Enregistré dans:
Détails bibliographiques
Auteurs principaux: Danek, Jan, Becvar, Zdenek, Janes, Adam
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.22149
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916764107931648
author Danek, Jan
Becvar, Zdenek
Janes, Adam
author_facet Danek, Jan
Becvar, Zdenek
Janes, Adam
contents We focus on computation offloading of applications based on convolutional neural network (CNN) from moving devices, such as mobile robots or autonomous vehicles, to MultiAccess Edge Computing (MEC) servers via a mobile network. In order to reduce overall CNN inference time, we design and implement CNN with early exits and splits, allowing a flexible partial or full offloading of CNN inference. Through real-world experiments, we analyze an impact of the CNN inference offloading on the total CNN processing delay, energy consumption, and classification accuracy in a practical road sign recognition task. The results confirm that offloading of CNN with early exits and splits can significantly reduce both total processing delay and energy consumption compared to full local processing while not impairing classification accuracy. Based on the results of real-world experiments, we derive practical models for energy consumption and total processing delay related to offloading of CNN with early exits and splits.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22149
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Real-World Modeling of Computation Offloading for Neural Networks with Early Exits and Splits
Danek, Jan
Becvar, Zdenek
Janes, Adam
Networking and Internet Architecture
Signal Processing
We focus on computation offloading of applications based on convolutional neural network (CNN) from moving devices, such as mobile robots or autonomous vehicles, to MultiAccess Edge Computing (MEC) servers via a mobile network. In order to reduce overall CNN inference time, we design and implement CNN with early exits and splits, allowing a flexible partial or full offloading of CNN inference. Through real-world experiments, we analyze an impact of the CNN inference offloading on the total CNN processing delay, energy consumption, and classification accuracy in a practical road sign recognition task. The results confirm that offloading of CNN with early exits and splits can significantly reduce both total processing delay and energy consumption compared to full local processing while not impairing classification accuracy. Based on the results of real-world experiments, we derive practical models for energy consumption and total processing delay related to offloading of CNN with early exits and splits.
title Real-World Modeling of Computation Offloading for Neural Networks with Early Exits and Splits
topic Networking and Internet Architecture
Signal Processing
url https://arxiv.org/abs/2505.22149