论文部分内容阅读
针对当前网络流量非线性时变、混沌等特点以及现有的基于支持向量机(support vector machine,SVM)网络流量预测模型存在预测稳定性不好、精度较低等问题,采用模糊层次分析法对SVM预测模型进行改进,首先使用模糊层次分析法对SVM的σ和C参数进行寻优,然后用寻找到的最优参数来训练SVM,最后建立预测模型,预测网络流量.实验结果表明,本文方法不但可以较好的跟踪网络流量变化趋势,从而可以使网络流量的预测值与实际非常接近,而且预测误差变化范围波动小,是一有效的并且预测精度高的网络流量预测方法.
According to the characteristics of current network traffic such as nonlinear time-varying and chaos, as well as the existing network traffic forecasting model based on support vector machine (SVM), the forecasting stability is poor and the accuracy is low. The fuzzy analytic hierarchy process SVM prediction model is improved firstly by using fuzzy analytic hierarchy process (AHP) to optimize the σ and C parameters of SVM, and then train the SVM with the best parameters found.Finally, a prediction model is established to predict the network traffic.Experimental results show that the proposed method Not only can the trend of network traffic be tracked well, so the predicted value of network traffic can be very close to the actual value, and the fluctuation range of the prediction error is small. It is an effective and predictive method for network traffic prediction.