超立方体网络的间歇性故障诊断度研究  

Research on intermittent fault diagnosability of hypercube networks

作　　者：冯浩[1] 梁家荣[1] 

机构地区：[1]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《广西大学学报（自然科学版）》2016年第5期1560-1566,共7页Journal of Guangxi University（Natural Science Edition）

基　　金：国家自然科学基金资助项目(61363002)

摘　　要：网络系统的诊断度是判断其自我诊断能力的重要度量,网络的故障类型包括永久性故障与间歇性故障两大类。与永久性故障相比,间歇性故障更具隐秘性,更难诊断。超立方体网络是一个具有性能优越的网络拓扑结构并已得到广泛的应用。针对超立方体网络在间歇性故障诊断理论方面的缺失,在本文中利用图论方法研究了超立方体网络(具有或不具有丢失边)的ti故障诊断度。应用所得到的结果,可以很容易判断整个超立方体或者其中一部分网络的间歇性故障诊断度,为超立方体网络的可靠性分析提供重要的理论依据。Diagnosability of networks is one key measure to judge its self-diagnose capability. Fault type of networks includes the permanent fault and the intermittent fault. Compared with the perma-nent fault, the intermittent fault is easier to be hided and harder to be diagnosed. The hypercube network is a kind of network topology with superior performances and has been used widely. In view of the absence of intermittent fault diagnosis theory in hypercube network, the ti-fault diagnosability of hypercube （ with or without missing links） is studied, by employing graph theory. By using the presented method, the intermittent fault diagnosability of one hypercube or just part of it can be de-termined, which provides an important theoretical basis for reliability analysis of hypercube net-works.

关 键 词：超立方体 间歇性故障诊断度 多处理机网络系统 PMC模型 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]