因特网时延空间中TIV与接入时延的研究

TIV and Access Delay in the Internet Delay Space

大量网络测量研究证实了违反三角不等式(TIV)是因特网时延空间存在的一种普遍现象,是影响网络坐标系统准确性的重要原因之一.通过将因特网分为接入网和核心网两部分,引入了时延空间模型来分析接入时延对于TIV的影响.理论分析表明TIV产生于网络的核心,接入时延可以使得在端到端路径中观察到的TIV数目会减少,并减轻TIV的严重程度.然后,在PlanetLab测试平台设计了一组网络测量实验,来测量端到端的时延矩阵和相应的拓扑信息.之后,设计了ScoutTIV算法来统计时延数据集中的TIV比例.在实验中,根据主机的IP属性将其分为3个子集,并生成了1个随机数据集来进行分析.在所有子集上的实验结果与理论分析结论一致,为网络坐标系统进一步提高预测精度提供了重要依据.

Many researches demonstrate that triangle inequality violation （TIV） is a universal phenomenon in the Internet delay space, which is the result of routing inefficiency. However, there are still no investigations on the TIV＇s position and its relationship with the access delay. Firstly, the Internet is divided into two parts, access network and core network, by different definitions. A delay model of the Internet delay space is proposed to analyze the TIV＇s position. Based on this model, it is found that TIV appears in the core of the Internet rather than the access networks and the access delay can reduce the TIV number and alleviate the TIV＇s severity. Then, a series of experiments are carried out on the PlanetLab to measure the end-to-end delay matrix and its corresponding topology. Afterwards, a TIV searching algorithm ScoutTIV is designed to count the TIV number in the measurement dataset by different definitions of edges between the access network and core network. In the experiments, the datasets are divided into three small datasets based on the country attributes of hosts and one random dataset. The experimental results on different datasets accord with our conclusion, which can help network coordinate systems to achieve better prediction accuracy.