NFVdeep adaptive online service function chain deployment with deep reinforcement learning

With the evolution of network function virtualization (NFV), diverse network services can be flexibly offered as service function chains (SFCs) consisted of different virtual network functions (VNFs). However, network state and traffic typically exhibit unpredictable variations due to stochastically...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the International Symposium on Quality of Service S. 1 - 10
Hauptverfasser: Xiao, Yikai, Zhang, Qixia, Liu, Fangming, Wang, Jia, Zhao, Miao, Zhang, Zhongxing, Zhang, Jiaxing
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: New York, NY, USA ACM 24.06.2019
Schriftenreihe:ACM Other Conferences
Schlagworte:
Computing methodologies > Machine learning
Deep Reinforcement Learning
Network Function Virtualization (NFV)
Networks > Network algorithms > Control path algorithms > Network resources allocation
Networks > Network components > Middle boxes > network appliances
Networks > Network properties > Network dynamics
QoS-Aware Resource Management
Service Function Chain
service function chain
deep reinforcement learning
network function virtualization (NFV)
QoS-aware resource management
ISBN:9781450367783, 145036778X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:With the evolution of network function virtualization (NFV), diverse network services can be flexibly offered as service function chains (SFCs) consisted of different virtual network functions (VNFs). However, network state and traffic typically exhibit unpredictable variations due to stochastically arriving requests with different quality of service (QoS) requirements. Thus, an adaptive online SFC deployment approach is needed to handle the real-time network variations and various service requests. In this paper, we firstly introduce a Markov decision process (MDP) model to capture the dynamic network state transitions. In order to jointly minimize the operation cost of NFV providers and maximize the total throughput of requests, we propose NFVdeep, an adaptive, online, deep reinforcement learning approach to automatically deploy SFCs for requests with different QoS requirements. Specifically, we use a serialization-and-backtracking method to effectively deal with large discrete action space. We also adopt a policy gradient based method to improve the training efficiency and convergence to optimality. Extensive experimental results demonstrate that NFVdeep converges fast in the training process and responds rapidly to arriving requests especially in large, frequently transferred network state space. Consequently, NFVdeep surpasses the state-of-the-art methods by 32.59% higher accepted throughput and 33.29% lower operation cost on average.
ISBN:9781450367783
145036778X
DOI:10.1145/3326285.3329056