Ultra-short-term Multi-step Prediction of Wind Power based on iHHT and TSLANet

With the increasing proportion of renewable energy sources such as wind power in the energy structure, high penetration of wind power has become crucial for the normal operation of the power system. In order to improve the accuracy of wind power prediction, this study proposes a wind speed correction algorithm based on improved Hilbert-Huang Transform (iHHT), and introduces TSLANet network for multi-step prediction of ultra short term wind power. Firstly, the improved HHT method was used to decompose and analyze the wind speed in Numerical Weather Prediction (NWP), effectively solving the mode mixing problem in Empirical Mode Decomposition (EMD). Next, model the model through linear network layers and determine the weight coefficients. Finally, the corrected wind speed data is input into the TSLANet network for feature learning and ultra short term multi-step wind power prediction. The experimental results indicate that the method proposed in this study can effectively improve the accuracy of power prediction.