Preferential Link Tomography in Dynamic Networks

Abstract

Inferring fine-grained link metrics by using aggregated path measurements, known as network tomography , is essential for various network operations, such as network monitoring, load balancing, and failure diagnosis. Given a set of interesting links and the changing topologies of a dynamic network, we study the problem of calculating the metrics of these interesting links by end-to-end cycle-free path measurements among selected monitors, i.e., preferential link tomography. We propose MAPLink, an algorithm that assigns a number of nodes as monitors to solve this tomography problem. As the first algorithm to solve the preferential link tomography problem in dynamic networks, MAPLink guarantees that the assigned monitors can calculate the metrics of all interesting links in each possible topology of a dynamic network. We formally prove the above property of MAPLink based on graph theory. We implement MAPLink and evaluate its performance using two real-world dynamic networks, including a vehicular network and a sensor network, both with constantly changing topologies due to node mobility or wireless dynamics. Results show that MAPLink achieves significant better performance compared with four baseline solutions in both of these two dynamic networks.