Prediction of Photovoltaic Output Power using GRU and Weather Data Fusion

The reliability of renewable energy systems and the power grid depends on accurate predictions of solar panel output. This research proposes a deep learning-based approach to photovoltaic (PV) power forecasting by integrating weather forecasts with gated recurrent unit (GRU) networks. The performance of the GRU network is evaluated using root mean square error (RMSE), mean absolute deviation (MAD), and the coefficient of determination (R²), after training on weather and solar energy generation datasets. Results show that the GRU-based model delivers more accurate forecasts compared to conventional machine learning methods. Overall, this study highlights the potential of GRU networks combined with meteorological data to improve solar power prediction and support smarter grid management.