Parallel Network Slicing for Multi-SP Services

Rongxin Han, Dezhi Chen, Song Guo, Xiaoyuan Fu, Jingyu Wang, Qi Qi, Jianxin Liao

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)

Abstract

Network slicing is rapidly prevailing in edge cloud, which provides computing, network and storage resources for various services. When the multiple service providers (SPs) respond to their tenants in parallel, individual decisions on the dynamic and shared edge cloud may lead to resource conflicts. The resource conflicts problem can be formulated as a multi-objective constrained optimization model; however, it is challenging to solve it due to the complexity of resource interactions caused by co-existing multi-SP policies. Therefore, we propose a CommDRL scheme based on multi-agent deep reinforcement learning (MADRL) and multi-agent communication to tackle the challenge. CommDRL can coordinate network resources between SPs with less overhead. Moreover, we design the neurons hotplugging learning in CommDRL to deal with dynamic edge cloud, which realizes scalability without a high cost of model retraining. Experiments demonstrate that CommDRL can successfully obtain deployment policies and easily adapt to various network scales. It improves the accepted requests by 7.4%, reduces resource conflicts by 14.5%, and shortens the model convergence time by 83.3%.

Original languageEnglish
Title of host publication51st International Conference on Parallel Processing, ICPP 2022 - Main Conference Proceedings
PublisherAssociation for Computing Machinery
Pages1–11
Number of pages11
ISBN (Electronic)9781450397339
DOIs
Publication statusPublished - 29 Aug 2022
Event51st International Conference on Parallel Processing, ICPP 2022 - Virtual, Online, France
Duration: 29 Aug 20221 Sept 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference51st International Conference on Parallel Processing, ICPP 2022
Country/TerritoryFrance
CityVirtual, Online
Period29/08/221/09/22

Keywords

  • MADRL
  • Multi-agent communication
  • Network slicing
  • Neurons hotplugging learning
  • Resource conflict

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Parallel Network Slicing for Multi-SP Services'. Together they form a unique fingerprint.

Cite this