自相似背景流量模型下的CBR流延迟抖动分析

Analysis of packet Jitter of CBR stream under self-similar background traffic

实时业务是网络中快速增长的业务类型,但网络中需要传送多种业务的混合流量。实时 业务的性能取决于分组延迟抖动。过大的分组延迟抖动将导致语音的中断,画面的停顿和跳跃。延 迟抖动主要是背景流量在边缘路由器的干扰引起的。以往的延迟抖动分析都是假设背景流量为泊松 过程,研究表明这种假设已经不符合当前网络流量的特性。本文将对自相似背景流量下的CBR流的 延迟抖动进行分析,给出其分布函数,并以仿真结果验证其与泊松流量对CBR流的不同影响。

Real-time application is an increasing application, but there are many application traffic should be transferred by Internet. The performance of real time applications such as video and voice streams relies on packet delay jitter. Large delay jitter causes buffer overflow and the user encounters interrupts. The delay jitter is mainly due to the perturbation of background traffic in the router. The jitter analysis has been made are all based on poisson process and recent study has proved its inaccurate. In this focus, a theoretical analysis of packet jitter of CBR stream was provided and different influence on CBR stream by self-similar and poisson back-ground traffic was validated by simulation result.