Statistical Learning for Short-Term Photovoltaic Power Predictions

A precise prediction of photovoltaic (PV) power has an important part to play as basis for operation and management strategies for a reliable and economical integration into the power grid. Due to fast changing weather conditions, e.g., clouds and fog, a precise forecast in the minute to hour range can be a difficult undertaking. But the growing IT-infrastructure allows a fine screening of PV power. On the basis of big data sets of PV measurements, we apply methods from statistical learning for a one-hour ahead prediction based on data with hourly resolution. In this work, we employ nearest neighbors regression and support vector regression for PV power predictions based on measurements and numerical weather predictions. We put an emphasis on the analysis of feature combinations based on PV time series and numerical weather predictions.