Ultra-Short-Term Prediction of Wind Power Based on Chaos Theory and ABC Optimized RBF Neural Network

Wind energy has strong randomness and volatility, which makes the prediction accuracy of wind power low. In an attempt to improve the accuracy and robustness of ultra-short-term prediction of wind power, a wind power prediction method in ultra-short term combining chaos theory and artificial bee colony(ABC) algorithm to optimize RBF neural network is studied in this paper. Firstly, based on chaos theory, the historical wind power data with the highest correlation is found, which is used for RBF neural network training after phase space reconstruction. Then, the artificial bee colony algorithm is used to solve the optimal RBF neural network parameters through multiple iterations to construct the optimized neural network model. Finally, considering the uncertainty of the prediction model and data noise, the prediction results are interval, and the robustness of the prediction results is evaluated by calculating the confidence of the corresponding interval. The results of the example show that the method proposed in this paper has good accuracy and robustness.