Author : Nihad AGHBALOU1, Abdérafi CHARKI, Saida RAHALI ElAZZOUZI and Kamal REKLAOUI

Maximizing gains from wind energy potential is the principle objective of the wind power sector. Consequently, wind tower size is radically increasing. However, choosing an appropriate wind turbine for a selected site requires having an accurate estimation of vertical wind profile. This is also imperative from the cost and maintenance strategy point of view. Installing tall towers or other expensive devices such as LIDAR or SODAR raises the costs of a wind power project. In this work, we aim to investigate the ability of a Neural Network trained using the Bayesian Regularization technique to estimate wind speed profile up to a height of 100m based on knowledge of wind speed at lower heights. Results show that the proposed approach can achieve satisfactory predictions and prove the suitability of the proposed method for generating wind speed profile and probability distributions based on knowledge of wind speed at lower heights.

Keywords: Wind energy, Wind speed profile, Neural network, Bayesian regularization

Article published in International Journal of Current Engineering and Technology, Vol.7, No.6 (Nov/Dec 2017)