Multi-agent approach for the scheduling of manufacturing systems

In real manufacturing environments, the control of the system elements such as machines and Automated Guided Vehicles has some difficulties when planning operations dynamically. Multi agent-based systems, a newly maturing area of distributed artificial intelligence, provide some effective mechanisms for the management of such dynamic operations in manufacturing environments. In this study, an evolutionary scheduling approach to AGVs and machines within a manufacturing system is proposed and implemented through a Multi-Agent System (MAS) exhibiting the characteristics of a Holonic System. The proposed multi-agent based approach works under a real-time environment which is stochastic, continuous, distributed, and possessing a high computational complexity. Feasible schedules are emerged from negotiation/bidding mechanisms between agents.The proposed architecture is applied to a case study which was taken from the literature and compared with offline scheduling methods and online scheduling rules (dispatching rules). Results showed that the proposed system is capable of generating good schedules in real time and its performance is comparable with optimization algorithms and frequently used dispatching rules.