复合协方差函数高斯回归的网络流量建模与预测

MODELLING AND PREDICTION OF NETWORK TRAFFIC BASED ON HYBRID COVARIANCE FUNCTION GAUSSIAN REGRESSION

为了获得更优的网络流量预测结果,提出一种复合协方差函数高斯过程(GP)的网络流量预测模型。首先采用复合协方差函数构建GP模型,然后对网络流量训练集进行训练,找到协方差和均值函数的最优参数,最后建立网络流量预测模型,并与支持向量机、神经网络、传统高斯过程进行网络流量的单步和多步预测对比测试。结果表明,相对于对比模型,复合协方差函数GP模型更加能够辨识非线性的网络流量变化趋势,提高了网络流量的预测精确性,是一种有效的复杂网络流量变化预测方法。

In order to obtain better prediction results of the network traffic,this paper proposes a network traffic prediction model which is based on hybrid covariance function Gauss process （GP）.First,we use hybrid covariance function to build GP model,and then train the training set of network traffic to find optimal parameters of covariance and mean function,finally,the network traffic prediction model is built, and one-step and multi-step network traffic prediction are tested and compared with those of support vector machine,neural network,and traditional Gauss process.Results show that compared with the contrast model,the proposed mode can distinguish the nonlinear change trends of network traffic better,and improves the prediction accuracy of network traffic,so it is an effective prediction method for complex network traffic.