Trend detection of wind speed probability distribution by adaptive neuro-fuzzy methodology

The probabilistic distribution of wind speed is one of the critical wind parameters for the evaluation of wind energy potential. The wind energy distribution can be acquired when wind speed probability function is known. The two-parameter Weibull distribution has been regularly utilized and prescribed in expositive expression to express the wind speed distribution function for most wind areas. Consequently, the shape and scale parameters of the distribution are used to plan and portray wind turbines. Therefore modeling the probabilistic distribution of wind speed is necessary because it has a great influence on the actual energy output of a wind farm. Since it is a nonlinear problem in the present study an exertion has been made to figure out the best fitting function of wind speed information by a soft computing methodology. In this paper, we analyze three wind speed models generally utilized for assessing these parameters as a part of request to focus on the model that is best suited. We utilized adaptive neuro-fuzzy inference system (ANFIS) in this paper, which is a particular sort of the neural systems family, to anticipate the wind speed probability density distribution. The main goal is to detect the trend of the wind speed probability density distribution by the ANFIS approach.