数据挖掘技术与通信网的故障管理

Today’s large and complex telecommunication networks produce large amounts of alarms and abnormal traffic data daily. In order to improve telecommunication network management, It is very important to analyze, filtrate and manage these data by using of data mining technique. The project researches the relations between alarm and fault management,the selection of alarms, the pre-process of alarms and the arithmetic of alarm association.rules. Some useful association rules have been found and analyzed based on real alarm data from the local telephone network in Nanchang. It is well known that many discovered.associations are redundant or minor variations of others. Their existence may simply be due to chance rather than true correlation. Thus, those spurious and insignificant rules should be.removed. In this report, we propose a novel technique to overcome this problem. The technique firstly introduces the new concept .Structure Rule Cover, and then present a.quantitative method to prune redundant correlation patterns. The user can now obtain a complete picture of the domain without being overwhelmed by a huge number of rules.Moreover, the relations between multiple switches and traffic alarms have also been discussed in this report for improving fault management in telecommunication networks.

本课题系采用数据挖掘技术和通信网话务理论等综合方法研究通信网海量告警信息和话务异常信息等变化特性以及分析、过滤、管理和诊断这些信息的方法，为通信网的故障诊断提供可靠的理论依据。该研究结合我国通信网告警信息和话务异常信息特点，它将使通信网数据挖掘技术及其故障诊断研究向前推进一步，其应用前景广阔，..........