基于改进FCM聚类的窃电行为检测
CSTR:
作者:
通讯作者:

武超飞(1989-),男,硕士,主要从事电力大数据、电能计量技术研究;E-mail:707683266@qq.com

中图分类号:

TM715

基金项目:

国网公司总部科技项目(5400-201925177A-0-0-00)


Detection of stealing electricity energy based on improved fuzzy Cmeans clustering
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [11]
  • | | | |
  • 文章评论
    摘要:

    窃电行为检测的主要目的在于发现窃电用户,降低电力系统运营成本。在此背景下,提出基于改进模糊 C 均值聚类的窃电行为检测模型,包括因子分析、基于改进模糊 C均值聚类的局部离群因子计算、ROC曲线模型评价与调参及最佳检测阈值选取等模块,适用于无大量已知窃电用户样本的情况。首先,通过因子分析对用户用电特征 (包括用电负荷数据和电能表异常事件)进行维度规约,提升模型检测效率。再利用遗传模拟退火算法对模糊 C均值聚类算法进行改进,对用户用电特征进行检测。最后与现有成熟算法进行比较,验证该模型对窃电行为具有较高的检测准确度。检测模型可输出所有被测用户用电行为离群度得分和窃电概率排序,利用该文检测模型的输出,能够以较高精度检测出窃电行为用户,根据结果进行现场稽查,可提升反窃电工作效率。

    Abstract:

    Power stealing detection can find power stealing users efficiently and then reduce the operation cost of the power system. In this paper, a detection model of power stealing behavior based on improved fuzzy cmeans clustering is proposed, which is suitable for the situation without many known power stealing user samples. The model includes factor analysis, local outlier calculation based on improved fuzzy cmeans clustering, model evaluation and parameter adjustment with ROC curve, and the selection of the best detection threshold. Firstly, through factor analysis, the dimension specification of the user's power consumption characteristics (including power load data and abnormal events of electric energy meter) is carried out to improve the efficiency of model detection. Then, the FCM clustering algorithm integrated with a genetic simulated annealing algorithm is applied to detect the user's power consumption characteristics. Finally, compared with the existing mature algorithm, the result indicates that the model has a high detection accuracy for electricity theft. The detection model can output the power consumption behavior outlier and all the tested users' power stealing probability order. The output of the detection model can detect the power stealing users with high precision. The results can be employed into the field inspection, and the efficiency of antistealing work will be improved.

    参考文献
    [1] 杨学良,陶晓峰,熊霞,等.基于深度森林算法的窃电行为检测方法研究[J].智慧电力,2019,47(10):85-92.YANG Xueliang,TAO Xiaofeng,XIONG Xia,et al.Detection method for electricity theft based on deep forest algorithm[J].Smart Power,2019,47(10):85-92.
    [2] 庄池杰,张斌,胡军,等.基于无监督学习的电力用户异常用电模式检测[J].中国电机工程学报,2016,36(2):379-387.ZHUANG Chijie,ZHANG Bin,HU Jun,et al.Anomaly detection for power consumption patterns based on unsupervised learning[J].Proceedings of the CSEE,2016,36(2):379-387.
    [3] 程超,张汉敬,景志敏,等.基于离群点算法和用电信息采集系统的反窃电研究[J].电力系统保护与控制,2015,43(17):69-74.CHENG Chao,ZHANG Hanjing,JING Zhimin,et al.Study on the antielectricity stealing based on outlier algorithm and the electricity information acquisition system[J].Power System Protection and Control,2015,43(17):69-74.
    [4] 赵莉,候兴哲,胡君,等.基于改进Kmeans算法的海量智能用电数据分析[J].电网技术,2014,38(10):2715-2720.ZHAO Li,HOU Xingzhe,HU Jun,et al.ImprovedKmeans algorithm based analysis on massive data of intelligent power utilization[J].Power System Technology,2014,38(10):2715-2720.
    [5] 黄星知,杨奕纯,杨兰,等.基于BP神经网络的配电网防窃电降线损研究[J].电力科学与技术学报,2019,34(4):143-147.HUANG Xingzhi,YANG Yichun,YANG Lan,et al.Study of antipower theft and line loss reduction for power distribution network based on BP neural network[J].Journal of Electric Power Science and Technology,2019,34(4):143-147.
    [6] 许刚,谈元鹏,戴腾辉.稀疏随机森林下的用电侧异常行为模式检测[J].电网技术,2017,41(6):1964-1971.XU Gang,TAN Yuanpeng,DAI Tenghui.Sparse random forest based abnormal behavior pattern detection of electric power user side[J].Power System Technology,2017,41(6):1964-1971.
    [7] 曹敏,邹京希,魏龄,等.基于RBF神经网络的配电网窃电行为检测[J].云南大学学报(自然科学版),2018,40(5):872-878.CAO Min,ZOU Jingxi,WEI Ling,et al.Detection of power theft behavior of distribution network based on RBF neural network[J].Journal of Yunnan University(Natural Sciences Edition),2018,40(5):872-878.
    [8] 段旭晨,彭道刚,姚峻,等.基于SAPSOAHP的火电厂控制系统信息安全威胁评估[J].中国电力,2019,52(5):29-35.DUAN Xuchen,PENG Daogang,YAO Jun,et al.Assessment on the threat to the information security of power plant control system based on SAPSOAHP method[J].Electric Power,2019,52(5):29-35.
    [9] 施佳君,秦川,鞠平,等.一种变电站负荷行业构成比例估算方法[J].电力自动化设备,2019,39(10):201-207+223.SHI Jiajun,QIN Chuan,JU Ping,et al.Estimation method of industry composition of substation loads[J].Electric Power Automation Equipment,2019,39(10):201-207+223.
    [10] 张承智,肖先勇,郑子萱.基于实值深度置信网络的用户侧窃电行为检测[J].电网技术,2019,43(3):1803-1091.ZHANG Chengzhi,XIAO Xianyong,ZHENG Zixuan.Electricity theft detection for customers in power utility based on realvalued deep belief network[J].Power System Technology,2019,43(3):1803-1091.
    [11] 田力,向敏.基于密度聚类技术的电力系统用电量异常分析算法[J].电力系统自动化,2017,41(5):64-70.TIAN Li,XIANG Min.Abnormal power consumption analysis based on densitybased spatial clustering of applications with noise in power systems[J].Automation of Electric Power Systems,2017,41(5):64-70.
    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

武超飞,孙冲,刘厦,等.基于改进FCM聚类的窃电行为检测[J].电力科学与技术学报,2021,36(6):164-170.
WU Chaofei, SUN Chong, LIU Sha, et al. Detection of stealing electricity energy based on improved fuzzy Cmeans clustering[J]. Journal of Electric Power Science and Technology,2021,36(6):164-170.

复制
分享
文章指标
  • 点击次数:223
  • 下载次数: 1447
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2022-01-05
文章二维码