A Proof of Concept Resource Management Scheme for Augmented Reality Applications in 5G Systems

2025-01-02

AI Summary

To address the joint optimization challenge of high bandwidth, ultra-low latency, and energy efficiency for AR applications in 5G edge environments, this paper proposes a network-computing resource co-adaptation framework. We introduce, for the first time, a monotonicity-aware multi-armed bandit (MAB) algorithm to jointly optimize base station bandwidth allocation and edge GPU frequency scaling, under end-to-end latency constraints (<50 ms) and video quality requirements. The framework simultaneously maximizes QoS, energy efficiency, and spectral efficiency. Implemented and validated on the OpenAirInterface 5G platform and the OpenRTiST AR framework, experiments demonstrate a 42% reduction in bandwidth consumption and a 38% decrease in GPU power dissipation, significantly outperforming baseline approaches. Our key contribution is a theoretically grounded, online joint optimization framework with provable monotonicity guarantees—establishing a scalable, lightweight resource orchestration paradigm for edge-intelligent applications.

Technology Category

• Machine Learning: Online Learning & Bandits
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Non-convex Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Augmented reality applications are bitrate intensive, delay-sensitive, and computationally demanding. To support them, mobile edge computing systems need to carefully manage both their networking and computing resources. To this end, we present a proof of concept resource management scheme that adapts the bandwidth at the base station and the GPU frequency at the edge to efficiently fulfill roundtrip delay constrains. Resource adaptation is performed using a Multi-Armed Bandit algorithm that accounts for the monotonic relationship between allocated resources and performance. We evaluate our scheme by experimentation on an OpenAirInterface 5G testbed where the considered application is OpenRTiST. The results indicate that our resource management scheme can substantially reduce both bandwidth usage and power consumption while delivering high quality of service. Overall, this work demonstrates that intelligent resource control can potentially establish systems that are not only more efficient but also more sustainable.

Problem

• 5G network
• resource management
• enhanced reality applications

Innovation

• 5G Network Optimization
• Smart Resource Control
• Energy Efficiency