Effect of Cloudiness on Solar Radiation Forecasting
Abstract
Solar radiation forecasting has become critical information to facilitate the integration of PV and thermal solar power plants into the electricity grid of any country. Artificial neural network (ANN) approaches in time series forecasting are known to be a useful tool to achieve this task, due to their capability of describing non-linear relationships hidden inside historical data. Unfortunately, fast cloudiness transients add a stochastic signal to the solar radiation time series, thus diminishing the effectiveness of this methodology. In this work, ANNs are trained to provide 1-day-ahead forecasts of global solar radiation under different cloudiness regimes. Nine years of data measured at eight U.S. SURFRAD network stations with diverse climates are used. Different results on forecast accuracy are found depending on cloud fraction, with RMS errors ranging from 10% up to 35%.