Citation
Almeida, Marcelo Pinho and Perpiñan Lamigueiro, Oscar and Narvarte Fernández, Luis
(2015).
Using a nonparametric PV model to forecast AC power output of PV plants.
In: "31st European Photovoltaic Solar Energy Conference and Exhibition: EUPVSEC 2015", 14/09/2015-18/09/2015, Hamburg, Germany. ISBN 3-936338-39-6. pp. 2227-2233.
Abstract
In this paper, a methodology using a nonparametric model is used to forecast AC power output of PV plants using as inputs several forecasts of meteorological variables from a Numerical Weather Prediction (NWP) model and actual AC power measurements of PV plants. The methodology was built upon the R environment and uses Quantile Regression Forests as machine learning tool to forecast the AC power with a confidence interval. Real data from five PV plants was used to validate the methodology, and results show that the daily production of individual plants can be predicted with a skill score up to 0.361.