Abstract:  A short-term wind speed forecasting method based on phase-space reconstruction and evolutionary Gaussian process model is proposed in this paper. Firstly, the autocorrelation method and false nearest neighbor method are applied to calculate the delay time and embedding dimension of the wind speed time series, which are used to accomplish the phase-space reconstruction of the chaotic wind speed time series. Secondly, the evolutionary Gaussian process model, which combines Gaussian process with evolutionary algorithm, is used to forcast the wind speed. This model uses Gaussian process model to determine the relationship between the input and output variables， and the improved PSO algorithm to optimize the hyper parameters. The prediction results show that the proposed method can improve the prediction accuracy.

Key words:  wind speed forecast, short-term, phase-space reconstruction, evolutionary Gaussian process, improved PSO algorithm