Continuous short-term irradiance forecasts using sky images

We present a system for forecasting occlusions of the sun and the expected Global Horizontal Irradiance (GHI) for solar power plants. Our system uses non-rigid registration for detecting cloud motion and a Kalman filter to establish continuous forecasts for up to 10 min. The optimal parameters of the system are determined through the use of the binary classification metrics Precision, Recall and F2 Score while evaluating the forecasting of occlusions. The Kalman filter and the use of a dense motion field instead of a global cloud speed prove to be key elements of the forecasting pipeline: by incorporating information from previous forecasts into the current one, a Kalman filtering facilitates forecasting times below 3 min and the dense motion field enhances the accuracy of our forecasts. Our evaluation of the proposed approach on 15 days of real world data collected in Kitzingen, Bavaria, Germany, produced a mean RMSE for forecasting GHI of (164±9) W m−2.