Machine Learning Methods for Solar Irradiation Forecasting: A Comparison in a Mediterranean Site

Abstract : In this survey, several statistical and machine learning tools are analyzed and compared in view to forecast the solar irradiation in Ajaccio (Corsica, France, 41°55 N, 8°44 E, 4m asl). The forecasting horizon is from 1 to 6 hours with an hourly time granularity. Eleven forecasting models are compared: persistence, scaled persistence, ARMA, MLP, regression trees, boosted regression trees, bagged regression trees, pruned regression trees, random forest, Gaussian processes and support vector regression. The models are compared in term of error metrics: nRMSE (normalized root mean squared error), MAE (mean absolute error) and skill score related to the smart persistence.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01635190
Contributor : Cyril Voyant <>
Submitted on : Thursday, November 23, 2017 - 8:03:47 AM
Last modification on : Thursday, January 11, 2018 - 6:16:29 AM

File

PaperForecastingextended.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01635190, version 1

Collections

Citation

Alexis Fouilloy, Cyril Voyant, Gilles Notton, Marie Laure Nivet, Jean Laurent Duchaud. Machine Learning Methods for Solar Irradiation Forecasting: A Comparison in a Mediterranean Site. 2017. ⟨hal-01635190⟩

Share

Metrics

Record views

132

Files downloads

468