Machine Learning-Driven Performance Analysis of Compressed Communication in Aerial-RIS Networks for Future 6G Networks

Abstract

In the future 6G and wireless networks, particularly in dense urban environments, bandwidth exhaustion and limited capacity pose significant challenges to enhancing data rates. We introduce a novel system model designed to improve the data rate of users in next-generation multi-cell networks by integrating Unmanned Aerial Vehicle (UAV)-Assisted Reconfigurable Intelligent Surfaces (RIS), Non-Orthogonal Multiple Access (NOMA), and Coordinated Multipoint Transmission (CoMP). Optimally deploying Aerial RIS for higher data rates, employing NOMA to improve spectral efficiency, and utilizing CoMP to mitigate inter-cell interference (ICI), we significantly enhance the overall system capacity and sum rate. Furthermore, we address the challenge of feedback overhead associated with Quantized Phase Shifts (QPS) from the receiver to RIS. The feedback channel is band-limited and cannot support a large overhead of QPS for uplink communication. To ensure seamless transmission, we propose a Machine Learning Autoencoder technique for a compressed communication of QPS from the receiver to RIS, while maintaining high accuracy. Additionally, we investigate the impact of the number of Aerial RIS elements and power allocation ratio for NOMA on the individual data rate of users. Our simulation results demonstrate substantial improvements in spectral efficiency, outage probability, and bandwidth utilization, highlighting the potential of the proposed architecture to enhance network performance.