Short-term prediction of wind power combining GM(1,1) model with cloud model

This paper proposes a new method to predict wind power of wind farm using the combination of GM(1,1) model and cloud model. The original wind power signals are decomposed into high frequency part and low frequency part by wavelet decomposition. Cloud model is constructed to predict wind power of high frequency part and GM(1,1) model is used to predict wind power of low frequency part. The predicted power can be obtained by high frequency part and low frequency part. The simulation example shows that the method proposed in this paper is obviously better than single predicting method and the effectiveness of the method is verified by the predicting results.