Abstract
In this work, we assess the performance of three probabilistic models for intra-day solar forecasting. More precisely, a linear quantile regression method is used to build three models for generating 1 h–6 h-ahead probabilistic forecasts. Our approach is applied to forecasting solar irradiance at a site experiencing highly variable sky conditions using the historical ground observations of solar irradiance as endogenous inputs and day-ahead forecasts as exogenous inputs. Day-ahead irradiance forecasts are obtained from the Integrated Forecast System (IFS), a Numerical Weather Prediction (NWP) model maintained by the European Center for Medium-Range Weather Forecast (ECMWF). Several metrics, mainly originated from the weather forecasting community, are used to evaluate the performance of the probabilistic forecasts. The results demonstrated that the NWP exogenous inputs improve the quality of the intra-day probabilistic forecasts. The analysis considered two locations with very dissimilar solar variability. Comparison between the two locations highlighted that the statistical performance of the probabilistic models depends on the local sky conditions.
Highlights
Solar forecasts are required to increase the penetration of solar power into electricity grids.Accurate forecasts are important for several tasks
The third quantile regression (QR) model developed in this work considers as predictors the six past ground measurements plus exogenous data provided by the day-head European Center for Medium-Range Weather Forecast (ECMWF) forecasts
Over a testing set of significant size, the difference between observed and nominal probabilities should be as small as possible. This first requirement of reliability will be assessed with the help of reliability diagrams or by calculating the prediction interval coverage probability (PICP) [13], which permits one to assess the reliability of the forecasts in terms of coverage rate
Summary
Solar forecasts are required to increase the penetration of solar power into electricity grids. Energies 2017, 10, 1591 parametric approach based on a combination of two linear time series model (ARMA-GARCH) to generate 10 min–6 h GHI probabilistic forecasts using only past ground data. Lauret et al [7] demonstrated that intra-day point deterministic forecasts can be improved by considering both past ground measurements and day-ahead ECMWF forecasts in the set of predictors In this work, it is investigated if such a combination could improve the quality of the probabilistic forecasts. Solar irradiance is characterized by deterministic diurnal and seasonal variations Such a component can be removed from the analysis by working with the clear sky index (kt∗ ) instead of the original GHI time series, where kt∗ is defined as: kt∗ (t) =. This procedure is described at length in [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
