AutoML for video analytics with edge computing

Apostolos Galanopoulos, Jose A. Ayala-Romero, Douglas J. Leith, George Iosifidis

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

Video analytics constitute a core component of many wireless services that require processing of voluminous data streams emanating from handheld devices. Multi-Access Edge Computing (MEC) is a promising solution for supporting such resource-hungry services, but there is a plethora of configuration parameters affecting their performance in an unknown and possibly time-varying fashion. To overcome this obstacle, we propose an Automated Machine Learning (AutoML) framework for jointly configuring the service and wireless network parameters, towards maximizing the analytics' accuracy subject to minimum frame rate constraints. Our experiments with a bespoke prototype reveal the volatile and system/data-dependent performance of the service, and motivate the development of a Bayesian online learning algorithm which optimizes on-the-fly the service performance. We prove that our solution is guaranteed to find a near-optimal configuration using safe exploration, i.e., without ever violating the set frame rate thresholds. We use our testbed to further evaluate this AutoML framework in a variety of scenarios, using real datasets.

Original languageEnglish
Title of host publicationINFOCOM 2021 - IEEE Conference on Computer Communications
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages10
ISBN (Electronic)9780738112817
DOIs
Publication statusPublished - 2021
EventINFOCOM 2021: IEEE International Conference on Computer Communications - Virtual/online event due to COVID-19, Virtual at Vancouver, Canada
Duration: 10 May 202113 May 2021
https://infocom2021.ieee-infocom.org/

Publication series

NameProceedings - IEEE INFOCOM
Volume2021-May
ISSN (Print)0743-166X

Conference

ConferenceINFOCOM 2021: IEEE International Conference on Computer Communications
Abbreviated titleINFOCOM 2021
CountryCanada
CityVirtual at Vancouver
Period10/05/2113/05/21
Internet address

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • Edge Computing
  • GP-UCB
  • Online Learning

Fingerprint

Dive into the research topics of 'AutoML for video analytics with edge computing'. Together they form a unique fingerprint.

Cite this