Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Rana M. Sohaib, Syed Tariq Shah, Poonam Yadav

TL;DR

This paper proposes a DRL-based resource allocation framework integrated with meta-learning to manage eMBB and URLLC services adaptively, aiming to maximize energy efficiency (EE) while minimizing URLLC latency, even under varying environmental conditions.

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.

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

TL;DR

This paper proposes a DRL-based resource allocation framework integrated with meta-learning to manage eMBB and URLLC services adaptively, aiming to maximize energy efficiency (EE) while minimizing URLLC latency, even under varying environmental conditions.

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.
Paper Structure (18 sections, 34 equations, 8 figures, 1 table, 2 algorithms)

This paper contains 18 sections, 34 equations, 8 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. Main Contribution
  3. System Model
  4. Throughput Estimation
  5. URLLC Latency Estimation
  6. Problem Formulation
  7. Proposed Intelligent Framework
  8. Heuristic Approach for optimizing the $\vartheta(t)$
  9. DRL-based Resource Scheduling
  10. PPO-based approach
  11. Adaptive scheduling via Meta-Learning Framework
  12. Near-RT-RIC with On-Policy Meta-Learning
  13. Non-RT-RIC with Off-Policy Meta-Learning
  14. Complexity Analysis
  15. Simulation Results
  16. ...and 3 more sections

Figures (8)

  • Figure 1: Multiconectivity enabled O-RAN based Small Cell Network and Considered Resource Grid.
  • Figure 2: Different delays in O-RAN based Small Cell Network.
  • Figure 3: Convergence performance
  • Figure 4: Impact of incoming URLLC traffic on EE of the system in rural pathloss model
  • Figure 5: Average URLLC latency in rural environment
  • ...and 3 more figures