基于集群智能的智能电能表异常检测技术  

Anomaly detection technology based on swarm intelligence for smart meters

作　　者：白志霞 刘馨卉 索思远 陈雯 Bai Zhixia;Liu Xinhui;Suo Siyuan;Chen Wen(Metrological Center of State Grid Shanxi Electric Power Corporation,Taiyuan 030000,China)

机构地区：[1]国网山西省电力公司计量中心,太原030000

出　　处：《电测与仪表》2022年第1期195-200,共6页Electrical Measurement & Instrumentation

摘　　要：智能电能表是智能电网与高级计量体系(Advanced Metering Infrastructure,AMI)中的重要基础设施,有效提升了电力系统的自动化与智能化,但同时也面临更隐蔽与更广泛的攻击形式。针对智能电能表的异常检测问题,提出三类基于集群智能(Swarm Intelligence,SI)的异常检测技术,分别从矢量距离、置信度与Kullback-Leibler散度三种指标出发识别异常设备。在每个随机形成的群体中标记可疑的智能电能表,并在一定次数的迭代后作出决策。真实数据集的实验结果表明,算法在充分提升召回率的同时有效地降低了误报率,具有较高实用性。Smart meters play critical role in smart grid and advanced metering infrastructure(AMI),which efficiently improves automation and intelligence of power system.However,this modernization also introduced a lot of scope for the different anomalies and attacks on smart meters.In order to solve the anomaly detection problem for smart meters,three swarm intelligence(SI)based anomaly detection methods are proposed,which are based on vector distance,honesty coefficient and Kullback-Leibler divergence.The proposed algorithms mark suspicious smart meters in randomly formed swarms,and make decisions after a certain number of iterations.Experimental results on real-world dataset demonstrate that the proposed algorithms are of high detection rate and low false alarm rate,which are highly practicable.

关 键 词：智能电能表 异常检测 集群智能 高级计量体系 

分 类 号：TM933[电气工程—电力电子与电力传动]