Survey of four models of probability density functions of wind speed and directions by adaptive neuro-fuzzy methodology

•Probabilistic distribution of wind speed.•Two parameter Weibull distribution.•The Gumbel and Frechet dissemination.•The joint probability density functions (JPDF) model.•Adaptive neuro-fuzzy inference system (ANFIS) as alternative to analytical approach.

The probabilistic distribution of wind speed is one of the discriminating wind qualities for the assessment of wind energy potential and for the execution of wind energy conversion frameworks. The wind energy spread might be obtained when wind speed probability function is known. Thusly, the probability movement of wind speed is an uncommonly huge touch of information needed in the assessment of wind energy potential. The two-parameter Weibull circulation has been normally used, recognized and endorsed in expositive interpretation to express the wind speed repeat transport for most wind regions. The Gumbel and Frechet dissemination is frequently used to model large wind speeds. The joint probability density functions (JPDF) model is advanced by minimal disseminations of wind speed and wind direction that is expected as an Extreme-Value mathematical statement. In the present study an exertion has been made to figure out the best fitting circulation of wind speed information by a soft computing methodology. We used adaptive neuro-fuzzy inference framework (ANFIS) in this paper, which is a specific kind of the neural frameworks family, to foresee the wind speed probability density dispersion. For this reason, two parameters Weibull and JPDF and three parameter Frechet and Gumbel conveyances are fitted to data and parameters for each distribution and utilized as preparing and checking information for ANFIS model. At long last, ANFIS effects are contrasted and the four introduced appropriations recommending that ANFIS conveyances are discovered to be most suitable as contrasted with the Weibull, JPDF, Frechet and Gumbel circulations.