No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Cloud servers vs. dedicated servers — A survey
Abstract
Dedicated servers are deployed by companies to meet the ever growing computing demand. More storage and more security are sought after by companies. The inefficient scaling of hardware, higher deployment time, installation of old operating systems on new hardware are just some of the areas where dedicated servers suffer. Cloud severs can be used in lieu of dedicated servers. This will not only decrease the overall IT budget of companies but will be more flexible. This paper is a survey done on three start-up companies to inquire about the dedicated servers. Amazon Web Services have been used to rent a cloud server which hosts a website. Comparisons are done graphically and some observations drawn by the companies' executives about cloud and dedicated servers are mentioned in the latter stage of the paper.
... Usually, it is the shared hosting paradigm which is associated with cloud computing environments. Organizations' migration to the cloud (to the approach of renting shared hosting servers' resources) often results in decrease in operations costs and improved flexibility in terms of scalability [14]. Nevertheless, cloud providers like Amazon may offer options like Dedicated Instances, which, despite being hosted in the cloud environment, include a physical server fully dedicated to a single customer [16]. ...
... At any given time, the sums of CPU or memory requirements of all pods running on a specific server should not exceed the total CPU or memory resources available on the server. The first set of constraints is stated in (14) for CPU resources and (15) for memory resources. ...
The object of the research is resource management and scheduling in Kubernetes clusters, in particular, data centers. It was determined that in many publications dedicated to optimization models of scheduling for Kubernetes, mathematical models either do not include constraints at all, or only have the constraints determined on the high level only. The purpose of the research is the creation of a dynamic low-level mathematical optimization model for resource management and scheduling in cloud computing environments that utilize Kubernetes. Examples of such environments include the data centers where the customers can rent both dedicated servers and resources of shared hosting servers that are allocated on demand. The suggested model was created using the principles of creation of mathematical models of discrete (combinatorial) optimization, and was given the name “dynamic” because it takes the time parameter into account. The model receives data about individual servers in the cluster and individual pods that should be launched as an input. The model aims to regulate not only individual assignments of pods to nodes, but also turning on and off the servers. The model has objectives of: minimization of the average number of shared hosting servers running; maximization of the average resource utilization coefficient on such servers; minimization of the number of occasions when the servers are turned on and off; minimization of resource utilization by the pods that are running on shared hosting servers but created by the customers renting the dedicated servers. The model considers resource constraints, among other limitations.
... Almost all information technologies (IT) currently used are hosted and managed by servers devoted to performing one or more activities as services [1]. For example, many servers host and manage web pages, handle e-mails, perform complex data computing operations or managing critical systems [2], [3]. ...
... This section provides an overview of a virtualization system. The idea of virtualization is to provide a faithful and complete abstraction of the hardware of a physical machine [1], [31]. This abstraction allows generating a VM whose behavior is identical to a physical machine; thanks to this abstraction, the same software's and operating systems designed for physical calculators can also be executed by VMs. ...
Information technology servers are complex, delicate, and expensive systems; power grid interruption is one of the possible causes that can lead to hardware damage or logical disk structure damage, with severe consequences. Moreover, a power grid drop causes a sudden interruption of the services managed by a server. Uninterruptible power supplies (UPS) provide backup power when the regular power grid source drops. UPSs can only maintain a server for a short time. Therefore, it is necessary to introduce a blackout manager who can correctly shut down the server activities. Moreover, the manager must be able to restore the servers' status when the electrical grid power returns to its normal state. This paper proposes a possible UPS power manager able to manage servers during a prolonged electrical blackout. The UPS power manager identifies the blackout and keeps the servers safe by saving their state and shutting them down properly. Following the power grid restoration, the UPS power manager restarts the servers and restores their state. The proposed approach has been evaluated on a virtualization cluster used for critical activities at the Politecnico di Torino.
... %) were SA). Furthermore there was no significant correlation between age and usability score, and there was no effect of gender as shown in other studies (Abidi and Singh 2013). Moreover the correlations analysis showed the strength of relations between constructs (See Fig. 6). ...
... This quantitative results further emphasised the high system reliability and efficiency during the experimental phase, confirmed by the higher acceptability and usability results. Furthermore, the cloud offers more flexibility at a lower cost compared to dedicated servers (Abidi and Singh 2013). ...
Information and Communication Technology and personal robots could play a fundamental role in efficiently managing chronic diseases and avoiding improper medications. They could support senior citizens with reminders, thus promoting their independent living and quality of life, especially in the presence of several chronic diseases (multimorbidity). In this context, this article proposes a service model for personalised medical support that is able to provide adequate healthcare service by means of a hybrid robot-cloud approach. This service was quantitatively and qualitatively tested to assess the technical feasibility and user acceptability level of the service. The service was tested with 23 older people (65–86 years) in the DomoCasa Lab (Italy). This study demonstrated the feasibility of the proposed hybrid cloud solution and the usability and acceptability were positively evaluated thus confirming the ability to utilise these innovative technologies for active and healthy ageing.
... In this paradigm sensor networks cooperate with robots to extend their sensing capabilities to provide more complex services to all citizens. Nevertheless networked robots show some limitations related to the continuity of service [8], the flexibility and scalability of resources [9] and the bandwidth [10]. ...
... Additionally, cloud resources allow robots to use the proposed SaaS in a pay-per-use modality, so this solution is cheaper then the same solutions with a local server, where the users have to pay the system even when they do not use it [9]. ...
In the future, social robots will permeate our daily life. An autonomous robot that has to move among different buildings needs to manage huge amount of data, as a consequence it is clear that the configuration of the navigation system becomes hard to manage. This paper presents a system, based on a cloud robotics paradigm, conceived to allow autonomous robots to navigate in indoor environment, which are not known a priori. The environment is divided into sub-maps and all the necessary information and the topological representation of the world, are stored into a remote cloud
infrastructure. By means of specific Environmental Tags, composed of a set of ARTags and QR codes, the robot gets the access to the Cloud Service and it is able to update its navigation configuration in a dynamic and automatic way. Experiments have been conducted in order to choose an appropriate marker dimension and to demonstrate the feasibility of the proposed procedure.
... In this paradigm sensor networks cooperate with robots to extend their sensing capabilities to provide more complex services to all citizens. Nevertheless networked robots show some limitations related to the continuity of service [8], the flexibility and scalability of resources [9] and the bandwidth [10]. ...
... Additionally, cloud resources allow robots to use the proposed SaaS in a pay-per-use modality, so this solution is cheaper then the same solutions with a local server, where the users have to pay the system even when they do not use it [9]. ...
A cloud robotics solution was designed and initially tested with a mobile robotic platform and a smart environment, in order to provide health-care management services to senior citizens and improve their independent living. The solution was evaluated in terms of Quality of Service (QoS) and tested in the realistic scenario of the DomoCasa Living Lab, Peccioli, Italy. In particular, a medication reminding service, a remote home monitoring and a user indoor localization algorithm were outsourced in the cloud and provided to the robots, users and carers. The system acquired data from a smart environment and addressed the robot to the user for service delivery. Experiments showed a service’s Reliability of Response at least of the 0.04% and a Time of Response of the same order of magnitude of the processing time required by the user localization algorithm.
... Being successfully deployed in a Raspberry Pi ensures the light-weightiness and portability of the backend system that can be very convenient in time of a disaster. But, in the case of real-life implementation, cloud computing services like AWS, Azure, Google Cloud will be much more efficient and fail-safe, economically more attainable, and also flexible [73]. ...
This paper presents an IoT-based system with redundant communication layers including
conventional cellular network, hybrid mesh LoRaWAN, and Bluetooth Low Energy (BLE) that
tracks disaster victims using GNSS, transmits their bio-signs, and can be installed in disaster
safety kits. This system not only will increase a victim’s chance of survival during or after a
disastrous event but also, will help the rescue operation to be more accurate, organized, and
efficient providing them geo-local and biometric data of victims. Moreover, usages of UAV
and UGV equipped with LoRaWAN gateways and BLE receivers can expand the reach of
rescue operations and potentially can save more lives. Having two long-range and a short-range
communication layers ensures its operation even in extreme conditions where typical network-
enabled devices and systems may not be very useful. Analyzing previous attempts to define
resilient disaster-time networks and disaster management lifecycles, a complete framework has
been discussed here in this paper along with implementation and simulation of the system.
... Dedicated hosting [4] is a term used to describe web hosting packages that provide a dedicated server with dedicated resources to a single client. Dedicated hosting plans are ideal for large organizations or websites with much higher traffic. ...
Microserver is a technology that is currently being developed, this cannot be separated from the development of computer technology that has little power. This is certainly a challenge to be able to develop this microserver to be more sophisticated. Dedicated Server Host is a technology that is widely used today due to developments in website and application technology. On this research we want to test microserver if microserver used as local web server and accessed by number of users. Based on this research, it can be concluded that the use of a microserver as a dedicated server host can be used as a CMS (Content Management System) server and also web monitoring, this is shown in the results of the experiment which shows the processor usage when used as cms and web monitoring is below 50% simultaneously with That's a packet error that appears, but a little packet error appears. Different results are shown when users access web streaming and file sharing on the microserver when there are 10 users, the CPU usage is above 50% but the packet error that appears is still below 10%, but when the number of users is more than 20 there is a surge in processor usage and also packet error is indicated by processor usage of more than 50% and packet error of more than 40%. This occurs because the need to run the streaming function and file sharing is heavier.
This book constitutes the thoroughly refereed post-conference proceedings of the 4th International Conference on Computing and Network Communications (CoCoNet'20), October 14–17, 2020, Chennai, India. The papers presented were carefully reviewed and selected from several initial submissions. The papers are organized in topical sections on Signal, Image and Speech Processing, Wireless and Mobile Communication, Internet of Things, Cloud and Edge Computing, Distributed Systems, Machine Intelligence, Data Analytics, Cybersecurity, Artificial Intelligence and Cognitive Computing and Circuits and Systems. The book is directed to the researchers and scientists engaged in various fields of computing and network communication domains.
Cloud Computing is rising fast, with its data centres growing at an unprecedented rate. However, this has come with concerns of privacy, efficiency at the expense of resilience, and environmental sustainability, because of the dependence on Cloud vendors such as Google, Amazon, and Microsoft. Community Cloud Computing makes use of the principles of Digital Ecosystems to provide a paradigm for Clouds in the community, offering an alternative architecture for the use cases of Cloud Computing. It is more technically challenging to deal with issues of distributed computing, such as latency, differential resource management, and additional security requirements. However, these are not insurmountable challenges, and with the need to retain control over our digital lives and the potential environmental consequences, it is a challenge we must pursue.
Currently, a large number of cloud computing servers waste a tremendous amount of energy and emit a considerable amount of carbon dioxide. Thus, it is necessary to significantly reduce pollution and substantially lower energy usage. This paper seeks to implement six innovative green task scheduling algorithms that have two main steps: assigning as many tasks as possible to a cloud server with lowest energy, and setting the same optimal speed for all tasks assigned to each cloud server. A newly proven theorem can determine the optimal speed for all tasks assigned to a computer. These novel green algorithms are developed for heterogeneous cloud servers with adjustable speeds and parameters to effectively reduce energy consumption and finish all tasks before a deadline. Based on sufficient simulations, three green algorithms that allocate a task to a cloud server with minimum energy are more effective than three others that assign a task to a randomly selected cloud server. Sufficient simulation results indicate that the best algorithm among the six algorithms is Shortest Task First for Computer with Minimum Energy algorithm.
As an emerging technology and business paradigm, Cloud Computing has taken commercial computing by storm. Cloud computing platforms provide easy access to a company’s high-performance computing and storage infrastructure through web services. With cloud computing, the aim is to hide the complexity of IT infrastructure management from its users. At the same time, cloud computing platforms provide massive scalability, 99.999% reliability, high performance, and specifiable configurability. These capabilities are provided at relatively low costs compared to dedicated infrastructures. This article gives a quick introduction to cloud storage. It covers the key technologies in Cloud Computing and Cloud Storage, several different types of clouds services, and describes the advantages and challenges of Cloud Storage after the introduction of the Cloud Storage reference model.
Cloud computing refers to a network that distributes processing power, applications, and large systems among many computers. Social media channels and many other applications use cloud computing as their platform. But cloud computing goes beyond that, offering a way for people to expand their local computing power onto the (seemingly) infinite processing power of the Internet. One of the results is a changing method of communication. Cloud computing can be a single-function application, an infrastructure on which these applications (and many others) can run, a set of services that offer the advantages of huge amounts of computing resources, and the ability to store large amounts of data remotely. Many companies and educational institutions are just beginning to realize the benefits of cloud-based applications that have traditionally required site licensing, installation, and maintenance. Cloud computing, SaaS, software as a service, social media.
150,000 cloud virtual machines to help solve mysteries of Universe at Cern
- J Brodkin
Amazon's cloud crash destroyed many customers' data
- H Blodget