Detecting and classifying delay Data Exceptions on communication networks using rule based algorithms

Network performance monitoring is essential for managing a network efficiently and for ensuring reliable operation of the network. Monitored network performance changes reflect events in the network, such as faults, significant changes in usage patterns or planned alterations. Network managers are interested in how and when the performance of a network changes; however it is inefficient to analyse all the data resulting from the monitoring operation manually. In this paper a rule based algorithm to automate detection of the changes in one of the network performance parameters, namely delay, is presented and described in detail. The nature of the delay pattern in a commercial communication network was the key issue in developing this algorithm. The approach was tested with monitored delay data generated from three different networks and showed good results. Also, the algorithm was tested with sets of delay data which have been already input to a previously developed detector based on a different approach, and the results between the two detectors are compared. In addition to a noticeable improvement in detection performance, the new approach provides more generality and independency of the source of the delay data, making the approach generally applicable to other networks. Copyright (C) 2004 John Wiley Sons, Ltd.