改进粒子群算法优化最小二乘支持向量机的网络流量混沌预测  

Network traffic chaotic predicting based on least squares support vector machine optimized by improved particle swarm optimization algorithm

作　　者：黄国权[1] 尤新华[2] 

机构地区：[1]广东药学院医药信息工程学院,广州510006 [2]湖北大学知行学院计科系,武汉432100

出　　处：《激光杂志》2015年第3期96-99,共4页Laser Journal

摘　　要：为了提高网络流量的预测准确性,针对最小二乘支持向量机参数优化方法的缺陷,提出一种改进粒子群算法优化最小二乘支持向量机的网络流量混沌预测模型。首先将最小二乘支持向量机参数作为粒子初始位置,然后通过粒子群之间信息交流、互相协作找到最优参数,并对惯性权重和学习因子进行改进,最后对网络流量数据进行重构,并采用最优参数的最小二乘支持向量机建立网络流量预测模型。实验结果表明,本文模型提高了网络流量的预测精度,并大幅度减少了训练时间,可以满足网络流量在线预测要求。In order to improve the prediction accuracy of network traffic,aiming at the existing defects of parameter optimization of least squares support vector machine,a new network traffic chaotic predicting based on least squares support vector machine optimized by improved particle swarm optimization algorithm is proposed in this paper. Firstly,the least squares support vector machines parameters is considered as the initial position of particle,secondly,the optimal parameters are found by information exchange between particle swarms,and the inertia weight and learning factor is improved,and finally,the network traffic data is reconstruct and least squares support vector machine with using the optimal parameters is used to establish the prediction model of network traffic. The experimental results show that the proposed model has improved the prediction accuracy of network traffic,and greatly reduce the training time,and therefore it can meet the requirements of online network traffic prediction.

关 键 词：网络流量 粒子群优化算法 混沌理论 最小二乘支持向量机 

分 类 号：TP393.06[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]