一种基于增量贝叶斯疑似度的事件驱动故障定位算法  

An Event-Driven Fault Localization Algorithm Based on Incremental Bayesian Suspected Degree

作　　者：张成[1,2] 廖建新[1,2] 朱晓民[1,2] 

机构地区：[1]北京邮电大学网络与交换技术国家重点实验室,北京100876 [2]东信北邮信息技术有限公司,北京100083

出　　处：《电子与信息学报》2009年第6期1501-1504,共4页Journal of Electronics & Information Technology

基　　金：国家杰出青年科学基金(60525110);国家973计划项目(2007CB307100;2007CB307103);新世纪优秀人才支持计划(NCET-04-0111);电子信息产业发展基金项目(基于3G的移动业务应用系统)资助课题

摘　　要：现有的故障定位算法大多基于时间窗口,窗口大小设置的合理与否会对算法准确度产生重要影响。为了避免因窗口设置不当造成算法性能的下降,该文以概率加权的二分图作为故障传播模型,提出了一种基于增量贝叶斯疑似度(Incremental Bayesian Suspected Degree,IBSD)的启发式故障定位算法。IBSD算法采用事件驱动的方式依次分析观察到的征兆,通过增量计算对应故障的贝叶斯疑似度,确定当前征兆前提下最有可能的故障集。仿真实验表明,IBSD算法具有较高的故障检测率和较低的故障误检率,即使在部分告警无法观察的情况下,算法依然具有较高的故障检测率。算法具有多项式计算复杂度,可以满足大规模通信网故障定位的要求。Most fault localization techniques is based on time windows. The size of time windows impacts on the accuracy of the algorithms greatly. This paper takes weighted bipartite graph as fault propagation model and proposes a heuristic fault localization algorithm based on Incremental Bayesian Suspected Degree （IBSD） to eliminate the above shortcomings. IBSD sequentially analyzes the incoming symptoms in an event-driven way and incrementally computes the Bayesian Suspected Degree and determine the most probable fault set for the current observed symptoms. Simulation results show that the algorithm has high fault detection ratio as well as low false positive ratio and has a good performance even in the presence of unobserved alarms. The algorithm which has a polynomial computational complexity could be applied to large scale communication network.

关 键 词：故障管理 故障诊断 故障定位 故障传播模型 

分 类 号：TN915[电子电信—通信与信息系统]