A multi-agent system for distributed maintenance scheduling

Due to the intrinsically geo-distributed subcontracting maintenance activity practice, the maintenance scheduling has for a long time been a major challenge in the industry. This research work presents a methodology to schedule the maintenance activities of geo-distributed assets. A multi-agent system based approach is proposed to enable the decision-making for the subcontractors in a distributed industrial environment under uncertainty. An auction based negotiation mechanism is designed to promote competition and cooperation among the different agents, and to obtain global good schedule. Compared to the Weighted Shortest Processing Time first-Heuristic-Earliest Due Date (WSPT-H-EDD) method, the experimental results show that the proposed approach is able to provide scheduling scheme with good performances in terms of Global Cost, Total Weighted Tardiness Cost and makespan. (C) 2019 Elsevier Ltd. All rights reserved.