Correlation based feature importance analysis for improving machine learning stability predictions in hybrid PV systems

Abstract Accurate prediction of grid voltage and stability is critical for ensuring reliable and efficient operation of modern power systems, especially with the increasing integration of intermittent renewable energy sources. This study rigorously evaluates five Machine Learning (ML) models, viz., Random Forest (RF), Extra Trees (ET), Support Vector Regression (SVR), Cat Boost (CB), and Gradient Boosting (GB), for their predictive performance in grid connected hybrid PV systems. Using a multimetric framework (R 2 , MAE, RMSE, MAPE) and advanced visual diagnostics (error distributions, temporal trend analysis), Gradient Boosting emerged as the top performing model, demonstrating superior accuracy and robustness across both voltage and stability prediction tasks. For grid voltage prediction, GB achieved the highest test R 2 = 0.9785 and lowest MAPE = 0.25%, with 95% of errors confined to ± 0.5 V. In stability score forecasting, GB again outperformed all alternatives, attaining the best R 2 = 0.9300 and lowest MAE = 0.75, while maintaining tight residual distributions ± 2.5 units. Comparative analysis revealed GB’s consistent superiority over tree based (RF, ET, CB) and kernel based (SVR) models, particularly in handling extreme operational ranges and temporal fluctuations. The results position Gradient Boosting as a unified, high precision solution for smart grid forecasting, offering actionable insights for real time monitoring and control. Its balanced performance across static and dynamic conditions underscores its suitability for resilient grid management in renewable rich environments. This work is novel in generating a controlled MATLAB/ Simulink dataset to capture nonlinear hybrid PV operating regimes and applying correlation-weighted feature engineering to enhance model interpretability. A unified benchmarking of five ML models under identical preprocessing identifies Gradient Boosting as the most reliable predictor. The framework further integrates extended KPIs and dynamic learning-rate scheduling, offering a robust and transparent approach for voltage and stability forecasting. Future research ought to examine hybrid GB ensembles and include optimization to enhance further on scalability with largescale deployments.