首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于反馈机制的自愈算法
引用本文:赵季红,曲 桦,陈文东.基于反馈机制的自愈算法[J].通信学报,2012(1):1-9.
作者姓名:赵季红  曲 桦  陈文东
作者单位:西安交通大学电子与信息工程学院;西安邮电学院通信与信息工程学院
基金项目:国家自然科学基金资助项目(60872058,61071126);国家高技术研究发展计划(“863”计划)基金资助项目(2009AA01Z213);新一代宽带无线移动通信网国家科技重大专项基金资助项目~~
摘    要:提出了一种网络自愈算法,当网络中的节点发生故障或链路出现拥塞时,该算法利用Q学习的反馈机制、多QoS约束的评价函数和基于Boltzmann-Gibbs分布的路径选择策略,自适应地选择恢复路径,降低了选择发生故障和拥塞路径的概率,从而实现了自愈。仿真结果表明,该算法在恢复率、区分业务能力和网络资源优化等方面,表现出了良好的性能。

关 键 词:故障恢复  网络自愈  Q学习  多QoS约束  区分业务  资源优化

Self-healing algorithm based on feedback mechanism
ZHAO Ji-hong,QU Hua,CHEN Wen-dong.Self-healing algorithm based on feedback mechanism[J].Journal on Communications,2012(1):1-9.
Authors:ZHAO Ji-hong  QU Hua  CHEN Wen-dong
Institution:1(1.School of Electronic and Information Engineering,Xi’an Jiaotong University,Xi’an 710049,China; 2.School of Telecommunications and Information Engineering,Xi’an University of Posts & Telecommunications,Xi’an 710061,China)
Abstract:A network self-healing algorithm was presented.The proposed algorithm reduced the probability of selecting the failure or congestion paths and achieved self-healing by selecting recovery path adaptively when the nodes failure or link congestion in the network,which was based on Q-learning feedback mechanism,multi-QoS constrained of the evaluation function and path selection strategy using Boltzmann-Gibbs distribution.Simulation results show that the proposed algorithm outperforms in the recovery rate,the diffserv-aware capability and network resource optimization.
Keywords:failure recovery  self-healing  Q-learning  multi-QoS constraints  diffserv-aware  resource optimization
本文献已被 CNKI 等数据库收录!
点击此处可从《通信学报》浏览原始摘要信息
点击此处可从《通信学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号