Joint Compression and Offloading Decisions for Deep Learning Services in 3-Tier Edge Systems

Minoo Hosseinzadeh, Nathaniel Hudson, Xiaobo Zhao, Hana Khamfroush, Daniel Enrique Lucani Rötter

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

Abstract

Task offloading in edge computing infrastructure remains a challenge for dynamic and complex environments, such as Industrial Internet-of-Things. The hardware resource constraints of edge servers must be explicitly considered to ensure that system resources are not overloaded. Many works have studied task offloading while focusing primarily on ensuring system resilience. However, in the face of deep learning-based services, model performance with respect to loss/accuracy must also be considered. Deep learning services with different implementations may provide varying amounts of loss/accuracy while also being more complex to run inference on. That said, communication latency can be reduced to improve overall Quality-of-Service by employing compression techniques. However, such techniques can also have the side-effect of harming the provided loss/accuracy provided by deep learning-based service. As such, this work studies a joint optimization problem for task offloading decisions in 3-tier edge computing platforms where decisions regarding task offloading are made in tandem with compression decisions. The objective is to optimally offload requests with compression such that the trade-off between latency-accuracy is not greatly jeopardized. We cast this problem as a mixed-integer nonlinear program. Due to its nonlinear nature, we then decompose it into separate sub-problems for offloading and compression. An efficient algorithm is proposed to solve the problem. Empirically, we show that our algorithm attains roughly a 0.958-approximation of the optimal solution provided by a block coordinate descent method for solving the two sub-problems back-to-back.
Original languageEnglish
Title of host publication2021 IEEE International Symposium on Dynamic Spectrum Access Networks, DySPAN 2021
Number of pages8
PublisherIEEE
Publication date2021
Pages254-261
ISBN (Electronic)9781665413398
DOIs
Publication statusPublished - 2021
Event2021 IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, DySPAN - Los Angeles , United States
Duration: 13 Dec 202115 Dec 2021

Conference

Conference2021 IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, DySPAN
Country/TerritoryUnited States
CityLos Angeles
Period13/12/202115/12/2021

Keywords

  • Compression
  • Deep Learning
  • Edge Computing
  • Industrial Internet-of-Things
  • Network Optimization
  • Task Offloading

Fingerprint

Dive into the research topics of 'Joint Compression and Offloading Decisions for Deep Learning Services in 3-Tier Edge Systems'. Together they form a unique fingerprint.
  • Scale-loT

    Lucani Rötter, D. E.

    01/01/201831/12/2022

    Project: Research

Cite this