A Scalable Approach to Tomography-based Internet Measurement System

Network tomography enables network operators to detect and mitigate congestion by inferring internal states from multiple end-to-end active performance measurements. In previous studies, network tomography was applied to either small networks, e.g., a network which allows measurements in a full-mesh manner, or a reasonably large network, e.g., overlay-network with 100 end nodes. In contrast, our study was conducted to develop a large-scale tomography-based measurement system that scales with the nation-wide Internet. In this paper, we propose a novel architecture which consists of a probability measurement path selection method and a distributed database building method. The architecture provides network operators with look up services for measurement results so that they can achieve network-tomography applications.