基于Q学习的无线传感网络自愈算法  

A self-healing algorithm based on Q-learning for wireless sensor network

作　　者：卞辉[1] 范新南[1] 巫鹏[1] 顾丽萍[1] 李威龙[1] 郑庆元 

机构地区：[1]河海大学计算机与信息学院,江苏常州213022 [2]江苏鑫源烟草薄片有限公司,江苏南京223002

出　　处：《电子设计工程》2013年第4期44-47,共4页Electronic Design Engineering

摘　　要：无线传感网络存在关键区域节点能量消耗过快,节点能量供应有限以及通信链路拥塞等问题,容易造成节点故障和路由破坏。为减小上述问题对网络传输造成的影响,提出一种基于Q学习的无线传感网络自愈算法,通过引入Q学习的反馈机制,动态感知网络的状态信息,当故障发生时,自适应地选择恢复路径,保证数据实时顺利传输。仿真结果表明,该算法降低了错误选择故障或拥塞路径的概率,在故障感知、故障恢复和延长网络寿命等方面,表现出了良好的性能。Wireless Sensor Network has some disadvantages, such as excessive energy consumption of nodes on the key path , limited energy supply of nodes, and communication link congestion. These problems will cause the fault of nodes and damage of routing. To reduce the influence on network transmission, a self-healing algorithm based on Q-learning is proposed for wireless sensor network. In this algorithm, a feed back mechanism of Q-learning is introduced, to perceive the status of network dynamically and select a recovery routing automatically, which can ensure the data transmission is successful. The experimental results show that the proposed algorithm can reduce the probability of selecting the failure and congestion path. The proposed algorithm has some good performances in fault-aware, fault recovery, and extending network life.

关 键 词：无线传感网络 Q学习 自愈算法 故障恢复 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]