DT-LSMAS: Digital Twin-Assisted Large-Scale Multiagent System for Healthcare Workflows

Abstract

Digital healthcare has garnered much attention from academia and industry for health and well-being. Many digital healthcare architectures based on large-scale edge and cloud multiagent systems (LSMASs) have recently been presented. The LSMAS allows agents from different institutions to work together to achieve healthcare processing goals for users. This article presents a digital twin large-scale multiagent strategy (DT-LSMAS) comprising mobile, edge, and cloud agents. The DT-LSMAS comprised different schemes for healthcare workflows, such as added healthcare workflows, application partitioning, and scheduling. We consider healthcare workflows with different biosensor data such as heartbeat, blood pressure, glucose monitoring, and other healthcare tasks. We partitioned workflows into mobile, edge, and cloud agents to meet the deadline, total time, and security of workflows in large-scale edge and cloud nodes. To handle the large-scale resource for real-time sensor data, we suggested digital twin-enabled edge nodes, where delay-sensitive workflow tasks are scheduled and executed under their quality of service requirements. Simulation results show that the DT-LSMAS outperformed in terms of total time by 50%, minimizing the risk of resource leakage and deadline missing during scheduling on heterogeneous nodes. In conclusion, the DT-LSMAS obtained optimal results for workflow applications.