A Multi-Agent System Architecture for Coordination of the Real-Time Control Functions in Complex Industrial Systems

Multi-agent system architecture for coordination of the real-time control functions in complex industrial systems is presented. The problem which must be solved out is how efficiently to organize the interactions between tasks in order to satisfy the functionality and the time restriction of the system. In order to solve this problem, the treatment of the task interactions is separated from the tasks and is implemented by the proposed multi-agent system. A general three level multi-agent system is introduced to manage the interactions and schedule of tasks. A framework of building of the schedule of the tasks is also presented. Finally, the benefits of the proposed architecture are discussed.