Deployment method for vEPC virtualized network function via Q-learning

Quan YUAN; Hong-bo TANG; Kai-zhi HUANG; Xiao-lei WANG; Yu ZHAO

doi:10.11959/j.issn.1000-436x.2017173

您当前的位置：

首页 >

文章列表页 >

Deployment method for vEPC virtualized network function via Q-learning

Correspondences | 更新时间：2024-06-05

- Deployment method for vEPC virtualized network function via Q-learning
- Journal on Communications Vol. 38, Issue 8, Pages: 172-182(2017)
- 作者机构：
  
  1. 国家数字交换系统工程技术研究中心，河南郑州 450002
  2. 移动互联网安全技术国家工程实验室，北京 100876
- 作者简介：
- 基金信息：
  
  The Nationa1 High Techno1ogy Research and Deve1opment Program of China（863 Program）(2015AA01A706);The Innovation Group Program Project of National Natural Science Foundation of China(61521003);The National Key Technology R＆D Program(2014BAH30B01)
- DOI：10.11959/j.issn.1000-436x.2017173
  CLC： TN915.81
- Online First：2017-08，
  
  Published：25 August 2017
- 稿件说明：
移动端阅览
Quan YUAN, Hong-bo TANG, Kai-zhi HUANG, et al. Deployment method for vEPC virtualized network function via Q-learning[J]. Journal on Communications, 2017, 38(8): 172-182.
DOI：

Quan YUAN, Hong-bo TANG, Kai-zhi HUANG, et al. Deployment method for vEPC virtualized network function via Q-learning[J]. Journal on Communications, 2017, 38(8): 172-182. DOI： 10.11959/j.issn.1000-436x.2017173.

摘要

针对虚拟化演进分组核心网（vEPC）环境下，现有虚拟网络功能（VNF）部署方法无法在优化时延的同时保证服务链部署收益的问题，提出一种改进的基于Q-1earning算法的vEPC虚拟网络功能部署方法。在传统0-1规划模型的基础上，采用马尔可夫决策过程建立了 vEPC 服务链部署的空间—时间优化模型，并设计了改进的Q-1earning算法求解。该方法同时考虑了空间维度下的EPC服务链虚拟映射和时间维度下的VNF生命周期管理，实现了VNF部署的收益—时延多目标优化。仿真结果表明，与其他VNF部署方法相比，该方法在降低网络时延的同时提高了VNF部署的收益和请求接受率。

Abstract

In the context of vEPC，a method of virtua1ized network function（VNF）dep1oyment via an improved Q-1earning a1gorithm was proposed to so1ve the prob1em that the existing methods cannot achieve the optimization of time de1ay and revenue of VNF dep1oyment simu1taneous1y.To get the optima1 dep1oyment po1icy in both space dimension and time dimension，a Markov decision process mode1 of vEPC service function chain dep1oyment on the basis of the traditiona1 0-1 programming mode1 was estab1ished and a so1ution with an improved Q-1earning a1gorithm was proposed.The method had taken fu11 consideration of both virtua1 network embedding in space dimension and orchestration of VNF 1ife cyc1e in time dimension，and thus，the mu1ti-objective optimization of revenue and de1ay cou1d be attained.Simu1ation shows that the method can reduce network de1ay whi1e increasing the revenue and the ratio of request acceptance compared with other dep1oyment methods.

关键词

Keywords

references

SAMA M R , CONTRERAS L M , KAIPPALLIMALIL J , et al . Software-defined control of the virtualized mobile packet core [J ] . IEEE Communications Magazine , 2015 , 53 ( 2 ): 107 - 115 .

TALEB T , CORICI M , PARADA C , et al . EASE:EPC as a service to ease mobile core network deployment over cloud [J ] . IEEE Network , 2015 , 29 ( 2 ): 78 - 88 .

MOENS H , DE F . VNF-P:a model for efficient placement of virtualized network functions [C ] // IEEE International Conference on Network and Service Management . 2014 : 418 - 423 .

CLAYMAN S , MAINI E , GALIS A , et al . The dynamic placement of virtual network functions [C ] // IEEE International Conference on Network Operations and Management Symposium . 2014 : 1 - 9 .

BASTA A , KELLERER W , HOFFMANN M , et al . Applying NFV and SDN to LTE mobile core gateways,the functions placement problem [C ] // ACM Workshop on All Things Cellular:Operations,Applications,＆ Challenges , 2014 : 33 - 38 .

江逸茗 , 兰巨龙 , 周惠琴 . 网络虚拟化环境下的资源监控策略 [J ] . 电子与信息学报 , 2014 , 36 ( 3 ): 708 - 714 .

JIANG Y M , LAN J L , ZHOU H Q . Resource monitoring policy for network virtualization environment [J ] . Journal of Electronics ＆ Information Technology , 2014 , 36 ( 3 ): 708 - 714 .

MIJUMBI R , SERRAT J , GORRICHO J L , et al . Design and evaluation of algorithms for mapping and scheduling of virtual network functions [C ] // IEEE Conference on Network Softwarization . 2015 : 1 - 9 .

HAN B , GOPALAKRISHNAN V , JI L S , et al . Network function virtualization:challenges and opportunities for innovations [J ] . IEEE Communications Magazine , 2015 , 53 ( 2 ): 90 - 97 .

BASTA A , KELLERER W , HOFFMANN M , et al . A virtual SDN-enabled LTE EPC architecture:a case study for S-/P-Gateways functions [C ] // IEEE International Conference on SDN for Future Networks and Services . 2013 : 1 - 7 .

FISCHER A , BOTERO J F , TILL BECK M , et al . Virtual network embedding:a survey [J ] . IEEE Communications Surveys ＆ Tutorials , 2013 , 15 ( 4 ): 1888 - 1906 .

ROSS S M . Stochastic processes [J ] . John Wiley ＆ Sons Inc New York , 1996 , 48 ( 1 ): 528 - 529 .

SONG H , LIU C , LAWARRÉE J , et al . Optimal electricity supply bidding by Markov decision process [J ] . IEEE Transactions on Power Systems , 2000 , 15 ( 2 ): 618 - 624 .

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

BUSONIU L , BABUSKA R . Reinforcement learning and dynamic programming using function approximators [M ] . Florida : CRC PressPress , 2010 .

DUONG T , CHU Y , NGUYEN T , et al . Virtual machine placement via Q-learning with function approximation [C ] // 2015 IEEE Global Communications Conference . 2015 : 1 - 6 .

ZEGURA E W , CALVERT K L , ACHARJEE S B . How to model an internetwork [C ] // IEEE Conference of Computer Societies,Networking the Next Generation . 1996 : 594 - 602 .

ORLOWSKI S , WESSÄLY R , PIÓRO M , et al . 0-survivable network design library [J ] . Networks , 2010 , 55 ( 3 ): 276 - 286 .

Views

2736

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

OTN+5G education private network empowers digital transformation——taking the construction of education private network in Bao’an District, Shenzhen as an example

Research and construction of new digital foundation for the fusion between IPv6 and 5G

Endogenous security common problems and solutions of the mobile communication networks

Survey of high-precision localization and the prospect of future evolution

Dynamic interference coordination scheme based on the iterative joint transmission in ultra dense network

Related Author

XIAO Chunguang

LI Tao

ZHAO Xing

ZHU Yue

LIANG Zhelong

JIAO Baochen

LIN Chujian

Xinsheng JI

Related Institution

Shenzhen Bao'an District Education Development Center

Big Data Management Center, Nankai University

College of Electronic Information and Optical Engineering, Nankai University

College of Computer Science、College of Cyber Science, Nankai University

National Digital Switching System Engineering ＆ Technological R＆D Center

AI问答

⁰