A Photovoltaic Power Theft Detection Method based on Data-driven Stacking Model

The growth of distributed generation (DG) has established a connection between photovoltaic power generation and economic benefits. However, some users exploit this by engaging in photovoltaic power theft through network attacks on smart meters (SM) to manipulate power readings for financial gain. To tackle this problem, this paper proposes a data-driven stacking model for detecting photovoltaic power theft.The proposed method involves preprocessing real power generation data and designing attack functions to generate malicious data. Photovoltaic power generation features are categorized using the Person correlation coefficient. The stacking model combines three machine learning(ML) algorithms (Artificial Neural Networks, Random Forest, and XGBoost) as base predictors, with Support Vector Regression acting as the meta-predictor to accurately estimate power readings. The anomaly classification threshold is optimized using Sequential Model-Based Optimization based on residuals. Bayesian probability analysis updates the detection probability and makes decisions regarding power theft.Evaluation results demonstrate that the ensemble models outperform individual nonlinear models, highlighting the effectiveness of the proposed approach. Overall, this research presents a comprehensive solution for detecting photovoltaic power theft using a data-driven stacking model, which surpasses individual nonlinear models in identifying anomalies in photovoltaic power generation data.