Efficient Distributed Learning for Autonomous Multi-Reconfigurable Intelligent Surfaces Operation

The sixth-generation (6G) wireless communication networks promise transformative advancements in various sectors by enhancing speed, reliability, and connectivity to support applications like autonomous vehicles, smart healthcare, immersive augmented reality (AR), and the Internet of Everything (IoE). Integrated sensing and communication (ISAC) technologies are pivotal in 6G, enabling advanced applications through intelligent metasurfaces. The deployment of AI and machine learning (ML) within 6G networks is essential for managing complex network tasks, enhancing security, and optimizing performance. These technological advancements collectively contribute to the realization of intelligent, context-aware, and user-centric applications across various domains, heralding a new era of connectivity and smart services.
Integrating and operating passive RIS into 6G communication networks presents several challenges, particularly in the search space for optimizing RIS-aided communication networks. We therefore seek to design an efficient distributed learning approach over a novel hybrid RIS architecture with energy-efficient sensing capabilities. This work builds upon the previous MITACS Accelerate project # IT29537 where a passive RIS prototype operating at 3.75GHz (n77 and n78 TDD 5G frequency band) has been developed and integrated to the 5G Open radio access network.

Faculty Supervisor:

Messaoud Ahmed Ahmed Ouameur

Student:

Partner:

BCi Technique

Discipline:

Engineering

Sector:

Professional, scientific and technical services

University:

Université du Québec à Trois-Rivières

Program: