•  
  •  
 

Abstract

Electricity theft is a serious problem that results in significant revenue losses and jeopardizes economic stability. The accurate detection of theft is hindered by the prevalence of imbalanced, real-world electricity consumption datasets. Consequently, data balancing is necessary prior to the classification of normal and abnormal consumers in order to mitigate the classifier’s inherent biases toward the majority class. This study proposes a deep learning–based electricity theft detection model coupled with a hybrid resampling technique (synthetic minority over-sampling technique–edited nearest neighbor (SMOTEENN)). This hybrid technique resolves the bias problem in classifying the imbalanced data, reduces the risk of overfitting, and preserves the stability of the model learning process. Furthermore, the convolutional neural network (CNN), renowned for its ability to identify and recognize complex distributions within electricity consumption datasets, is employed for feature extraction and classification tasks. The superior performance of the proposed model is demonstrated through rigorous comparisons against alternative resampling methods and state-of-the-art machine and deep learning classifiers. The ROC-AUC, accuracy, F1 score, recall, and precision of the model indicate it significantly outperforms existing approaches.

Keywords

Smart Grid, Electricity Theft, Deep Learning, CNN, imbalanced data, hybrid resampling technique

Article Type

Article

First Page

95

Last Page

105

Publication Date

4-30-2025

Download

Share

COinS