Towards Resilient 6G O-RAN: An Energy-Efficient URLLC Resource Allocation Framework

TL;DR

This paper introduces a DRL-based resource allocation framework with meta-learning for 6G O-RAN that balances energy efficiency and URLLC latency, adapting to environmental changes and traffic uncertainties.

Contribution

It presents a novel adaptive resource allocation method combining DRL and meta-learning to optimize energy efficiency and latency in 6G networks.

Findings

Outperforms traditional resource allocation methods.

Demonstrates robustness across different path loss models.

Effectively manages traffic uncertainty in multi-connectivity scenarios.

Abstract

The demands of ultra-reliable low-latency communication (URLLC) in ``NextG" cellular networks necessitate innovative approaches for efficient resource utilisation. The current literature on 6G O-RAN primarily addresses improved mobile broadband (eMBB) performance or URLLC latency optimisation individually, often neglecting the intricate balance required to optimise both simultaneously under practical constraints. This paper addresses this gap by proposing a DRL-based resource allocation framework integrated with meta-learning to manage eMBB and URLLC services adaptively. Our approach efficiently allocates heterogeneous network resources, aiming to maximise energy efficiency (EE) while minimising URLLC latency, even under varying environmental conditions. We highlight the critical importance of accurately estimating the traffic distribution flow in the multi-connectivity (MC) scenario, as its uncertainty can significantly degrade EE. The proposed framework demonstrates superior adaptability across different path loss models, outperforming traditional methods and paving the way for more resilient and efficient 6G networks.