基于域间依赖模型的多域故障诊断算法  

Multi-domain Fault Diagnosis Algorithm Based on Inter-domain Dependency Model

作　　者：简江涛[1] 荀鹏[1] 蔡开裕[1] 

机构地区：[1]国防科学技术大学计算机学院,湖南长沙410073

出　　处：《计算机技术与发展》2015年第4期13-17,共5页Computer Technology and Development

基　　金：国家自然科学基金资助项目(61170285);信息保障实验室科技基金(KJ-12-07)

摘　　要：在多域环境下,组合服务所调用的子服务跨越多个管理域,对域间故障传播产生的跨域症状进行诊断时需要管理域之间相互协作。针对这一问题,文中提出了域间依赖模型,阐明了症状与管理域的依赖关系,并基于该模型提出多域故障诊断算法,并从时间性能方面对算法进行了改进。文中首先通过症状簇划分算法对症状集合进行划分,对同一症状簇协同诊断;然后通过对跨域症状与关联域依赖关系的概率评估,选择最可能的关联域集合进行诊断;最后,仿真结果表明该算法可以较为准确地诊断多域环境下的服务故障。In multi-domain environment, the composite service is composed of multiple sub-services crossing different administrative do- mains, and symptoms caused by inter-domain fault propagation need administrative domain work with each other to diagnose. In response to this problem, propose a multi-domain dependency model which describes the dependence relationship between symptom and associated domain. Based on the dependency model, a multi-domain fault diagnosis algorithm is proposed, and the algorithm is improved in time performance. First, divide the set of symptoms into clusters of symptoms by clustering algorithm, and a cluster of symptoms will be diag- nosed together. Then choose the set of most probable domains to diagnose by evaluating the probability of dependence relationship be- tween symptom and associated domain. Lastly the simulation results show that the algorithm can accurately diagnose service fault in multi -domain environment.

关 键 词：依赖关系 域间依赖模型 故障诊断 概率评估 症状簇 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]