Deep Reinforcement Learning Based Migration Mechanism for Service Function Chain in Operator Networks

被引：0
|
作者：
Chen Z. [1 ,2 ]
Feng G. [2 ]
He Y. [2 ]
Zhou Y. [3 ]
机构：
[1] College of Computer Science and Engineering, Chongqing University of Technology, Chongqing
[2] National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu
[3] Department of Computer Science and Software Engineering, Auburn University, Auburn
来源：
Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology | 2020年 / 42卷 / 09期
基金：
中国国家自然科学基金;
关键词：
Deep Reinforcement Learning (DRL); Migration mechanism; Operator network; Service Function Chain (SFC);
D O I：
10.11999/JEITdzyxxxb-42-9-2173
中图分类号：
学科分类号：
摘要：
To improve the service experience provided by the operator network, this paper studies the online migration of Service Function Chain(SFC). Based on the Markov Decision Process(MDP), modeling analysis is performed on the migration of multiple Virtual Network Functions(VNF) in SFC. By combining reinforcement learning and deep neural networks, a double Deep Q-Network(double DQN) based service function chain migration mechanism is proposed. This method can make online migration decisions and avoid over-estimation. Experimental result shows that when compared with the fixed deployment algorithm and the greedy algorithm, the double DQN based SFC migration mechanism has obvious advantages in end-to-end delay and network system revenue, which can help the mobile operator to improve the quality of experience and the efficiency of resources usage.
引用
收藏
页码：2173 / 2179
页数：6
相关论文
共 16 条
  • [1] CHATRAS B, OZOG F F., Network functions virtualization: The portability challenge, IEEE Network, 30, 4, pp. 4-8, (2016)
  • [2] ZHANG Qixia, LIU Fangming, ZENG Chaobing, Adaptive interference-aware VNF placement for service-customized 5G network slices, IEEE Conference on Computer Communications, pp. 2449-2457, (2019)
  • [3] AGARWAL S, MALANDRINO F, CHIASSERINI C F, Et al., Joint VNF placement and CPU allocation in 5G, IEEE Conference on Computer Communications, pp. 1943-1951, (2018)
  • [4] KUO T W, LIOU B H, LIN K C J, Et al., Deploying chains of virtual network functions: On the relation between link and server usage, The 35th Annual IEEE International Conference on Computer Communications, pp. 1-9, (2016)
  • [5] TALEB T, KSENTINI A, FRANGOUDIS P A., Follow-me cloud: When cloud services follow mobile users, IEEE Transactions on Cloud Computing, 7, 2, pp. 369-382, (2019)
  • [6] ERAMO V, MIUCCI E, AMMAR M, Et al., An approach for service function chain routing and virtual function network instance migration in network function virtualization architectures, IEEE/ACM Transactions on Networking, 25, 4, pp. 2008-2025, (2017)
  • [7] HOUIDI O, SOUALAH O, LOUATI W, Et al., An efficient algorithm for virtual network function scaling, 2017 IEEE Global Communications Conference, pp. 1-7, (2017)
  • [8] CHO D, TAHERI J, ZOMAYA A Y, Et al., Real-time Virtual Network Function (VNF) migration toward low network latency in cloud environments, The 10th IEEE International Conference on Cloud Computing, pp. 798-801, (2017)
  • [9] LAN Julong, YU Changhe, HU Yuxiang, Et al., A SDN routing optimization mechanism based on deep reinforcement learning, Journal of Electronics&Information Technology, 41, 11, pp. 2669-2674, (2019)
  • [10] HUANG Xiaohong, YUAN Tingting, QIAO Guanhua, Et al., Deep reinforcement learning for multimedia traffic control in software defined networking, IEEE Network, 32, 6, pp. 35-41, (2018)
12