A cross-enterprise collaborative production scheduling decision support algorithm with multi-agent support

This study harnesses the capabilities of intelligent agent technology to develop a framework for cross-enterprise collaborative production scheduling decision-making. It conducts a comprehensive examination of the business processes and production scheduling decisions encapsulated within this framework. The research begins by pinpointing the challenges inherent in cross-enterprise collaborative production scheduling. Subsequently, it introduces a genetic algorithm tailored for agent-based decision-making in this context and delineates its algorithmic parameters. The effectiveness of this approach is validated through a series of simulation experiments focused on a case study of cross-enterprise collaborative production scheduling from an agent-oriented perspective. The findings indicate that implementing the agent structure and genetic algorithms in a scenario involving ten workpieces and ten machines (10×10) results in a new job reach time of 30, a workshop load of 0.5338, and an average reduction in scheduling time of 11.60%. These results underscore the efficacy of the proposed agent structure and genetic algorithms in enhancing decision support for cross-enterprise collaborative production scheduling, thereby laying a scientific foundation for achieving heightened production efficiency through intelligent agent technology.