Prédiction de la moyenne horaire de la vitesse du vent sur le site de Lomé par réseau de neurones

Résumé

This study presents software with graphical user interfaces, developed in our Laboratory to predict wind speeds. The aim of the study is to predict the mean hourly wind speed of the site of Lomé with a neural network approach. The interesting result obtained in the site of Lomé with a Mean Square Error of prediction MSE =1,293 and a linear correlation coefficient between the observed and predicted data R² = 0.71 shows clearly that it is possible to predict the hourly wind speed with a neural network approach.