Philippe Lauret

University of La Réunion · Laboratory of Physics and Mathematical Engineering for Energy and the Environment (PIMENT)

Large and frequent variations of solar radiation can be observed in tropical climates with amplitudes reaching 800 W/m² and occurring within a short time interval, from few seconds to few minutes, according to the geographical location. Such fluctuations can be due for example to the dynamic of clouds which can be very complex and depend on cloud t...

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 m...

Résumé L'exploitation de l'Energie Nouvelle et Renouvelable est une priorité pour la mise en oeuvre de la politique d'Electrification Rurale Décentralisée (ERD) de Madagascar. Le haut plateau et le versant est de l'île regorgent de potentialité pour l'installation de Micro et Pico Centrale hydroélectrique (MCH). Malheureusement le manque de données...

When one attempts to build a diffuse fraction model, a term like the clearness index is necessarily included, but the inclusion of the other terms is open to doubt. This raises the question of selection among a range of possible variables or equally of possible models. For instance, Reindl used stepwise regresssion to reduce a set of 28 potential v...

Short term load forecasting (STLF) is an essential tool for efficient power system planning and operation. We propose in this paper the use of Bayesian techniques in order to design an optimal neural network based model for electric load forecasting. The Bayesian approach to modelling offers significant advantages over classical neural network (NN)...

In this paper, we propose a new pruning algorithm to obtain the optimal number of hidden units of a single layer of a fully connected neural network (NN). The technique relies on a global sensitivity analysis of model output. The relevance of the hidden nodes is determined by analysing the Fourier decomposition of the variance of the model output....

The exploitation of New and Renewable Energy is a priority for the implementation of the policy of Decentralized Rural Electrification (DRE). The high plateau and the East slope of Madagascar abound in potentiality for the installation of micro and pico hydroelectric power plant. Unfortunately the lack of hydrological data penalizes the development...