基于动态时间窗口及告警等级权重的告警相关性研究

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名

邮箱

手机号码

标题

留言内容

验证码

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

摘要: 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。
- 告警相关性分析 /
- 动态时间窗口 /
- 告警等级权重 /
- FP-growth算法
Abstract: 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.
- Alarm correlation /
- Dynamic time window /
- Alarm level weight /
- FP-growth algorithm

[1]	鲁显光,杜学绘,王文娟.基于改进 FP_growth 的告警关联算法[J].计算机科学,2019,46(8):64-70.
[2]	贾海涛.基于数据挖掘的动环监控系统告警相关性研究[D].北京:北京交通大学,2018.
[3]	李彤岩.基于数据挖掘的通信网告警相关性分析研究[D].成都:电子科技大学,2010.
[4]	赵明.基于数据挖掘的移动告警关联系统[D].长沙:湖南大学,2010.
[5]	徐前方.基于数据挖掘的网络故障告警相关性研究[D].北京:北京邮电大学,2007.