Abstract: In order to reduce the volatility of wind power series and improve the prediction accuracy of wind power,a combined wind power interval prediction model based on SSA-VMD-SE-KELM and Monte Carlo method is proposed. The variational mode decomposition（VMD）algorithm optimized by the sparrow search algorithm（SSA）is used to decompose the power sequence into subsequences of ideal number,and then reconstruct them by calculating the sample entropy（SE）to obtain new subsequences to establish kernel limit learning machine（KELM）point prediction model,superimpose the prediction results of each point to obtain the final point prediction result and power error sequence,and Monte Carlo method is used to randomly sample to obtain the prediction interval under the corresponding confidence. Taking the actual collected historical data as an example,the experimental results show that compared with the traditional model,the power prediction interval obtained by the proposed model closely follows the change trend of wind power power,and its interval coverage rate is higher and the average width is narrower.