RBF Neural Network Based on Particle Swarm Optimization Algorithm Realizes Self-similar Traffic Prediction

Aiming at the problem that network traffic prediction can effectively improve network congestion control, A traffic prediction model based on Radial Basis Function (RBF) neural networks optimized by Particle Swarm Optimization (PSO) has been proposed for predicting self-similar network traffic. After a large number of studies, it is shown that high-performance and high-efficiency network traffic has self-similarity characteristics, and according to this characteristic, the self-similar traffic can be predicted. In order to achieve high-precision network traffic prediction, firstly, the datasets are input into the RBF neural network, and then the parameters of the RBF neural network are optimized using the Particle Swarm Optimization algorithm to reduce the prediction error of traffic. Finally, experimental results show that the PSO-RBF neural network prediction model has high prediction accuracy and better adaptability compared to the BP neural network optimized by genetic algorithms, enabling efficient and accurate traffic prediction to meet the demand for improved network performance.