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
Ye Liu, Leyu Zhao, Jingtong Wu, Di Liu, Xiaojun Hei
2024-12-13

5G O-RAN base stationsdeep reinforcement learningenergy efficiencygraph neural networksnetwork slicing
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).
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.

network slicing-enabled 5G O-RAN base stations under dynamic multi-service traffic and resource competition

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
Authors
Ye Liu
Leyu Zhao
Jingtong Wu
Di Liu
Xiaojun Hei
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%