Ultra-Short-Term Prediction of Wind Power Based on the NARX Neural Network

High-precision wind power prediction in the process of wind power integration has become an important means of power dispatching and smoothing grid-connected fluctuations. To predict the power of the wind power generation system more accurately, this paper establishes a NARX dynamic neural network prediction model. Under the condition of considering the influence of wind speed on wind power, the model adopts the nonlinear autoregressive neural network structure with external input and uses the powerful nonlinear mapping and generalization ability of the NARX neural network to predict wind power. Finally, the model is verified by the real data of wind power plants. The results show that the method proposed in this paper has high prediction accuracy and good applicability to ultra-short-term wind power prediction.