基于CNN‑LSTM混合模型的多类别窃电行为检测
CSTR:
作者:
作者单位:

(广西电网有限责任公司计量中心,广西 南宁 530023)

通讯作者:

陈珏羽(1992—),女,硕士,主要从事电能计量研究;E?mail: jueyuchen@qq.com

中图分类号:

TM73

基金项目:

广西电网有限责任公司科技项目(GXKJXM20200020);国家自然科学基金(51777061)


Multi‑class electricity theft detection based on the CNN‑LSTM hybrid model
Author:
Affiliation:

(Measurement Center of Guangxi Power Grid Co.,Ltd.,Nanning 530023,China)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [17]
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对复杂电网环境下窃电行为难以准确检测的问题,提出一种基于CNN?LSTM混合模型的多类别窃电行为检测方法。首先基于卷积神经网络(CNN)良好的特征抽象能力提取一维用电数据的非周期性的局部特征,通过长短时记忆网络(LSTM)捕捉每日电能消耗数据间的相关性,提取周期性的用电特征建立特征融合层网络,再将CNN与LSTM提取的特征向量横向拼接获得新的融合向量,据此实现多类别窃电行为的准确检测。实验结果表明,本文提出方法能准确识别多类别窃电行为,相比现有检测方法检测结果更加全面准确。

    Abstract:

    This paper addresses the difficulty of the accurately detecting electricity theft in complex grid environment and proposes a multi?category electricity theft detection method based on CNN?LSTM hybrid model. Firstly, the excellent feature abstraction ability of convolutional neural networks (CNN) is utilized to extract the non?periodic local features of one?dimensional electricity consumption data. Then, the long short?term memory (LSTM) is adopted to capture the correlation between daily power consumption data and extract periodic power consumption features to establish feature fusion layer network. After that, the feature vectors extracted by CNN and LSTM are horizontally splicing to obtain a new fusion vector. Based on this, the accurate detection of multiple types of electric theft behavior are realized. Experimental results show that the proposed method can accurately identify multiple types of electric theft behavior, and the detection results are more comprehensive and accurate than the existing detection methods.

    参考文献
    [1] 董立红,肖纯朗,叶鸥,等.一种基于CAEs?LSTM融合模型的窃电检测方法[J].电力系统保护与控制,2022,50(21):118?127. DONG Lihong,XIAO Chunlang,YE Ou,et al.A detection method for stealing electric theft based on CAEs?LSTM fusion model[J].Power System Protection and Control,2022,50(21):118?127.
    [2] ZANETTI M,JAMHOUR E,PELLENZ M,et al.A tunable fraud detection system for advanced metering infrastructure using short?lived patterns[J].IEEE Transactions on Smart Grid,2019,10(1):830?840.
    [3] 吕笃良,刘梦爽,桓露,等.基于重加权策略平衡损失与LSTM的窃电行为检测研究[J]. 智慧电力,2022,50(4):15?20+58. Lü Duliang,LIU Mengshuang,HUAN Lu,et al.Electricity stealing detection based on reweighted strategy balancing loss and LSTM[J].Smart Power,2022,50(4):15?20+58.
    [4] ZHENG K D,CHEN Q X,WANG Y,et al.A novel combined data?driven approach for electricity theft detection[J].IEEE Transactions on Industrial Informatics,2019,15(3):1809?1819.
    [5] 王圆圆,白宏坤,王世谦,等.基于信息增益与Spearman相关系数的电力用户行为画像[J].电力工程技术2022,41,(4):220?228. WANG Yuanyuan,BAI Hongkun,WANG Shiqian,et al.Power users’ behavior portrait based on information gain and Spearman correlation coefficien[J].Electric Power Engineering Technology,2022,41(4):220?228.
    [6] NAGI J,YAP K S,TIONG S K,et al.Nontechnical loss detection for metered customers in power utility using support vector machines[J].IEEE Transactions on Power Delivery,2010,25(2):1162?1171.
    [7] 苏欣,田浩,秦昌龙,等.多变量数据聚类最优选择的用电关联分析算法[J].电网与清洁能源,2022,38(4):86?94+103. SU Xin,TIAN Hao,QIN Changlong,et al.Electricity consumption association analysis algorithm for optimal selection of multivariate data clustering[J].Power System and Clean Energy,2022,38(4):86?94+103.
    [8] YAN Z Z,WEN H.Electricity theft detection base on extreme gradient boosting in AMI[J].IEEE Transactions on Instrumentation And Measurement,2021,70:1?9.
    [9] YAO D,WEN M,LIANG Z,et al.Energy theft detection with energy privacy preservation in the smart grid[J].IEEE Internet of Things Journal,2019,6(5):7659?7669.
    [10] JAVAID N,GUL H,BAIG S,et al.Using GANCNN and ERNET for detection of non technical losses to secure smart grids[J].IEEE Access,2021,9:98679?98700.
    [11] 严勤,邓高峰,胡涛,等.基于深度循环神经网络的异常用电检测方法[J].中国测试,2021,47(7):99?104. YAN Qin,DENG Gaofeng,HU Tao,et al.Abnormal electricity detection method based on deep recurrent neural network[J].China Measurement & TEST,2021,47(7):99?104.
    [12] 蔡嘉辉,王琨,董康,等.基于DenseNet和随机森林的电力用户窃电检测[J].计算机应用,2021,41(S1):75?80. CAI Jiahui,WANG Kun,DONG Kang,et al.Power user stealing detection based on DenseNet and random forest[J].Journal of Computer Applications,2021,41(S1):75?80.
    [13] 王永明,陈宇星,殷自力,等.基于大数据分析的电力用户行为画像构建方法研究[J7.高压电器,2022,58(10):173?179+187. WANG Yongming,CHEN Yuxing,YIN Zili,et al.Research on construction method of power user behavior portrait based on big data analysis[J]. High Voltage Apparatus,2022,58(10):173?179+187.
    [14] FABIAN A N,GERARDO F,CHU C C.NTL detection in electric distribution systems using the maximal overlap discrete wavelet?packet transform and random undersampling boosting[J].IEEE Transactions on Power Systems,2018,33(6):7171?7180.
    [15] PEREIRA J,SARAIVA F.Convolutional neural network applied to detect electricity theft:a comparative study on unbalanced data handling techniques[J].International Journal of Electrical Power & Energy Systems,2021,131(9):107085.
    [16] BIAN J,WANG L,SCHERER R,et al.Abnormal detection of electricity consumption of user based on particle swarm optimization and long short term memory with the attention mechanism[J].IEEE Access,2021,9:47252?47265.
    [17] 马宗彪,许素安,朱少斌,等.基于特征加权模糊聚类的电力负荷分类[J].中国电力,2022,55(6):25?32. MA Zongbiao, XU Suan, ZHU Shaobin, et al. Power load classification based on feature weighted fuzzy clustering[J].Electric Power,2022,55(6):25?32.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

李金瑾,陈珏羽,黄柯颖.基于CNN‑LSTM混合模型的多类别窃电行为检测[J].电力科学与技术学报,2023,38(1):226-234.
LI Jinjin, CHEN Jueyu, HUANG Keying. Multi‑class electricity theft detection based on the CNN‑LSTM hybrid model[J]. Journal of Electric Power Science and Technology,2023,38(1):226-234.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 在线发布日期: 2023-04-10
文章二维码