Short-Term Wind Power Prediction Based on BP Neural Network Improved by t-Tent-SSA Algorithm

Abstract

With the increasing proportion of new energy in the power system, the accurate prediction of wind power becomes more and more important to improve the economic benefits and stability of the power system. The traditional Sparrow search algorithm (SSA) optimized BP(SSA-BP) neural network for wind power prediction has the problems of easy to fall into local optimum, slow convergence rate and low prediction accuracy. This paper proposes a wind power prediction method based on sparrow search algorithm based on fusion of tent chaotic mapping and t distribution (t-Tent-SSA) and BP(t-Tent-SSA-BP) neural network. This paper takes a wind farm in northwest China as the research object, first introduces Perason's correlation coefficient, and analyzes the data with strong correlation with wind power output as the input of the model, so as to avoid redundant data affecting the accuracy of prediction and calculation speed. Secondly, SSA algorithm and t-Tent-SSA algorithm are used to optimize the BP neural network. Finally, the measured historical data of the wind farm are used to simulate the prediction models. The simulation results show that the prediction model based on t-Tent-SSA-BP has better prediction accuracy than SSA-BP, and is more in line with the requirements of power system operation. eezhouqiang@163.com