Simulation supported agent-based adaptive production scheduling

Distributed (agent-based) control architectures offer prospects of reduced complexity, high flexibility and a high robustness against disturbances in manufacturing. However, it has also turned out that distributed control architectures, usually banning all forms of hierarchy, cannot guarantee optimum performance and the system behaviour can be unpredictable. The paper addresses the area of agent-based manufacturing systems, particularly it is devoted to distributed intelligent techniques for managing complexity, changes and disturbances on shop floor control level. More precisely, the paper outlines an attempt to enhance the performance of a market-based distributed manufacturing system by using reinforcement learning. In order to enable a constructive, decision supporting environment the mentioned techniques are integrated in a discrete event simulation framework. The experimental results demonstrate the applicability of the proposed solutions, which can contribute to significant improvements in system performance, keeping the known benefits of distributed control.