VMD-HPCA-GRU ultra-short-term wind power forecasting based on COOT algorithm

In order to improve the prediction accuracy of ultra-short-term wind power, a combined prediction model of variational mode decomposition (VMD), hierarchical principal component analysis (HPCA) and gated recurrent unit neural network (GRU) based on COOT algorithm optimization is proposed. Firstly, the energy difference method is used to determine the number of sub-modes of variational mode decomposition, so that the original power sequence with strong nonlinearity is decomposed into a group of relatively stable sub-modes. Secondly, the correlation value between high-dimensional meteorological characteristics and power sequence is calculated by grey correlation analysis and sorted and layered. The first principal component of each layered characteristic variable is extracted by principal component analysis to achieve dimensionality reduction of high-dimensional meteorological characteristics. Finally, the COOT algorithm is introduced to optimize the hyperparameters of the gated recurrent unit prediction model, accelerate the model convergence speed, and improve the prediction accuracy of the model. The measured data of a wind farm in Guizhou are simulated and analyzed. The results show that compared with the prediction results of the traditional GRU model, the root mean square error, mean absolute error, and mean absolute percentage error of the proposed method are reduced 67.41%、72.25%、45.69%, and the prediction accuracy is higher than that of the other four combined prediction models, which effectively improves the prediction accuracy of ultra-short-term wind power.