Wind power prediction at southwest coast of Korea from measured wind data

Abstract

Generated power by 5 MW wind turbine was predicted by using measured wind data at weather station called Herald of Meteorological and Oceanographic Special Unit-1 (HeMOSU-1) which is installed at south west coast of Korea. Transient time history of turbulent wind was generated from 10-min mean wind speed stored at HeMOSU-1 and then it was used in estimation of electric power by Bladed. Those estimated powers were used in both polynomial regression and neural network based power estimation. They were compared with each other for daily power and yearly power. Effect of mean wind speed and turbulence intensity was quantitatively analyzed and discussed. This technique further can be used to assess lifetime power of wind turbine.