TARMM: Scaling Delay-Critical Edge AI Offloading in 5G O-RAN via Temporal Graph Mobility Management

2026-04-27

AI Summary

This work addresses the limitations of existing 5G mobility management mechanisms in meeting the stringent low-latency and high-reliability requirements of edge AI applications, which often lead to degraded handover performance. To overcome this challenge, the authors propose a novel mobility management approach tailored for O-RAN architecture, integrating spatio-temporal graph neural networks with multi-agent reinforcement learning. This is the first study to incorporate spatio-temporal graph modeling into O-RAN handover decisions, enhanced by a rule-driven action masking scheme and resource pre-configuration mechanism to enable near real-time, secure, and efficient user handovers. Experimental results on a multi-cell indoor 5G O-RAN testbed demonstrate that the proposed method reduces tail latency by 44% and packet loss by 56% compared to the state-of-the-art, significantly improving handover stability and efficiency for latency-sensitive AI tasks.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Learning on the Edge & Model Compression
• Multiagent Systems: Mechanism Design

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Emerging delay-critical edge AI applications, such as VR perception and real-time video analytics, impose stringent latency and reliability requirements on 5G networks. However, existing mobility management mechanisms are largely reactive and fail to adapt to dynamic network conditions, resulting in suboptimal handover decisions and degraded performance. In this paper, we present TARMM, a 5G Open Radio Access Network (O-RAN) system that optimizes user mobility management for delay-critical edge AI offloading. The core of TARMM is a temporal graph model that captures the spatiotemporal dynamics of the RAN across users and cells, enabling near real-time handover decisions. Building on this representation, we design a multi-agent reinforcement learning (MARL) framework with rule-based action masking and proactive resource preparation to ensure safe, stable, and efficient handovers. We implement TARMM on a multi-cell indoor 5G O-RAN testbed and evaluate it using diverse VR workloads. Extensive experiments show that TARMM reduces tail latency by up to 44% and packet loss by up to 56% compared to state-of-the-art approaches.

Problem

• delay-critical
• edge AI
• mobility management
• 5G O-RAN
• handover

Innovation

• Temporal Graph Model
• Multi-Agent Reinforcement Learning
• Edge AI Offloading
• Mobility Management
• 5G O-RAN