Cross-domain service chain mapping mechanism based on Q-learning

Hongqi ZHANG; Rui HUANG; Yingjie YANG; Dexian CHANG; Liancheng ZHANG

doi:10.11959/j.issn.1000-436x.2018283

您当前的位置：

首页 >

文章列表页 >

Cross-domain service chain mapping mechanism based on Q-learning

Papers | 更新时间：2024-06-05

- Cross-domain service chain mapping mechanism based on Q-learning
- Journal on Communications Vol. 39, Issue 12, Pages: 102-112(2018)
- 作者机构：
  
  中国人民解放军战略支援部队信息工程大学密码工程学院，河南郑州 450001
- 作者简介：
- 基金信息：
  
  The National High Technology Research and Development Program of China(863 Program)(No.2012AA012704);The National Natural Science Foundation of China(No.61402526);The National Natural Science Foundation of China(No.61402525);The National Natural Science Foundation of China(No.61502528);Zhengzhou Science and Technology Talents Project(No.131PLJRC644)
- DOI：10.11959/j.issn.1000-436x.2018283
  CLC： TP393
- Online First：2018-12，
  
  Published：25 December 2018
- 稿件说明：
移动端阅览
Hongqi ZHANG, Rui HUANG, Yingjie YANG, et al. Cross-domain service chain mapping mechanism based on Q-learning[J]. Journal on Communications, 2018, 39(12): 102-112.
DOI：

Hongqi ZHANG, Rui HUANG, Yingjie YANG, et al. Cross-domain service chain mapping mechanism based on Q-learning[J]. Journal on Communications, 2018, 39(12): 102-112. DOI： 10.11959/j.issn.1000-436x.2018283.

摘要

针对软件定义网络功能虚拟化环境下跨域服务链映射问题，提出了一种区域集中管理、全局协同调度的虚拟服务资源管控架构。在此基础上，建立了一种有效的跨域服务链映射框架，在此框架下将跨域服务链映射问题建模为以最小化映射开销为目标的整数线性规划问题，并基于Q-learning机制设计跨域服务链构建请求分割算法进行优化求解。仿真实验表明该方法在平均分割时间、平均映射开销和服务链构建请求接受率等方面相较传统方法具有更优的表现。

Abstract

A virtual service resources controlling architecture with regional centralized management and global coordinated scheduling was proposed for the problem of cross-domain service chain mapping in SDNFV environment. On this basis

an effective mapping framework was built and the cross-domain mapping problem was modeled as an ILP with the purpose of minimizing mapping cost. A partitioning algorithm was designed to solve the problem based on Q-learning mechanism under this framework. Simulation results show that the performances of this method are better than other traditional methods on average partition time

average mapping cost

and acceptance ratioof service chain mapping request.

关键词

Keywords

references

KREUTZ D , RAMOS F M V , VERÍSSIMO P E , et al . Software-defined networking: a comprehensive survey [J ] . Proceedings of the IEEE , 2015 , 103 ( 1 ): 14 - 76 .

黄韬，刘江，霍如，等 . 未来网络体系架构研究综述 [J ] . 通信学报， 2014 , 35 ( 8 ): 184 - 197 .

HUANG T , LIU J , HUO R , et al . Survey of research on future network architectures [J ] . Journal on Communications , 2014 , 35 ( 8 ): 184 - 197 .

MIJUMBI R , SERRAT J , GORRICHO J L , et al . Network function virtualization: state-of-the-art and research challenges [J ] . IEEE Communications Surveys & Tutorials , 2017 , 18 ( 1 ): 236 - 262 .

SUN C , BI J , ZHENG Z , et al . NFP: enabling network function parallelism in NFV [C ] // ACM Conference of the Special Interest Group on Data Communication . 2017 : 43 - 56 .

LI Y , CHEN M . Software-defined network function virtualization: a survey [J ] . IEEE Access , 2015 , 3 ( 1 ): 2542 - 2553 .

BHAMARE D , JAIN R , SAMAKA M , et al . A survey on service function chaining [J ] . Journal of Network and Computer Applications , 2016 , 75 ( 3 ): 138 - 155 .

XIONG G , HU Y , LAN J , et al . A mechanism for configurable network service chaining and its implementation [J ] . KSII Transactions on Internet and Information Systems , 2016 , 10 ( 8 ): 3701 - 3727 .

ZHANG Q , XIAO Y , LIU F , et al . Joint optimization of chain placement and request scheduling for network function virtualization [C ] // 2017 IEEE International Conference on Distributed Computing Systems . 2017 : 731 - 741 .

YE Z , CAO X , WANG J , et al . Joint topology design and mapping of service function chains for efficient, scalable, and reliable network functions virtualization [J ] . IEEE Network , 2016 , 30 ( 3 ): 81 - 87 .

MOENS H , TURCK F D . Customizable function chains: managing service chain variability in hybrid NFV networks [J ] . IEEE Transactions on Network and Service Management , 2016 , 13 ( 4 ): 711 - 724 .

DIETRICH D , ABUJODA A , RIZK A , et al . Multi-provider service chain embedding with nestor [J ] . IEEE Transactions on Network and Service Management , 2017 , 14 ( 1 ): 91 - 105 .

LIN P , BI J , WANG Y . WEBridge: west-east bridge for distributed heterogeneous SDN NOSespeering [J ] . Security and Communication Networks , 2015 , 8 ( 10 ): 1926 - 1942 .

LIN P , BI J , WOLFF S , et al . A west-east bridge based SDN inter-domain testbed [J ] . Communications Magazine IEEE , 2015 , 53 ( 2 ): 190 - 197 .

WANG Y , BI J , LIN P , et al . SDI: a multi-domain SDN mechanism for fine-grained inter-domain routing [J ] . Annals of Telecommunications , 2016 , 71 ( 11 - 12 ): 625 - 637 .

HOUIDI I , LOUATI W , AMEUR W B , et al . Virtual network provisioning across multiple substrate networks [J ] . Computer Networks , 2011 , 55 ( 4 ): 1011 - 1023 .

GROSSMAN P . Introduction to algorithms [M ] . MCGRAW : MIT press , 2011 .

ZHANG Q , LIN M , YANG L T , et al . Energy-efficient scheduling for real-time systems based on deep Q-learning model [J ] . IEEE Transactions on Sustainable Computing , 2017 , 12 ( 9 ): 41 - 49 .

WATKINS C , DAYAN P . Q-learning [J ] . Machine Learning , 1992 , 8 ( 3 - 4 ): 279 - 292 .

WEI Q , LEWISF L , SUN Q , et al . Discrete-time deterministic Q-learning: a novel convergence analysis [J ] . IEEE transactions on cybernetics , 2016 : 1 - 14 .

DIETRICH D , RIZK A , APADIMITRIOU P . Multi-domain virtual network embedding with limited information disclosure [C ] // The 16th IFTP Networking Conference , 2013 : 1 - 3 .

贾伟，夏靖波 . 跨域虚拟网络映射问题研究 [J ] . 电子与信息学报， 2016 , 38 ( 3 ): 728 - 734 .

JIA W , XIA J B . Research on virtual network embedding across multiple domains [J ] . Journal of Electronics & Information Technology , 2016 , 38 ( 3 ): 728 - 734 .

WANG X , LOGUINOY D . Understanding and modeling the Internet topology: economics and evolution perspective [J ] . IEEE/ACM Transactions on Networking , 2010 , 18 ( 1 ): 257 - 270 .

MECHTRI M , GHRIBI C , ZEGHLACHE D . A scalable algorithm for the placement of service function chains [J ] . IEEE Transactions on Network and Service Management , 2016 , 13 ( 3 ): 533 - 546 .

CHOWDHURY M , SAMUEL F , BOUTABA R . PolyViNE: policy-based virtual network embedding acrossmultiple domains [C ] // The 2nd ACM SIGCOMMVISA . 2010 : 49 - 56 .

Views

1480

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Service chain mapping algorithm based on reinforcement learning

QL-STCT: an intelligent routing convergence method for SDN link failure

Service chain deployment algorithms for deterministic end-to-end delay upper bound

MicroNF:a microservice-based hybrid framework for NFV

Discrete particle swarm optimization based multi-objective service path constructing algorithm

Related Author

Liang WEI

Tao HUANG

Jiao ZHANG

Zenan WANG

Jiang LIU

Yunjie LIU

Chuanhuang LI

Yangting CHEN

Related Institution

State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications

School of Information and Electronic Engineering (Sussex Artificial Intelligence Institute), Zhejiang Gongshang University

Purple Mountain Laboratories

Carleton University

Institute for Network Sciences and Cyberspace, Tsinghua University

AI问答

⁰