Adaptive neuro-fuzzy approach for estimation of wind speed distribution

Abstract

Abstract Probability distribution of wind speed is very important information needed in the assessment of wind energy potential. For this reason, a large number of studies have been published concerning the use of a variety of probability density functions to describe wind speed frequency distributions. Two parameter Weibull distribution is widely used and accepted method. In this investigation adaptive neuro-fuzzy inference system (ANFIS) was used to predict the probability density distribution of wind speed. The estimation and prediction results of ANFIS model are calculated using three statistical indicators i.e. root means square error, coefficient of determination and Pearson coefficient. The results show that an improvement in predictive accuracy and capability of generalization can be achieved by the ANFIS approach. Moreover, the results indicate that proposed ANFIS model can adequately predict the probability distribution of wind speed.