Saved in:
Bibliographic Details
Main Authors: Cotter, Jamie, Castineiras, Ignacio, Cionca, Victor
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.01885
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916985510559744
author Cotter, Jamie
Castineiras, Ignacio
Cionca, Victor
author_facet Cotter, Jamie
Castineiras, Ignacio
Cionca, Victor
contents In this paper, we present a solution for low-latency deadline-constrained DNN offloading on mobile edge devices. We design a scheduling algorithm with lightweight network state representation, considering device availability, communication on the network link, priority-aware pre-emption, and task deadlines. The scheduling algorithm aims to reduce latency by designing a resource availability representation, as well as a network discretisation and a dynamic bandwidth estimation mechanism. We implement the scheduling algorithm into a system composed of four Raspberry Pi 2 (model Bs) mobile edge devices, sampling a waste classification conveyor belt at a set frame rate. The system is evaluated and compared to a previous approach of ours, which was proven to outcompete work-stealers and a non-pre-emption based scheduling heuristic under the aforementioned waste classification scenario. Our findings show the novel lower latency abstraction models yield better performance under high-volume workloads, with the dynamic bandwidth estimation assisting the task placement while, ultimately, increasing task throughput in times of resource scarcity.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01885
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accuracy vs Performance: An abstraction model for deadline constrained offloading at the mobile-edge
Cotter, Jamie
Castineiras, Ignacio
Cionca, Victor
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
In this paper, we present a solution for low-latency deadline-constrained DNN offloading on mobile edge devices. We design a scheduling algorithm with lightweight network state representation, considering device availability, communication on the network link, priority-aware pre-emption, and task deadlines. The scheduling algorithm aims to reduce latency by designing a resource availability representation, as well as a network discretisation and a dynamic bandwidth estimation mechanism. We implement the scheduling algorithm into a system composed of four Raspberry Pi 2 (model Bs) mobile edge devices, sampling a waste classification conveyor belt at a set frame rate. The system is evaluated and compared to a previous approach of ours, which was proven to outcompete work-stealers and a non-pre-emption based scheduling heuristic under the aforementioned waste classification scenario. Our findings show the novel lower latency abstraction models yield better performance under high-volume workloads, with the dynamic bandwidth estimation assisting the task placement while, ultimately, increasing task throughput in times of resource scarcity.
title Accuracy vs Performance: An abstraction model for deadline constrained offloading at the mobile-edge
topic Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
url https://arxiv.org/abs/2510.01885