Abstract
With the popularization of smart meters around the world and the appearance of a large amount of electricity consumption data, the analysis of smart meter data is of major interest to electricity distributors around the world. Therefore, we proposed a hybrid artificial intelligence (AI) technique considering sudden changes of consumption in order to accurately predict fraudulent consumers in the smart network. Thus, the proposed hybrid model is based on the support vector machine (SVM) and a particle swarm optimization (PSO) algorithm to detect energy fraudsters in the network. In addition, a real smart grid dataset is used to verify the effectiveness of the proposed algorithm. Moreover, a smart calendar context is modeled showing the scheduling of energy consumption. The effectiveness of the proposed technique is evaluated using performance coefficients such as precision, recall, F1‐score, and area under ROC curve (AUC). We also perform sensitivity analysis through regression, variance, and variogram analysis. The results obtained give a performance of 98.9% in the detection of irregular consumers in the smart power grid. These results demonstrate the effectiveness of the proposed method compared to that in the literature.