Decentralized learning multi-agent system for online machine shop scheduling problem

Customer profiles have rapidly changed over the past few years, with products being requested with more customization and with lower demand. In addition to the advances in technologies owing to Industry 4.0, manufacturers explore autonomous and smart factories. This paper proposes a decentralized multi-agent system (MAS), including intelligent agents that can respond to their environment autonomously through learning capabilities, to cope with an online machine shop scheduling problem. In the proposed system, agents participate in auctions to receive jobs to process, learn how to bid for jobs correctly, and decide when to start processing a job. The objective is to minimize the mean weighted tardiness of all jobs. In contrast to the existing literature, the proposed MAS is assessed on its learning capabilities, producing novel insights concerning what is relevant for learning, when re-learning is needed, and system response to dynamic events (such as rush jobs, increase in processing time, and machine unavailability). Computational experiments also reveal the outperformance of the proposed MAS to other multi-agent systems by at least 25% and common dispatching rules in mean weighted tardiness, as well as other performance measures