基于改进的QPSO训练BP网络的网络流量预测*

为了提高网络流量预测的精度，采用一种改进的QPSO算法训练BP神经网络对网络流量数据的时间序列进行建模预测。针对标准的QPSO算法不可避免地出现早熟的不足，提出一种新的基于参数自适应的QPSO算法，较好地避免了粒子群的早熟，提高了算法的全局收敛性能。仿真实验结果表明，与PSO训练的BP网络、QPSO训练的BP网络作为预测模型相比，该模型具有更高的预测精度及很好的稳定性。

Network traffic prediction based on BP neural network trained by improved QPSO

In order to improve the precision of the network traffic prediction,proposed the BP neural network(BPNN)trained by an optimized QPSO algorithm to model and predict the time series of network traffic data. Proposed a new adaptive parameter control method for QPSO to avoid the particle prematurely and improved the ability of global convergence. The experimental results prove that, compared with the model of BPNN trained by PSO, and BPNN trained by QPSO, this model is more efficient in network traffic prediction with higher precision and better stability.