Skip to main navigation Skip to search Skip to main content

DeepDefrag: Spatio-Temporal Defragmentation of Time-Varying Virtual Networks in Computing Power Network based on Model-Assisted Reinforcement Learning

  • Huangxu Ma*
  • , Jiawei Zhang*
  • , Zhiqun Gu
  • , Hao Yu
  • , Tarik Taleb
  • , Yuefeng Ji
  • *Corresponding author for this work
  • Beijing University of Posts and Telecommunications
  • University of Oulu

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

Abstract

We propose DeepDefrag, a model-assisted reinforcement learning for spatio-temporal defragmentation of time-varying virtual networks in a cross-layer optical network testbed, which realizes the efficient utilization of computing nodes and lightpaths by co-optimizing scheduling and embedding with fragment matching, reduces >13.5% cost of computing power network.

Original languageEnglish
Title of host publication2022 European Conference on Optical Communication, ECOC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781957171159
StatePublished - 2022
Externally publishedYes
Event2022 European Conference on Optical Communication, ECOC 2022 - Basel, Switzerland
Duration: 18 Sep 202222 Sep 2022

Publication series

Name2022 European Conference on Optical Communication, ECOC 2022

Conference

Conference2022 European Conference on Optical Communication, ECOC 2022
Country/TerritorySwitzerland
CityBasel
Period18/09/2222/09/22

Fingerprint

Dive into the research topics of 'DeepDefrag: Spatio-Temporal Defragmentation of Time-Varying Virtual Networks in Computing Power Network based on Model-Assisted Reinforcement Learning'. Together they form a unique fingerprint.

Cite this