A compound model for TCP connection arrivals: Empirical study within a general framework

We propose a two level model for TCP connection arrivals in local area networks. The first level are user sessions whose arrival is time-varying Poisson. The second level are connections within a user session. Their number and mean interrival are independent and biPareto across user session. The interarrivals within a user session are Weibull, and across all users are correlated Weibull. Our model has a small number of parameters which are inferred from real traffic colected at a firewall. We show that traffic synthesized with our model closely characterizes the original data. We extend this approach to a general model involving shot noise that is shown to be asymptotically consistent with more common fractal models used in data networks.