STATISTICAL ANALYSIS OF WIND SPEED DATA WITH SOME DİSTRİBUTİONS


Creative Commons License

Erdoğan N. , Kara M. , Yılmaz A.

2nd International Conference on Pure and Applied Mathematics (ICPAM-VAN 2018), Van, Turkey, 11 - 13 September 2018, pp.73

  • Publication Type: Conference Paper / Summary Text
  • City: Van
  • Country: Turkey
  • Page Numbers: pp.73

Abstract

Precisely and efficiently modeling wind speed is important in estimating the wind energy potential of a specified region. Two- parameter Weibull distribution is the most widely used and accepted distribution in the energy literature. However, it does not model the all wind speed data encountered in nature. Therefore, in this study, different distributions are used for modeling wind energy, such as Gamma, log- normal, Rayleigh. The estimators of the unknown parameters of these distributions are found by using maximum likelihood estimators (MLEs). Finally, hourly wind speed data (m/s), measured hourly at 10m from Adilcevaz and anakkale Turkey during December 2017 is used. These data are taken from the Turkish State Meteorological Service. The fit distribution is determined with respect to root mean square error (RMSE), Kolmogorov Smirnov and coefficient of determination R2 criteria