基于非线性算法的网络业务流量预测  

Nonlinear prediction algorithm of network traffic flow

作　　者：赵海阔[1] 朱正平[2] 

机构地区：[1]兰州城市学院培黎石油工程学院,甘肃兰州730070 [2]兰州城市学院信息工程学院,甘肃兰州730070

出　　处：《自动化与仪器仪表》2010年第4期144-146,共3页Automation & Instrumentation

摘　　要：基于递归最小二乘支持向量机,提出了一种网络业务流量非线性预测算法。通过最小二乘支持量机首先将原始的网络流量数据映射到一个高维空间中,进而在这个高维空间中对流量数据进行预测,使得在低维空间中非线性预测转化为高维空间中的线性预测,提高了预测性能。仿真结果表明,预测误差能够维持在5%以内。Based on Least Squares Support Vector Machines,A nonlinear prediction method of network traffic flow was proposed.The network traffic flow data was mapped into a high dimension space utilizing Least Squares Support Vector Machines,and the prediction was carried out in this space.The prediction performance was increased since the nonlinear prediction in low dimension space was transformed into a linear prediction in a high dimension space.The simulation results show that the prediction error can keep within 5%.

关 键 词：网络流量 预测 非线性 支持向量机 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]