GPU accelerated planning and placement of edge clouds

Patrick Kalmbach, Andreas Blenk, Wolfgang Kellerer, Rastin Pries, Michael Jarschel, Marco Hoffmann

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Future 5G communication will rely on edge computing to meet diverse Quality of Service Requirements, in particular, end-to-end latency in the order of milliseconds. Placing edge clouds requires solving a large-scale set cover problem. We show how the challenge posed by the size of the problem can be overcome through GPU accelerated Natural Evolutional Strategies (NES). We present a system that allows the evaluation of technology choices, latency requirements and locations that should be covered at the example of the United States.

Original languageEnglish
Title of host publicationProceedings of the 2019 International Conference on Networked Systems, NetSys 2019
EditorsGeorg Carle, Tobias Hossfeld, Wolfgang Kellerer, Jorg Ott
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728105680
DOIs
StatePublished - Mar 2019
Event2019 International Conference on Networked Systems, NetSys 2019 - Garching bei Munchen, Germany
Duration: 18 Mar 201921 Mar 2019

Publication series

NameProceedings of the 2019 International Conference on Networked Systems, NetSys 2019

Conference

Conference2019 International Conference on Networked Systems, NetSys 2019
Country/TerritoryGermany
CityGarching bei Munchen
Period18/03/1921/03/19

Keywords

  • Edge Cloud Computing
  • GPU Computing

Fingerprint

Dive into the research topics of 'GPU accelerated planning and placement of edge clouds'. Together they form a unique fingerprint.

Cite this