A deep learning strategy for vehicular floating content management

Manzo, Gaetano (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Otalora, Juan Sebastian (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Ajmon Marsan, Marco (IMDEA Networks Institute, Spain; Politecnico di Torino, Italy) ; Rizzo, Gianluca (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis))

Floating Content (FC) is a communication paradigm for the local dissemination of contextualized information through D2D connectivity, in a way which minimizes the use of resources while achieving some specified performance target. Existing approaches to FC dimensioning are based on unrealistic system assumptions that make them, highly inaccurate and overly conservative when applied in realistic settings. In this paper, we present a first step towards the development of a cognitive approach to efficient dynamic management of FC. We propose a deep learning strategy for FC dimensioning, which exploits a Convolutional Neural Network (CNN) to efficiently modulate over time the resources employed by FC in a QoS-aware manner. Numerical evaluations show that our approach achieves a maximum rejection rate of 3%, and resource savings of 37.5% with respect to the benchmark strategy.


Article Type:
scientifique
Faculty:
Economie et Services
School:
HEG-VS
Institute:
Institut Informatique de gestion
Subject(s):
Informatique
Date:
2018-12
Pagination:
pp. 159-162
Published in:
ACM SIGMETRICS performance evaluation review
Numeration (vol. no.):
December 2018, vol. 46, no. 3
DOI:
ISSN:
0163-5999
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2019-11-01, last modified 2019-11-28

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)