The advent of multi access edge computing (MEC) will enable latency-critical applications such as cooperative adaptive cruise control (also known as platooning) to be hosted at the edge of the network. MEC-based platooning will leverage the coverage of the cellular infrastructure to enable inter-vehicular communications, potentially overcoming crucial problems of vehicular ad-hoc networks (VANETs) such as non-trivial packet loss rates. However, MEC-based platooning will require the controller to be migrated to the most suitable positions at the network edge, in order to maintain low-latency connections as the platoon moves. In this paper, we propose a context-aware Q-learning algorithm that carries out such migrations only as often as is necessary, and thereby reduces the additional delays implicit in application migration across MEC hosts. When compared to the state-of-the-art approach named FollowME, our scheme exhibits better compliance of vehicle speed and spacing values to preset targets, as well as a reduced statistical dispersion.
Closer than Close: MEC-Assisted Platooning with Intelligent Controller Migration / Ayimba, Constantine; Segata, Michele; Casari, Paolo; Mancuso, Vincenzo. - ELETTRONICO. - (2021), pp. 23-32. (Intervento presentato al convegno MSWiM tenutosi a Alicante, Spagna nel Novembre 2021) [10.1145/3479239.3485681].
Closer than Close: MEC-Assisted Platooning with Intelligent Controller Migration
Michele Segata;Paolo Casari;
2021-01-01
Abstract
The advent of multi access edge computing (MEC) will enable latency-critical applications such as cooperative adaptive cruise control (also known as platooning) to be hosted at the edge of the network. MEC-based platooning will leverage the coverage of the cellular infrastructure to enable inter-vehicular communications, potentially overcoming crucial problems of vehicular ad-hoc networks (VANETs) such as non-trivial packet loss rates. However, MEC-based platooning will require the controller to be migrated to the most suitable positions at the network edge, in order to maintain low-latency connections as the platoon moves. In this paper, we propose a context-aware Q-learning algorithm that carries out such migrations only as often as is necessary, and thereby reduces the additional delays implicit in application migration across MEC hosts. When compared to the state-of-the-art approach named FollowME, our scheme exhibits better compliance of vehicle speed and spacing values to preset targets, as well as a reduced statistical dispersion.File | Dimensione | Formato | |
---|---|---|---|
MSWiM_Platooning_Ayimba_2021.pdf
accesso aperto
Descrizione: Articolo principale
Tipologia:
Post-print referato (Refereed author’s manuscript)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.87 MB
Formato
Adobe PDF
|
1.87 MB | Adobe PDF | Visualizza/Apri |
3479239.3485681.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
2.37 MB
Formato
Adobe PDF
|
2.37 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione