In 5G research, it is traditionally assumed that vertical industries (a.k.a verticals) set the performance requirements for the services they want to offer to mobile users, and the mobile operators alone are in charge of orchestrating their resources so as to meet such requirements. Motivated by the observation that successful orchestration requires reliable traffic predictions, in this paper we investigate the effects of having the verticals, instead of the mobile operators, performing such predictions. Leveraging a real-world, large-scale, crowd-sourced trace, we find that involving the verticals in the prediction process reduces the prediction errors and improves the quality of the resulting orchestration decisions.

5G Traffic Forecasting: If Verticals and Mobile Operators Cooperate

Malandrino Francesco;Chiasserini Carla Fabiana
2019

Abstract

In 5G research, it is traditionally assumed that vertical industries (a.k.a verticals) set the performance requirements for the services they want to offer to mobile users, and the mobile operators alone are in charge of orchestrating their resources so as to meet such requirements. Motivated by the observation that successful orchestration requires reliable traffic predictions, in this paper we investigate the effects of having the verticals, instead of the mobile operators, performing such predictions. Leveraging a real-world, large-scale, crowd-sourced trace, we find that involving the verticals in the prediction process reduces the prediction errors and improves the quality of the resulting orchestration decisions.
2019
Istituto di Elettronica e di Ingegneria dell'Informazione e delle Telecomunicazioni - IEIIT
Inglese
IEEE/IFIP Wireless On-demand Network systems and Services Conference (WONS)
International Federation for Information Processing (IFIP)
IEEE
New York
Laxenburg
AUSTRIA
STATI UNITI D'AMERICA
Sì, ma tipo non specificato
2019
5G
verticals
2
none
Malandrino, Francesco; Chiasserini, Carla Fabiana
273
info:eu-repo/semantics/conferenceObject
04 Contributo in convegno::04.01 Contributo in Atti di convegno
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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: https://hdl.handle.net/20.500.14243/352893
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact