R-Learning-based admission control for service federation in multi-domain 5G networks

e-Archivo Repository

Show simple item record

dc.contributor.author Bakhshi, Bahador
dc.contributor.author Mangues-Bafalluy, Josep
dc.contributor.author Baranda, Jorge
dc.date.accessioned 2022-02-15T11:20:04Z
dc.date.available 2022-02-15T11:20:04Z
dc.date.issued 2021-12-07
dc.identifier.bibliographicCitation Bakhshi, B., Mangues-Bafalluy, J. & Baranda, J. (7-11 Dec. 2021). R-Learning-based admission control for service federation in multi-domain 5G networks [proceedings]. 2021 IEEE Global Communications Conference (GLOBECOM), Madrid, Spain.
dc.identifier.isbn 978-1-7281-8104-2 (Electronic)
dc.identifier.isbn 978-1-7281-8105-9 (Print on Demand(PoD))
dc.identifier.uri http://hdl.handle.net/10016/34128
dc.description Proceedings of: IEEE Global Communications Conference (GLOBECOM), 7-11 Dec. 2021, Madrid, Spain.
dc.description.abstract Network service federation in 5G/B5G networks enables service providers to extend service offering by collaborating with peering providers. Realizing this vision requires interoperability among providers towards end-to-end service orchestration across multiple administrative domains. Smart admission control is fundamental to make such extended offering profitable. Without prior knowledge of service requests, the admission controller (AC) either determines the domain to deploy each demand or rejects it to maximize the long-term average profit. In this paper, we first obtain the optimal AC policy by formulating the problem as a Markov decision process, which is solved through the policy iteration method. This provides the theoretical performance bound under the assumption of known arrival and departure rates of demands. Then, for practical solutions to be deployed in real systems, where the rates are not known, we apply the Q-Learning and R-Learning algorithms to approximate the optimal policy. The extensive simulation results show that learning approaches outperform the greedy policy and are capable of getting close to optimal performance. More specifically, R-learning always outperformed the rest of practical solutions and achieved an optimality gap of 3-5% independent of the system configuration, while Q-Learning showed lower performance and depended on discount factor tuning.
dc.description.sponsorship This work has been partially funded by the MINECO grant TEC2017-88373-R (5G-REFINE), the EC H2020 5Growth Project (grant no. 856709), and Generalitat de Catalunya grant 2017 SGR 1195.
dc.format.extent 6
dc.language.iso eng
dc.publisher IEEE
dc.rights © 2021 IEEE.
dc.subject.other Multi-domain 5G/B5G networks
dc.subject.other Admission control
dc.subject.other Service federation
dc.subject.other MDP
dc.subject.other Q-Learning
dc.subject.other R-Learning
dc.title R-Learning-based admission control for service federation in multi-domain 5G networks
dc.type conferenceObject
dc.subject.eciencia Telecomunicaciones
dc.identifier.doi https://doi.org/10.1109/GLOBECOM46510.2021.9685936
dc.rights.accessRights openAccess
dc.relation.projectID Gobierno de España. TEC2017-88373-R
dc.relation.projectID info:eu-repo/grantAgreement/EC/856709
dc.type.version acceptedVersion
dc.relation.eventdate 2021-12-07
dc.relation.eventplace Madrid, Spain
dc.relation.eventtitle 2021 IEEE Global Communications Conference (GLOBECOM)
dc.relation.eventtype proceeding
dc.identifier.publicationfirstpage 1
dc.identifier.publicationlastpage 6
dc.identifier.publicationtitle 2021 IEEE Global Communications Conference (GLOBECOM)
dc.contributor.funder European Commission
dc.contributor.funder Ministerio de Economía y Competitividad (España)
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record