Simulation of network traffic at coarse time-scales

Simulation of large-scale networks demands that we model some flows at coarser time-scales than others, simply to keep the execution cost manageable. This paper studies a method for periodically computing traffic at a time-scale larger than that typically used for detailed packet simulations. Applications of this technique include computation of background flows (against which detailed foreground flows are simulated), and simulation of worm propagation in the Internet. Our approach considers aggregated traffic between Internet points of presence, and computes the throughput of each POP-to-POP flow through each router on its path. This problem formulation leads to a non-linear system of equations. We develop means of reducing this system to a smaller set of equations, which are solved using fixed point iteration. We study the convergence behavior, as a function of traffic load, on topologies based on Internet backbone networks. We find that the problem reduction method is very effective, and that convergence is achieved rapidly. We also examine the comparative speedup of the method relative to using pure packet simulation for background flows, and observe speedups of exceeding 5000 using an ordinary PC. We also simulate foreground flows interacting with background flows, and compare the foreground behavior using our solution with that of pure packet flows. We find that these flows behave accurately enough in our approach to justify use of the technique in our motivating application.