Electricity load forecasting and backcasting with semi-parametric models

Raphaël Nedellec 1 Jairo Cugliari 2 Yannig Goude 1
2 SELECT - Model selection in statistical learning
Inria Saclay - Ile de France, LMO - Laboratoire de Mathématiques d'Orsay, CNRS - Centre National de la Recherche Scientifique : UMR
Abstract : We sum up the methodology of the team tololo for the Global Energy Forecasting Competition 2012: Load Forecasting. Our strategy consisted of a temporal multi-scale model that combines three components. The first component was a long term trend estimated by means of non-parametric smoothing. The second was a medium term component describing the sensitivity of the electricity demand to the temperature at each time step. We use a generalized additive model to fit this component, using calendar information as well. Finally, a short term component models local behaviours. As the factors that drive this component are unknown, we use a random forest model to estimate it.
Type de document :
Article dans une revue
International Journal of Forecasting, Elsevier, 2013, 30 (2), pp.375-381. 〈10.1016/j.ijforecast.2013.07.004〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00942688
Contributeur : Erwan Le Pennec <>
Soumis le : jeudi 6 février 2014 - 11:36:12
Dernière modification le : mardi 6 mars 2018 - 15:58:42

Identifiants

Collections

Citation

Raphaël Nedellec, Jairo Cugliari, Yannig Goude. Electricity load forecasting and backcasting with semi-parametric models. International Journal of Forecasting, Elsevier, 2013, 30 (2), pp.375-381. 〈10.1016/j.ijforecast.2013.07.004〉. 〈hal-00942688〉

Partager

Métriques

Consultations de la notice

203