Predicting Telecommunication Equipment Failures from Sequences of Network Alarms

The computer and telecommunication industries rely heavily on knowledge-based expert systems to manage the performance of their networks. These expert systems are developed by knowledge engineers, who must first interview domain experts to extract the pertinent knowledge. This knowledge acquisition process is laborious and costly, and typically is better at capturing qualitative knowledge than quantitative knowledge. This is a liability, especially for domains like the telecommunication domain, where enormous amounts of data are readily available for analysis. Data mining holds tremendous promise for the development of expert systems for monitoring network performance since it provides a way of automatically identifying subtle, yet important, patterns in data. This case study describes a project in which a temporal data mining system called Timeweaver is used to identify faulty telecommunication equipment from logs of network alarm messages.