A BAYESIAN MODEL COMMITTEE APPROACH TO FORECASTING GLOBAL SOLAR RADIATION

Philippe Lauret (1) , Auline Rodler (2) , Marc Muselli (3, 4) , Mathieu David (1) , Hadja Maïmouna Diagne (1) , Cyril Voyant (3, 5)

1 PIMENT - Physique et Ingénierie Mathématique pour l'Énergie, l'environnemeNt et le bâtimenT
2 SPE
3 SPE - Sciences pour l'environnement
4 International Organization for Dew Utilization
5 CHD Castellucio - CHD Castelluccio

This paper proposes to use a rather new modelling approach in the realm of solar radiation forecasting. In this work, two forecasting models: Autoregressive Moving Average (ARMA) and Neural Network (NN) models are combined to form a model committee. The Bayesian inference is used to affect a probability to each model in the committee. Hence, each model's predictions are weighted by their respective probability. The models are fitted to one year of hourly Global Horizontal Irradiance (GHI) measurements. Another year (the test set) is used for making genuine one hour ahead (h+1) out-of-sample forecast comparisons. The proposed approach is benchmarked against the persistence model. The very first results show an improvement brought by this approach.

Domaines: Recherche d'information [cs.IR]

Philippe Lauret, Auline Rodler, Marc Muselli, Mathieu David, Hadja Maïmouna Diagne, et al.. A BAYESIAN MODEL COMMITTEE APPROACH TO FORECASTING GLOBAL SOLAR RADIATION. WREF 2012 : World Renewable Energy Forum, May 2012, Denver, United States. pp.1. ⟨hal-00682217⟩