Reliable solar radiation and photovoltaic power prediction is essential for the safe and stable operation of electric power systems. Cloud cover is highly related with solar radiation, but existing advection-/extrapolation-based cloud forecast methods have difficulties in capturing cloud development. Researchers from KNMI have applied and compared two deep learning models and an advection method (optical flow) for solar radiation forecasting on the basis of geostationary satellite observations. Data from the Ruisdael Observatory station in Cabauw was used for validation. Results are published in a journal article in Solar Energy. The article can be found here.
For the first time the novel Deep Generative Model of Radar (originally developed for radar precipitation nowcasting) has been applied to predict solar radiation (named as DGMR-SO). The UNet deep learning model and an advection method based on cloud physical properties forecasting were used for comparison.
A spatial blurring strategy was also applied to the optical flow results in order to reduce the forecast errors. Finally, the smart persistence model and the HARMONIE numerical weather prediction model forecast were utilized as benchmark methods. The forecast horizon was 0–4 h with 15 min temporal resolution. All methods were validated using ground-based observations from the Baseline Surface Radiation Network (BSRN) station inCabauw . In general, UNet shows the lowest errors, while DGMR-SO outperforms the competitors on qualitative performance after around 45 min. The forecast accuracy of each method also depends on sky conditions. The study findings are expected to encourage the inclusion of satellite data in solar radiation nowcasting, and can provide scientific guidance for power systems and solar power plants. The code is open-sourced and can be found here.
Photo credit: Arnoud Apituley (KNMI), BSRN-field in Cabauw
