Multi-Step Short-Term Wind Power Prediction Model Based on CEEMD and Improved Snake Optimization Algorithm

Abstract

To effectively mitigate and address the impact of wind power uncertainty on the efficient operation of the power grid, this study proposes a novel multi-step short-term wind power prediction model based on complementary ensemble empirical modal decomposition (CEEMD), Improved Snake Optimization Algorithm (ISCASO), and Kernel Extreme Learning Machine (KELM). Firstly, the non-smooth wind power data are decomposed into a series of relatively smoother components using CEEMD to mitigate the complexity and instability of the original data. Subsequently, an improved snake optimization algorithm is introduced to optimize the KELM parameters, thereby establishing the prediction model of CEEMD-ISCASO-KELM for each stationary component and residual. Finally, by superimposing the prediction results of each component and residual, we obtain the final wind power prediction model. The simulation results show that, in comparison with existing prediction models, the proposed model in this study exhibits exceptional capability in accurately forecasting short-term wind power trends.

Keywords

• Improved snake optimization
• kernel extreme learning machine
• multi-step prediction
• short-term wind power prediction