基于多层次非负稀疏编码和SVM的窃电检测方法  

Electricity theft detection based on multi-level non-negative sparse coding and electricity theft scenario analysis

作　　者：黄刚 颜伟[1] 王浩 文旭[1,3] 张爱枫 夏春 HUANG Gang;YAN Wei;WANG Hao;WEN Xu;ZHANG Aifeng;XIA Chun(State Key Laboratory of Power Transmission Equipment&System Security and New Technology,Chongqing University,Chongqing 400044,P.R.China;Shenzhen Power Supply Bureau Co.nLtd.,Shenzhen 440310,Guangdong,P.R.China;Southwest Subsection of State Grid,Chengdu 610041,P.R.China;Chongqing Electric Power Trading Center Co.,Ltd.,Chongqing 400013,P.R.China)

机构地区：[1]重庆大学输配电装备及系统安全与新技术国家重点实验室,重庆400044 [2]深圳供电局有限公司,广东深圳440310 [3]国家电网公司西南分部,成都610041 [4]重庆电力交易中心有限公司,重庆400013

出　　处：《重庆大学学报》2022年第7期1-12,23,共13页Journal of Chongqing University

基　　金：国家自然科学基金资助项目(51677012)。

摘　　要：针对现有方法对新型窃电方式检测准确率不高的问题,文中提出了一种基于多层次非负稀疏编码和支持向量机(support vector machines,SVM)的窃电检测新方法。该方法以月度用电曲线为检测对象,基于多层次非负稀疏编码提取样本的多层次用电模式特征,以及窃电情景分析提取样本的数值统计特征,将二者的融合检测特征输入SVM分类器进行窃电检测。以爱尔兰智能电表数据集构造的算例验证了所提方法能够提高窃电检测的精确率和召回率。Existing detection methods of electricity theft have low detection accuracy for new means of electricity theft.This paper proposes a new theft detection method based on multi-level non-negative sparse coding and SVM.Using the monthly electricity consumption curve as the detection object,firstly,the multi-level electricity consumption pattern characteristics of the sample are extracted based on the multi-level non-negative sparse coding;next,the numerical statistical characteristics of the sample are extracted based on the electricity theft scenario analysis;then,the fusion detection features of the above two characteristics are input into the SV M classifier for electricity theft detection.Finally,the Irish smart meter.data set is used as the example to verify the effectiveness of the proposed method,showing the improved accuracy and recall rate of the detection.

关 键 词：窃电检测 多层次 非负稀疏编码 情景分析 支持向量机 

分 类 号：TM721[电气工程—电力系统及自动化]