Multi-branch wind power prediction based on optimized variational mode decomposition

Abstract

Wind power has obvious characteristics of non-stationary, intermittent, and complex fluctuations, making it difficult to achieve reliable wind power generation. This brings great challenges to the safe and stable operation of power grid regulation, so accurate wind power prediction is very important. In this paper, we proposed a prediction method for wind power based on optimized variational mode decomposition (VMD) and deep learning algorithm of nonlinear weighted combination. Due to the low adaptability of the VMD, this paper adopted whale optimization algorithm (WOA) to automatically optimize the core parameters of the VMD. The decomposed components and historical wind power were spliced to form a composite vector,and the Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) were used to extract local feature and global trend feature respectively. Finally, the obtained features were fused to predict future wind power. The experimental results showed that the prediction accuracy of this proposed method has been greatly improved, compared with the existing single and combined forecasting methods, and the prediction error is within an acceptable range.