Skip to Main content Skip to Navigation
Master Thesis

Prévision du rayonnement solaire : classification en journées types et combinaisons de modèles statistiques

Abstract : This paper deals with different methods for solar forecasting. Method: First, we study two kinds of classification. We try to develop a classification which keeps the temporal structure of the data. Then, we test combined forecast. We use linear regression and a method of optimisation under constraint where the sum of the weights is equal to one. Results: In this study, the results for the classification are not so good, but they make us think about a lot of possible improvements. In our case, combining models improves the forecast precision.
Document type :
Master Thesis
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download

https://dumas.ccsd.cnrs.fr/dumas-01103952
Contributor : Agrocampus Ouest <>
Submitted on : Thursday, January 15, 2015 - 4:43:11 PM
Last modification on : Friday, October 23, 2020 - 4:34:03 PM
Long-term archiving on: : Friday, September 11, 2015 - 6:52:21 AM

Identifiers

  • HAL Id : dumas-01103952, version 1

Collections

Citation

Emmanuelle Héritier. Prévision du rayonnement solaire : classification en journées types et combinaisons de modèles statistiques. Sciences agricoles. 2014. ⟨dumas-01103952⟩

Share

Metrics

Record views

335

Files downloads

499