Personalized PV system recommendation for enhanced solar energy harvesting using deep learning and collaborative filtering

Electricity is a crucial aspect of modern life, and with the increasing population and industrialization, energy demand has risen significantly. A swift transition to renewable energy sources such as wind and solar is essential for saving the planet. Solar energy is one of the most widely used renewable energy solutions, but choosing a PVSC poses a challenging problem that involves considering various factors, such as geographical location and energy consumption patterns. In this study, we investigate the effectiveness of using machine learning techniques to assist users in selecting the most suitable PVSC for their needs. We propose a new framework for PVSC recommendation, which encompasses a PV power forecasting model and a PV configuration recommendation system. We propose two forecasting models, one based on LSTM and the other based on CNN architecture. These two elements are responsible for extracting relevant features from time-series meteorological data, which are then passed to a feed-forward MLP layer that predicts the monthly energy production for different PVSCs. Subsequently, the prediction results are utilized to determine the optimal Residential scale PVSC for households, taking into account location and historical consumption data. The system was trained on simulated data and then tested on both a hold-out simulated test set and a real-world dataset. Our experiments show that the proposed framework is effective for long-term PV power forecasting and PVSC recommendation.