Multi-Step Short-Term Wind Power Prediction Based on Three-level Decomposition and Improved Grey Wolf Optimization

Abstract

Wind power prediction is of great importance in enhancing wind energy penetration. This paper proposes a novel wind power prediction method which combining three-level decomposition with optimized prediction method. In the decomposition part, the Wavelet Packet Decomposition (WPD) is introduced as the first level decomposition, then the obtained sub-series are further decomposed by Variable Mode Decomposition (VMD). At last, Singular Spectrum Analysis (SSA) is carried out for each Intrinsic Mode Function (IMF), and the dominant component and residual components are separated as the input of the prediction. In the prediction part, Kernel Extreme Learning Machine (KELM) is adopted to complete the multi-steps wind power prediction. In this paper, an Improved Grey Wolf Optimization (IGWO) algorithm with redesign of the hierarchy and architecture is proposed, which especially suitable for optimizing wind power prediction. Finally, ten different models are compared, and the results show that the proposed method in this paper can extract the trend information of wind power greatly and has achieved excellent accuracy in short-term wind power prediction.