Resource Efficient Federated LoRaWAN Architecture for Far-Edge IoT Applications

This study introduces an innovative, resource-efficient architecture that incorporates advanced technologies to create a lightweight, flexible, and scalable framework for remote and limited data collecting and processing in next-generation Internet of Things (IoT) applications. It specifically proposes an integrated Federated LoRaWAN (LoRA-FL) system that combines hierarchical, privacy-preserving Federated Learning (FL), Knowledge Distillation (KD), and a customised Medium Access Control (MAC) protocol, identified as FCA-LoRa, to address the significant limitations of LoRaWAN networks. These encompass strict duty cycle rules, restricted bandwidth, and energy limitations, elements that conventionally hinder the implementation of intelligent IoT devices in rural or isolated settings. The proposed architecture features a hierarchical FL approach enabling multi-tier Artificial Intelligence (AI) model aggregation across edge nodes, gateways, and a central server. The effectiveness of the proposed system is confirmed by two practical applications, smart agriculture and smart livestock farming, which exemplify standard situations for far-edge intelligence. The results indicate that the distilled model consistently attains over 90% packet delivery success, illustrating the architecture’s capacity to provide scalable and energy-efficient intelligence at the edge. This research addresses a significant gap in previous studies that frequently examine FL, communication optimisation, and model compression independently. This study offers a comprehensive, implementable approach that tackles model scalability, and network-layer issues within a cohesive architecture, enhancing the practical implementation of AI-driven IoT deployments over LoRaWAN.