The SunCast solar energy forecasting system is designed to meet these challenges. Several forecasting components predict 15-minute average global horizontal irradiance (GHI) over a range of nowcasting time horizons. These components include site-based statistical learning methods (StatCast), satellite cloud advection forecasting (CIRACast), multi-sensor advective diffusion forecasting (MADCast), and the WRF-Solar numerical weather prediction model. The goal of SunCast is to blend these systems into a single solar energy forecasting product.
In this study we compare the performance of SunCast component forecasts for different sky cover regimes near Sacramento, including marine stratocumulus, which is a notoriously difficult forecasting problem for utilities on the West Coast. We also show better GHI forecasts for these case studies as the component systems were continually improved over the past year.