Using machine learning ensemble method for detection of energy theft in smart meters

Electricity theft is a primary concern for utility providers, as it leads to substantial financial losses. To address the issue, a novel extreme gradient boosting (XGBoost)-based model utilizing the consumers' electricity consumption patterns for analysis is proposed for electricity theft detection (ETD). To remove the imbalance in the real-world electricity consumption dataset and ensure an even distribution of theft and non-theft data instances, six different artificially created theft attacks were used. Moreover, the utilization of the XGBoost algorithm for classification, especially to identify malicious instances of electricity theft, yielded commendable accuracy rates and a minimal occurrence of false positives. The proposed model identifies electricity theft specific to the regions, utilizing electricity consumption parameters, and other variables as input features. The authors' model outperformed existing benchmarks like k-neural networks, light gradient boost, random forest, support vector machine, decision tree, and AdaBoost. The simulation results using the false attacks for balancing the dataset have improved the proposed model's performance, achieving a precision, recall, and F1-score of 96%, 95%, and 95%, respectively. The results of the detection rate and the false positive rate (FPR) of the proposed XGBoost-based detection model have achieved 96% and 3%, respectively. The goal of this study is to reduce the false-positive rate by selecting relevant features for detecting electricity theft in areas where weather conditions and unpredictability of power outages cause customers to deviate from their normal electricity usage behaviour. In the same way, the constructed attack types based on these conditions are used in simulations to improve the detection rate.image