This paper addresses the use of machine learning techniques for the determination of subgroups within 5G networks. Currently, the burden of determining the subgroups falls uniquely on the gNB. The aim of this work is to lighten the computation burden of the gNB in estimating the evaluation of the position and mobility of users, with the ultimate aim of determining the optimal modulation and coding scheme (MCS). This work proposes an innovative approach based on machine learning techniques that are interposed among user and gNB, helping the latter to determine the network configuration. The results obtained show how direct communication between UEs and neural network speeds up the determination of the MCS and the allocation of resources to subgroups within 5G technology.

Using user's position to improve video multicast subgrouping in 5G NR

Anedda, M.;Fadda, M.;Giusto, D. D.;Murroni, M.
2021

Abstract

This paper addresses the use of machine learning techniques for the determination of subgroups within 5G networks. Currently, the burden of determining the subgroups falls uniquely on the gNB. The aim of this work is to lighten the computation burden of the gNB in estimating the evaluation of the position and mobility of users, with the ultimate aim of determining the optimal modulation and coding scheme (MCS). This work proposes an innovative approach based on machine learning techniques that are interposed among user and gNB, helping the latter to determine the network configuration. The results obtained show how direct communication between UEs and neural network speeds up the determination of the MCS and the allocation of resources to subgroups within 5G technology.
978-1-6654-4908-3
5G New Radio & New Core, Machine learning, Channel modelling & Simulation, Multicast Video Delivery, Subgrouping, UE position, Mobile Edge Computing (MEC).
File in questo prodotto:
File Dimensione Formato  
Anedda et al. - 2021 - Using user's position to improve video multicast s.pdf

Solo gestori archivio

Tipologia: versione post-print
Dimensione 798.13 kB
Formato Adobe PDF
798.13 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11584/319629
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact