We study average performance and costs for routing service requests in a virtualized environment, where either the MEC or the Cloud can serve user's requests. Employing a simple yet precise analytical model validated via simulation, we focus on latency, service request losses, energy consumption, and provider utility. The model is very effective in providing insight and guidelines for setting up server selection strategies with different characteristics (e.g., energy consumption, penalties, etc.) and performance requirements. In particular, our results show that the MEC is latency-efficient but incurs higher costs than Cloud, and then, to make its use sustainable, it is desirable that the MEC server is powered with renewable source energy.

Efficiency of Virtualization over MEC plus Cloud

Paolo Castagno;Matteo Sereno
2021-01-01

Abstract

We study average performance and costs for routing service requests in a virtualized environment, where either the MEC or the Cloud can serve user's requests. Employing a simple yet precise analytical model validated via simulation, we focus on latency, service request losses, energy consumption, and provider utility. The model is very effective in providing insight and guidelines for setting up server selection strategies with different characteristics (e.g., energy consumption, penalties, etc.) and performance requirements. In particular, our results show that the MEC is latency-efficient but incurs higher costs than Cloud, and then, to make its use sustainable, it is desirable that the MEC server is powered with renewable source energy.
2021
WEEE 2021 : 2nd International Workshop on Energy-Efficient Learning at the Edge
Virtual Torino
Jun 28, 2021
Proceedings of WEEE-2021 workshop - workshop satellite di e-Energy 2021
ACM
1
6
https://dl.acm.org/doi/10.1145/3447555.3465325
Network performance analysis, Cloud computing
Vincenzo Mancuso, Paolo Castagno, Matteo Sereno
File in questo prodotto:
File Dimensione Formato  
MEC_or_CLOUD_goes_green__WEEE_.pdf

Open Access dal 26/05/2023

Tipo di file: PREPRINT (PRIMA BOZZA)
Dimensione 3.64 MB
Formato Adobe PDF
3.64 MB Adobe PDF Visualizza/Apri

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/2318/1795181
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact