vrAIn: a deep learning approach tailoring computing and radio resources in virtualized RANs

e-Archivo Repository

Show simple item record

dc.contributor.author Ayala Romero, Jose A.
dc.contributor.author Garcia Saavedra, Andres
dc.contributor.author Gramaglia, Marco
dc.contributor.author Costa Pérez, Xavier
dc.contributor.author Banchs Roca, Albert
dc.contributor.author Alcaraz, Juan J.
dc.date.accessioned 2019-10-30T11:11:00Z
dc.date.available 2019-10-30T11:11:00Z
dc.date.issued 2019-09-05
dc.identifier.bibliographicCitation Proceedings of the 25th Annual International Conference on Mobile Computing and Networking (MobiCom'19). New York: ACM, cop. 2019. Article nº 30, [16] pp.
dc.identifier.isbn 978-1-4503-6169-9
dc.identifier.uri http://hdl.handle.net/10016/29093
dc.description Proceeding of: 25th Annual International Conference on Mobile Computing and Networking (MobiCom'19), October 21-25, 2019, Los Cabos, Mexico.
dc.description.abstract The virtualization of radio access networks (vRAN) is the last milestone in the NFV revolution. However, the complex dependencies between computing and radio resources make vRAN resource control particularly daunting. We present vrAIn, a dynamic resource controller for vRANs based on deep reinforcement learning. First, we use an autoencoder to project high-dimensional context data (traffic and signal quality patterns) into a latent representation. Then, we use a deep deterministic policy gradient (DDPG) algorithm based on an actor-critic neural network structure and a classifier to map (encoded) contexts into resource control decisions. We have implemented vrAIn using an open-source LTE stack over different platforms. Our results show that vrAIn successfully derives appropriate compute and radio control actions irrespective of the platform and context: (i) it provides savings in computational capacity of up to 30% over CPU-unaware methods; (ii) it improves the probability of meeting QoS targets by 25% over static allocation policies using similar CPU resources in average; (iii) upon CPU capacity shortage, it improves throughput performance by 25% over state-of-the-art schemes; and (iv) it performs close to optimal policies resulting from an offline oracle. To the best of our knowledge, this is the first work that thoroughly studies the computational behavior of vRANs, and the first approach to a model-free solution that does not need to assume any particular vRAN platform or system conditions.
dc.description.sponsorship The work of University Carlos III of Madrid was supported by H2020 5GMoNArch project (grant agreement no. 761445) and H2020 5G-TOURS project (grant agreement no. 856950). The work of NEC Laboratories Europe was supported by H2020 5GTRANSFORMER project (grant agreement no. 761536) and 5GROWTH project (grant agreement no. 856709). The work of University of Cartagena was supported by Grant AEI/FEDER TEC2016-76465-C2-1-R (AIM) and Grant FPU14/03701.
dc.format.extent 16
dc.language.iso eng
dc.publisher Association for Computing Machinery
dc.rights © 2019 Association for Computing Machinery.
dc.subject.other RAN virtualization
dc.subject.other Resource management
dc.subject.other Machine learning
dc.subject.other Network algorithms
dc.subject.other Mobile networks
dc.title vrAIn: a deep learning approach tailoring computing and radio resources in virtualized RANs
dc.type conferenceObject
dc.description.status Publicado
dc.subject.eciencia Telecomunicaciones
dc.identifier.doi https://doi.org/10.1145/3300061.3345431
dc.rights.accessRights openAccess
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/761445/5G-MoNArch
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/856950/5G-TOURS
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/761536/5G Transformer
dc.relation.projectID info:eu-repo/grant/Agreeement/EC/H2020/856709/5GROWTH
dc.type.version acceptedVersion
dc.relation.eventdate October 21-25, 2019
dc.relation.eventnumber 25
dc.relation.eventplace Los Cabos, México.
dc.relation.eventtitle Annual International Conference on Mobile Computing and Networking (MobiCom'19)
dc.relation.eventtype proceeding
dc.identifier.publicationtitle Proceedings of the 25th Annual International Conference on Mobile Computing and Networking (MobiCom'19)
dc.identifier.uxxi CC/0000029938
dc.contributor.funder European Commission
 Find Full text

Files in this item

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


The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record