Skip to Main content Skip to Navigation
Reports

Prévision d'un processus à valeurs fonctionnelles en présence de non stationnarités. Application à la consommation d'électricité.

Anestis Antoniadis 1 Xavier Brosat 2 Jairo Cugliari 3, * Jean-Michel Poggi 4
* Corresponding author
1 SAM - Statistique Apprentissage Machine
LJK - Laboratoire Jean Kuntzmann
3 SELECT - Model selection in statistical learning
LMO - Laboratoire de Mathématiques d'Orsay, Inria Saclay - Ile de France
Abstract : We study here the problem of predicting a functional valued stochastic process. We first explore the model proposed by Antoniadis et al. (2006) in the context of a practical application -the french electrical power demand- where the hypothesis of stationarity may fail. The departure from stationarity is twofold: an evolving mean level and the existence of groups that may be seen as classes of stationarity. We explore some corrections that enhance the prediction performance. The corrections aim to take into account the presence of these nonstationary features. In particular, to handle the existence of groups, we constraint the model to use only the data that belongs to the same group of the last available data. If one knows the grouping, a simple post-treatment suffices to obtain better prediction performances.
Complete list of metadata

https://hal.inria.fr/hal-00703570
Contributor : Jairo Cugliari <>
Submitted on : Monday, June 4, 2012 - 11:32:41 AM
Last modification on : Tuesday, July 6, 2021 - 3:39:31 AM
Long-term archiving on: : Wednesday, September 5, 2012 - 2:18:43 AM

File

RR-7982.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00703570, version 1

Citation

Anestis Antoniadis, Xavier Brosat, Jairo Cugliari, Jean-Michel Poggi. Prévision d'un processus à valeurs fonctionnelles en présence de non stationnarités. Application à la consommation d'électricité.. [Rapport de recherche] RR-7982, INRIA. 2012. ⟨hal-00703570⟩

Share

Metrics

Record views

798

Files downloads

842