A Distributed Measurement Scheme for Internet Latency Estimation

Estimating latency between the hosts in the Internet can play a significant role in the improvement of the performance of many services that use latency among hosts to make routing decisions. A popular example is peer-to-peer networks that need to build an overlay between peers in a way that minimizes the message exchange delay among the peers. Acquisition of latency information requires a considerable amount of measurements to be performed at each node in order for that node to keep a record of its latency to all the other nodes. Moreover, measured latency values are frequently subject to change and need to be regularly repeated in order to be updated against network dynamics. This has motivated the use of techniques that alleviate the need for a large number of empirical measurements and try to predict the entire network latency matrix using a small set of latency measurements. Coordinate-based approaches are the most popular solutions to this problem. The basic idea behind coordinate-based schemes is to model the latency between each pair of nodes as the virtual distance among those nodes in a virtual coordinate system. This paper proposes a new decentralized coordinate-based solution to the problem of Internet delay measurement. The simulation results demonstrate that the proposed system provides relatively accurate estimations.