Unsupervised learning for C-RAN power control and power allocation

This letter applies a feedforward neural network trained in an unsupervised fashion to the problem of optimizing the transmit powers in centralized radio access networks operating on a cell-free basis. Both uplink and downlink are considered. Various objectives are entertained, some leading to conve...

Full description

Bibliographic Details
Authors: Nikbakht Silab, Rasoul, Jonsson, Anders, 1973-, Lozano Solsona, Angel
Format: article
Status:Versión aceptada para publicación
Publication Date:2021
Country:España
Institution:Universitat Pompeu Fabra
Repository:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/47547
Online Access:http://hdl.handle.net/10230/47547
http://dx.doi.org/10.1109/LCOMM.2020.3027991
Access Level:Open access
Keyword:Neural networks
Unsupervised learning
Cell-free networks
Ultradense networks
Power control
Power allocation
C-RAN
id ES_b53a3330521920e68cdbc75cee0bc596
oai_identifier_str oai:repositori.upf.edu:10230/47547
network_acronym_str ES
network_name_str España
repository_id_str
spelling Unsupervised learning for C-RAN power control and power allocationNikbakht Silab, RasoulJonsson, Anders, 1973-Lozano Solsona, AngelNeural networksUnsupervised learningCell-free networksUltradense networksPower controlPower allocationC-RANThis letter applies a feedforward neural network trained in an unsupervised fashion to the problem of optimizing the transmit powers in centralized radio access networks operating on a cell-free basis. Both uplink and downlink are considered. Various objectives are entertained, some leading to convex formulations and some that do not. In all cases, the performance of the proposed procedure is very satisfactory and, in terms of computational cost, the scalability is manifestly superior to that of convex solvers. Moreover, the optimization relies on directly measurable channel gains, with no need for user location information.Work supported by the European Research Council under the H2020 Framework Programme/ERC grant 694974, by the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502), and by the ICREA Academia program. Parts of this paper were presented at the 2019 IEEE Int’l Symp. Personal, Indoor & Mobile Radio Communications and at the 2020 IEEE Int’l Conf. Communications.Institute of Electrical and Electronics Engineers (IEEE)202120212021info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/47547http://dx.doi.org/10.1109/LCOMM.2020.3027991reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésIEEE Communications Letters. 2021;25(3):687-91info:eu-repo/grantAgreement/EC/H2020/694974© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/LCOMM.2020.3027991info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/475472026-06-12T07:21:37Z
dc.title.none.fl_str_mv Unsupervised learning for C-RAN power control and power allocation
title Unsupervised learning for C-RAN power control and power allocation
spellingShingle Unsupervised learning for C-RAN power control and power allocation
Nikbakht Silab, Rasoul
Neural networks
Unsupervised learning
Cell-free networks
Ultradense networks
Power control
Power allocation
C-RAN
title_short Unsupervised learning for C-RAN power control and power allocation
title_full Unsupervised learning for C-RAN power control and power allocation
title_fullStr Unsupervised learning for C-RAN power control and power allocation
title_full_unstemmed Unsupervised learning for C-RAN power control and power allocation
title_sort Unsupervised learning for C-RAN power control and power allocation
dc.creator.none.fl_str_mv Nikbakht Silab, Rasoul
Jonsson, Anders, 1973-
Lozano Solsona, Angel
author Nikbakht Silab, Rasoul
author_facet Nikbakht Silab, Rasoul
Jonsson, Anders, 1973-
Lozano Solsona, Angel
author_role author
author2 Jonsson, Anders, 1973-
Lozano Solsona, Angel
author2_role author
author
dc.subject.none.fl_str_mv Neural networks
Unsupervised learning
Cell-free networks
Ultradense networks
Power control
Power allocation
C-RAN
topic Neural networks
Unsupervised learning
Cell-free networks
Ultradense networks
Power control
Power allocation
C-RAN
description This letter applies a feedforward neural network trained in an unsupervised fashion to the problem of optimizing the transmit powers in centralized radio access networks operating on a cell-free basis. Both uplink and downlink are considered. Various objectives are entertained, some leading to convex formulations and some that do not. In all cases, the performance of the proposed procedure is very satisfactory and, in terms of computational cost, the scalability is manifestly superior to that of convex solvers. Moreover, the optimization relies on directly measurable channel gains, with no need for user location information.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021
2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/47547
http://dx.doi.org/10.1109/LCOMM.2020.3027991
url http://hdl.handle.net/10230/47547
http://dx.doi.org/10.1109/LCOMM.2020.3027991
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv IEEE Communications Letters. 2021;25(3):687-91
info:eu-repo/grantAgreement/EC/H2020/694974
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417326273626112
score 15,812429

Similar Items