Research on Wind Speed Vertical Extrapolation Based on Extreme Learning Machine

In engineering, the method of wind speed vertical extrapolation is based on the actual wind data of the wind tower, and the wind shear index is used to calculate the wind speed at any height in the near ground. The wind shear index is only considered in the neutral state of the atmosphere, without considering the impact of atmospheric stability on the wind shear index, which has some limitations. At the same time, the calculation of the wind shear index is a rather complicated task when considering the atmospheric stability. In order to solve these problems, this paper puts forward to use extreme learning machine for fitting the relationship between wind speed at different heights. Extreme learning machine has the advantages of fast learning speed, good generalization ability and so on. In this paper, the results obtained by the extreme learning machine and traditional methods are compared with the measured values. The results show that the extreme learning machine has a better application prospect in the vertical wind speed extrapolation.