SubEdge: A Subscriber-Centric Edge Computing Subsystem in 6G Networks for AI
2026-06-29 • Networking and Internet Architecture
Networking and Internet ArchitectureDistributed, Parallel, and Cluster Computing
AI summaryⓘ
The authors propose SubEdge, a system designed for future 6G networks to handle personalized AI computing tasks for individual users, like robots or smart glasses, that can't run their AI models locally or share them with others. SubEdge ensures that both the communication and computing resources move together smoothly when a user changes location, maintaining quick and reliable service. Their approach uses existing network interfaces without changing the core network and was tested in real scenarios, showing significant improvements in latency and reliability during user mobility. This work focuses on making sure personal AI services keep running well even as users move around.
6GAI-native terminalsedge computingper-subscriber provisioningmobility managementNetwork Exposure Function (NEF)inference containerlatencyservice continuity
Authors
Abdirazak Ali Asir Rage, Riccardo Pozza, Rahim Tafazolli
Abstract
Beyond traditional connectivity, 6G is envisioned to transform mobile networks into a distributed fabric that provides native integrated communication, computing, and intelligence services. AI-native terminals (e.g., robots, autonomous vehicles, and smart glasses) require real-time inference from individualised, manufacturer-specific models that cannot be executed on-board nor shared across subscribers, making per-subscriber edge compute the necessary complement to per-subscriber connectivity. Existing Network for AI (Net4AI) architectures provision compute for application providers through shared deployments and do not address per-subscriber provisioning. This paper proposes SubEdge, a Net4AI subsystem that provisions integrated communication and compute resources on a per-subscriber basis, ensuring the coupled migration of both dimensions to maintain service continuity during mobility. SubEdge contributes the computing context--a per-subscriber data structure binding a Subscription Permanent Identifier (SUPI) to its inference container, edge node, and service entitlement--and a mobility-event-driven mechanism that simultaneously migrates the subscriber's compute instance and its traffic-routing policy when the serving cell changes. SubEdge operates as an Application Function over existing Network Exposure Function (NEF) APIs with zero 3GPP core modifications. Experimental evaluation on a real-world testbed shows that SubEdge's mobility-driven joint communication-and-compute migration reduces 95th-percentile latency from 22.9 ms to 12.2 ms with zero packet loss across six mobility events, sustains 99.92% frame delivery for an end-to-end 30 fps inference workload, and completes 1,560 migration operations across batches of up to 50 simultaneously migrating subscribers with 100% success.