A compound model for TCP connection arrivals for LAN and WAN applications

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 interarrival times are independent and biPareto across user sessions. 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 collected at a firewall. We show that traffic synthesized with our model closely matches the original data. We extend this approach to a general model involving shot noise and show it is asymptotically consistent with more common fractal models used in data networks. Finally, we show that this model extends to the wide area network applications without alteration and it predicts smoothing of wide area network traffic profiles due to spatial aggregation, which we observe experimentally by synthetically creating a large aggregate TCP load. (C) 2002 Elsevier Science B.V. All rights reserved.