Service chain mapping algorithm based on reinforcement learning

A service chain resource scheduling architecture of multi-agent based on artificial intelligence technology was proposed.Meanwhile,a service chain mapping algorithm based on reinforcement learning was designed.Through the Q-learning mechanism,the location of each virtual network element in the servi...

Full description

Saved in:
Bibliographic Details
Main Authors: Liang WEI, Tao HUANG, Jiao ZHANG, Zenan WANG, Jiang LIU, Yunjie LIU
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2018-01-01
Series:Tongxin xuebao
Subjects:
Online Access:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2018002/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841539421213556736
author Liang WEI
Tao HUANG
Jiao ZHANG
Zenan WANG
Jiang LIU
Yunjie LIU
author_facet Liang WEI
Tao HUANG
Jiao ZHANG
Zenan WANG
Jiang LIU
Yunjie LIU
author_sort Liang WEI
collection DOAJ
description A service chain resource scheduling architecture of multi-agent based on artificial intelligence technology was proposed.Meanwhile,a service chain mapping algorithm based on reinforcement learning was designed.Through the Q-learning mechanism,the location of each virtual network element in the service chain was determined according to the system status and the reward and punishment feedback after the deployment.The experimental results show that compared with the classical algorithms,the algorithm effectively reduces the average transmission delay of the service and improves the load balance of the system.
format Article
id doaj-art-51bbd3cbeaa3408f9fbad171441d89b2
institution Kabale University
issn 1000-436X
language zho
publishDate 2018-01-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-51bbd3cbeaa3408f9fbad171441d89b22025-01-14T07:14:07ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2018-01-01399010059715954Service chain mapping algorithm based on reinforcement learningLiang WEITao HUANGJiao ZHANGZenan WANGJiang LIUYunjie LIUA service chain resource scheduling architecture of multi-agent based on artificial intelligence technology was proposed.Meanwhile,a service chain mapping algorithm based on reinforcement learning was designed.Through the Q-learning mechanism,the location of each virtual network element in the service chain was determined according to the system status and the reward and punishment feedback after the deployment.The experimental results show that compared with the classical algorithms,the algorithm effectively reduces the average transmission delay of the service and improves the load balance of the system.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2018002/network function virtualizationartificial intelligenceservice chainreinforcement learning
spellingShingle Liang WEI
Tao HUANG
Jiao ZHANG
Zenan WANG
Jiang LIU
Yunjie LIU
Service chain mapping algorithm based on reinforcement learning
Tongxin xuebao
network function virtualization
artificial intelligence
service chain
reinforcement learning
title Service chain mapping algorithm based on reinforcement learning
title_full Service chain mapping algorithm based on reinforcement learning
title_fullStr Service chain mapping algorithm based on reinforcement learning
title_full_unstemmed Service chain mapping algorithm based on reinforcement learning
title_short Service chain mapping algorithm based on reinforcement learning
title_sort service chain mapping algorithm based on reinforcement learning
topic network function virtualization
artificial intelligence
service chain
reinforcement learning
url http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2018002/
work_keys_str_mv AT liangwei servicechainmappingalgorithmbasedonreinforcementlearning
AT taohuang servicechainmappingalgorithmbasedonreinforcementlearning
AT jiaozhang servicechainmappingalgorithmbasedonreinforcementlearning
AT zenanwang servicechainmappingalgorithmbasedonreinforcementlearning
AT jiangliu servicechainmappingalgorithmbasedonreinforcementlearning
AT yunjieliu servicechainmappingalgorithmbasedonreinforcementlearning