Optimal Accuracy-Time Trade-off For Deep Learning Services in Edge Computing Systems

Minoo Hosseinzadeh, Andrew Wachal, Hana Khamfroush, Daniel Enrique Lucani Rötter

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

Abstract

With the increasing demand for computationally intensive services like deep learning tasks, emerging distributed computing platforms such as edge computing (EC) systems are becoming more popular. Edge computing systems have shown promising results in terms of latency reduction compared to the traditional cloud systems. However, their limited processing capacity imposes a trade-off between the potential latency reduction and the achieved accuracy in computationally-intensive services such as deep learning-based services. In this paper, we focus on finding the optimal accuracy-time trade-off for running deep learning services in a three-tier EC platform where several deep learning models with different accuracy levels are available. Specifically, we cast the problem as an Integer Linear Program, where optimal task scheduling decisions are made to maximize overall user satisfaction in terms of accuracy-time trade-off. We prove that our problem is NP-hard and then provide a polynomial constant-time greedy algorithm, called GUS, that is shown to attain near-optimal results. Finally, upon vetting our algorithmic solution through numerical experiments and comparison with a set of heuristics, we deploy it on a test-bed implemented to measure for real-world results. The results of both numerical analysis and real-world implementation show that GUS can outperform the baseline heuristics in terms of the average percentage of satisfied users by a factor of at least 50%.
Original languageEnglish
Title of host publicationICC 2021 - IEEE International Conference on Communications, Proceedings
Number of pages6
PublisherIEEE
Publication dateJun 2021
ISBN (Electronic)9781728171227
DOIs
Publication statusPublished - Jun 2021
EventIEEE International Conference on Communications -
Duration: 14 Jun 202123 Jun 2021

Conference

ConferenceIEEE International Conference on Communications
Period14/06/202123/06/2021

Keywords

  • Mobile edge computing
  • deep learning
  • quality of experience
  • raspberry pi
  • resource management
  • task offloading
  • user satisfaction

Fingerprint

Dive into the research topics of 'Optimal Accuracy-Time Trade-off For Deep Learning Services in Edge Computing Systems'. Together they form a unique fingerprint.
  • Scale-loT

    Lucani Rötter, D. E.

    01/01/201831/12/2022

    Project: Research

Cite this