Enhancing Wireless Sensor Networks with Federated Reinforcement Learning and Distributed Quantum Cryptography: A Simulation Study
Wadhah Al-Zofi, Ziqiang Hao, Yijun Wang
Wireless Sensor Networks (WSNs) are the foundation for Internet of Things (IoT) applications, facilitating paramount applications in smart cities, industrial automation, and healthcare. WSNs in dynamic resource-constrained environments, nevertheless, continue to lag in energy efficiency, adaptability, and security. In this paper, we present a new architecture that combines Federated Reinforcement Learning (FRL) and Distributed Quantum Cryptography (DQC) to break through these constraints. FRL module endows sensor nodes with decentralized, privacy-preserving intelligence for adaptive energy consumption control, routing, and transmission power control. DQC module uses Quantum Key Distribution (QKD) for securing communications against classical and quantum eavesdroppers. The FRL-DQC solution is extensively verified by large-scale simulations under diverse network topologies, traffic models, and threat scenarios. Experimental results are accompanied by significant gains in energy efficiency, communication delay, and quantum-resistant security over traditional WSNs and centralized learning. As an open and dynamic solution, the FRL-DQC solution facilitates the deployment of secure, energy-efficient, and future-proof WSN infrastructures with the ability to provide resilient performance in dynamic and smart environments.
•Jul 24, 2025•0 citations