Short-Term Wind Power Prediction Based on OLHS-DBO-BP Neural Network

To enhance the precision of short-term wind power forecasting, an optimized BP neural network-based model for short-term wind power prediction is introduced. Slow convergence speed and easy to fall into local optimal solutions in traditional BP neural networks lead to poor prediction accuracy. The initial population of the dung beetle optimization algorithm is improved by the feature that the optimal Latin hypercube can optimize the position of the sampling points in space, and the weights and thresholds of the BP neural network are optimized using the improved dung beetle optimization algorithm, and the wind power data of a power plant in Inner Mongolia is used as the research object. Model building and simulation test are carried out. The simulation results show that the average absolute error, mean square error and average absolute percentage error of this prediction model are reduced by 10.11%, 1.91% and 25.32%, respectively, compared with the BP neural network prediction model, which proves the feasibility of this model.