Multi-agent model-based intensification-driven tabu search for solving the dual-resource constrained flexible job shop scheduling

In today's rapidly evolving manufacturing landscape, the efficient allocation of human resources is crucial for optimizing production systems. This paper addresses the dual resource-constrained flexible job shop scheduling problem (DRCFJSP) by implementing a Multi-Start Tabu Search-based Multi-Agent Model (MuSTAM). MuSTAM considers a set of initial solutions that are run in parallel using an intensification technique. The main objective of MuSTAM is to reduce the completion time (makespan), which is an important metric in workshops. The proposed model is composed of two classes of agents: a supervisor agent named MainAgent and a set of tabu search agents called TabuAgents. The MainAgent launches the system, collects inputs, generates the initial population, creates TabuAgents based on the number of solutions in the initial population (PopSize), and displays the best solution. Each TabuAgent receives a solution from the initial population and then conducts a concentrated search around its neighbourhood space by applying the intensification technique of tabu search. TabuAgents cooperate and communicate with each other to enhance search quality. Numerical tests are performed during the experimental phase to compare MuSTAM with ITS based on well-known benchmark instances of the DRCFJSP. The results demonstrate that MuSTAM is effective in terms of makespan and CPU time.