Title :

On meteorological forecasts for energy management and large historical data: A first look

Author(s) :

Voyant, Cyril [Auteur]
Laboratoire « Sciences pour l’Environnement » (UMR CNRS 6134 SPE) [SPE]
Join, Cédric [Auteur]
Centre de Recherche en Automatique de Nancy [CRAN]
Non-Asymptotic estimation for online systems [NON-A]
Fliess, Michel [Auteur]
Laboratoire d'informatique de l'École polytechnique [Palaiseau] [LIX]
Nivet, Marie-Laure [Auteur]
Laboratoire « Sciences pour l’Environnement » (UMR CNRS 6134 SPE) [SPE]
Muselli, Marc [Auteur]
Laboratoire « Sciences pour l’Environnement » (UMR CNRS 6134 SPE) [SPE]
Paoli, Christophe [Auteur]
Université Galatasaray [GSU]

Conference title :

International Conference on Renewable Energies and Power Quality, ICREPQ'15

City :

La Coruña

Country :

Espagne

Start date of the conference :

2015-03-25

Book title :

Renewable Energy and Power Quality Journal (RE&PQJ)

Publication date :

2015

English keyword(s) :

scaled persistence
multilayer perceptron
meteorology
time series
big data
quick fluctuations
persistence
forecasting
trend

HAL domain(s) :

Sciences de l'environnement/Ingénierie de l'environnement
Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Base de données [cs.DB]
Informatique [cs]/Réseau de neurones [cs.NE]
Statistiques [stat]/Machine Learning [stat.ML]
Mathématiques [math]/Logique [math.LO]
Informatique [cs]/Informatique ubiquitaire
Sciences de l'ingénieur [physics]/Automatique / Robotique

English abstract : [en]

This communication is devoted to a comparison between various meteorological forecasts, for the purpose of energy management, via different time series techniques. The first group of methods necessitates a large number of ...
Show more >This communication is devoted to a comparison between various meteorological forecasts, for the purpose of energy management, via different time series techniques. The first group of methods necessitates a large number of historical data. The second one does not and is much easier to implement, although its performances are today only slightly inferior. Theoretical justifications are related to methods stemming from a new approach to time series, artificial neural networks, computational intelligence and machine learning. Several numerical simulations are provided and discussed.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Comment :

Published in Renewable Energy and Power Quality Journal, n°13, mars 2015

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL