Network traffic had long related and nonlinear characteristics, in order to improve the prediction accuracy of network traffic, this paper proposed a network traffic prediction method based on particle swarm algorithm optimizing the parameters of least square support vector machine. Parameters of least square support vector machine were taken as the position vector of particle, and then the particle swarm algorithm is used to find the optimal parameters of the model, finally, the prediction model of traffic model is established based on least square support vector machine with the optimal parameters. The simulation results showed that the proposed model had improved prediction accuracy ompared with other network traffic prediction models and could more accurately describe the change rule of network traffic.