Speedup vs. Simulation Granularity

This paper describes a packet network simulator whose timing granularity can shift continuously from ne, packet-level detail to coarse, conversation-level detail. Simulation run time decreases with coarser timing granularity, but the details in the underlying model become faded as the timing granularity coarsens. The ner the gran-ularity, the slower but more precise the simulation. If a simulation becomes resource limited, it is possible to coarsen the timing granularity to scale the simulation larger. This paper introduces a new simulation technique to speedup simulation of high speed, wide area networks. The new technique can yield order of magnitude speedup and memory savings on simulations of large-scale packet networks. The speedup is achieved by introducing a degree of approximation into abstracting packet streams. We call this technique Flowsim. Flowsim can yield diierent simulation metrics than packet simulation due to its diierent degree of simulation gran-ularity. We have replicated simulations presented in the literature and, in this paper, show that it is frequently possible to employ coarse timing granularity when studying ow and congestion control algorithms. This paper motivates the need for faster and less memory intensive simulators, introduces two other simulation techniques which can together double the performance of well written simulators, describes Flowsim's traac representation scheme and internal algorithms, explores the tradeoo between speed and accuracy, and explores some of the limitations of traditional simulation. It demonstrates that speedups of a factor of 50 are possible when simulating ATM networks.