Enhancement of electricity theft detection model for electricity metering system using machine learning and Pearson’s correlation coefficient
-
Shuai Yang
,
Zhendong Shi
Abstract
Power metering system electricity theft may jeopardize the security and stability of the power system in addition to reducing the financial gains of the power grid. This research suggests a power theft detection model based on the Pearson correlation coefficient and support vector machine (SVM) to increase the detection accuracy. The relationship between the user’s daily electricity consumption and the line loss of electricity of the day in the station region is first examined using the Pearson correlation coefficient to determine whether a user is committing power theft. The SMOTE technique is used to oversample a few classes of samples to address the issue of the limited amount of data on electricity theft users. This prevents sample imbalance from having an impact on the detection model. The SVM algorithm is then used to build the electricity theft detection model, and the Gaussian kernel function is used to translate the linearly indivisible power consumption data to the high-dimensional space to guarantee the dataset’s linear divisibility. With a classification accuracy of 93.8 % and a positive sample classification accuracy of 95.4 % for the detection of electricity theft users, the experimental portion uses the State Grid of China’s actual electricity consumption dataset. Following model training and cross-validation, the results demonstrate that the model can successfully identify electricity theft, demonstrating the model’s superiority and applicability in this area.
-
Research ethics: This article does not contain any studies with human participants performed by any of the authors.
-
Informed consent: Not applicable.
-
Author contributions: Shuai Yang, Qiong Cao is responsible for designing the framework, analyzing the performance, validating the results, and writing the article. Wei Zhang, Zhendong Shi, Yinlong Zhu is responsible for collecting the information required for the framework, provision of software, critical review, and administering the process.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: Authors do not have any conflicts
-
Research funding: Authors did not receive any funding.
-
Data availability: No datasets were generated or analyzed during the current study.
References
1. Ali, A, Arshid, A, et al.. Exploiting machine learning to tackle peculiar consumption of electricity in power grids: a step towards building green smart cities. IET Gener, Transm Distrib 2024;18:413–45. https://doi.org/10.1049/iet-gtd.2023.12345.Search in Google Scholar
2. Huang, Q, Tang, Z, Weng, X, He, M, Liu, F, Yang, M, et al.. A novel electricity theft detection strategy based on dual-time feature fusion and deep learning methods. Energies 2024;17:275. https://doi.org/10.3390/en17020275.Search in Google Scholar
3. Sebastian, PK, Deepa, K, Neelima, N, Paul, R, Özer, T. A comparative analysis of deep neural network models in IoT-based smart systems for energy prediction and theft detection. IET Renew Power Gener 2024;18:398–411. https://doi.org/10.1049/iet-rpg.2023.12345.Search in Google Scholar
4. Bashir, S. Retracted: real-time water and electricity consumption monitoring using machine learning techniques. IEEE Access 2023;11:11511–28. https://doi.org/10.1109/ACCESS.2023.1234567.Search in Google Scholar
5. Bai, Y, Sun, H, Zhang, L, Wu, H. Hybrid CNN–transformer network for electricity theft detection in smart grids. Sensors 2023;23:8405. https://doi.org/10.3390/s23208405.Search in Google Scholar PubMed PubMed Central
6. Pengwah, AB, Razzaghi, R, Andrew, LH. Model-less non-technical loss detection using smart meter data. IEEE Trans Power Deliv 2023;38:3469–79. https://doi.org/10.1109/TPWRD.2023.123456.Search in Google Scholar
7. Zhang, Z, Zhang, C, Li, M, Xie, T. Target positioning based on particle centroid drift in large-scale WSNs. IEEE Access 2020;8:127709–19. https://doi.org/10.1109/ACCESS.2020.1234567.Search in Google Scholar
8. He, L, Niu, J. Identification of traditional culture communication in social media based on information dissemination tree. J Combin Math Combin Comput 2024;120:219–29. https://doi.org/10.1016/j.jcombin.2024.01.002.Search in Google Scholar
9. Dewangan, F, Abdelaziz, AY, Biswal, M. Load forecasting models in smart grid using smart meter information: a review. Energies 2023;16:1404. https://doi.org/10.3390/en16031404.Search in Google Scholar
10. Pazderin, A, Kamalov, F, Gubin, PY, Safaraliev, M, Samoylenko, V, Mukhlynin, N, et al.. Data-driven machine learning methods for nontechnical losses of electrical energy detection: a state-of-the-art review. Energies 2023;16:7460. https://doi.org/10.3390/en16217460.Search in Google Scholar
11. Alsirhani, A, Mujib Alshahrani, M, Abukwaik, A, Taloba, AI, Abd El-Aziz, RM, Salem, M. A novel approach to predicting the stability of the smart grid utilizing MLP-ELM technique. Alex Eng J 2023;74:495–508. https://doi.org/10.1016/j.aej.2023.02.009.Search in Google Scholar
12. Guzel, T, Cinar, H, Cenet, MN, Oguz, KD, Yucekaya, A, Hekimoglu, M. A framework to forecast electricity consumption of meters using automated ranking and data preprocessing. Int J Energy Econ Pol 2023;13:179–93. https://doi.org/10.1016/j.ijee.2023.05.010.Search in Google Scholar
13. Guo, L, Sun, Y. Economic forecasting analysis of high-dimensional multifractal action based on financial time series. Int J Hous Sci Appl 2024;45:11–19. https://doi.org/10.1016/j.ijhsa.2024.01.001.Search in Google Scholar
14. Ahir, RK, Chakraborty, B, Mitra, P. Informed change-point detection approach for solar prosumer detection and statistical verification in smart grid. IEEE Trans Smart Grid 2023;15:987–98. https://doi.org/10.1109/TSG.2023.1234567.Search in Google Scholar
15. Abdalzaher, MS, Fouda, MM, Elsayed, HA, Salim, MM. Toward secured IoT-based smart systems using machine learning. IEEE Access 2023;11:20827–41. https://doi.org/10.1109/ACCESS.2023.1234567.Search in Google Scholar
16. Panthi, M, Das, TK. Detection of cyber-attacks for sensor measurement data using supervised machine learning models for modern power grid system. Int J Crit Comput Base Syst 2023;10:330–54. https://doi.org/10.1016/j.ijccbs.2023.04.001.Search in Google Scholar
17. Yusof, YB, Ping, TH, Isa, FBM. Strengthening smart grids through security measures: a focus on real-time monitoring, redundancy, and cross-sector collaboration. Int J Intell Autom Comput 2023;6:14–36. https://doi.org/10.1109/IJIAC.2023.1234567.Search in Google Scholar
18. Mogos, AS, Liang, X, Chung, CY. Distribution transformer failure prediction for predictive maintenance using hybrid one-class deep SVDD classification and lightning strike failures data. IEEE Trans Power Deliv 2023;38:3250–61. https://doi.org/10.1109/TPWRD.2023.1234567.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
