Article

ACHO: A Framework for Flexible Re-Orchestration of Virtual Network Functions

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Network Function Virtualization enables network slicing as a novel paradigm for service provisioning. With network slicing, Virtual Network Functions (VNFs) can be instantiated at different locations of the infrastructure, choosing their optimal placement based on parameters such as the requirements of the service or the resources available. One limitation of state-of-the-art technology for network slicing is the inability to re-evaluate orchestration decisions once the slice has been deployed, in case of changing service demands or network conditions. In this paper, we present ACHO, a novel software framework that enables seamless re-orchestration of VNFs of any kind, including RAN and Core. With ACHO, VNFs and resources can be easily re-assigned to match, e.g., varying user demands or changes in the nodes’ load. ACHO uses lightweight mechanisms, such as splitting the engine of a VNF from the data it requires to perform its operation, in such a way that, when re-allocating a VNF, only the data is moved (a new engine is instantiated in the new location). We demonstrate the use of ACHO in a small scale testbed, showing that (i) the proposed re-orchestration is feasible, (ii) it results much faster than existing alternatives (especially for relocation), and (iii) the framework can be readily applied to existing VNFs after minimal changes to their implementation.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
The increasing consumption of multimedia services and the demand of high-quality services from customers has triggered a fundamental change in how we administer networks in terms of abstraction, separation, and mapping of forwarding, control and management aspects of service. The industry and the academia are embracing 5G as the future network capable to support next generation vertical applications with different service requirements. To realize this vision in 5G network, the physical network has to be sliced into multiple isolated logical networks of varying sizes and structures which are dedicated to different types of services based on their requirements with different characteristics and requirements(e.g., a slice for massive IoT devices, smartphones or autonomous cars, etc.). Softwarization using Software-Defined Networking (SDN) and Network Function Virtualization (NFV)in 5G networks are expected to fill the void of programmable control and management of network resources. In this paper, we provide a comprehensive review and updated solutions related to 5G network slicing using SDN and NFV. Firstly, we present 5G service quality and business requirements followed by a description of 5G network softwarization and slicing paradigms including essential concepts, history and different use cases. Secondly, we provide a tutorial of 5G network slicing technology enablers including SDN, NFV, MEC, cloud/Fog computing, network hypervisors, virtual machines & containers. Thidly, we comprehensively survey different industrial initiatives and projects that are pushing forward the adoption of SDN and NFV in accelerating 5G network slicing. A comparison of various 5G architectural approaches in terms of practical implementations, technology adoptions and deployment strategies is presented.. Moreover, we provide discussion on various open source orchestrators and proof of concepts representing industrial contribution.. The work also investigates the standardization efforts in 5G networks regarding network slicing and softwarization. Additionally, the article presents the management and orchestration of network slices in a single domain followed by a comprehensive survey of management and orchestration approaches in 5G network slicing across multiple domains while supporting multiple tenants. Furthermore, we highlight the future challenges and research directions regarding network softwarization and slicing using SDN and NFV in 5G networks.
Article
Full-text available
The unprecedented growth of energy consumption in data centers created critical concern in recent years for both the research community and industry. Besides its direct associated cost; high energy consumption also results in a large amount of CO2 emission and incurs extra cooling expenditure. The foremost reason for overly energy consumption is the underutilization of data center resources. In modern data centers, virtualization provides a promising approach to improve the hardware utilization level. Virtual machine placement is a process of mapping a group of virtual machines (VMs) onto a set of physical machines (PMs) in a data center with the aim of maximizing resource utilization and minimizing the total power consumption by PMs. An optimal virtual machine placement algorithm substantially contributes to cutting down the power consumption through assigning the input VMs to a minimum number of PMs and allowing the dispensable PMs to be turned off. However, VM Placement Problem is a complex combinatorial optimization problem and known to be NP-Hard problem. This paper presents an extensive review of virtual machine placement problem along with an overview of different approaches for solving virtual machine placement problem. The aim of this paper is to illuminate challenges and issues for current virtual machine placement techniques. Furthermore, we present a taxonomy of virtual machine placement based on various aspects such as methodology, number of objectives, operation mode, problem objectives, resource demand type and number of clouds. The state-of-the-art VM Placement techniques are classified in single objectives and multi-objective groups and a number of prominent works are reviewed in each group. Eventually, some open issues and future trends are discussed which serve as a platform for future research work in this domain.
Article
Full-text available
The novel network slicing paradigm represents an effective turning point to operate future wireless networks. Available networking and computational resources may be shared across different (instantiations of) services tailored onto specific vertical needs, envisioned as the main infrastructure tenants. While such customization enables meeting advanced key performance indicators (KPIs) introduced by upcoming 5G networks, advanced multi-tenancy approaches help to abate the cost of deploying and operating the network. However, the network slicing implementation requires a number of non-trivial practical considerations, including how resource sharing operations are actually implemented, how involved parties establish the corresponding agreement to instantiate, operate, and terminate such a sharing or the design of functional modules and interfaces supporting these operations. In this paper, we present a novel framework that unveils proper answers to the above design challenges. While existing initiatives are typically limited to single-domain and single-owner scenarios, our framework overcomes these limitations by enlarging the administrative scope of the network deployments fostering different providers to collaborate so as to facilitate a larger set of resources even spread across multiple domains. Numerical evaluations confirm the effectiveness and efficiency of the presented solution.
Conference Paper
Full-text available
The fifth generation telecommunication standard (5G) will make use of novel technologies, such as Software Defined Networks (SDN) and Network Function Virtualization (NFV). New models are integrating SDN and NFV in a control plane entity responsible of the Management and Orchestration (MANO) of the whole system. This entity, acting as director of the 5G control plane, is known as Service Orchestrator. This work presents SENATUS, an experimental service orchestrator targeting research and testing environments. SENATUS implements a set of innovations to support the validation of the future network planner modules that will be integrated on the management entities of the 5G architecture. Furthermore, we present two testbed scenarios to show the capability of SENATUS to control the SDN and NFV technologies previously mentioned.
Conference Paper
Full-text available
Vertical markets and industries are addressing alarge diversity of heterogeneous services, use cases, and ap-plications in 5G. It is currently common understanding thatfor networks to be able able to satisfy those needs, a flexible,adaptable, and programmable architecture based on networkslicing is required. Moreover, a softwarization and cloudifi-cation of the communications networks is already happening,where network functions (NFs) are transformed from monolithicpieces of equipment to programs running over a shared poolof computational and communication resources. However, thisnovel architecture paradigm requires new solutions to exploit itsinherent flexibility. In this paper, we introduce the concept ofresource elasticityas a key means to make an efficient use of thecomputational resources in 5G systems. Besides establishing adefinition as well as a set of requirements and key performanceindicators (KPIs), we propose mechanisms for the exploitationof elasticity in three different dimensions, namelycomputationalelasticityin the design and scaling of NFs,orchestration-drivenelasticityby flexible placement of NFs, andslice-aware elasticityvia cross-slice resource provisioning mechanisms. Finally, weprovide a succinct analysis of the architectural components thatneed to be enhanced to incorporate elasticity principles
Article
Full-text available
When users flood in cloud data centers, how to efficiently manage hardware resources and Virtual Machines (VMs) in a data center to both lower economical cost and ensure a high service quality becomes an inevitable work for cloud providers. VM migration is a cornerstone technology for the majority of cloud management tasks. It frees a VM from the underlying hardware. This feature brings a plenty of benefits to cloud providers and users. Many researchers are focusing on pushing its cutting edge. In this paper, we firstly give an overview of VM migration and discuss both its benefits and challenges. VM migration schemes are classified from three perspectives: manner, distance, and granularity. The studies on non-live migration are simply reviewed, and then those on live migration are comprehensively surveyed based on the three main challenges it faces: memory data migration, storage data migration, and network connection continuity. The works on quantitative analysis of VM migration performance are also elaborated. With the development and evolution of cloud computing, user mobility becomes an important motivation for live VM migration in some scenarios (e.g., fog computing). Thus, the studies regarding linking VM migration to user mobility are summarized as well. At last, we list the open issues which are waiting for solutions or further optimizations on live VM migration.
Article
Full-text available
Testbeds are essential for experimental evaluation as well as for product development. In the context of LTE networks, existing testbed platforms are limited either in functionality and/or extensibility or are too complex to modify and customise. In this work we present srsLTE, an open-source platform for LTE experimentation designed for maximum modularity and code reuse and fully compliant with LTE Release 8. We show the potential of the srsLTE library by extending the baseline code to allow LTE transmissions in the unlicensed bands and coexistence with WiFi. We also expand previous results on this emerging research area by showing how different vendor-specific mechanisms in WiFi cards might affect coexistence.
Article
Full-text available
Software-defined networking (SDN) and network function virtualization (NFV) have emerged as the most promising candidates for improving network function and protocol programmability and dynamic adjustment of network resources. On the one hand, SDN is responsible for providing an abstraction of network resources through well-defined application programming interfaces. This abstraction enables SDN to perform network virtualization, that is, to slice the physical infrastructure and create multiple coexisting application-specific virtual tenant networks (VTNs) with specific quality-of-service and service-level-agreement requirements, independent of the underlying optical transport technology and network protocols. On the other hand, the notion of NFV relates to deploying network functions that are typically deployed in specialized and dedicated hardware, as software instances [called virtual network functions (VNFs)] running on commodity servers (e.g., in data centers) through software virtualization techniques. Despite all the attention that has been given to virtualizing IP functions (e.g., firewall; authentication, authorization, and accounting) or Long-Term Evolution control functions (e.g., mobility management entity, serving gateway, and packet data network gateway), some transport control functions can also be virtualized and moved to the cloud as a VNF. In this work we propose virtualizing the tenant SDN control functions of a VTN and moving them into the cloud. The control of a VTN is a key requirement associated with network virtualization, since it allows the dynamic programming (i.e., direct control and configuration) of the virtual resources allocated to the VTN. We experimentally assess and evaluate the first SDN/NFV orchestration architecture in a multipartner testbed to dynamically deploy independent SDN controller instances for each instantiated VTN and to provide the required connectivity within minutes.
Conference Paper
Full-text available
Cloud computing is the future wave of information technology that provides infrastructure, platform and application as on demand services with low cost and rapid scalability. Infrastructure resources virtualization is the backbone of cloud computing to meet on demand, rapid scalability and resource pooling as the main cloud computing characteristics. Live migration is one of the powerful features in datacenters virtualization. Hosts load balance, power saving, failure recovery and dynamic resource allocation are all dependent on having live migration for the virtual machines. So studying and modeling live migrations is important to predict its impact on the datacenter performance and to take the migration decision at the optimum times. In this paper, we study the impact of live migration on the datacenter resources network and power consumption for VMware environment. This overhead modeling can be used to estimate the live migration impact on datacenter resources utilization given the virtual machine and network characteristics. Based on this estimation, the network admin can be alerted with this estimated overhead in order to confirm the live migration request or to postpone it to another optimum time for minimum interruption on the running applications.
Article
Cloud computing and network slicing are essential concepts of forthcoming 5G mobile systems. Network slices are essentially chunks of virtual computing and connectivity resources, configured and provisioned for particular services according to their characteristics and requirements. The success of cloud computing and network slicing hinges on the efficient allocation of virtual resources (e.g. VCPU, VMDISK) and the optimal placement of Virtualized Network Functions (VNFs) composing the network slices. In this context, this paper elaborates issues that may disrupt the placement of VNFs and VMs. The paper classifies the existing solutions for VM Placement (VMP) based on their nature, whether the placement is dynamic or static, their objectives, and their metrics. The paper then proposes a classification of VNF Placement (VNFP) approaches, first, regarding the general placement and management issues of VNFs, and second, based on the target VNF type.
Article
Network slicing represents a new paradigm to operate mobile networks. With network slicing, the underlying infrastructure is "sliced" into logically separate networks that can be customized to the specific needs of their tenant. Hands-on experiments on this technology are essential to understand its benefits and limits, and to validate the design and deployment choices. While some network slicing prototypes have been built for RANs, leveraging on the wide availability of radio hardware and open source software, there is currently no open source suite for end-to-end network slicing available to the research community. In this article we fill this gap by developing an end-to-end network slicing protocol stack, POSENS, which relies on a slice-aware shared RAN solution. We design the required algorithms and protocols, and provide a full implementation leveraging on state-of-the-art software components. We validate the effectiveness of POSENS in achieving tenant isolation and network slices customization, showing that no price in performance is paid toward this end. We believe that our tool will prove very useful to researchers and practitioners working on this novel architectural paradigm.
Conference Paper
By providing especially tailored instances of a virtual network,network slicing allows for a strong specialization of the offered services on the same shared infrastructure. Network slicing has profound implications on resource management, as it entails an inherent trade-off between: (i) the need for fully dedicated resources to support service customization, and (ii) the dynamic resource sharing among services to increase resource efficiency and cost-effectiveness of the system. In this paper, we provide a first investigation of this trade-off via an empirical study of resource management efficiency in network slicing. Building on substantial measurement data collected in an operational mobile network (i) we quantify the efficiency gap introduced by non-reconfigurable allocation strategies of different kinds of resources, from radio access to the core of the network, and (ii) we quantify the advantages of their dynamic orchestration at different timescales. Our results provide insights on the achievable efficiency of network slicing architectures, their dimensioning, and their interplay with resource management algorithms.
Article
The traffic explosion and the rising of diverse requirements lead to many challenges for traditional mobile network architecture on flexibility, scalability, and deployability. To meet new requirements in the 5G era, service based architecture is introduced into mobile networks. The monolithic network elements (e.g., MME, PGW, etc.) are split into smaller network functions to provide customized services. However, the management and deployment of network functions in service based 5G core network are still big challenges. In this paper, we propose a novel management architecture for 5G service based core network based on NFV and SDN. Combined with SDN, NFV and edge computing, the proposed framework can provide distributed and on-demand deployment of network functions, service guaranteed network slicing, flexible orchestration of network functions and optimal workload allocation. Simulations are conducted to show that the proposed framework and algorithm are effective in terms of reducing network operating cost.
Conference Paper
Emerging 5G mobile networks are envisioned to become multi-service environments, enabling the dynamic deployment of services with a diverse set of performance requirements, accommodating the needs of mobile network operators, verticals and over-the-top (OTT) service providers. Virtualizing the mobile network in a flexible way is of paramount importance for a cost-effective realization of this vision. While virtualization has been extensively studied in the case of the mobile core, virtualizing the radio access network (RAN) is still at its infancy. In this paper, we present Orion, a novel RAN slicing system that enables the dynamic on-the-fly virtualization of base stations, the flexible customization of slices to meet their respective service needs and which can be used in an end-to-end network slicing setting. Orion guarantees the functional and performance isolation of slices, while allowing for the efficient use of RAN resources among them. We present a concrete prototype implementation of Orion for LTE, with experimental results, considering alternative RAN slicing approaches, indicating its efficiency and highlighting its isolation capabilities. We also present an extension to Orion for accommodating the needs of OTT providers.
Article
Increasing the density of access points is one of the most effective mechanisms to cope with the growing traffic demand in wireless networks. To prevent energy wastage at low loads, a resource-on-demand (RoD) scheme is required to opportunistically (de)activate access points as network traffic varies. While previous publications have analytically modelled these schemes in the past, they have assumed that resources are immediately available when activated, an assumption that leads to inaccurate results and might result in inappropriate configurations of the RoD scheme. In this paper, we analyse a general RoD scenario with N access points and non-zero start-up times. We first present an exact analytical model that accurately predicts performance but has a high computational complexity, and then derive a simplified analysis that sacrifices some accuracy in exchange for a much lower computational cost. To illustrate the practicality of this model, we present the design of a simple configuration algorithm for RoD. Simulation results confirm the validity of the analyses, and the effectiveness of the configuration algorithm.
Article
With rapid adoption of the cloud computing model, many enterprises have begun deploying cloud-based services. Failures of virtual machines (VMs) in clouds have caused serious quality assurance issues for those services. VM replication is a commonly used technique for enhancing the reliability of cloud services. However, when determining the VM redundancy strategy for a specific service, many state-of-the-art methods ignore the huge network resource consumption issue that could be experienced when the service is in failure recovery mode. This paper proposes a redundant VM placement optimization approach to enhancing the reliability of cloud services. The approach employs three algorithms. The first algorithm selects an appropriate set of VM-hosting servers from a potentially large set of candidate host servers based upon the network topology. The second algorithm determines an optimal strategy to place the primary and backup VMs on the selected host servers with k-fault-tolerance assurance. Lastly, a heuristic is used to address the task-to-VM reassignment optimization problem, which is formulated as finding a maximum weight matching in bipartite graphs. The evaluation results show that the proposed approach outperforms four other representative methods in network resource consumption in the service recovery stage.
Article
Self-Organizing Networks (SON) is a common term for mobile network automation, critical to the cost-efficient deployment, operation and maintenance of mobile networks. This article provides an overview of SON standardization in 3GPP, including both existing and planned functionalities. It also provides an operator perspective on the relevance and use of 3GPP SON functionalities at different stages of the network design-and-operations cycle. In the long-term it is envisaged that automation will become a natural component in network operations, although the success of SON will depend on automation's benefits in relation to its cost.
Article
Network functions virtualization (NFV) together with software-defined networking (SDN) has the potential to help operators satisfy tight service level agreements, accurately monitor and manipulate network traffic, and minimize operating expenses. However, in scenarios that require packet processing to be redistributed across a collection of network function (NF) instances, simultaneously achieving all three goals requires a framework that provides efficient, coordinated control of both internal NF state and network forwarding state. To this end, we design a control plane called OpenNF. We use carefully designed APIs and a clever combination of events and forwarding updates to address race conditions, bound overhead, and accommodate a variety of NFs. Our evaluation shows that OpenNF offers efficient state control without compromising flexibility, and requires modest additions to NFs.
Conference Paper
Developing elastic applications should be easy. This paper takes a step toward the goal of generalizing elasticity by observing that a broadly deployed class of software-- the network middlebox--is particularly well suited to dynamic scale. Middleboxes tend to achieve a clean separation between a small amount of per-flow network state and a large amount of complex application logic. We present a state-centric, systems-level abstraction for elastic middleboxes called Split/Merge. A virtual middlebox that has appropriately classified its state (e.g., perflow state) can be dynamically scaled out (or in) by a Split/Merge system, but remains ignorant of the number of replicas in the system. Per-flow state may be transparently split between many replicas or merged back into one, while the network ensures flows are routed to the correct replica. As a result, Split/Merge enables load-balanced elasticity. We have implemented a Split/Merge system, called FreeFlow, and ported Bro, an open-source intrusion detection system, to run on it. In controlled experiments, FreeFlow enables a 25% reduction in maximum latency while eliminating hotspots during scale-out and a 50% quicker scale-in than standard approaches.
Article
Due to the growing demand of flexible resource management for cloud computing services, researches on live virtual machine migration have attained more and more attention1. Live migration of virtual machine across different hosts has been a powerful tool to facilitate system maintenance, load balancing, fault tolerance and so on. In this paper, we use a measurement-based approach to compare the performance of two major live migration technologies under certain network conditions, i.e., VMotion and XenMotion. The results show that VMotion generates much less data transferred than XenMotion when migrating identical VMs. However, in network with moderate packet loss and delay, which are typical in a VPN (virtual private network) scenario used to connect the data centers, XenMotion outperforms VMotion in total migration time. We hope that this study can be helpful in choosing suitable virtualization environments for data center administrators and optimizing existing live migration mechanisms.
The orchestration in 5G exchange – a multi-provider NFV framework for 5G services
  • Ger
Unikernels: library operating systems for the cloud
  • Madhavapeddy