5G network API supports flexible AI inference at the edge
Exposing AI Inference as a Telco Network API over the 5G User Plane
Artificial Intelligence
Summary
Connecting AI to mobile networks is hard because networks don't usually understand the details behind the AI calculations they carry. The paper’s authors suggest a new way called Inference on Demand (IoD) that lets the mobile network see and manage parts of AI tasks, adjusting how and where calculations happen. They built and tested this system on a 5G network setup with AI that recognizes images, showing it can adapt better than fixed setups. This approach could let networks and AI work together more smartly for better app experiences.
What this means in practice
- •For mobile network operators: Deploy adaptive AI inference services within 5G networks to improve resource use and latency for mobile applications.
- •For visual ai developers: Use network-exposed inference splitting to dynamically balance computation between devices and edge, optimizing performance for image recognition apps.
Authors
Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira, Joberto S. B. Martins, Tereza C. Carvalho, Flávio de Oliveira Silva
Abstract
Supporting edge Artificial Intelligence (AI) inference as a network service is challenging because current mobile systems can transport tensors but do not expose or understand the inference context that gives those tensors operational meaning. Prior studies have addressed this gap through dynamic partitioning, collaborative inference, and split pipelines; however, these solutions remain application-bound, network-blind, or context-free. This work proposes Inference on Demand (IoD), an inference-on-demand abstraction that exposes split inference through a CAMARA-like Application Program Interface (API) and carries a split-aware tensor context in-band across the 5G user plane path. We evaluate the IoD on a programmable user plane function (UPF)-based testbed using a partitionable visual AI workload, showing that adaptive split selection can operate as a network-facing service while avoiding the rigid cost profile of static configurations. Including our findings, split inference becomes more than offloading when the service intent, runtime partitioning, and tensor transport are made visible to the mobile data plane. This opens a path toward network-native AI services, in which programmable telco infrastructure coordinates computation, context, and connectivity for user-facing applications.