The renewable energy industry requires accurate forecasts of intermittent solar irradiance SI to effectively manage solar power generation and supply. A simulation study of multivariate data-generating processes was carried out to compare the forecasting accuracy of the models when predicting global horizontal solar irradiance.
However, the evaluations of the pinball loss scores and mean absolute scaled errors demonstrated a clear superiority of the QGAM.
Similar results were obtained in an application to real-life data. Therefore, we recommend that the QGAM be preferred ahead of decision tree-based models when predicting solar irradiance. However, the QRRF model can be used alternatively to predict the forecast distribution. Both the QGAM and QRRF modelling frameworks went beyond representing forecast uncertainty of SI as probability distributions around a prediction interval to give complete information through the estimation of quantiles.
Extensions of the QRRF and QGAM frameworks can be made to model other renewable sources of energy that have meteorological characteristics similar to solar irradiance. Citation: Masache A, Mdlongwa P, Maposa D, Sigauke C Short-term forecasting of solar irradiance using decision tree-based models and non-parametric quantile regression. This is an open access article distributed under the terms of the Creative Commons Attribution License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Competing interests: The authors have declared that no competing interests exist. Photovoltaic power generation directly and heavily depends on solar irradiance SI. The rapid fluctuating uncertainty characteristics of SI make photovoltaic power generation have intermittent and uncontrollable characteristics that greatly impact the stability of solar power systems [ 1 ]. SI data is often characterised by significant covariate multicollinearity, existence of outliers, heavy right-tailed, platykurtic, lot of noise and no known probability distribution [ 2 — 5 ].
