🤖 AI Summary
This work addresses the critical need for personalized, real-time AI inference at AI-native user equipment in 6G mobile networks, a capability hindered by the absence of user-centric edge resource allocation in existing Net4AI architectures. To bridge this gap, we propose SubEdge, a novel system that introduces the “computation context”—a data structure binding user identity to dedicated inference containers, edge nodes, and access permissions. SubEdge enables joint migration of communication and computation resources through a mobility event–driven cooperative handover mechanism, operating without modifications to the 3GPP core network. Leveraging NEF APIs and containerized deployment, our implementation demonstrates significant performance gains: the 95th-percentile latency drops from 22.9 ms to 12.2 ms, achieves zero packet loss across six handovers, sustains a 99.92% frame delivery ratio for 30-fps inference tasks, and supports 50 concurrent users completing 1,560 migrations.
📝 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.