A Modified Particle Swarm Optimization and Radial Basis Function Neural Network Hybrid Algorithm Model and Its Application

Abstract—The study is to improve the power short-term forecast accuracy and speed, and the modified particle swarm optimization algorithm was brought up. The forecast model is set up by using the modified particle swarm optimization and radial basis function neural network combined to form MPSO-RBF algorithm, and then training the neural network by using the MPSO-RBF algorithm. It can automatically determine the structure and parameters of the neural network from the sample data. Form the power short-term forecast model based on the modified particle swarm optimization and radial basis function neural network, considering weather, date and other factors. The result shows the convergence of method is faster and forecast accuracy is more accurate than that of the traditional radial basis function neural network, the particle swarm optimization and radial basis function neural networks algorithm. The method improved forecast accuracy, and improves the radial basis function neural network generalization capacity, and overcomes the RBF neural networks that exist in some of the shortcomings. The model can be used to forecast the short-term load forecast of the power system.