Abstract: Network traffic prediction is positive significance for design of network and resource management，and it is an important section of traffic engineering.This paper presents a method of network traffic prediction based on the algorithm of QPSO and BP neural network.QPSO algorithm is applied to optimize the weights and thresholds in BP neural network，and historical records are used to train BP neural network.The emulation experiment results show that compared with the model only based on BP neural network model and the model of BPNN trained by PSO，the model of BPNN trained of QPSO is more successful in the network traffic prediction.

Key words: Quantum-behaved Particle Swarm Optimization（QPSO）, Particle Swarm Optimization（PSO）, neural network, network traffic, prediction

摘要： 网络流量预测对于大规模网络的规划设计和网络资源管理等方面都具有积极的意义，是网络流量工程重要组成部分。结合QPSO算法和BP神经网络的优势，采用QPSO算法对BP神经网络的权值和阈值进行优化，并利用历史记录训练BP网络。仿真实验表明，与PSO训练的BP网络以及直接用BP网络进行预测的模型相比，基于QPSO训练的BP网络流量预测模型具有更好的预测能力。

关键词: 量子粒子群算法, 粒子群算法, 神经网络, 网络流量, 预测