Abstract: Aiming at the problem that wind power generation fluctuates greatly due to environmental changes and a kernel extreme learning machine is easy to fall into the local optimal solution, this paper constructs a short-term wind power prediction model of an optimized kernel extreme learning machine based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) Analysis, wavelet threshold denoising and particle swarm algorithm. Firstly, CEEMDAN is used to decompose the environmental factors that are closely related to the output power of wind power generation, and several modal components with strong regularity are obtained. Besides, the threshold denoising method is used to denoise the first modal component containing much noise to weaken the non-stationarity of environmental factors. Then, after particle swarm optimization, the decomposed subcomponents and historical wind power data are used as the input of the kernel extreme learning machine algorithm for prediction. Finally, the measured data of a wind farm in Zhangjiakou, Hebei Province are selected for experimental comparison and analysis. The experimental results show that the improved wind power forecasting combination model proposed in this paper has higher forecasting accuracy and is suitable for wind power forecasting in different seasons.