SDN中的端到端时延  

End-to-end delay in software defined networks

作　　者：黄晓鹏[1] 黄传河[1] 农黄武 杨丹凤[1] 杨金羚 

机构地区：[1]武汉大学计算机学院,湖北武汉430072 [2]四川大学计算机学院,四川成都410044

出　　处：《计算机工程与科学》2016年第1期67-72,共6页Computer Engineering & Science

基　　金：国家自然科学基金(61373040;61173137);教育部博士点基金(20120141110073)

摘　　要：随着大规模SDN的不断发展,用来管理和衡量网络性能的指标也越来越重要。端到端时延就是其中重要的部分,针对该指标已经提出了很多计算的方法,主要分为主动探测和被动探测,但是各有优缺点。因此,提出一种主动探测和被动探测相结合的方法,通过特殊方法计算出第一个数据包的时延,再通过快速方法计算相邻数据包端到端时延之差,得到所有数据包的端到端时延。实验结果表明,新方法在时钟不同步的情况下,可以有效地计算出端到端时延。With the deployment of large scale software defined networks （SDNs）, metrics used to monitor and measure network performance become increasingly important. End-to-end delay is an important part of the indicators, and a number of methods for end-to-end delay calculation have been proposed. These methods can be divided into two groups.active detection and passive detection, each with advantages and disadvantages. We propose a method combining active and passive detections. We first calculate the first packet delay, and then calculate the difference of end-to-end delay between adjacent packets, thus obtaining all the end-to-end packet delay. Experimental results show that our approach a- chieves high calculation performance without clock synchronization.

关 键 词：软件定义网络 时钟漂移 时钟同步 端到端时延 网络仿真 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]