Unanticipated behavior as a cue for system-level diagnosis
Roy A. Maxion · 2003
A general method is described for detecting and using unanticipated or surprise events for system-level diagnosis. The author describes an approach which uses these ideas in controlling resource utilization for an intelligent diagnostic system whose immediate application is real-time diagnosis of communication networks. The system is in 24-hr, real-time operation and has been used successfully in the detection and diagnosis of network hardware, software, and configuration faults.>