This study develops a model and algorithm to solve the decentralized resource-constrained multi-project scheduling problem (DRCMPSP) and provides a suitable priority rule (PR) for coordinating global resource conflicts among multiple projects.
This study addresses the DRCMPSP, which respects the information privacy requirements of project agents; that is, there is no single manager centrally in charge of generating multi-project scheduling. Accordingly, a three-stage model was proposed for the decentralized management of multiple projects. To solve this model, a three-stage solution approach with a repeated negotiation mechanism was proposed.
The experimental results obtained using the Multi-Project Scheduling Problem LIBrary confirm that our approach outperforms existing methods, regardless of the average utilization factor (AUF). Comparative analysis revealed that delaying activities in the lower project makespan produces a lower average project delay. Furthermore, the new PR LMS performed better in problem subsets with AUF < 1 and large-scale subsets with AUF > 1.
A solution approach with a repeated-negotiation mechanism suitable for the DRCMPSP and a new PR for coordinating global resource allocation are proposed.
