Multi-view broad learning system for electricity theft detection

Abstract

Electricity theft poses a huge hazard to the economic efficiency of power companies and the safe operation of the power system. Analysis of smart grid data can help to identify abnormal electricity usage patterns of the thieves. However, existing models may suffer from underfitting issues due to the high dimensionality and imbalanced class distribution in the electricity dataset. To address these challenges and improve the performance of electricity theft detection, this study proposes a multi-view detection model based on broad learning system (BLS). First, a new multi-view framework is presented to map the raw power data into different sub-views, thereby reducing redundant electricity data features. Then, an adaptive weighting strategy based on the regional distribution of the data is developed. The optimized sub-views are obtained by considering the sample size and dispersion of the data. Finally, a power theft detection model is constructed by combining the region distribution weighted BLS and the multi-view rotation BLS. Comparative experiments on real-world electricity dataset demonstrate the superiority of our proposed approach.