Publication:
Bayesian online learning for energy-aware resource orchestration in virtualized RANs

Simple item page
dc.contributor.authorAyala Romero, José A.
dc.contributor.authorGarcia-Saavedra, Andres
dc.contributor.authorCosta-Pérez, Xavier
dc.contributor.authorIosifidis, George
dc.contributor.funderEuropean Commissionen
dc.date.accessioned2022-02-14T11:08:28Z
dc.date.available2022-02-14T11:08:28Z
dc.date.issued2021-05-10
dc.descriptionProceedings of: IEEE International Conference on Computer Communications, 10-13 May 2021, Vancouver, BC, Canada.en
dc.description.abstractRadio Access Network Virtualization (vRAN) will spearhead the quest towards supple radio stacks that adapt to heterogeneous infrastructure: from energy-constrained platforms deploying cells-on-wheels (e.g., drones) or battery-powered cells to green edge clouds. We perform an in-depth experimental analysis of the energy consumption of virtualized Base Stations (vBSs) and render two conclusions: (i) characterizing performance and power consumption is intricate as it depends on human behavior such as network load or user mobility; and (ii) there are many control policies and some of them have non-linear and monotonic relations with power and throughput. Driven by our experimental insights, we argue that machine learning holds the key for vBS control. We formulate two problems and two algorithms: (i) BP-vRAN, which uses Bayesian online learning to balance performance and energy consumption, and (ii) SBP-vRAN, which augments our Bayesian optimization approach with safe controls that maximize performance while respecting hard power constraints. We show that our approaches are data-efficient and have provably performance, which is paramount for carrier-grade vRANs. We demonstrate the convergence and flexibility of our approach and assess its performance using an experimental prototype.en
dc.description.sponsorshipThis work was supported by the European Commission through Grant No. 856709 (5Growth) and Grant No. 101017109 (DAEMON); and by SFI through Grant No. SFI 17/CDA/4760.en
dc.format.extent10
dc.identifier.bibliographicCitationAyala-Romero, J. A., Garcia-Saavedra, A., Costa-Perez, X. & Iosifidis, G. (10-13 May 2021). Bayesian Online Learning for Energy-Aware Resource Orchestration in Virtualized RANs [proceedings]. IEEE INFOCOM 2021 - IEEE Conference on Computer Communications, Vancouver, BC, Canada.en
dc.identifier.doihttps://doi.org/10.1109/INFOCOM42981.2021.9488845
dc.identifier.isbn978-1-6654-0325-2 (Electronic)
dc.identifier.isbn978-1-6654-3131-6 (Print on Demand(PoD))
dc.identifier.issn2641-9874 (Electronic)
dc.identifier.issn0743-166X (Print on Demand(PoD))
dc.identifier.publicationfirstpage1
dc.identifier.publicationlastpage10
dc.identifier.publicationtitleIEEE INFOCOM 2021 - IEEE Conference on Computer Communicationsen
dc.identifier.urihttps://hdl.handle.net/10016/34113
dc.language.isoengen
dc.publisherIEEEen
dc.relation.eventdate2021-05-10
dc.relation.eventplaceVancouveren
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/856709
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/101017109
dc.rights© 2021 IEEE.en
dc.rights.accessRightsopen accessen
dc.subject.ecienciaTelecomunicaciones
dc.subject.otherEnergy consumptionen
dc.subject.otherBase stationsen
dc.subject.otherPower demanden
dc.subject.otherMachine learningen
dc.subject.otherTelecommunication trafficen
dc.subject.otherThroughputen
dc.subject.otherBayes methodsen
dc.titleBayesian online learning for energy-aware resource orchestration in virtualized RANsen
dc.typeconference proceedings*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Bayesian_IEEE-INFOCOM_2021_ps.pdf
Size:
1.41 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
OpenAIRE: Open Access Infrastructure for Research in Europe