Determination of Wind Potential by Two Components Mixture Probability Distribution Models in the Ankara, Turkey

Abstract

In this study, hourly average wind speed data in the Ankara, Turkey are modeled with Weibull, Gamma and Rayleigh probability distribution and theirs two component mixture probability distributions. Expectation-Maximization (EM) algorithm is introduced for Maximum Likelihood Estimation (MLE) of mixture probability distributions used in modeling wind speed data. In comparing the modeling performances of probability distributions, the Akaike information criteria, the coefficient of determination, the root of the mean squares and chi-square criteria were used as comparison criteria. Also, in this study, the success in estimation of wind potential was evaluated with relative error. In the study results, it was observed that the mixture distribution models obtained from two different distributions were more successful in modeling wind speed data. The results obtained from the study revealed that the wind potential of Kecioren/Baglum region is higher than Cankaya/Caldag region. According to the wind speed data observed in Kecioren/Baglum and Cankaya/Caldag regions, wind power densities per unit area were calculated as 153.926 W/m(2), and 62.785 W/m(2), respectively.