Modeling on Quicksand

Researchers studying the inter-domain routing system, its properties and new protocols, face many challenges in performing realistic evaluations and simulations. Modeling decisions with respect to AS-level topology, routing policies and traffic matrices are complicated by a dearth of ground truth for each of these components. Moreover, scalability is-sues arise when attempting to simulate over large (although still incomplete) empirically-derived AS-level topologies. In this paper, the authors discuss their approach for analyzing the robustness of their results to incomplete empirical data.