DRL for Network Slicing: Resource Efficiency Optimisation under Reconfiguration Avoidance

Zhaozhou Wu*, Anderson C Bravalheri, Juan Marcelo Parra Ullauri, Adrian-Cristian Nicolaescu, Yulei Wu, Dimitra Simeonidou

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

Network Slicing (NS) can satisfy the differentiated service demands of vertical industries by tailoring a common infrastructure to multiple isolated logical networks. Such slices may need to be reconfigured given the varying traffic patterns, service requirements, device mobility and resource constraints. Frequent slice reconfigurations lead to service quality degradation for slice consumers. However, avoiding reconfigurations of existing slices leads to fewer deployed slices, in comparison to allowing reconfigurations. To mitigate this problem in the avoidance of reconfiguration, this paper proposes using Deep Reinforcement Learning (DRL) to optimise successful slice deployments over time, while avoiding reconfigurations. The DRL agent instructs a Linear Programming (LP) algorithm to deploy slices to maximise the chance of successful slice deployments over time. The results show that more slices are deployed compared to avoiding reconfiguration with LP-only algorithms. Our DRL-based slice orchestrator provides approximately 11% more slices, compared to existing slice orchestrations without such DRL guidance, demonstrating the potential advantage of DRL in NS applications.
Original languageEnglish
Title of host publicationIEEE INFOCOM 2024 - IEEE Conference on Computer Communications
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
Publication statusAccepted/In press - 19 May 2025
EventIEEE International Conference on Computer Communications - London, United Kingdom, London, United Kingdom
Duration: 19 May 202522 May 2025
https://infocom2025.ieee-infocom.org/

Publication series

NameIEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies
PublisherIEEE
ISSN (Print)0743-166X
ISSN (Electronic)2641-9874

Workshop

WorkshopIEEE International Conference on Computer Communications
Country/TerritoryUnited Kingdom
CityLondon
Period19/05/2522/05/25
Internet address

Research Groups and Themes

  • Smart Internet Lab

Fingerprint

Dive into the research topics of 'DRL for Network Slicing: Resource Efficiency Optimisation under Reconfiguration Avoidance'. Together they form a unique fingerprint.

Cite this