Search

Research on Electricity Theft Detection Technology Based on Deep Learning

Author(s)

Ren Lu, Gong Dianxuan*, Zhang Hao

Affiliation(s)

School of Science, North China University of Science and Technology, Tangshan, Hebei, China *Corresponding Author

Abstract

The global issue of electricity theft has become increasingly severe, posing significant threats to the stability of power systems and public safety. This paper introduces a Multi-Dimensional Perception Network for Electricity Anomaly Detection, which integrates the DSAE module and MSSPAM module to enhance the model's capability in capturing both global and local features and improving temporal dependency modeling. Experimental results demonstrate that the proposed model outperforms existing baseline methods across multiple metrics, including accuracy, precision, and recall, providing an efficient and reliable solution for electricity theft detection.

Keywords

Electricity Theft Detection; Anomaly Detection; Deep Learning; Feature Fusion; Attention Mechanism

References

[1] Smith T B. Electricity theft: a comparative analysis [J]. Energy policy, 2004, 32(18):2067-2076. [2] Gaur V, Gupta E. the determinants of electricity theft: An empirical analysis of Indian states [J]. Energy Policy, 2016, 93:127-136. [3] Golden M A, Min B. Theft and loss of electricity in an Indian state [M]. International Growth Centre, 2012. [4] Friedman E, Lee C K. Remaking the world of Chinese labour: A 30‐year retrospective [J]. British journal of industrial relations, 2010, 48(3):507-533 [5] Ahir R K, Chakraborty B. Pattern-based and context-aware electricity theft detection in smart grid [J]. Sustainable Energy, Grids and Networks, 2022, 32:100833. [6] Lepolesa L J, Achari S, Cheng L. Electricity theft detection in smart grids based on deep neural network [J]. Ieee Access, 2022, 10:39638-39655. [7] Xia X, Lin J, Jia Q, et al. ETD-ConvLSTM: A deep learning approach for electricity theft detection in smart grids [J]. IEEE Transactions on Information Forensics and Security, 2023, 18:2553-2568. [8] Zheng K, Chen Q, Wang Y, et al. A novel combined data-driven approach for electricity theft detection [J]. IEEE Transactions on Industrial Informatics, 2018, 15(3):1809-1819. [9] Munawar S, Javaid N, Khan Z A, et al. Electricity theft detection in smart grids using a hybrid BiGRU–BiLSTM model with feature engineering-based preprocessing [J]. Sensors, 2022, 22(20):7818. [10] Blazakis K V, Kapetanakis T N, Stavrakakis G S. Effective electricity theft detection in power distribution grids using an adaptive neuro fuzzy inference system [J]. Energies, 2020, 13(12):3110. [11] Akram R, Ayub N, Khan I, et al. Towards big data electricity theft detection based on improved rusboost classifiers in smart grid [J]. Energies, 2021, 14(23):8029. [12] Wang Q, Wu B, Zhu P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks [C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020:11534-11542. [13] Cai H, Li J, Hu M, et al. Efficientvit: Multi-scale linear attention for high-resolution dense prediction [J]. arXiv preprint arXiv:2205.14756, 2022.