基于动态时间窗口及告警等级权重的告警相关性研究

Research on Alarm Correlation Based on Dynamic Time Window and Alarm Level Weight

针对移动通信网络告警量大,告警之间相关性不明朗的问题,本文提出了一种基于FP-growth算法,采用动态时间窗口,分别按告警开始、结束时间提取告警事务,同时根据告警等级进行告警事务加权的关联规则算法,从而达到提高维护工作效率的目的。实验结果证明,与传统方法相比,该方法在执行时间、规则提取效果上都有一定提升。

Aiming at the problem of large amount of alarms in mobile communication network and the uncertain correlation between alarms,this paper proposes an association rule algorithm based on FP growth algorithm,which uses dynamic time window to extract alarm transactions according to the start and end time of alarms,and adds weights to alarm transactions according to alarm levels,so as to improve the maintenance efficiency.The experimental results show that compared with the traditional methods,this method has a certain improvement in the execution time and the rule extraction effect.