Short term wind speed forecasting using wavelet transform and grey model improved by particle swarm optimization

Nowadays wind energy is one of the most important source of renewable energy worldwide. Wind power generation is an important form of wind energy utilization. The energy problem has become increasingly prominent, which requires to speeding up the development of wind energy industry. However, the existing wind speed forecasting using grey model is inaccurate. Direct prediction of original wind speed sequence produces large error because of the randomness of wind power. To solve the above problems, a novel method for short term wind speed forecasting based on grey model is proposed in this paper. In order to reduce the error of short term wind speed forecasting, one of the most successful approaches is particle swarm optimization algorithm, which chooses the parameters of grey model to avoid the man-made blindness and enhances the efficiency and capability of forecasting. In the present paper, the wavelet de composition and reconstruction are used to separate the high frequency signal and the low frequency signal. To verify its efficiency, this proposed method is applied to a wind farm's wind speed forecasting in China. The result confirms that the performance of the method proposed in this paper is much more favor able in comparison with the original methods studied.