遗传算法优化支持向量机的网络流量混沌预测  

Network traffic chaotic prediction based on genetic algorithm optimization and support vector machine

作　　者：熊凡[1] XIONG Fan(School of Computer Science and Engineering,Wuhan Institute of Technology,Wuhan 430205,China)

机构地区：[1]武汉工程大学计算机科学与工程学院,湖北武汉430205

出　　处：《现代电子技术》2018年第18期166-169,共4页Modern Electronics Technique

摘　　要：基于支持向量机的网络流量混沌预测方法通常基于人工经验设置参数,参数的性能较差,大大降低网络流量预测精度。因此,提出遗传算法优化支持向量机的网络流量混沌预测方法,通过相空间重构获取新的网络流量时间序列,获取具有最佳非线性预测结果的支持向量机函数,采用遗传算法优化支持向量机参数。基于优化的支持向量机参数,设计基于遗传算法优化支持向量机的交通流量预测模型,实现网络流量混沌预测。实验结果表明,所提方法在网络流量预测方面整体性能优、具有较高的精度。The network traffic chaotic prediction method based on the support vector machine usually has parameters set based on the artificial experience and has poor parameter performance,greatly reducing the prediction accuracy of network traffic.Therefore,a network traffic chaotic prediction method based on genetic algorithm optimization and support vector machine(SVM)is proposed.The new network traffic time series and the SVM function with optimal nonlinear prediction results are ob-tained by means of phase space reconstruction.The genetic algorithm is used to optimize the support vector machine parameters.On the basis of the optimized support vector machine parameters,the traffic flow prediction model is designed based on genetic algorithm optimization and SVM,so as to realize chaotic prediction of network traffic.The experimental results show that the pro-posed method has good overall performance and high precision in network traffic prediction.

关 键 词：遗传算法优化 支持向量机 网络流量 混沌预测 相空间重构 预测模型 

分 类 号：TN711-34[电子电信—电路与系统] TP391[自动化与计算机技术—计算机应用技术]