|
|
|
| Electricity Theft Detection Based on Multiscale Residual Attention Network |
| CHANG Hanyun, CHEN Lishen, QIAN Jianghai
|
| College of Mathematics and Physics, Shanghai University of Electric Power, Shanghai 200090, China |
|
|
|
|
Abstract Aiming at the shortcomings of traditional power theft detection methods, which only use one-dimensional power, rely on manual features, and have low detection accuracy, an eletricity theft detection model based on multiscale residual attention network is proposed. The model is based on pyramidal convolution to fully extract multi-scale detail features, and introduces hybrid dilated convolutional attention residual network to improve the detection performance. In this paper, the proposed method is experimentally validated using the public dataset of the State Grid, and the results show that compared with the traditional logistic regression, support vector machine, random forest, and other models, the AUC, MAP, and F1 score indexes of the proposed model have achieved effective improvement.
|
|
Received: 30 January 2024
Published: 13 February 2026
|
|
|
|
|
|
| No related articles found! |
|
|
|
|
