ANN-Based Large-Scale Cooperative Solar Generation Forecasting

In this work we introduce the concept and method of so-called cooperative solar generation forecasting, where geographically close data sources are utilized in order to improve forecasting accuracy. We devised examined various largescale one-hour-ahead artificial neural networks based scenarios prove benefits cooperation. The introduced showed significant improvement accuracy, especially when combined with previous data, a root mean square error reduction at least 50% could be achieved majority cases. believe these results point scientific economical benefit international cooperation forecasting.