Alarms Association Rules Based on Sequential Pattern Mining Algorithm

摘要

Alarms association will play an important role in improving the service and reliability in modern telecommunication networks. As the network grows in size and complexity, the supervisors of network are finding it increasingly difficult to cope with the volume of alarm messages produced even from a single network fault. This paper introduces the related studies of alarms association and sequential pattern mining, presents a kind of arithmetic named EW (Effective Windows)-WINEPI, and a new alarms association analysis model based on this is designed, which can be used to forecast fault source.