Increasing robustness of fault localization through analysis of lost, spurious, and positive symptoms

Proceedings - IEEE INFOCOM - Tập 1 - Trang 322-331 vol.1
M. Steinder1, A.S. Sethi1
1Computer and Information Sciences Department, University of Delaware, Newark, DE, USA

Tóm tắt

This paper utilizes belief networks to implement fault localization in communication systems taking into account comprehensive information about the system behavior. Most previous work on this subject performs fault localization based solely on the information about malfunctioning system components (i.e., negative symptoms). We show that positive information, i.e., the lack of any disorder in some system components, may be used to improve the accuracy of this process. The technique presented allows lost and spurious symptoms to be incorporated in the analysis. We show through simulation that in a noisy network environment the analysis of lost and spurious symptoms increases the robustness of fault localization with belief networks. We also demonstrate that belief networks yield high accuracy even for approximate probability input data and therefore are a promising model for non-deterministic fault localization.

Từ khóa

#Robustness #Working environment noise #Information analysis #Analytical models #Collaboration #Government #Communication systems #Availability #Fault diagnosis #Bipartite graph

Tài liệu tham khảo

10.1109/TCOMM.1994.577079 10.1109/49.661110 10.1109/MILCOM.2001.985975 1993, Integrated Network Management II cowell, 1999, Probabilistic Networks and Expert Systems 1999, Integrated Network Management VI 10.1109/49.661103 10.1016/0004-3702(93)90036-B 10.1007/978-0-387-34890-2_24 dechter, 1996, Bucker elimination: A unifying framework for probabilistic inference, Proc of the Twelfth Conference on Uncertainty in Artificial Intelligence cooper, 1988, Probabilistic inference using belief networks is NP-Hard perlman, 1999, Interconnections Second Edition Bridges Routers Switches and Internetworking Protocols 10.17487/rfc1905 10.1109/INM.1999.770687 wu, 0, Alarm correlation engine (ACE), In Proc of Network Operation and Management Symposium New Orleans LA 1998, 733 10.1109/65.244794 10.1007/978-0-387-34890-2_25 jordaan, 0, Event correlation in heterogeneous networks using the OSI management framework, Integrated Network Management II, 683 lewis, 0, A case-based reasoning approach to the resolution of faults in communications networks, Integrated Network Management II, 671 10.1109/49.257935 10.1145/203330.203336 steinder, 2001, The present and future of event correlation: A need for end-to-end service fault localization, World Multi-Conf Systemics Cybernetics and Informatics, 12, 124 10.1109/INM.2001.918051 steinder, 0, Non-deterministic diagnosis of end-to-end service failures in a multi-layer communications system, Proc of ICCCN Scottsdale AR 2001, 374 10.1109/NOMS.2000.830425 10.1109/49.257936 10.1109/INM.1999.770686 10.1109/90.477721 1995, Integrated Network Management IV 10.1109/NOMS.2002.1015595 10.1109/26.380064 pearl, 1988, Probabilistic Reasoning in Intelligent Systems Networks of Plausible Inference 10.1109/ICDP.1996.864202 10.1109/35.492975