Statistical calibration of weather forecasts for power generation
In 2020, 36.6% of the total electricity demand of the world was covered by renewable sources, whereas in the EU (UK included) this share reached 49.3%. A substantial part of green energy is produced by wind and solar farms, where accurate short range power predictions are required for successful integration of wind and photovoltaic energy into the electrical grid. Accurate predictions of the produced electricity require accurate forecasts of the corresponding weather quantities, where the state-of-the-art method is the probabilistic approach based on ensemble forecasts. However, ensemble forecasts are often uncalibrated and might also be biased, thus require some form of post-processing to improve their predictive performance.
To calibrate (hub height) wind speed ensemble forecasts we propose a novel flexible machine learning approach, which results either in a truncated normal or a lognormal predictive distribution. In a case study based on 100m wind speed forecasts of the operational AROME-EPS of the Hungarian Meteorological Service, the forecast skill of this method is compared with the predictive performance of three different ensemble model output statistics approaches and the raw ensemble predictions. We show that compared with the raw ensemble, post-processing always improves the calibration of probabilistic and accuracy of point forecasts, and from the five competing methods the novel machine learning based approaches result in the best overall performance.
We also introduce a post-processing model for ensemble weather predictions of solar irradiance, which provides probabilistic forecasts in the form of a censored logistic distribution. Based on a case study involving AROME-EPS ensemble forecasts of global horizontal irradiance, we find that post-processing consistently and significantly improves the forecast performance of the raw ensemble for lead times up to at least 48h and is well able to correct the systematic lack of calibration.