An Electricity Theft Detection Based on Image Coding Technique and ConvNeXt

The deep learning techniques has been effective means for electricity theft detection. However, most exiting works are based on one-dimensional time series data, which makes it challenging to fully capture and utilize the multidimensional features of the electricity data. Therefore, a novel electricity theft detection approach based on gramian angular summation field (GASF) and ConvNeXt is proposed. Specifically, the paper designs a GASF-based image coding strategy to convert onedimensional electricity consumption data into two-dimensional images. In this case, the multidimensional features of electricity consumption behavior can be preserved in the GASF images. And then, the image classifier is designed that utilizes ConvNeXt as a feature extractor to learn multidimensional features of GASF images, thereby achieving electricity theft detection. Experimental results based on a real-world dataset show that the proposed detector reaches the accuracy of 0.973, which is superior to state-of-the-art methods. Furthermore, the detection performance of different anomaly detectors against smart electricity theft behaviors are evaluated, and the economic losses they can recover for power companies are quantified. The results indicate that the proposed detector, by virtue of its strong capability in identifying inter-class differences among electricity theft behaviors, can thereby minimize the economic losses sustained by power companies.