Decentralized Multi-Hop Federated Reinforcement Learning for Energy-Efficient and Secure Routing in LoRaWAN-based Smart City Infrastructure

Outlet Title

Engineering Open Access

Authors

Harsha Sammangi, Dakota State UniversityFollow
Aditya Jagatha, Dakota State University
Jun Liu, Dakota State University

Document Type

Article

Publication Date

Spring 5-2025

Abstract

This paper proposes a decentralized hybrid framework that integrates Federated Learning (FL) and Reinforcement Learning (RL) to enable energy-efficient and secure multi-hop routing in LoRaWAN-based smart city networks. The method allows local model training at gateways and relay nodes, combining real-time routing decisions with privacy-preserving federated aggregation. Key metrics such as residual energy, link quality, and node trust levels are embedded into the reward function, and lightweight encryption plus differential privacy safeguard routing metadata. Simulation results demonstrate substantial gains in packet-delivery ratio, latency, network lifetime and resilience to adversarial attacks when compared to traditional routing protocols.

Comments

This version is deposited in Beadle Scholar for institutional archiving and indexing. Originally published in Engineering Open Acce

Recommended Citation

Sammangi, Harsha; Jagatha, Aditya; and Liu, Jun, "Decentralized Multi-Hop Federated Reinforcement Learning for Energy-Efficient and Secure Routing in LoRaWAN-based Smart City Infrastructure" (2025). Research & Publications. 462.
https://scholar.dsu.edu/bispapers/462