Enhancing Solar Power Forecasting Through Hybrid Machine Learning Models, Satellite Data Integration, and Transfer Learning Techniques

This paper introduces an innovative method for improving solar power prediction accuracy by integrating realtime weather forecasting, advanced machine learning techniques, and hybrid modelling frameworks. The proposed methodology incorporates satellite-based solar irradiance data, time-series prediction leveraging Long Short-Term Memory (LSTM) networks, and transfer learning for cross-regional model adaptation. These innovations aim to address the limitations of traditional models and provide a more resilient framework for forecasting solar power in diverse geographic regions.