Abstract: In order to improve the prediction precision of network traffic, this paper proposes a nonlinear network traffic prediction model based on parameters joint optimization algorithm, which uses the relationship between the phase space reconstruction and prediction model parameters. The phase space reconstruction and prediction model parameters are taken as particle of Improved Particle Swarm Optimization algorithm（IPSO） while the prediction accuracy of network traffic as the evaluation function of CPSO, and then, the optimization parameters are obtained by collaboration among particles. The optimal nonlinear network traffic prediction model is built according to the parameters. The performance of the proposed model is tested by network traffic data. The results show that the proposed method has improved the prediction precision of network traffic compared with the traditional parameters optimization algorithm; it has provided a new way for the nonlinear prediction problem.

Key words: network traffic prediction, phase space reconstruction, neural network, Particle Swarm Optimization（PSO）

摘要： 为了提高网络流量预测精度，利用相空间重构和神经网络参数间的相互联系，提出一种参数联合优化的网络流量非线性预测模型。将相空间重构和预测模型参数作为粒子群优化算法的粒子，网络流量预测精度作为粒子适应度函数，通过粒子之间相互协作获得全局最优参数，根据最优参数建立最优网络流量非线性预测模型，通过网络流量实例对模型性能进行测试。结果表明，相对于传统参数优化方法，参数联合优化方法大幅度提高了网络流量的预测精度，为非线性预测问题提供了一种新的研究思路。

关键词: 网络流量预测, 相空间重构, 神经网络, 粒子群优化算法