基于序贯概率比检验的自私路径检测方法  

Detection method for selfish routes based on the sequential probability ratio test

作　　者：王骐[1] 王青萍[1] 王怀兴[1] 肖正安[1] 

机构地区：[1]湖北第二师范学院,湖北武汉430205

出　　处：《电信科学》2016年第3期81-86,共6页Telecommunications Science

基　　金：湖北省高等学校优秀中青年科技创新团队基金资助项目(No.T201417)~~

摘　　要：根据基于序贯概率比检验的无线传感器网络模型,对基于路由功能的自私路径的检测方法进行了研究。通过分析节点接收到的观测样本值,将计算得出的路径评判值与已知阈值进行比较,从而判定是否为自私路径。仿真结果表明,这种基于序贯概率比检验的序贯抽样方案所需观测值的数量大大减少,运行更快,且具有较高的检测精度。相比于其他固定抽样方案,这种方法无需事先确定检验统计假设所需的样本观测值数量,有利于对危害网络安全的行为做出快速响应,从而限制受损网络的范围。According to a network model based on the sequential probability ratio test（SPRT）, one detection method of selfish routes with respect to the routing functionality in wireless sensor network was developed. Through the analysis of the observed sample values of the nodes, the calculated routes evaluation values were compared with the known threshold values so as to determine whether it was selfish route. Simulation results show that the sequential sampling scheme based on the sequential probability ratio test had high detection accuracy, and the number of the required observation was greatly reduced, so it could operate faster. A merit of SPRT is that the number of observations required to test statistical hypotheses need not be determined in advance when compared to other methods based on a fixed number of observations. This allows for making prompt decision on the behavior of damage to the network, thus it can limit the scope of the damaged networks.

关 键 词：无线传感器网络 序贯概率比检验 网络模型 自私行为检测 评判 NS-2仿真 

分 类 号：TN918.91[电子电信—通信与信息系统]