Achieving High Energy Efficiency for Network Slicing-Enabled 5G O-RAN Base Stations
Достижение высокой энергоэффективности базовых станций 5G O-RAN с поддержкой сетевой нарезки
2024-12-13
SCID: 54.1/6wa7aj4g
Discuss with AI
5G O-RAN base stationsdeep reinforcement learningenergy efficiencygraph neural networksnetwork slicing
Figures from the paper
Abstract (AI)
With the rapid advancement of 5G networks, data-intensive services has been surging and significantly increasing energy consumption. It is a critical challenge in addressing energy efficiency for 5G access networks. In this paper, we propose an effective load balancing algorithm that optimizes energy efficiency as users access multiple services from base stations (BS). Utilizing network slicing, the physical network is segmented into multiple independent virtual networks. We have applied graph neural networks (GNN) to extract features from dynamic traffic, model relationships between different services, and manage resource competition among BSs and network slices, treating each network slice as a distinct node. The GNN model predicts nodes workload, guiding the allocation of frequency domain resources and facilitating load balancing. Additionally, to reduce operational times and minimize disparities among slices at each BS, we propose a deep reinforcement learning (DRL) strategy. This strategy is integrated with the C-states mechanism of CPUs on general x86 computing platforms to further enhance energy efficiency. In simulations, our GNN algorithm demonstrated high precision in predicting and allocating frequency domain resources, achieving a high accuracy of 99.8%. Our DRL algorithm showed a maximum global energy efficiency improvement of 12% compared to benchmark algorithms. Overall, our approach enhanced energy efficiency by an average of 3.155 B/J under conditions of resource competition, significantly outperforming strategies that allocate equal physical resource blocks (PRB).
Key Findings
1
A deep reinforcement learning strategy integrated with CPU C-states reduced operational time and slice-level disparities while improving energy efficiency.
2
A graph neural network models dynamic traffic, service relationships, and competition among base stations and slices to predict workload and allocate frequency-domain resources.
3
The DRL approach improved global energy efficiency by up to 12% over benchmark algorithms and achieved an average improvement of 3.155 B/J under resource competition, outperforming equal-PRB allocation.
4
The GNN achieved 99.8% accuracy in predicting and allocating frequency-domain resources in simulations.
5
The paper proposes a load-balancing algorithm for improving energy efficiency in network slicing-enabled 5G O-RAN base stations.
Research Object
network slicing-enabled 5G O-RAN base stations under dynamic multi-service traffic and resource competition
Research Subject
energy efficiency and load balancing through workload prediction and coordinated allocation of frequency-domain resources, CPU C-states, and network-slice resources
Publication Details
Publication Date
2024-12-13
Journal
Publisher
ISSN
Access Type
Author Information
Download PDF
Subscribe to digest