The exist of residents electric larceny not only damages the economic benefits of power supply enterprises, but also affects the security of electric grid. With the rapid development of China’s digital economy and the improvement of electric acquisition system, electric larceny detected methods which are based on big data are updating constantly. The paper puts forward a new method which combines Pearson correlation coefficient, SMOTE algorithm and SVM. Firstly, the paper uses Pearson correlation coefficient to collect abnormal users’ effective power stealing data which are recorded, then SMOTE algorithm is used to enrich effective power stealing database. At last the paper builds a detection mathematical model based on the data base by SVM. By comparing the results of detection mathematical model and the reality situation of users, the validity and feasibility of the method is proved. The new method not only gives a new thought for electricity anti-stealing in power enterprises, but also improves the efficient of working team.
GUO Liang
,
GUO Zixue
,
JIA Hongtao
,
FAN Ruoyu
. Residents electric larceny detection based on Pearson correlation coefficient and SVM[J]. Journal of Hebei University(Natural Science Edition), 2023
, 43(4)
: 357
-363
.
DOI: 10.3969/j.issn.1000-1565.2023.04.003
[1] 赵海波.电力行业大数据研究综述[J].电工电能新技术, 2020, 39(12): 62-72. DOI: 10.12067/ATEEE2004038.
[2] NIU R K, LIU J P, ZHANG X L, et al. Research on risk analysis technology of electricity stealing behavior characteristics in smart grid[C] //2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms(EEBDA), Changchun, 2022. DOI: 10.1109/EEBDA53927.2022.9744851.
[3] CHANG S, CHAO Y, LI N H. Research and implementation of current detection technology for electricity stealing and omission[C] //2021 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers(IPEC). Dalian, 2021. DOI: 10.1109/IPEC51340.2021.9421072.
[4] XIA X F, XIAO Y, LIANG W, et al. Detection methods in smart meters for electricity thefts: a survey[J]. Proc IEEE, 2022, 110(2): 273-319. DOI: 10.1109/JPROC.2021.3139754.
[5] 薛阳,张蓬鹤,杨艺宁,等.基于线损协方差分析的群体性固定比例窃电行为检测方法[J].电力系统自动化, 2022, 46(13): 112-120. DOI: 10.7500/AEPS20210922004.
[6] 郑应俊,杨艺宁,舒一飞,等.基于边缘计算的低压用户窃电检测[J].电力系统自动化, 2022, 46(11): 111-120. DOI: 10.7500/AEPS20210624008.
[7] 杨森,马文,孙占功,等.一种基于大数据的低压单相用户窃电分析方法[J].电力信息与通信技术, 2022, 20(2): 34-41. DOI: 10.16543/j.2095-641x.electric.power.ict.2022.02.00.
[8] 覃华勤,梁叶,钱奇,等.基于典型窃电用户相似性检索的窃电行为检测方法[J].电力系统自动化, 2022, 46(6): 58-65. DOI: 10.7500/AEPS20210616001.
[9] 刘康,李彬,薛阳,等.基于传递熵密度聚类的用户窃电识别方法[J].中国电机工程学报, 2022, 42(20): 7535-7545.
[10] 唐伟宁,刘颖,于旭,等.基于离群数据挖掘的低压窃电行为辨识方法研究[J].电子设计工程, 2021, 29(23): 56-59, 64. DOI: 10.14022/j.issn1674-6236.2021.23.012.
[11] 李春芳,张锐峰,贾璐,等.基于改进k-means算法和大数据分析的新型窃电识别模型与仿真[J].电子设计工程, 2022, 30(22): 84-88. DOI: 10.14022/j.issn1674-6236.2022.22.017.
[12] 王安军,韩丽,周亚静.基于用电数据和机器学习的窃电行为识别方法[J].信息技术, 2021, 45(5): 116-121. DOI: 10.13274/j.cnki.hdzj.2021.05.020.
[13] 卢峰,丁学峰,尹小明,等.基于样本优化选取的支持向量机窃电辨识方法[J].计算机测量与控制, 2018, 26(6): 223-226. DOI: 10.16526/j.cnki.11-4762/tp.2018.06.057.
[14] YANG Y N, SONG R N, XUE Y, et al. A detection method for group fixed ratio electricity thieves based on correlation analysis of non-technical loss[J]. IEEE Access, 2022, 10: 5608-5619. DOI: 10.1109/access.2022.3141610.
[15] FURONG Y, QUAN W, BAO Y, et al. Research on identification method of stealing electricity based on data analysis[C] //2021 International Conference on Intelligent Computing, Automation and Systems(ICICAS). Chongqing, 2021. DOI: 10.1109/ICICAS53977.2021.00095.
[16] CUI X Y, LIU S Y, LIN Z Z, et al. Two-step electricity theft detection strategy considering economic return based on convolutional autoencoder and improved regression algorithm[J]. IEEE Trans Power Syst, 2022, 37(3): 2346-2359. DOI: 10.1109/TPWRS.2021.3114307. (
