AI-Enhanced Quantum-Secured IoT Communication Framework for 6G Cognitive Radio Networks

Abstract

The advent of 6G wireless communication promises improvements in signal coverage, data rates, and latency, addressing increased connectivity demands due to the proliferation of 5G, IoT, and augmented reality. This paper introduces a Quantum-Secured IoT Communication Framework designed for 6G Cognitive Radio Networks (CRNs) in order to cater to the growing need for dependable and protected connectivity. Noteworthy aspects of this framework encompass dual-layer authentication utilizing Quantum Key Distribution (QKD) and Public Key Infrastructure (PKI), secured spectrum access regulations, and efficient beamforming strategies. Moreover, the framework employs a Reinforcement Learning-based Ensemble Regression (RL-ER) model for spectrum sensing and a Multi-Layer Perceptron with Kalman Filter (MLP-KF) for Channel State Information (CSI) prediction. Simulations demonstrate that the framework significantly improves prediction accuracy, encryption and decryption times, and error rates, thereby enhancing IoT network performance with better signal coverage, reduced latency, and robust security.

Keywords

• 6G wireless communication
• cognitive radio networks (CRNs)
• quantum key distribution (QKD)
• reinforcement learning-based ensemble regression (RL-ER)
• multi-layer perceptron with Kalman filter (MLP-KF)