Un nouveau papier vient d'être accepté au sein d'une conférence dans le domaine de l'intelligence artificielle. Il s'agit de la ICIC'09 : "2009 International Conference on Intelligent Computing", co-sponsorisé par "IEEE Computational Intelligence Society" et "International Neural Network Society". Notre papier (cf ci-dessous : titre, auteurs et résumé) apparaitra dans les "proceedings" (Collection de communications scientifiques) de la conférence qui seront publiés au sein de Springer Verlag, incluant Lecture Notes in Computer Sciences (LNCS)/Lecture Notes in Artificial Intelligence (LNAI)/Lecture Notes in Bioinformatics (LNBI)/ Communications in Computer and Information Science (CCIS).

Title of the paper: Solar radiation forecasting using ad-hoc time series preprocessing and neural networks.

Authors : Christophe Paoli, Cyril Voyant, Marc Muselli, Marie-Laure Nivet.

Abstract: In this paper, we present an application of neural networks in the renewable energy domain. We have developed a methodology for the daily prediction of global solar radiation on a horizontal surface. We use an ad-hoc time series preprocessing and a Multi-Layer Perceptron (MLP) in order to predict solar radiation at daily horizon. First results are promising with nRMSE < 21% and RMSE < 998 Wh/m². Our optimized MLP presents prediction similar to or even better than conventional methods such as ARIMA techniques, Bayesian inference, Markov chains and k-Nearest-Neighbors approximators. Moreover we found that our data preprocessing approach can reduce significantly forecasting errors.

Source
http://www.ic-ic.org