An application of artificial neural networks to assessment of the wind energy potential in Libya

Abstract

We modeled in this paper the variation of wind speed as a renewable energy in Mediterranean Sea of Libya (North of Africa) using an artificial neural network (ANN). We developed multi-layer, feed-forward, back-propagation artificial neural networks for prediction monthly mean wind speed. The monthly mean wind speed data of 25 cities in Libya were monitored during the period of six years from 2010 to 2015. Meteorological (mean temperature, relative humidity and mean sunshine duration) and geographical data (latitude, longitude and altitude) are used as the inputs and the wind speed is used as the output of the ANN. The experimental results show that the correlation coefficients between the predicted and measured wind speeds for training data sets are higher than 0.99. Therefore, the ANN model can be used with high prediction accuracy at locations where wind speed data are not measured.