Abstract-Due to the inherent uncertainty involved in renewable energy forecasting, uncertainty quantification is a key input to maintain acceptable levels of reliability and profitability in power system operation. A proposal is formulated and evaluated here for the case of solar power generation, when only power and meteorological measurements are available, without skyimaging and information about cloud passages. Our empirical investigation reveals that the distribution of forecast errors do not follow any of the common parametric densities. This therefore motivates the proposal of a nonparametric approach to generate very short-term predictive densities, i.e., for lead times between a few minutes to one hour ahead, with fast frequency updates. We rely on an Extreme Learning Machine (ELM) as a fast regression model, trained in varied ways to obtain both point and quantile forecasts of solar power generation. Four probabilistic methods are implemented as benchmarks. Rival approaches are evaluated based on a number of test cases for two solar power generation sites in different climatic regions, allowing us to show that our approach results in generation of skilful and reliable probabilistic forecasts in a computationally efficient manner.
In the probabilistic energy forecasting literature, emphasis is mainly placed on deriving marginal predictive densities for which each random variable is dealt with individually. Such marginals description is sufficient for power systems related operational problems if and only if optimal decisions are to be made for each lead-time and each location independently of each other. However, many of these operational processes are temporally and spatially coupled, while uncertainty in photovoltaic (PV) generation is strongly dependent in time and in space. This issue is addressed here by analysing and capturing spatio-temporal dependencies in PV generation. Multivariate predictive distributions are modelled and space-time trajectories describing the potential evolution of forecast errors through successive lead-times and locations are generated. Discrimination ability of the relevant scoring rules on performance assessment of space-time trajectories of PV generation is also studied. Finally, the advantage of taking into account space-time correlations over probabilistic and point forecasts is investigated. The empirical investigation is based on the solar PV dataset of the Global Energy Forecasting Competition (GEFCom) 2014.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.