Wind Power Prediction Based On Multi-Algorithm Fusion Optimization Model

Abstract

Accurate wind power forecasting is important for improving the economic and stable operation of power systems. In order to overcome the problems of neural network selection in wind power prediction and low prediction accuracy, the particle swarm optimization algorithm is proposed to optimize the topology and parameters of BP neural network and apply it to wind farm power prediction. Finally, the validity of the prediction model is verified by two sets of experimental data. The results show that the proposed algorithm can effectively deal with the randomness and uncertainty characteristics of wind power timing, and has higher modeling accuracy and faster convergence speed.