Real-time Resource Management Mechanism for Mobile IoT Devices in 5G-enabled Edge Computing

The time-sensitive Internet of Things (IoT) applications within 5G and edge computing environments presents unique challenges in network resource management. Current systems struggle with efficiently managing the high-density and variable conditions typical in such mobile networks. This study aims to address these challenges by introducing the Federated Learning-Enhanced Resource Management System for Mobile IoT networks (FLERMS-IoT). The proposed FLERMS-IoT system incorporates a novel federated learning framework that incorporates localized data processing at the edge to reduce latency and bandwidth usage. It includes algorithms that adaptively manage computational and network resources. The core of the system is a dual-module approach that dynamically adjusts to network conditions, enhancing both stability and scalability. Empirical evaluations demonstrate significant enhancements in resource utilization efficiency, with FLERMS-IoT achieving 90% in high-density scenarios and 85% in variable network conditions in comparison with 5GTFF, JCSR, and SKUNK.