MDP and Machine Learning-Based Cost-Optimization of Dynamic Resource Allocation for Network Function Virtualization

Shi, Runyu; Zhang, Jia; Chu, Wenjing; Bao, Qing; Jin, Xiatao; Gong, Chenran; Zhu, Qihao; Yu, Chang; Rosenberg, Steven

doi:10.1109/scc.2015.19

Cited by 65 publications

(28 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In contrast, Shi et al [410] use BN to predict future resource reliability, the ability of a resource to ensure constant system operation without disruption, of NFV components based on historical resource usage of VNFC. The learning algorithm is triggered when an NFV component is initially allocated to resources.…”

Section: Resource Allocationmentioning

confidence: 99%

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Boutaba

Salahuddin

Limam

et al. 2018

J Internet Serv Appl

792

391

View full text Add to dashboard Cite

Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve problems and enable automation in diverse domains. Primarily, this is due to the explosion in the availability of data, significant improvements in ML techniques, and advancement in computing capabilities. Undoubtedly, ML has been applied to various mundane and complex problems arising in network operation and management. There are various surveys on ML for specific areas in networking or for specific network technologies. This survey is original, since it jointly presents the application of diverse ML techniques in various key areas of networking across different network technologies. In this way, readers will benefit from a comprehensive discussion on the different learning paradigms and ML techniques applied to fundamental problems in networking, including traffic prediction, routing and classification, congestion control, resource and fault management, QoS and QoE management, and network security. Furthermore, this survey delineates the limitations, give insights, research challenges and future opportunities to advance ML in networking. Therefore, this is a timely contribution of the implications of ML for networking, that is pushing the barriers of autonomic network operation and management.

show abstract

Section: Resource Allocationmentioning

confidence: 99%

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Boutaba

Salahuddin

Limam

et al. 2018

J Internet Serv Appl

792

391

View full text Add to dashboard Cite

show abstract

“…In addition, it does not integrate the QoS constraints with reinforcement learning framework like our work (see in later sections). Shi et al proposed the MDP model for NFV resource allocation to form a service chain with cost optimization. It adopts the Bayesian probability to predict the transition probabilities among VNF instances; thus, it boils down to the model‐based reinforcement learning, where transition probabilities must be fully observable and the value iteration approach is used for solution.…”

Section: Related Workmentioning

confidence: 99%

“…Reinforcement learning, with its trial‐and‐error mechanism (for aspect 1), reward mechanism (for aspect 2), exploration‐exploitation ability (for aspect 3), etc, makes a competitive candidate for the SFC orchestration framework in 5G slices. Meanwhile, recent years have also seen its applications in modern network paradigms for user experience optimization, cost minimization in resource allocation, Internet of things and smart city services, resource provisioning in vehicular clouds, etc. Based on the discussion above, this paper proposes the reinforcement learning–based QoS/QoE‐aware SFC framework in the context of software‐driven (ie, SDN/NFV‐enabled) 5G slices.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement learning–based QoS/QoE‐aware service function chaining in software‐driven 5G slices

Chen

Zhang

et al. 2018

Trans Emerging Tel Tech

View full text Add to dashboard Cite

With the ever‐growing diversity of devices and applications that will be connected to 5G networks, flexible and agile service orchestration with acknowledged quality of experience (QoE) that satisfies the end user's functional and quality‐of‐service (QoS) requirements is necessary. Software‐defined networking (SDN) and network function virtualization (NFV) are considered key enabling technologies for 5G core networks. In this regard, this paper proposes a reinforcement learning–based QoS/QoE‐aware service function chaining (SFC) scheme in SDN/NFV‐enabled 5G slices. First, it implements a lightweight QoS information collector based on the Link Layer Discovery Protocol, which works in a piggyback fashion on the southbound interface of the SDN controller, to enable QoS‐awareness. Then, a deep Q‐network–based orchestration agent is designed to support SFC in the context of NFV. The agent takes into account the QoE and QoS as key aspects to formulate the reward so that it is expected to maximize QoE while respecting QoS constraints. The experiment results show that the proposed framework exhibits good performance in QoE provisioning and QoS requirements maintenance for SFC in dynamic network environments.

show abstract

“…[30] proposes two algorithms to embed network service chains with a target of minimizing the overall embedding cost. The authors in [31] use machine learning techniques to find an optimal placement for VNFs given data center resources. An optimal locationaware VNF mapping is proposed in [32], that minimizes the function processing and traffic transmission cost.…”

Section: B Dimensioning and Resource Allocation Problemsmentioning

confidence: 99%

Towards a Cost Optimal Design for a 5G Mobile Core Network Based on SDN and NFV

Basta

Blenk

Hoffmann

et al. 2017

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

With the rapid growth of user traffic, service innovation, and the persistent necessity to reduce costs, today's mobile operators are faced with several challenges. In networking, two concepts have emerged aiming at cost reduction, increase of network scalability and deployment flexibility, namely Network Functions Virtualization (NFV) and Software Defined Networking (SDN). NFV mitigates the dependency on hardware, where mobile network functions are deployed as software Virtual Network Functions (VNF) on commodity servers at cloud infrastructure, i.e., data centers (DC). SDN provides a programmable and flexible network control by decoupling the mobile network functions into control plane and data plane functions. The design of the next generation mobile network (5G) requires new planning and dimensioning models to achieve a cost optimal design that supports a wide range of traffic demands. We propose three optimization models that aim at minimizing the network load cost as well as data center resources cost by finding the optimal placement of the data centers as well the SDN and NFV mobile network functions. The optimization solutions demonstrate the trade-offs between the different data center deployments, i.e., centralized or distributed, and the different cost factors, i.e., optimal network load cost or data center resources cost. We propose a Pareto optimal multi-objective model that achieves a balance between network and data center cost. Additionally, we use prior inference, based on the solutions of the single objectives, to pre-select data center locations for the multi-objective model that results in reducing the optimization complexity and achieves savings in run time while keeping a minimal optimality gap.

show abstract

MDP and Machine Learning-Based Cost-Optimization of Dynamic Resource Allocation for Network Function Virtualization

Cited by 65 publications

References 25 publications

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Reinforcement learning–based QoS/QoE‐aware service function chaining in software‐driven 5G slices

Towards a Cost Optimal Design for a 5G Mobile Core Network Based on SDN and NFV

Contact Info

Product

Resources

About