cs.AIOct 10, 2026

Exposing AI Inference as a Telco Network API over the 5G User Plane

Authors: Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira, Joberto S. B. Martins, Tereza C. Carvalho, Flávio de Oliveira Silva

Organizations: Federal University of Viçosa (UFV), Minas Gerais, Brazil · University of Salvador (UNIFACS), Salvador, Brazil · University of São Paulo (USP), São Paulo, Brazil · University of Minho (UMinho), Braga, Portugal

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

ApproachDynamic SplitQoS ControlTensor TransportUser PlaneIn-Band MetadataCAMARA API
Djuhera et al. [ 13 ]      
Shah et al. [ 22 ]      
Koch et al. [ 14 ]      
Zhang et al. [ 15 ]      
Tran et al. [ 11 ]      
Lim et al. [ 16 ]      
TABLE I: Short state-of-the-art Survey
Fig. 1: Inference-on-Demand problem setting.
Fig. 2: Our testbed.
Fig. 3: Baseline model validation on FLAME 2: (a) training and validation dynamics over epochs and (b) the resulting test-set confusion matrix.
Fig. 4: Compute–bytes operating frontier across fixed split points and IoD. IoD operates near the middle of the frontier without a priori selection of kk .
Fig. 5: Fraction of IoD rounds in the network-protection regime as the number of active UE replicas increases.
Fig. 6: Observed IoD split point as a function of active UE replicas. Error bars show variation across seeds.
Fig. 7: Share of IoD rounds assigned to the nominal and network-protection regimes.
Fig. 8: UPF-counted load under increasing numbers of active UE replicas.
Fig. 9: Per-seed paired difference between IoD and each static baseline in UE bytes per frame. Negative values indicate that IoD transmits fewer bytes than the corresponding static split.
More in this topic

Edge Inference

Edge inference runs trained AI models on nearby devices such as phones, cameras, robots, and embedded computers under tight resource and latency limits.

See all 219 papers

Explore similar work

CardsList

  1. SLA-Aware Distributed LLM Inference Across Device-RAN-Cloud

    Feb 27, 2026Hariz Yet, Nguyen Thanh Tam, Mao V. Ngo +5LLM Inference ServingLLM Inference

    Singapore University of Technology and Design (SUTD)

  2. Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States

    Mar 3, 2026Jierui Zhang, Jianhao Huang, Kaibin HuangAdaptive InferenceEdge Inference

    Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong

  3. MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks

    Sep 13, 2026Sokratis Nikolaidis, Stylianos I. Venieris, Leonidas Malachias +1Edge InferenceDistributed Inference

    National Technical University of Athens, Athens, Greece · Samsung AI Center, Cambridge, UK