Evaluating the Weather Forecasting Models and the Impact to PV Generation Forecasting

Accurate photovoltaic (PV) generation forecasting is an important feature that can assist utilities and plant operators in the direction of energy management and dispatchability planning. However, the accuracy of the PV forecasting is directly related to the quality of the weather forecasts. In this work, an evaluation of the various weather forecasting models is performed. Additionally, an investigation of the effect of the quality of the weather forecasts on PV generation forecasting will be examined. Finally, this study focused to propose an approach to improve the quality of the weather forecasts and eventually the PV production forecasting accuracy by employing machine learning and linear regression models that could record the behaviour of the local weather.