page 1  (29 pages)
2to next section

An Empirical Workload Model for Driving
Wide-Area TCP/IP Network Simulations

Peter B. Danzig* Sugih Jamin* Ram?n C?ceres? Danny J. Mitzel* Deborah Estrin*
*Computer Science Department, University of Southern California,
Los Angeles, California 90089-0781
?Computer Science Division, University of California,
Berkeley, California 94720
traffic@excalibur.usc.edu
Abstract

We present an artificial workload model of wide-area internetwork traffic. The model can be used to drive simulation experiments of communication protocols and flow and congestion control experiments. The model is based on analysis of wide-area TCP/IP traffic collected from one industrial and two academic networks. The artificial workload model uses both detailed knowledge and measured characteristics of the user application programs responsible for the traffic. Observations drawn from our measurements contradict some commonly held beliefs regarding wide-area TCP/IP network traffic.

The simulation techniques presented here will be useful in studying congestion control, routing algorithms, and other resource management schemes, for existing and future networks.

Keywords: Wide-Area Networks, Artificial Workload Models, Trace Analysis, Simulation, TCP/IP Internetworks

1. Introduction

When simulating new congestion control, flow control, and adaptive routing algorithms one needs to model the overall pattern of traffic flowing through the network, from distribution of packet sizes and interarrival times, to characteristics such as distribution of host reference patterns and direction of traffic flow. This paper presents an artificial workload model of widearea network traffic based upon application-level analysis of wide-area TCP/IP [1] traces collected on two campus networks, the University of Southern California (USC) and the University of California at Berkeley (UCB), and one industrial research site, Bellcore.

This research was supported by an equipment grant from the Charles Lee Powell Foundation. Ram?n C?ceres was supported by the NSF and DARPA under Cooperative Agreement NCR-8919038 with CNRI, by AT&T Bell Laboratories, Hitachi, a University of California MICRO grant, and ICSI. Danny Mitzel was supported by a fellowship from Hughes Aircraft Company.