An Alarm Denoising Method for Network Security in Power Monitoring System Based on Rule-Statistical-Transformer Three-Stage Fusion

ZHU Hongyu; CHEN Qian; LI Mingguang; LUO Weiqiang

doi:10.3969/j.issn.1008-0198.2025.04.018

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

An Alarm Denoising Method for Network Security in Power Monitoring System Based on Rule-Statistical-Transformer Three-Stage Fusion

更新时间：2025-12-08

- An Alarm Denoising Method for Network Security in Power Monitoring System Based on Rule-Statistical-Transformer Three-Stage Fusion
- Vol. 45, Issue 4, Pages: 126-132(2025)
- 作者机构：
  
  1. 国网湖南省电力有限公司信息通信分公司,湖南,长沙,410004
  2. 泛在电力物联网湖南省重点实验室,湖南,长沙,410004
  3. 国网湖南省电力有限公司,湖南,长沙,410004
  4. 湖南大学信息科学与工程学院,湖南,长沙,410082
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1008-0198.2025.04.018
  CLC： TM76
- Published Online：05 September 2025，
  
  Published：05 September 2025
- 稿件说明：
移动端阅览
朱宏宇, 陈乾, 李明光, 罗伟强. 基于规则-统计-Transformer三阶段融合的电力监控系统网络安全告警信息降噪方法[J]. 湖南电力, 2025, 45(4): 126-132.

ZHU Hongyu, CHEN Qian, LI Mingguang, et al. An Alarm Denoising Method for Network Security in Power Monitoring System Based on Rule-Statistical-Transformer Three-Stage Fusion[J]. 2025, 45(4): 126-132.
朱宏宇, 陈乾, 李明光, 罗伟强. 基于规则-统计-Transformer三阶段融合的电力监控系统网络安全告警信息降噪方法[J]. 湖南电力, 2025, 45(4): 126-132. DOI： 10.3969/j.issn.1008-0198.2025.04.018.

ZHU Hongyu, CHEN Qian, LI Mingguang, et al. An Alarm Denoising Method for Network Security in Power Monitoring System Based on Rule-Statistical-Transformer Three-Stage Fusion[J]. 2025, 45(4): 126-132. DOI： 10.3969/j.issn.1008-0198.2025.04.018.

摘要

为降低电力监控系统中的冗余告警

提高告警分析效率与准确性

提出一种基于规则-统计-Transformer三阶段融合的告警信息降噪方法

通过分层过滤机制实现高效精确的误告警识别。首先

采用规则匹配引擎快速筛除已知模式的误告警

完成数据初步清洗。其次

基于统计分析方法检测重复告警与周期性噪声

实现二次降噪。然后

利用Transformer模型对剩余告警进行深度语义分析

通过注意力机制捕捉复杂误报模式。最后

依托某网省公司的网安平台采集数据进行效果验证。实验结果表明

所提方法在确保检测精度的同时

可以显著提高检测效率

数据量较大情况下执行时间降低15%以上。

Abstract

To reduce redundant alarms in the power monitoring system and improve the efficiency and accuracy of alarm analysis

an alarm denoising method based on rule-statistical-transformer three-stage fusion is developed in this study. Efficient and accurate false alarm identification is achieved through a layered filtering mechanism. First

false alarms with known patterns are rapidly screened using the rule matching engine

completing initial data cleaning. Second

duplicate alarms and periodic noise are detected through statistical analysis

accomplishing secondary noise reduction. Subsequently

in-depth semantic analysis of remaining alarms is performed by the transformer model

with complex false alarm patterns being captured via the attention mechanism. Finally

data are collected from a certain provincial company's network security platform for effect verification. The experimental results demonstrates that the proposed method significantly improves detection efficiency while maintaining accuracy. The execution time is reduced by over 15% for large-scale datasets.

关键词

Keywords

references

冉启鹏,吴飞,李洪江,等. 智能变电站应用研究[J]. 云南电力技术,2022,50(3):88-92.

苏适,张征容,谢青洋. 智能变电站发展综述[J]. 云南电力技术,2021,49(5):6-8.

华建秀. 综合测控装置通讯中断故障对电网的影响[J]. 中国高新技术企业,2015(34):135-136.

邓小玉,王向兵,曹华珍,等. 基于流聚类的PMU异常数据辨识算法[J]. 电力工程技术,2023,42(4):167-174.

CHATTOPADHYAY A,UKIL A,JAP D,et al.Toward threat of implementation attacks on substation security: case study on fault detection and isolation[J]. IEEE Transactions on Industrial Informatics,2018,14(6):2442-2451.

赵洋. 探析电网的电力调度监控系统应用[J]. 中国金属通报,2023(11):101-103.

徐冰珂,周宇喆,杨茂林,等. 面向电信行业网络告警系统的告警过滤算法[J]. 计算机应用,2018,38(10):2881-2885.

崔玉,曹海欧,余嘉彦,等. 智能变电站智能告警技术及应用研究[J]. 电力信息与通信技术,2021,19(5):65-70.

闪鑫,戴则梅,张哲,等. 智能电网调度控制系统综合智能告警研究及应用[J]. 电力系统自动化,2015,39(1):65-72.

李孟超,王允平,李献伟,等. 智能变电站及技术特点分析[J]. 电力系统保护与控制,2010,38(18):59-62,79.

PIETRASZEK T,TANNER A.Data mining and machine learning:Towards reducing false positives in intrusion detection[J]. Information Security Technical Report,2005, 10(3):169-183.

王星凯,吴复迪,童明凯,等. 网络安全告警降噪基线的智能生成方法[J]. 信息安全研究,2023,9(10):986-992.

李彤岩,李兴明. 基于双约束滑动时间窗口的告警预处理方法研究[J]. 计算机应用研究,2013,30(2):582-584.

欧阳庭辉,查晓明,秦亮,等. 风电功率爬坡事件预测时间窗口的选取[J]. 电网技术,2015,39(2):414-419.

廖振宇,宫翔.基于加权时间窗的告警聚类及关联方法研究[C]//中国高科技产业化研究会智能信息处理产业化分会,第十五届全国信号和智能信息处理与应用学术会议. 重庆,2022:10-12,25.

熊林林,冉兴隆,梁勇,等. 融合滑动时间窗和数据关联的告警降噪研究[C]//中国高科技产业化研究会智能信息处理产业化分会,第十六届全国信号和智能信息处理与应用学术会议. 2022:279-282,297.

施南廷. 基于AI告警降噪技术在政企网络安全防护中的实践应用[J]. 广播电视网络,2023,30(11):77-79.

黄健文,丁奕,朱林. 智能告警收敛系统的设计与实现[J]. 电信工程技术与标准化,2023,36(3):70-75.

原继东,王志海. 时间序列的表示与分类算法综述[J]. 计算机科学,2015,42(3):1-7.

杨海民,潘志松,白玮.时间序列预测方法综述[J]. 计算机科学,2019,46(1):21-28.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

ZHU Ji-ran

LENG Hua

XUN Ji-hui

XUE Wei

LI Da-gong

XIONG Hao-qing1

ZHANG Zhi-kun2

TANG Sheng-wei2

Related Institution

Hunan Electric Power Corporation Research Institute

Henan Electric Power Corporation

Hunan University

AI问答

⁰