Distributed Antenna Array and RIS-Assisted Planning Framework for Intelligent Coverage Optimization in B5G/6G...

Area of Science:

• Wireless communication networks
• Radio network planning
• Intelligent reflecting surfaces

Background:

• Conventional cell-centric architectures face limitations in Beyond 5G (B5G) and 6G networks, particularly concerning interference and coverage.
• The transition to higher frequency bands exacerbates these challenges, necessitating novel network designs.

Purpose of the Study:

• To present a scalable four-layer radio network planning framework for B5G/6G.
• To jointly optimize the deployment of distributed active antenna arrays and passive reconfigurable intelligent surfaces (RISs).
• To enhance spectral efficiency and coverage while reducing interference and capital expenditure (CAPEX).

Main Methods:

• Integration of a digital twin (DT) loop within an Open-RAN (O-RAN) architecture.
• Application of multi-agent deep reinforcement learning (MADRL) and fractional programming (FP) for joint optimization.
• Extensive Monte Carlo simulations in a dense urban environment.

Main Results:

• Achieved a 45% increase in spectral efficiency compared to legacy 5G networks.
• Demonstrated an 84% reduction in coverage holes and a 30% decrease in uplink interference.
• Extended non-line-of-sight (NLOS) coverage by 40% with reduced CAPEX.
• Showcased a 10-15% spectral efficiency improvement over existing DRL-based RIS frameworks.

Conclusions:

• The proposed framework offers a cost-effective, standards-compliant solution for future wireless networks.
• Joint optimization of active and passive components is crucial for overcoming B5G/6G limitations.
• The DT-integrated O-RAN architecture with MADRL and FP provides significant performance gains.