Huertas Tato, JavierAler, RicardoRodríguez Benítez, F. J.Arbizu Barrena, C.Galván, Inés M.2019-10-102019-10-102018-06-08Huertas-Tato, J., Aler, R., Rodríguez-Benítez, F.J., Arbizu-Barrena, C., Pozo-Vázquez, D. y Galván, I.M. (2018). Predicting Global Irradiance Combining Forecasting Models Through Machine Learning. In HAIS 2018: Hybrid Artificial Intelligent Systems,10870, pp. 622-633.978-3-319-92638-4https://hdl.handle.net/10016/29004This paper has been presented at : 13th International Conference on Hybrid Artificial Intelligence Systems (HAIS 2018)Predicting solar irradiance is an active research problem, with many physical models having being designed to accurately predict Global Horizontal Irradiance. However, some of the models are better at short time horizons, while others are more accurate for medium and long horizons. The aim of this research is to automatically combine the predictions of four different models (Smart Persistence, Satellite, Cloud Index Advection and Diffusion, and Solar Weather Research and Forecasting) by means of a state-of-the-art machine learning method (Extreme Gradient Boosting). With this purpose, the four models are used as inputs to the machine learning model, so that the output is an improved Global Irradiance forecast. A 2-year dataset of predictions and measures at one radiometric station in Seville has been gathered to validate the method proposed. Three approaches are studied: a general model, a model for each horizon, and models for groups of horizons. Experimental results show that the machine learning combination of predictors is, on average, more accurate than the predictors themselves.12eng© Springer International Publishing AG, part of Springer Nature 2018Global irradiance forecastingMachine learningCombining forecasting modelsconference paperInformáticahttps://doi.org/10.1007/978-3-319-92639-1_52open access622633HAIS 2018: Hybrid Artificial Intelligent Systems10870CC/0000030021