A hybrid methodology for the day-ahead PV forecasting exploiting a Clear Sky Model or Artificial Neural Networks

PhotoVoltaic (PV) plants can bring a positive impact on the sustainability of electric grids. Its variability and uncertainty, however, leads to challenging technical problems related to the efficient and secure operations of power systems. In this paper, a novel hybrid methodology for the day-ahead PV power forecasting is proposed. The methodology is able to use a Clear Sky Model (CSM) or an Artificial Neural Network (ANN), according to the day-ahead weather forecasting. Selection among these two methods is performed by a threshold on the Cloud Cover Index (CCI) determined by linear regression. The method has been tested and validated on a real PV plant.