PV power predictions on different spatial and temporal scales integrating PV measurements, satellite data and numerical weather predictions

摘要

1. PV power prediction contributes to successful grid integration of more than 36 GWpeak PV power in Germany 2. PV power forecasts based on satellite data (CMV) significantly better than NWP based forecasts up to 4 hours ahead 3. significant improvement by combining different forecast models with PV power measurements, in particular for regional forecasts 4. first evaluations of machine learning method SVR for PV power forecasting shows potential of this method.