactions on Circuits and Systems for Video

Technology, 25(12):2092–2104, December 2015.

[6] W. Cai, V. Leung, and L. Hu. A cloudlet-assisted multiplayer cloud

gaming system. Mobile Networks and Applications, 19(2):144–152,

November 2013.

[7] W. Cai, R. Shea, C. Huang, K. Chen, J. Liu, V. Leung, and C. Hsu.

The future of cloud gaming. Proceedings of the IEEE, 104(4):687–691,

April 2016.

[8] Y. Chang, P. Tseng, K. Chen, and C. Lei. Understanding the

performance of thin-client gaming. In Proc. of IEEE International

Workshop on Communications Quality and Reliability (CQR’11), pages

1–6, Naples, FL, May 2011.

[9] K. Chen, Y. Chang, H. Hsu, D. Chen, C. Huang, and C. Hsu. On

the quality of service of cloud gaming systems. IEEE Transactions on

Multimedia, 16(2):480–495, February 2014.

[10] K. Chen, Y. Chang, P. Tseng, C. Huang, and C. Lei. Measuring

the latency of cloud gaming systems. In Proc. of ACM International

Conference on Multimedia (MM’11), pages 1269–1272, Scottsdale, AZ,

November 2011.

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

[11] K. Chen, C. Huang, and C. Hsu. Cloud gaming onward: Research

opportunities and outlook. In Proc. of IEEE Conference on Multimedia

and Expo Workshops (ICMEW’14), pages 1–4, Chengdu, China, July

2014.

[12] G. Cheung, T. Sakamoto, and W. Tan. Graphics-to-video encoding

for 3G mobile game viewer multicast using depth values. In Proc. of

IEEE International Conference on Image Processing (ICIP’04), pages

2805–2808, Singapore, October 2004.

[13] S. Choy, B. Wong, G. Simon, and C. Rosenberg. The brewing storm in

cloud gaming: A measurement study on cloud to end-user latency. In

Proc. of Annual Workshop on Network and Systems Support for Games

(NetGames’12), pages 1–6, Venice, Italy, November 2012.

[14] S. Choy, B. Wong, G. Simon, and C. Rosenberg. A hybrid edge-

cloud architecture for reducing on-demand gaming latency. Multimedia

Systems, 20(5):503–519, October 2014.

[15] S. Chuah and N. Cheung. Layered coding for mobile cloud gaming.

In Proc. of International Workshop on Massively Multiuser Virtual

Environments (MMVE’14), pages 4:1–4:6, Singapore, March 2014.

[16] S. Chuah, N. Cheung, and C. Yuen. Layered coding for mobile cloud

gaming using scalable Blinn-Phong lighting. IEEE Transactions on

Image Processing, 25(7):3112–3125, July 2016.

[17] S. Chuah, C. Yuen, and N. Cheung. Cloud gaming: A green solution

to massive multiplayer online games. IEEE Wireless Communications,

21(4):78–87, August 2014.

[18] M. Claypool. Motion and scene complexity for streaming video games.

In Proc. of International Conference on Foundations of Digital Games

(FDG’09), pages 34–41, Orlando, FL, April 2009.

[19] M. Claypool and K. Claypool. Latency and player actions in online

games. Communications of the ACM, 49(11):40–45, November 2006.

[20] M. Claypool and D. Finkel. The effects of latency on player perfor-

mance in cloud-based games. In Proc. of Annual Workshop on Network

and Systems Support for Games (NetGames’14), pages 1–6, Nagoya,

Japan, December 2014.

[21] M. Claypool, D. Finkel, A. Grant, and M. Solano. Thin to win?

network performance analysis of the OnLive thin client game system.

In Proc. of Annual Workshop on Network and Systems Support for

Games (NetGames’12), pages 1–6, Venice, Italy, November 2012.

[22] E. Depasquale, A. Zammit, M. Camilleri, S. Zammit, A. Muscat,

P. Mallia, and S. Scerri. An analytical method of assessment of

RemoteFX as a cloud gaming platform. In Proc. of IEEE Conference

on Mediterranean Electrotechnical Conference (MELECON’14), pages

127–133, Beirut, Lebanon, April 2014.

[23] S. Dey. Cloud mobile media: Opportunities, challenges, and directions.

In Proc. of IEEE Conference on Computing, Networking and Commu-

nications (ICNC’12), pages 929–933, Maui, HI, February 2012.

[24] Emscripten web page, August 2013. http://emscripten.org.

[25] D. Finkel, M. Claypool, S. Jaffe, T. Nguyen, and B. Stephen. As-

signment of games to servers in the OnLive cloud game system. In

Proc. of Annual Workshop on Network and Systems Support for Games

(NetGames’14), pages 4:1–4:3, Nagoya, Japan, December 2014.

[26] G-cluster web page, January 2015. http://www.gcluster.com/eng.

[27] GaiKai web page, January 2015. http://www.gaikai.com/.

[28] GameNow web page, January 2015. http://www.ugamenow.com.

[29] R. Hans, U. Lampe, D. Burgstahler, M. Hellwig, and R. Steinmetz.

Where did my battery go? quantifying the energy consumption of cloud

gaming. In Proc. of IEEE International Conference on Mobile Services

(MS’14), pages 63–67, Anchorage, AK, June 2014.

[30] M. Hassam, N. Kara, F. Belqasmi, and R. Glitho. Virtualized infras-

tructure for video game applications in cloud environments. In Proc.

of ACM Symposium on Mobility Management and Wireless Access

(MobiWac’14), pages 109–114, Montreal, CA, September 2014.

[31] L. He, G. Liu, and C. Yuchen. Buffer status and content aware schedul-

ing scheme for cloud gaming based on video streaming. In Proc. of

IEEE Conference on Multimedia and Expo Workshops (ICMEW’14),

pages 1–6, Chengdu, China, July 2014.

[32] M. Hemmati, A. Javadtalab, A. Shirehjini, S. Shirmohammadi, and

T. Arici. Game as video: Bit rate reduction through adaptive object

encoding. In Proc. of ACM Workshop on Network and Operating

Systems Support for Digital Audio and Video (NOSSDAV’13), pages

7–12, Oslo, Norway, February 2013.

[33] H. Hong, D. Chen, C. Huang, K. Chen, and C. Hsu. QoE-aware virtual

machine placement for cloud games. In Proc. of Annual Workshop on

Network and Systems Support for Games (NetGames’13), pages 1–2,

Denver, CO, December 2013.

[34] H. Hong, D. Chen, C. Huang, K. Chen, and C. Hsu. Placing virtual

machines to optimize cloud gaming experience. IEEE Transactions on

Cloud Computing, 3(1):42–53, January 2015.

[35] H. Hong, C. Hsu, T. Tsai, C. Huang, K. Chen, and C. Hsu. Enabling

adaptive cloud gaming in an open-source cloud gaming platform.

IEEE Transactions on Circuits and Systems for Video Technology,

25(12):2078–2091, December 2015.

[36] H. Hong, C. Lee, K. Chen, C. Huang, and C. Hsu. GPU consolidation

for cloud games: Are we there yet? pages 3:1–3:6, Nagoya, Japan,

December 2014.

[37] M. Hossain, G. Muhammad, B. Song, M. Hassan, A. Alelaiwi, and

A. Alamri. Audiovisual emotion-aware cloud gaming framework.

IEEE Transactions on Circuits and Systems for Video Technology,

25(12):2105–2118, December 2015.

[38] C. Huang, K. Chen, D. Chen, H. Hsu, and C. Hsu. GamingAnywhere:

The ﬁrst open source cloud gaming system. ACM Transactions on Mul-

timedia Computing, Communications, and Applications, 10(1s):10:1–

10:25, January 2014.

[39] C. Huang, P. Chen, Y. Huang, K. Chen, and C. Hsu. Measuring the

client performance and energy consumption in mobile cloud gaming.

In Proc. of Annual Workshop on Network and Systems Support for

Games (NetGames’14), pages 1–3, Nagoya, Japan, December 2014.

[40] C. Huang, C. Hsu, Y. Chang, and K. Chen. GamingAnywhere: An open

cloud gaming system. In Proc. of ACM Multimedia Systems Conference

(MMSys’13), pages 36–47, Oslo, Norway, February 2013.

[41] C. Huang, C. Hsu, D. Chen, and K. Chen. Quantifying user satisfaction

in mobile cloud games. In Proc. of Workshop on Mobile Video Delivery

(MoVid’14), pages 4:1–4:6, Singapore, March 2013.

[42] M. Jarschel, D. Schlosser, S. Scheuring, and T. Hoßfeld. Gaming in the

clouds: QoE and the users’ perspective. Mathematical and Computer

Modelling, 57(11-12):2883–2894, June 2013.

[43] S. Jarvinen, J. P. Laulajainen, T. Sutinen, and S. Sallinen. QoS-aware

real-time video encoding: How to improve the user experience of a

gaming-on-demand service. In Proc. of IEEE Consumer Communi-

cations and Networking Conference (CCNC’06), pages 994–997, Las

Vegas, NV, January 2006.

[44] K. Kim, S. Bae, D. Lee, C. Cho, H. Lee, and K. Lee. Cloud-based

gaming service platform supporting multiple devices. ETRI Journal,

35(6):960–968, December 2013.

[45] S. Kim, K. Kim, and J. Won. Multi-view rendering approach for

cloud-based gaming services. In Proc. of International Conference

on Advances in Future Internet (AFIN’11), pages 102–107, French

Riviera, France, August 2011.

[46] U. Lampe, Q. Wu, S. Dargutev, R. Hans, A. Miede, and R. Steinmetz.

Assessing latency in cloud gaming. In Proc. of International Confer-

ence on Cloud Computing and Services Science (CLOSER’14), pages

52–68, Barcelona, Spain, September 2014.

[47] J. Laulajainen, T. Sutinen, and S. J¨

arvinen. Experiments with QoS-

aware gaming-on-demand service. In Proc. of International Conference

on Advanced Information Networking and Applications (AINA’06),

pages 805–810, Vienna, Austria, April 2006.

[48] K. Lee, D. Chu, E. Cuervo, J. Kopf, S. Grizan, A. Wolman, and J. Flinn.

Outatime: Using speculation to enable low-latency continuous interac-

tion for cloud gaming. In Proc. of Annual International Conference

on Mobile Systems, Applications, and Services (MobiSys’15), pages

151–165, Florence, Italy, May 2015.

[49] K. Lee, D. Chu, E. Cuervo, A. Wolman, and J. Flinn. Demo: Delorean:

Using speculation to enable low-latency continuous interaction for

mobile cloud gaming. In Proc. of Annual International Conference

on Mobile Systems, Applications, and Services (MobiSys’15), pages

347–347, Florence, Italy, May 2015.

[50] Y. Lee, K. Chen, H. Su, and C. Lei. Are all games equally cloud-

gaming-friendly? an electromyographic approach. In Proc. of Annual

Workshop on Network and Systems Support for Games (NetGames’12),

pages 1–6, Venice, Italy, November 2012.

[51] Y. Li, X. Tang, and W. Cai. Play request dispatching for efﬁcient virtual

machine usage in cloud gaming. IEEE Transactions on Circuits and

Systems for Video Technology, 25(12):2052–2063, December 2015.

[52] L. Lin, X. Liao, G. Tan, H. Jin, X. Yang, W. Zhang, and B. Li.

LiveRender: A cloud gaming system based on compressed graphics

streaming. In Proc. of ACM International Conference on Multimedia

(MM’14), pages 347–356, Orlando, FL, November 2014.

[53] Y. Liu, S. Dey, and Y. Lu. Enhancing video encoding for cloud

gaming using rendering information. IEEE Transactions on Circuits

and Systems for Video Technology, 25(12):1960–1974, December 2015.

[54] Y. Liu, S. Wang, and S. Dey. Modeling, characterizing, and enhancing

user experience in cloud mobile rendering. In Proc. of Interna-

tional Conference on Computing, Networking and Communications

(ICNC’12), pages 739–745, Maui, HI, January 2012.

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

[55] M. Manzano, J. Hernandez, M. Uruen:, and E. Calle. An empirical

study of cloud gaming. In Proc. of Annual Workshop on Network and

Systems Support for Games (NetGames’12), pages 1–2, Venice, Italy,

November 2012.

[56] M. Manzano, M. Urue ˜

na, M. Suˇ

znjevi´

c, E. Calle, J. Hern´

andez, and

M. Matijasevic. Dissecting the protocol and network trafﬁc of the

OnLive cloud gaming platform. Multimedia Systems, 20(5):451–470,

March 2014.

[57] M. Marzolla, S. Ferretti, and G. D’Angelo. Dynamic resource pro-

visioning for cloud-based gaming infrastructures. ACM Computers in

Entertainment, 10(3):4:1–4:20, December 2012.

[58] D. Meilnder, F. Glinka, S. Gorlatch, L. Lin, W. Zhang, and X. Liao.

Bringing mobile online games to clouds. In Proc. of IEEE Conference

on Computer Communications Workshops (INFOCOMW’14), pages

340–345, Toronto, Canada, April 2014.

[59] D. Mishra, M. El Zarki, A. Erbad, C. Hsu, and N. Venkatasubramanian.

Clouds + games: A multifaceted approach. IEEE Internet Computing,

18(3):20–27, May 2014.

[60] S. M¨

oller, D. Pommer, J. Beyer, and J. Rake-revelant. Factors

inﬂuencing gaming QoE: Lessons learned from the evaluation of cloud

gaming services. In Proc. of International Workshop on Perceptual

Quality of Systems (PQS’13), pages 1–5, Vienna, Austria, September

2013.

[61] C. Moreno, N. Tizon, and M. Preda. Mobile cloud convergence in

gaas: A business model proposition. In Proc. of Hawaii International

Conference on System Science (HICSS’12), pages 1344–1352, Maui,

HI, January 2012.

[62] Welcome to native client, March 2010. https://developer.chrome.com/

native-client.

[63] Google’s native client goes ARM and beyond,

March 2010. http://www.h-online.com/open/news/item/

Google-s- Native-Client-goes- ARM-and- beyond-957478.html.

[64] X. Nan, X. Guo, Y. Lu, Y. He, L. Guan, S. Li, and B. Guo. A novel

cloud gaming framework using joint video and graphics streaming.

In Proc. of IEEE International Conference on Multimedia and Expo

(ICME’14), pages 1–6, Chengdu, China, July 2014.

[65] NVidia Grid web page, May 2016. http://www.nvidia.com/object/

cloud-gaming.html.

[66] A. Ojala and P. Tyrvainen. Developing cloud business models: A case

study on cloud gaming. IEEE Software, 28(4):42–47, July 2011.

[67] OnLive web page, January 2015. http://www.onlive.com/.

[68] PlayStation Now web page, January 2015. http://www.playstation.com/

en-us/explore/playstationnow/.

[69] S. Prabu and S. Purushotham. Cloud gaming with P2P network

using XAML and Windows Azure. In Proc. of Conference on Recent

Trends of Computing, Communication and Information Technologies

(ObCom’11), pages 165–172, Vellore, India, December 2011.

[70] Z. Qi, J. Yao, C. Zhang, M. Yu, Z. Yang, and H. Guan. VGRIS:

Virtualized GPU resource isolation and scheduling in cloud gaming.

ACM Transactions on Architecture and Code Optimization, 11(2):203–

214, July 2014.

[71] P. Quax, A. Beznosyk, W. Vanmontfort, R. Marx, and W. Lamotte. An

evaluation of the impact of game genre on user experience in cloud

gaming. In Proc. of IEEE International Games Innovation Conference

(IGIC’13), pages 216–221, Vancouver, Canada, September 2013.

[72] K. Raaen, R. Eg, and C. Griwodz. Can gamers detect cloud delay? In

Proc. of Annual Workshop on Network and Systems Support for Games

(NetGames’14), pages 1–3, Nagoya, Japan, December 2014.

[73] L. Riungu-kalliosaari, J. Kasurinen, and K. Smolander. Cloud services

and cloud gaming in game development. pages 1–10, Prague, Czech

Republic, July 2013.

[74] P. Ross. Cloud computing’s killer app: Gaming. IEEE Spectrum,

46(3):14, March 2009.

[75] Cloud gaming to reach inﬂection point in 2015, November 2014. http:

//tinyurl.com/p3z9hs2.

[76] M. Semsarzadeh, M. Hemmati, A. Javadtalab, A. Yassine, and S. Shir-

mohammadi. A video encoding speed-up architecture for cloud gaming.

In Proc. of IEEE Conference on Multimedia and Expo Workshops

(ICMEW’14), pages 1–6, Chengdu, China, July 2014.

[77] M. Semsarzadeh, A. Yassine, and S. Shirmohammadi. Video encoding

acceleration in cloud gaming. IEEE Transactions on Circuits and

Systems for Video Technology, 25(12):1975–1987, December 2015.

[78] R. Shea, D. Fu, and J. Liu. Cloud gaming: Understanding the

support from advanced virtualization and hardware. IEEE Transactions

on Circuits and Systems for Video Technology, 25(12):2026–2037,

December 2015.

[79] R. Shea, D. Fu, and J. Liu. Towards bridging online game playing and

live broadcasting: Design and optimization. In Proc. of ACM Workshop

on Network and Operating Systems Support for Digital Audio and

Video (NOSSDAV’15), pages 61–66, Portland, OR, March 2015.

[80] R. Shea and J. Liu. On GPU pass-through performance for cloud

gaming: Experiments and analysis. In Proc. of Annual Workshop on

Network and Systems Support for Games (NetGames’13), pages 6:1–

6:6, Denver, CO, December 2013.

[81] R. Shea, J. Liu, E. Ngai, and Y. Cui. Cloud gaming: Architecture and

performance. IEEE Network, 27(4):16–21, August 2013.

[82] S. Shi, C. Hsu, K. Nahrstedt, and R. Campbell. Using graphics

rendering contexts to enhance the real-time video coding for mobile

cloud gaming. Proc. of ACM International Conference on Multimedia

(MM’11), pages 103–112, November 2011.

[83] M. Siekkinen, T. Kamarainen, Y. Xiao, and A. Yla-Jaaski. Towards

pervasive and mobile gaming with distributed cloud infrastructure. In

Proc. of Annual Workshop on Network and Systems Support for Games

(NetGames’14), pages 1–6, Nagoya, Japan, December 2014.

[84] I. Slivar, M. Suznjevic, L. Skorin-kapov, and M. Matijasevic. Empirical

qoe study of in-home streaming of online games. In Proc. of Annual

Workshop on Network and Systems Support for Games (NetGames’14),

pages 1–6, Nagoya, Japan, December 2014.

[85] O. Soliman, A. Rezgui, H. Soliman, and N. Manea. Mobile cloud

gaming: Issues and challenges. In Proc. of International Conference

on Mobile Web Information Systems (MobiWIS’13), pages 121–128,

Paphos, Cyprus, August 2013.

[86] Cloud gaming adoption is accelerating . . . and

fast!, July 2012. http://www.nttcom.tv/2012/07/09/

cloud-gaming- adoption-is- acceleratingand-fast/.

[87] Sony buys OnLive streaming game service, which will shut down later

this month, April 2015. http://goo.gl/6Xe9Dx.

[88] K. Sun and D. Wu. Video rate control strategies for cloud gaming.

Journal of Visual Communication and Image Representation, 30:234 –

241, 2015.

[89] M. Suznjevic, J. Beyer, L. Skorin-Kapov, S. Moller, and N. Sorsa. To-

wards understanding the relationship between game type and network

trafﬁc for cloud gaming. In Proc. of IEEE Conference on Multimedia

and Expo Workshops (ICMEW’14), pages 1–6, Chengdu, China, July

2014.

[90] R. Sselbeck, G. Schiele, and C. Becker. Peer-to-peer support for low-

latency Massively Multiplayer Online Games in the cloud. pages 1–2,

Paris, France, November 2009.

[91] M. Taher, H. Ahmadi, and M. Hashemi. Power-aware analysis of

H.264/AVC encoding parameters for cloud gaming. In Proc. of IEEE

Conference on Multimedia and Expo Workshops (ICMEW’14), pages

1–6, Chengdu, China, July 2014.

[92] H. Tian, D. Wu, J. He, Y. Xu, and M. Chen. On achieving cost-effective

adaptive cloud gaming in geo-distributed data centers. IEEE Transac-

tions on Circuits and Systems for Video Technology, 25(12):2064–2077,

December 2015.

[93] Ubitus web page, January 2015. http://www.ubitus.net.

[94] S. Wang and S. Dey. Modeling and characterizing user experience

in a cloud server based mobile gaming approach. In Proc. of IEEE

Global Telecommunications Conference (GLOBECOM’09), pages 1–7,

Honolulu, HI, November 2009.

[95] S. Wang and S. Dey. Addressing response time and video quality

in remote server based Internet mobile gaming. pages 1–6, Sydney,

Australia, April 2010.

[96] S. Wang and S. Dey. Rendering adaptation to address communication

and computation constraints in cloud mobile gaming. In Proc. of IEEE

Global Telecommunications Conference (GLOBECOM’10), pages 1–6,

Miami, FL, December 2010.

[97] S. Wang and S. Dey. Cloud mobile gaming: Modeling and measuring

user experience in mobile wireless networks. ACM SIGMOBILE

Mobile Computing and Communications Review, 16(1):10–21, January

2012.

[98] S. Wang, Y. Liu, and S. Dey. Wireless network aware cloud scheduler

for scalable cloud mobile gaming. In Proc. of IEEE International

Conference on Communications (ICC’12), pages 2081–2086, Ottawa,

Canada, June 2012.

[99] J. Wu, C. Yuen, N. Cheung, J. Chen, and C. Chen. Enabling adaptive

high-frame-rate video streaming in mobile cloud gaming applications.

IEEE Transactions on Circuits and Systems for Video Technology,

25(12):1988–2001, December 2015.

[100] Z. Wu. Gaming in the cloud: one of the future entertainment. In Proc.

of Interactive Multimedia Conference, pages 1–6, Southampton, UK,

January 2014.

http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

[101] L. Xu, X. Guo, Y. Lu, S. Li, O. Au, and L. Fang. A low latency cloud

gaming system using edge preserved image homography. In Proc. of

IEEE International Conference on Multimedia and Expo (ICME’14),

pages 1–6, Chengdu, China, July 2014.

[102] Z. Xue, D. Wu, J. He, X. Hei, and Y. Liu. Playing high-end video games

in the cloud: A measurement study. IEEE Transactions on Circuits and

Systems for Video Technology, 25(12):2013–2025, December 2015.

[103] C. Zhang, J. Yao, Z. Qi, M. Yu, and H. Guan. vGASA: Adaptive

scheduling algorithm of virtualized GPU resource in cloud gaming.

IEEE Transactions on Parallel and Distributed Systems, 25(11):3036–

3045, November 2014.

[104] Z. Zhao, K. Hwang, and J. Villeta. Game cloud design with virtualized

CPU/GPU servers and initial performance results. In Proc. of Workshop

on Scientiﬁc Cloud Computing Date (ScienceCloud’12), pages 23–30,

Delft, Netherlands, June 2012.

ABRAGame: automatic bit rate adjustment for cloud gaming

Article

Full-text available

Dec 2024
MULTIMED TOOLS APPL

Cloud Gaming has emerged as a promising alternative for enjoying high-quality video games on low-cost devices. These platforms run games on remote servers and stream multimedia content to the player’s device over the network. While they offer numerous advantages, they also present challenges and issues due to their heavy reliance on network quality. This work focuses on the research and development of a real-time algorithm that performs early detection of potential visual degradations and automatically adjusts the server’s encoding rate to prevent such issues. In doing so, it accomplishes the objective of maintaining a smooth gaming experience, even on congested networks, while concurrently enhancing the overall quality of experience of the users. The algorithm, called ABRAGame, was tested on fifteen games, covering four different genres, using a real Cloud Gaming platform owned by the company ABYA, which provides Cloud Gaming services in Latin America.

Virtual Net: a Decentralized Architecture for Interaction in Mobile Virtual Worlds

Preprint

Full-text available

Nov 2018

With the development of mobile technology, mobile virtual worlds have attracted massive users. To improve scalability, a peer-to-peer virtual world provides the solution to accommodate more users without increasing hardware investment. In mobile settings, however, existing P2P solutions are not applicable due to the unreliability of mobile devices and the instability of mobile networks. To address the issue, a novel infrastructure model, called Virtual Net, is proposed to provide fault-tolerance in managing user content and object state. In this paper, the key problem, namely object state update, is resolved to maintain state consistency and high interaction responsiveness. This work is important in implementing a scalable mobile virtual world.

Switching to Cloud Gaming: A Push-Pull-Mooring Perspective

Article

Full-text available

Dec 2024
J BUS RES

The video game industry has witnessed a switching of gamers from traditional means of gaming to cloud gaming. Understanding the psychological mechanisms underlying such switching behavior at the individual level is important. Drawing on the technology switching literature and the push-pull-mooring (PPM) framework, we proposed a research model explaining the switching intention to cloud gaming services. Using a mixed methods approach, we first drew insights from a qualitative interview study and the technology switching literature to identify antecedents specific to cloud gaming. Then, we developed a research model that consolidates salient push, pull, and mooring factors influencing the switching intention. Using a quantitative survey study, we tested the research model with data collected from 305 gamers. This study contributes to the technology switching literature by contextualizing the PPM framework into cloud gaming services. The findings provide cloud gaming service practitioners with insights into attracting new gamers and retaining existing ones.

Introduction to Cloud Gaming

Article

Oct 2024

Rajiv Tulsyan

Cloud Gaming can be defined as a technology that enables gamers to play video games using cloud-based servers and infrastructure, rather than relying on local hardware for processing and rendering game graphics. In cloud gaming, the games are streamed to the player's device with the help of the internet, allowing them to play high-quality games without needing to own a high-end gaming console or PC. The solution helps people to play games on their computers regardless of their own system as their gaming needs are met with the help of good enough customer service in the cloud. It also helps to overcome the problems of traditional games such as conflict and mobility. In this article, we will take a look at various aspects of Cloud Gaming System (CGS) to explain the many advantages and capabilities this concept has.

DSP as a Service: Foundations and Directions

Article

Full-text available

Jan 2024

This article proposes a vision for digital signal processing as a service (DSPaaS), which exploits the Internet of Musical Things’ capabilities to dematerialise and enhance music production tasks beyond networked music performance. If all musical devices were connected to the internet, which new services and value could be created for musicians, and which technical challenges and trade-offs would arise? First, we identify the main components of a DSPaaS system and introduce its building blocks, technological enablers, design trade-offs and network configurations. Then, we segment DSPaaS applications into three categories based on different latency constraints. Subsequently, we describe three illustrative case studies and analyse them under the key performance indicators of latency and reliability. Finally, we discuss the current research challenges, aiming to inform developers’ choices during the processes of creating new digital services for musicians, and to facilitate researchers’ understanding of the key research directions stemming from the DSPaaS vision.

Efficiency Enhancement of Online Gaming Environments Using Cloud Computing

Chapter

May 2025

Streaming the Future of Sustainability

Article

Apr 2025

The rapid growth of digital video traffic presents both challenges and opportunities for sustainable content delivery. We argue that the shift towards on-demand streaming, exemplified by services like Netflix, provides a path to significantly reduce the carbon footprint and e-waste associated with traditional computing paradigms. By eliminating the need for local operating systems, enabling more efficient edge devices, and leveraging renewable-powered cloud infrastructure, streaming on-demand hardware and content can drive down energy use and embodied emissions. We analyze the key factors behind streaming's improved sustainability and chart a course for further optimization, envisioning a future where streaming is the default across all computing domains. This future will be enabled by a new class of streaming-optimized edge devices and continued innovation in areas like video coding, adaptive bitrate algorithms, and energy-efficient processing.

Low-Latency Volumetric Video Conferencing in Congested Networks Through L4S

Conference Paper

Mar 2025

HortaCloud: An Open and Collaborative Platform for Whole Brain Neuronal Reconstructions

Preprint

Full-text available

Mar 2025

HortaCloud is a cloud-based, open-source platform designed to facilitate the collaborative reconstruction of long-range projection neurons from whole-brain light microscopy data. By providing virtual environments directly within the cloud, it eliminates the need for costly and time-consuming data downloads, allowing researchers to work efficiently with terabyte- scale volumetric datasets. Standardization of computational resources in the cloud make deployment easier and more predictable. The pay-as-you-go cloud model reduces adoption barriers by eliminating upfront investments in expensive hardware. Finally, HortaCloud's decentralized architecture enables global collaboration between researchers and between institutions.

VIGOR: Reviving Cloud Gaming Sessions

Article

Nov 2024

Cloud gaming is a multi-billion dollar industry. A client in cloud gaming sends its movement to the game server on the Internet, which renders and transmits the resulting video back. In order to provide a good gaming experience, a latency below 80 ms is required. This means that video rendering, encoding, transmission, decoding, and displaying have to finish within that time frame, which is especially challenging to achieve due to server overload, network congestion, and losses. In this paper, we propose VIGOR, a new method to revive cloud gaming sessions by recovering lost or corrupted video frames. Unlike traditional video frame recovery, VIGOR uses game states to enhance recovery accuracy significantly and utilizes partially decoded frames to recover lost portions. We develop a holistic system that consists of (i) efficiently extracting game states, (ii) modifying H.264 video decoder to generate a mask to indicate which portions of video frames need recovery, and (iii) designing a novel neural network to recover either complete or partial video frames. VIGOR is extensively evaluated using iPhone 12 and laptop implementations, and we demonstrate the utility of game states in the game video recovery and the effectiveness of our overall design.

Factors Influencing Gaming QoE: Lessons Learned from the Evaluation of Cloud Gaming Services

Conference Paper

Sep 2013

Outatime: Using Speculation to Enable Low-Latency Continuous Interaction for Mobile Cloud Gaming

Article

Dec 2015

On achieving cost-effective adaptive cloud gaming in geo-distributed data centers

Article

Jan 2015

H. Tian

Assignment of games to servers in the OnLive cloud game system

Conference Paper

Dec 2014

Layered Coding for Mobile Cloud Gaming Using Scalable Blinn-Phong Lighting

Article

Jul 2016

In a mobile cloud gaming, high-quality, high-frame-rate game images of immense data size need to be delivered to the clients over wireless networks under stringent delay requirement. For good gaming experience, reducing the transmission bit rate of the game images is necessary. Most existing cloud gaming platforms simply employ standard, off-the-shelf video codecs for game image compression. In this paper, we propose the layered coding scheme to reduce transmission bandwidth and latency. We leverage the rendering computation of modern mobile devices to render a low-quality local game image, or the base layer (BL). Instead of sending a high-quality game image, cloud servers can send enhancement layer information, which clients can utilize to improve the quality of the BL. Central to the layered coding scheme is the design of a complexity-scalable BL rendering pipeline that can be executed on a range of power-constrained mobile devices. In this paper, we focus on the lighting stage in modern graphics rendering and propose a method to scale the popular Blinn-Phong lighting for the use in BL rendering. We derive an information-theoretic model on the Blinn-Phong lighting to estimate the rendered image entropy. The analytic model informs the optimal BL rendering design that can lead to maximum bandwidth saving subject to the constraint on the computation capability of the client. We show that the information rate of the enhancement layer could be much less than that of the high-quality game image, while the BL can be generated with only a very small amount of computation. Experiment results suggest that our analytic model is accurate in estimating. For layered coding scheme, up to 84% reduction in bandwidth usage can be achieved by sending the enhancement layer information instead of the original high-quality game images compressed by H.264/AVC.

Outatime

Conference Paper

May 2015

Gaming on phones, tablets and laptops is very popular. Cloud gaming - where remote servers perform game execution and rendering on behalf of thin clients that simply send input and display output frames - promises any device the ability to play any game any time. Unfortunately, the reality is that wide-area network latencies are often prohibitive; cellular, Wi-Fi and even wired residential end host round trip times (RTTs) can exceed 100ms, a threshold above which many gamers tend to deem responsiveness unacceptable. In this paper, we present Outatime, a speculative execution system for mobile cloud gaming that is able to mask up to 120ms of network latency. Outatime renders speculative frames of future possible outcomes, delivering them to the client one entire RTT ahead of time, and recovers quickly from mis-speculations when they occur. Clients perceive little latency. To achieve this, Outatime combines: 1) future state prediction; 2) state approximation with image-based rendering and event time-shifting; 3) fast state checkpoint and rollback; and 4) state compression for bandwidth savings. To evaluate the Outatime speculation system, we use two high quality, commercially-released games: a twitch-based first person shooter, Doom 3, and an action role playing game, Fable 3. Through user studies and performance bench- marks, we find that players strongly prefer Outatime to traditional thin-client gaming where the network RTT is fully visible, and that Outatime successfully mimics playing across a low-latency network.

Assessing Latency in Cloud Gaming

Conference Paper

Sep 2014

With the emergence of cloud computing, diverse types of Information Technology services are increasingly provisioned through large data centers via the Internet. A relatively novel service category is cloud gaming, where video games are executed in the cloud and delivered to a client as audio/video stream. While cloud gaming substantially reduces the demand of computational power on the client side, thus enabling the use of thin clients, it may also affect the Quality of Service through the introduction of network latencies. In this work, we quantitatively examined this effect, using a self-developed measurement tool and a set of actual cloud gaming providers. For the two providers and three games in our experiment, we found absolute increases in latency between approximately 40 ms and 150 ms, or between 85% and 800% in relative terms, compared to a local game execution. In addition, based on a second complementary experiment, we found mean round-trip times ranging from about 30ms to 380ms using WLAN and approximately 40ms to 1050 ms using UMTS between a local computer and globally distributed compute nodes. Bilaterally among the compute nodes, results were in the range from approximately 10 ms to 530 ms. This highlights the importance of data center placement for the provision of cloud gaming services with adequate Quality of Service properties.

The Future of Cloud Gaming

Article

Apr 2016

Examines the future for cloud gaming services. These services have leveraged real-time video streaming technologies that have a long history of development. Cloud gaming refers to the technologies that offload parts of game software from traditional game consoles or personal computers (PCs) to powerful and elastic cloud infrastructures. Cloud gaming makes perfect sense to: 1) gamers, who otherwise have to constantly upgrade their consoles or PCs, which is certainly no fun and costly; 2) cloud service providers, who can sell the already-deployed and idling cloud resources to support the cutting-edge games that are extremely resource hungry; and 3) game developers, who no longer need to spend months to port their games to different platforms. As such, cloud gaming has attracted significant attention from both academia and industry.

Cloud Gaming with P2P Network Using XAML and Windows Azure

Chapter

Jan 2012

The next generation of Internet technology uses Windows Azure as a cloud for software as a service (Saas) and storage. In cloud gaming the responsibility for executing gaming engines(Saas) and graphics rendering is available in the cloud servers instead of mobile devices, PC’s since mobile devices and PCs can not run the game beyond the random access Memory(RAM) available. The application in Cloud is developed using XAML so that it can be reused windows presentation framework desktop application and browser, multi-touch screen, mobile silver light applications are integrated as single application, depending upon the type of device, the game will run. Peer 2 peer network (P2P) allows the application running in one computer can be shared by another application so that single game can be shared and played by mobile user, PC user at a time eg., Foot Ball, Cricket. The article aims to present rich internet games to mobile and PC users irrespective of the available memory of device and capacity to share the single game across mobile and PC users. Cloud gaming with P2P Network based upon Windows Azure and XAML, using single application which will lead to integration of desktop, browser, multi-touch screen and mobile applications.

Virtualized infrastructure for video game applications in cloud environments

Article

Sep 2014

Mobile video games are fast-growing and fast-evolving. Cloud computing's paradigm can bring several benefits to mobile video games, like cost reduction through an efficient usage of resources, or an easier and faster on-demand deployment of new applications. This paper focuses on the architecture aspects of mobile cloud-based video gaming and proposes a new service oriented and virtualized paradigm. The idea is to provide reusable game engines sub modules like the rendering or physics engines as cloud computing services. We call these sub modules substrates. Offered by different substrates providers as services, they can be dynamically discovered, used and composed. There are several motivations for substrates virtualization, including the rapid introduction of new video game applications and cost efficiency through resource sharing. This paper also describes the implementation of a prototype and the measurements performed to validate some aspects of our paradigm. As a preliminary validation of this solution, we analyze the effects of different parameters like virtualization or inner latency on the QoS. The performance analysis shows that the overhead introduced by substrate virtualization is acceptable, and reveals how the lowlatency connectivity between substrates that compose a video game application and the limitation of the amount of these substrates are crucial to achieve a satisfactory level of QoS.

A Survey on Cloud Gaming: Future of Computer Games

Abstract and Figures

Recommended publications

A Hybrid P2P System to Support MMORPG Playability

Game service platform based on the real-time streaming

Frag: A distributed approach to display wall gaming

A psychophysical study of fixation behavior in a computer game