Application of the Many Sources Asymptotic and Eeective Bandwidths to Traac Engineering

Accurate yet simple methods for tra c engineering are important for e cient management of resources in broadband networks. The goal of this paper is to apply and evaluate large deviation techniques for tra c engineering. In particular, we employ the recently developed theory of e ective bandwidths, where the e ective bandwidth depends not only on the statistical characteristics of the tra c stream, but also on a link's operating point through two parameters, the space and time parameters, which can be computed using the many sources asymptotic. We show that this e ective bandwidth de nition can accurately quantify resource usage. Furthermore, we estimate and interpret values of the space and time parameters for various mixes of real tra c demonstrating how these values can be used to clarify the e ects on the link performance of the time scales of tra c burstiness, of the link resources (capacity and bu er), and of tra c control mechanisms such as tra c shaping. Our experiments involve a large set of MPEG-1 compressed video and Internet Wide Area Network (WAN) traces, as well as modeled voice tra c.