Abstract
Data-driven electricity theft detection (ETD) based on machine learning and deep learning has the advantages of automation, real-time performance, and efficiency while requiring a large amount of labeled data to train models. However, the imbalance ratio between positive and unlabeled samples has reached 1:200, which significantly limits the accuracy of the ETD model. In cases like this, we refer to it as positive-unlabeled learning. Down-sampling wastes a large amount of negative samples, while up-sampling will result in the ETD model not being robust. Both can lead to ETD models performing well in experimental environments but poorly in production environments. In this context, this paper proposes a semi-supervised electricity theft detection algorithm based on fuzzy c-means and logistic regression cross detection (FCM-LR). Firstly, a statistical feature set based on business data and load data is proposed to depict the profile of electricity users, which can achieve the effect of reducing the complexity of data structure. Furthermore, by using the FCM-LR method, the utilization of unlabeled data can be maximized, and new electricity theft patterns can be discovered. The simulation results show that the theft detection effect of this method is significant, with Precision, Recall, F1, and Area under Curve all approaching 99%.
Similar content being viewed by others
Abbreviations
- ETD:
-
Electricity theft detection
- PUL:
-
Positive-unlabeled learning
- FCM-LR:
-
Fuzzy c-means and logistic regression cross detection
- TL:
-
Technical loss
- NTL:
-
Non-technical loss
- SGCC:
-
State grid corporation of China
- AMI:
-
Advanced measuring infrastructure
- SG186:
-
SG186 marketing system
- SMOTE:
-
Synthetic minority over-sampling technique
References
Angelos EWS, Saavedra OR, Cortés OAC, de Souza AN (2011) Detection and identification of abnormalities in customer consumptions in power distribution systems. IEEE Trans Power Delivery 26(4):2436–2442
Asif M, Nazeer O, Javaid N, Alkhammash EH, Hadjouni M (2022) Data augmentation using BiWGAN, feature extraction and classification by hybrid 2DCNN and BiLSTM to detect non-technical losses in smart grids. IEEE Access 10:27467–27483
Berghout T, Benbouzid M, Ferrag MA (2023) Multiverse recurrent expansion with multiple repeats: a representation learning algorithm for electricity theft detection in smart grids. IEEE Transact Smart Grid 14(6):4693–4703
Bretas AS, Rossoni A, Trevizan RD, Bretas NG (2020) Distribution networks nontechnical power loss estimation: a hybrid data-driven physics model-based framework. Electr Power Syst Res 1(186):106397
Buzau MM, Tejedor-Aguilera J, Cruz-Romero P, Gómez-Expósito A (2019) Detection of non-technical losses using smart meter data and supervised learning. IEEE Transact Smart Grid 10(3):2661–2670
Buzau M-M, Tejedor-Aguilera J, Cruz-Romero P, Gómez-Expósito A (2020) Hybrid deep neural networks for detection of non-technical losses in electricity smart meters. IEEE Trans Power Syst 35(2):1254–1263
Cai Q, Li P, Wang R (2023) Electricity theft detection based on hybrid random forest and weighted support vector data description. Int J Electr Power Energy Syst 1(153):109283
Cheng C, Zhang H, Jing Z, Chen M, Jiao L, Yang L (2015) Study on the anti-electricity stealing based on outlier algorithm and the electricity information acquisition system. Power Syst Protect Control 43(17):69–74
Donglai Tang, Youbo Liu, Zhilin Xiong, "Early Warning Method of Electricity Anti-theft in Distribution Station Area Based on Spatiotemporal correlation matrix," in CNKI Automation of Electric Power Systems, vol.44, no.19, Oct 2020
Fei K, Li Q, Zhu C, Dong M, Li Y (2022) Electricity frauds detection in Low-voltage networks with contrastive predictive coding. Int J Electr Power Energy Syst 1(137):107715
Gao A, Mei F, Zheng J, Sha H, Guo M, Xie Y (2023) Electricity theft detection based on contrastive learning and non-intrusive load monitoring. IEEE Transact Smart Grid 14(6):4565–4580
Gong X, Tang B, Zhu R, Liao W, Song L (2020) Data augmentation for electricity theft detection using conditional variational auto-encoder. Energies 13(17):4291
Haibo Zhao, "A survey of big data research in power industry," in CNKI Advanced Technology of Electrical Engineering, vol. 39, no. 12, Doc 2020
Hussain S, Mustafa MW, Jumani TA, Baloch SK, Alotaibi H, Khan I, Khan A (2021) A novel feature engineered-CatBoost-based supervised machine learning framework for electricity theft detection. Energy Rep 1(7):4425–4436
Jokar P, Arianpoo N, Leung VCM (2016) Electricity theft detection in ami using customers’ consumption patterns. IEEE Transact Smart Grid 7:216–226
Khan IU, Javeid N, Taylor CJ, Gamage KAA, Ma X (2022) A stacked machine and deep learning-based approach for analysing electricity theft in smart grids. IEEE Transact Smart Grid 13(2):1633–1644
Khan IU, Javaid N, Taylor CJ, Ma X (2023) Robust data driven analysis for electricity theft attack-resilient power grid. IEEE Trans Power Syst 38(1):537–548
Khan IU, Javaid N, Taylor CJ, Gamage KAA and Ma X, "Big Data Analytics for Electricity Theft Detection in Smart Grids," in IEEE Madrid PowerTech, pp. 1–6, Jun 2021
Kong J, Jiang W, Tian Q, Jiang M, Liu T (2023) Anomaly detection based on joint spatio-temporal learning for building electricity consumption. Appl Energy 15(334):120635
Kong X, Zhao X, Liu C, Li Q, Dong D, Li Y (2021) Electricity theft detection in low-voltage stations based on similarity measure and DT-KSVM. Int J Electr Power Energy Syst 1(125):106544
Lepolesa LJ, Achari S, Cheng L (2022) Electricity theft detection in smart grids based on deep neural network. IEEE Access 10:39638–39655
Liu Z, Gao Y, Guo J, Li Y, Gu D, Wen Y (2022) Abnormal detection of electricity theft using a deep auto-encoder Gaussian mixture model. Power Syst Prot Control 50:92–102
Massaferro P, Martino JMD, Fernández A (2022) Fraud detection on power grids while transitioning to smart meters by leveraging multi-resolution consumption data. IEEE Transact Smart Grid 13(3):2381–2389
Messinis GM, Hatziargyriou ND (2018) Review of non-technical loss detection methods. ELSEVIER Electr Power Syst Res 158:250–266
Nabil M, Ismail M, Mahmoud MMEA, Alasmary W, Serpedin E (2019) PPETD: privacy-preserving electricity theft detection scheme with load monitoring and billing for AMI networks. IEEE Access 7:96334–96348
Peng Y, Yang Y (2021) Electricity theft detection in ami based on clustering and local outlier factor. IEEE Access 9:107250–107259
Pereira J and Saraiva F, "A Comparative Analysis of Unbalanced Data Handling Techniques for Machine Learning Algorithms to Electricity Theft Detection," in IEEE Congress on Evolutionary Computation (CEC), pp. 1–8, July 2020
Pereira J, Saraiva F (2021) Convolutional neural network applied to detect electricity theft: a comparative study on unbalanced data handling techniques. Int J Electrical Power Energy Syst 1(131):107085
Qingqing Ma, Wei Li, Gaoying Cui, “Design and Implementation of an Anti-theft electric power analysis system based on electricity consumption information,” in CNKI Southeast University, pp.1, Feb 2021
Razavi R, Fleury M (2019) Socio-economic predictors of electricity theft in developing countries: An Indian case study. ELSEVIER Energy Sustain Dev 49:1–10
Razavi R, Gharipour A, Fleury M (2019) Ikpe Justice Akpan, “A practical feature-engineering framework for electricity theft detection in smart grids,.” ELSEVIER Appl Energy 238:481–494
Shaofeng Zhang, Jianyuan Wang, "Abnormal power consumption pattern detection based on linear discriminant analysis and density peaks clustering", in CNKI Northeast electric power university, June 2022
Shehzad F, Javaid N, Aslam S, Javed MU (2022) Electricity theft detection using big data and genetic algorithm in electric power systems. Electr Power Syst Res 1(209):107975
Souza Savian F, Siluk JC, Garlet TB, Nascimento FM, Pinheiro JR, Vale Z (2021) Non-technical losses: a systematic contemporary article review. Renew Sustain Energy Rev 147:111205
Takiddin A, Ismail M, Zafar U, Serpedin E (2022) Deep autoencoder-based anomaly detection of electricity theft cyberattacks in smart grids. IEEE Syst J 16(3):4106–4117
Tehrani SO, Shahrestani A, Yaghmaee MH (2022) Online electricity theft detection framework for large-scale smart grid data. Electric Power Syst Res 1(208):107895
Tong C, Zhu Z, Zhang Y, Zhou M, Peng S, Shan S, Wang P, Liu Y, Tong T, Zeng L (2022) Online monitoring data processing method of transformer oil chromatogram based on association rules. IEEJ Transact Electri Electr Eng 17(3):354–360
Ullah A, Javaid N, Asif M, Javed MU, Yahaya AS (2022) AlexNet, adaboost and artificial bee colony based hybrid model for electricity theft detection in smart grids. IEEE Access 10:18681–18694
Wen M, Yao D, Li B and Lu R, "State Estimation Based Energy Theft Detection Scheme with Privacy Preservation in Smart Grid," in IEEE International Conference on Communications (ICC), pp. 1–6, July 2018
Wenlong Liao, Ruijin Zhu, "Electricity Theft Detection Using Dynamic Graph Construction and Graph Attention Network," in IEEE Transactions on Industrial Informatics, pp. 1–13, 2023
Wu Q, Zhang M, Liao L (2022) Analysis of electricity stealing based on user electricity characteristics of electricity information collection system. Energy Rep 1(8):488–494
Wu R, Wang L and Hu T, "AdaBoost-SVM for Electrical Theft Detection and GRNN for Stealing Time Periods Identification," IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society, pp. 3073–3078, 2018
Xia R, Gao Y, Zhu Y, Gu D, Wang J (2023) An attention-based wide and deep CNN with dilated convolutions for detecting electricity theft considering imbalanced data. Electr Power Syst Res 1(214):108886
Zhu L, Wen W, Li J, Zhang C, Zhou B, Shuai Z (2024) Deep active learning-enabled cost-effective electricity theft detection in smart grids. IEEE Trans Industr Inf 20(1):256–268
Funding
This project does not have funding support.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Human or animals rights
No research involving Human Participants and/or Animals.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hu, R., Zhen, T. Research on FCM-LR cross electricity theft detection based on big data user profile. Int J Syst Assur Eng Manag (2024). https://doi.org/10.1007/s13198-024-02333-8
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13198-024-02333-8