Performance Analysis of the Knockout Switch Under Bursty Traffic Based on a Stochastic Activity Network Model

Abstract

The possibility of Asynchronous Transfer Mode (ATM)-based B-ISDNs has made desirable the integration of diverse services like voice, data, and multimedia. The success of these high-speed networks is critically dependent on the availability of Fast Packet Switches (FPS) with the capacity to switch and route at high speeds and to provide the required Quality of Service (QoS). The diversity of the applications, however, leads to widely differing QoS demands. The knockout switch is an FPS with low cell-loss probability and latency under steady input traffic. In this paper, we analyze the performance of the knockout switch in terms of cell loss probabil ities and distribution of queue length for a wide range of burst parameters. The switch is modeled using Stochastic Activity Networks (SANs), and the underlying Markov processes are generated and solved using UltraSAN. The results provide useful information about the switch sensitivity and robustness under a variety of burst parameters and illustrate the appropriateness of SANs for modeling and analyzing telecommunication switch architectures.