Hybrid Machine Learning Approach for Enhanced Fault Detection and Power Estimation in Photovoltaic Systems

Abstract

Accurate power prediction and fault detection in photovoltaic (PV) systems are essential for improving energy efficiency and enabling predictive maintenance. This study proposes a novel hybrid regression model based on a stacking ensemble architecture, which integrates multiple machine learning algorithms: histogram-based gradient boosting (HGB), k-nearest neighbors (k-NN), decision tree (DT), random forest (RF), and LightGBM as base learners and employs Ridge regression as the meta-learner. The model was designed to detect complex fault conditions such as partial shading and module-level failures using SCADA-type input features. The performance of the proposed model was evaluated using standard regression metrics (R2, RMSE, MAE), achieving superior results with an R2 of 0.9939, RMSE of 12.0184, and MAE of 8.0544. Paired t-tests confirmed the statistical significance of performance improvements over baseline models (p < 0.05). To ensure transparency, explainability analyses were conducted using SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME), which revealed that fault-related features had the greatest influence on model predictions. Comparative evaluation with recent state-of-the-art approaches demonstrated that the proposed hybrid model is scalable, computationally efficient, and robust under varying environmental and operational conditions. The findings suggest that the model can serve as a reliable and interpretable solution for real-time power forecasting and fault detection in PV systems. © 2026 The Author(s). IET Renewable Power Generation published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.