Electricity theft decreases electricity revenues and brings risks to power usage’s safety, which has been increasingly challenging nowadays. As the mainstream in the relevant studies, the state-of-the-art data-driven approaches mainly detect electricity theft events from the perspective of the correlations between different daily or weekly loads, which is relatively inadequate to extract features from hours or more of fine-grained temporal data. In view of the above deficiencies, we propose a novel electricity theft detection scheme based on text convolutional neural networks (TextCNN). Specifically, we convert electricity consumption measurements over a horizon of interest into a two-dimensional time-series containing the intraday electricity features. Based on the data structure, the proposed method can accurately capture various periodical features of electricity consumption. Moreover, a data augmentation method is proposed to cope with the imbalance of electricity theft data. Extensive experimental results based on realistic Chinese and Irish datasets indicate that the proposed model achieves a better performance compared with other existing methods.

Electricity theft has been a major concern to the secure operation of power systems and the interests of power companies. Due to the different methods and types of electricity theft behaviors, it is difficult to determine the suspicion levels of consumers in the research of electricity theft detection. An electricity theft detection method based on stacked autoencoder (SAE) and the undersampling and resampling based random forest (UaRe-RF) algorithm is proposed in this work to formulate appropriate strategies for the practical electricity theft detection requirements of the power company. In the proposed method, the supervised SAE is first trained to extract electricity consumption features that are more adaptable to the classification algorithm for electricity theft detection. Then, the UaRe-RF algorithm is used to establish the class-balanced subsets and determine the suspicion level of each electricity theft user. Finally, two cases of different datasets of electricity consumers are studied for demonstrating the effectiveness of the proposed method, and the results show that higher classification accuracy and more targeted detection strategies can be achieved through the proposed method.

No abstract

No abstract

No abstract