In: Proc. 4th Int. Conf. on Autonomous Agents, 3-7 June 2000, Barcelona, Spain, pages 56-63. 2000.
Abstract: Scalability is an issue that becomes important when developing practical software agent systems, to perform some of the applications that agent development tools identify. This paper addresses issues such as whether scalability is a theme that can be investigated in isolation to the a particular agent development environment or application, and more importantly, whether metrics can be identified to compare the relative performance of multi-agent systems. Scalability is considered from a performance engineering perspective, with intelligent agents using the same techniques. Petri net based performance models are presented, which can be run in various publicly available simulators. Approches taken by different segments of agent community are summarized, and this summary is used to to identify the disparity in what is termed as ``scalability''. The main contribution of this paper is to highlight the importance of combining performance engineering with agent oriented design methodologies, to design and build large agent based applications.
Keywords: Petri nets, agent-based system development, multi-agent systems, performance comparisons, scalability.