Characterization of Internet Traffic using a Fractal Model

R.R. Marie, J.M. Blackledge, and H.E. Bez (UK)


fractal, self-affinity, Internet traffic, RSF model, tcpdump, packet.


There are many models in the literature that consider the main characteristics of Internet traffic noise either by pro cessing real measurements of packets ( or bytes) traffic in the time or the frequency domain. Fractals are applicable when the underlying processes being modeled have a sim ilar appearance regardless of the time or observation scale and much of the traf c'riding' the Internet can be modeled using fractals. Further, it is arguable that as the Internet has become larger and larger, the fractal nature of the traffic has become more and more pronounced. In this paper we introduce a novel method that depends on the frequency analysis through which we attempt to capture the fractal behavior of Internet traffic by adopting a Random Scaling Fractal model to characteristics of the traffic. The relevance and validation of the proposed model are demonstrated by application studies for measured Internet traffic.

Important Links:

Go Back