光子学报, 2014, 43 (7): 0706023, 网络出版: 2014-08-18
端到端网络流量的混合估计方法
Mixed Estimation Approach to EndtoEnd Network Traffic
端到端流量 流量估计 主成分分析 迭代过程 流量建模 Endtoend traffic Traffic estimation Principal component analysis Iterative process Traffic modeling
摘要
利用主成分分析法获取端到端网络流量的主要特征分量并获得其初始估计结果.为克服其初值敏感性将估计结果作为遗传算法的初始值、链路流量估计偏差作为遗传算法的适应度函数, 通过构建合适的交叉和变异概率函数来控制遗传算法的交叉和变异过程.采用合适的约束迭代函数,利用遗传算法通过迭代寻优获得端到端流量的估计结果, 仿真结果表明所提出的方法是可行的.
Abstract
Principal component analysis was exploited to extract the principal features of endtoend network traffic and to attain the initial estiamtion results. This results are taken as the prior value of genetic algorithm to overcome its sensitiveness to the prior value. The estiamtion biases of link traffic is regarded as the fitness function of genetic algorithm. The crossover and mutation probability functions are built to control its corossover and mutation processes. The appropriate iterative funtion with contraints is built. The genetic algorithm is used to attain the endtoend traffic estimation results in the iterative way. Simulation results show that the proposed method is feasible.
蒋定德, 赵祖耀, 许宏伟, 王兴伟. 端到端网络流量的混合估计方法[J]. 光子学报, 2014, 43(7): 0706023. JIANG Dingde, ZHAO Zuyao, XU Hongwei, WANG Xingwei. Mixed Estimation Approach to EndtoEnd Network Traffic[J]. ACTA PHOTONICA SINICA, 2014, 43(7): 0706023.