Model estimation for PV generation forecasting using cloud cover information

We propose a parametric model approach to photovoltaic generation forecasting. The problem is addressed in the common scenario where measurements of meteorological variables (i.e. solar irradiance and temperature) at the plant site are not available. The proposed method exploits cloud cover data provided by a meteorological service as well as power generation measurements, and is characterized by low computational effort. Simulation and experimental validation are presented, as well as a performance comparison with a possible approach based on Artificial Neural Networks.