Traffic Trajectory Analysis Using Router Groups with Optimal Interface Selection Scheme
Detecting errors in traffic trajectories (i.e., packet forwarding paths) is important to operational networks. Several different traffic monitoring algorithms such as Trajectory Sampling, PSAMP and Fatih can be used for traffic trajectory error detection. However, a straight-forward application of these algorithms will incur the overhead of simultaneously monitoring all network interfaces in a network for the packets of interest. In this paper, the authors propose a novel technique called router group monitoring to improve the efficiency of trajectory error detection by only monitoring the periphery interfaces of a set of selected router groups. The authors analyze a large number of real network topologies and show that effective router groups with high trajectory error detection rates exist in all cases.