Short-Term Wind Speed Prediction of Wind Farms Based on Particle Swarm Optimization Support Vector Machine

Abstract

With the large-scale integration of wind power into the grid, grid-side instability caused by fluctuations in wind speed is becoming more and more significant, and the topic of wind speed prediction for wind farms is urgent. Based on this, in order to solve the problem of low prediction accuracy of a single support vector machine, this paper proposes a wind speed prediction method that uses particle swarm optimization to optimize the support vector machine. Use particle swarm algorithm to optimize the selection of penalty factors and kernel function parameters of support vector machines, then conduct model training on the optimized parameters, and then apply the established prediction model to wind speed prediction of wind farms, and finally analyze the prediction results. The prediction results show that the support vector machine algorithm optimized by the particle swarm optimization algorithm has better accuracy in predicting the wind speed of wind farms, which is significantly higher than the prediction accuracy of a single support vector machine.