Structured Engineering Process for Agent Communication Modelling

Intelligent multi-agent systems offer a new architectural style for distributed and knowledge-intensive applications. Now that agent systems are applied on a wider industrial scale, there is a practical need for structured conceptual modelling methods, similar to what is in use for conventional large-scale information and knowledge systems. Such knowledge-level methods are still inadequate for intelligent agent software, especially at the overall system level, i.e., the agent society. Therefore, we present a structured society-level process of agent communication modelling. It forms an integrated extension of the CommonKADS methodology, a widely used standard for knowledge management, analysis and systems development, and acts as a complement on top of existing agent communication languages. Our approach is illustrated by a large-scale multi-agent application for distributed energy management in industries and households, called HOMEBOTS, which is discussed as an extensive industrial case study.