Prediction intervals for global solar irradiation forecasting using regression trees methods

RENEWABLE ENERGY

卷:126

Article

Voyant, Cyril^1,2  Motte, Fabrice¹  Notton, Gilles¹  Fouilloy, Alexis¹  Nivet, Marie-Laure¹  Duchaud, Jean-Laurent¹ 

[1] Univ Corsica, CNRS UMR SPE 6134, F-20250 Corte, France

[2] Castelluccio Hosp, Radiotherapy Unit, BP 85, F-20177 Ajaccio, France

关键词: Probabilistic forecasts;    Bagging;    Boosting;    Pruning;    Mean interval length;    Prediction interval coverage probability;   

DOI  :  10.1016/j.renene.2018.03.055

来源: Elsevier

【 摘 要 】

A global horizontal irradiation prediction (from 1 h to 6 h) is performed using 2 persistence models (simple and smart ones) and 4 machine learning tools belonging to the regression trees methods family (normal, pruned, boosted and bagged). A prediction band is associated to each forecast using methodologies based on: bootstrap sampling and k-fold approach, mutual information, stationary time series process with clear sky model, quantiles estimation and cumulative distribution function. New reliability indexes (gamma index and gamma test) are built from the mean interval length (MIL) and prediction interval coverage probability (PCIP). With such methods and error metrics, good prediction bands are estimated for Ajaccio (France) with a MIL close to 113 Wh/m(2), a PCIP reaching 70% and a gamma index lower than 0.9. (C) 2018 Elsevier Ltd. All rights reserved.

【 授权许可】

Free