多路自相似流输入下基于FBM模型的丢包率分析

Packet loss rate analysis based on FBM model with multiple self-similar traffic input

从分形布朗运动(FBM)模型出发,结合高斯输入下的丢包性能,推导了多路自相似流输入下丢包率的理论分析.结果显示,在多路自相似流输入情况下,若各条流的均值、方差近似相等,则Hurst参数最大的流对合成流的丢包率具有决定性的影响.该结论通过仿真得到了很好的验证.所提出的分析方法和得出的结论对于网络节点性能分析、缓冲区设计及资源调度等具有实际的指导意义.

Theoretical analysis of packet loss rate with multiple self-similar traffic input was proposed based on FBM model and the condition with Gaussian input.The results show that if the mean and variance of each traffic flow are approxmitately equal,the traffic flow with the largest Hurst parameter has a decisive influence on the packet loss rate of multiple traffic.This conclusion was verified by simulation and can be used for the analysis of network node performance,buffer design,and resource allocation.