A QoS-aware network reconfiguration method in data centers based on deep reinforcement learning

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

2 Downloads (Pure)

Abstract

We demonstrate a dynamic network reconfiguration method (ACRO) based on deep reinforcement learning that can autonomously learn the scheme to reconfigure the application traffic with different QoS requirements. Numerical results based on real application traffics indicate that the ACRO provides up to 24.6% network latency improvement.

Original languageEnglish
Title of host publication45th European Conference on Optical Communication, ECOC 2019
PublisherInstitution of Engineering and Technology (IET)
Number of pages4
ISBN (Print)978-1-83953-185-9
DOIs
Publication statusPublished - 30 Jun 2020
Event45th European Conference on Optical Communication (ECOC 2019) - Dublin, Ireland
Duration: 22 Sep 201926 Sep 2019
Conference number: 45
https://www.ecoc2019.org/

Publication series

NameIET Conference Publications
NumberCP765

Conference

Conference45th European Conference on Optical Communication (ECOC 2019)
Abbreviated titleECOC 2019
Country/TerritoryIreland
CityDublin
Period22/09/1926/09/19
Internet address

Keywords

  • Application traffic
  • Deep reinforcement learning
  • OMNET++
  • Optical network reconfiguration

Fingerprint

Dive into the research topics of 'A QoS-aware network reconfiguration method in data centers based on deep reinforcement learning'. Together they form a unique fingerprint.

Cite this