Optimized Split Computing Framework for Edge and Core Devices

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tassi, Andrea, Kolawole, Oluwatayo Yetunde, Roig, Joan Pujol, Warren, Daniel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909775486255104
author Tassi, Andrea
Kolawole, Oluwatayo Yetunde
Roig, Joan Pujol
Warren, Daniel
author_facet Tassi, Andrea
Kolawole, Oluwatayo Yetunde
Roig, Joan Pujol
Warren, Daniel
contents With mobile networks expected to support services with stringent requirements that ensure high-quality user experience, the ability to apply Feed-Forward Neural Network (FFNN) models to User Equipment (UE) use cases has become critical. Given that UEs have limited resources, running FFNNs directly on UEs is an intrinsically challenging problem. This letter proposes an optimization framework for split computing applications where an FFNN model is partitioned into multiple sections, and executed by UEs, edge- and core-located nodes to reduce the required UE computational footprint while containing the inference time. An efficient heuristic strategy for solving the optimization problem is also provided. The proposed framework is shown to be robust in heterogeneous settings, eliminating the need for retraining and reducing the UE's memory (CPU) footprint by over 33.6% (60%).
format Preprint
id arxiv_https___arxiv_org_abs_2509_06049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimized Split Computing Framework for Edge and Core Devices
Tassi, Andrea
Kolawole, Oluwatayo Yetunde
Roig, Joan Pujol
Warren, Daniel
Networking and Internet Architecture
With mobile networks expected to support services with stringent requirements that ensure high-quality user experience, the ability to apply Feed-Forward Neural Network (FFNN) models to User Equipment (UE) use cases has become critical. Given that UEs have limited resources, running FFNNs directly on UEs is an intrinsically challenging problem. This letter proposes an optimization framework for split computing applications where an FFNN model is partitioned into multiple sections, and executed by UEs, edge- and core-located nodes to reduce the required UE computational footprint while containing the inference time. An efficient heuristic strategy for solving the optimization problem is also provided. The proposed framework is shown to be robust in heterogeneous settings, eliminating the need for retraining and reducing the UE's memory (CPU) footprint by over 33.6% (60%).
title Optimized Split Computing Framework for Edge and Core Devices
topic Networking and Internet Architecture
url https://arxiv.org/abs/2509.06049