In recent years, as the share of solar power in the electrical grid has been increasing, accurate methods for forecasting solar irradiance have become necessary to manage the electrical grid. More specifically, as solar generators are geographically dispersed, it is very important to have general models that can predict solar irradiance without the need of ground data. In this paper, we propose a novel technique that can accomplish that: using satellite images, the proposed model is able to forecast solar irradiance without the need of ground measurements. To illustrate the performance of the proposed model, we consider 15 locations in The Netherlands, and we show that the proposed model is as accurate as local models that are individually trained with ground data.@en

Due to the increasing integration of solar power into the electrical grid, forecasting short-term solar irradiance has become key for many applications, e.g. operational planning, power purchases, reserve activation, etc. In this context, as solar generators are geographically dispersed and ground measurements are not always easy to obtain, it is very important to have general models that can predict solar irradiance without the need of local data. In this paper, a model that can perform short-term forecasting of solar irradiance in any general location without the need of ground measurements is proposed. To do so, the model considers satellite-based measurements and weather-based forecasts, and employs a deep neural network structure that is able to generalize across locations; particularly, the network is trained only using a small subset of sites where ground data is available, and the model is able to generalize to a much larger number of locations where ground data does not exist. As a case study, 25 locations in The Netherlands are considered and the proposed model is compared against four local models that are individually trained for each location using ground measurements. Despite the general nature of the model, it is shown show that the proposed model is equal or better than the local models: when comparing the average performance across all the locations and prediction horizons, the proposed model obtains a 31.31% rRMSE (relative root mean square error) while the best local model achieves a 32.01% rRMSE.

@en