Predictive Migration Performance in Vehicular Edge Computing Environments
Advanced learning algorithms for autonomous driving require lots of processing and storage power, which puts a strain on vehicles’ computing resources. Using a combination of 5G network connectivity with ultra-high bandwidth and low latency together with extra computing power located at the edge of...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/3/944 |
id |
doaj-5640b5da35e84c1298b041c81dc66da3 |
---|---|
record_format |
Article |
spelling |
doaj-5640b5da35e84c1298b041c81dc66da32021-01-22T00:01:20ZengMDPI AGApplied Sciences2076-34172021-01-011194494410.3390/app11030944Predictive Migration Performance in Vehicular Edge Computing EnvironmentsKatja Gilly0Sonja Filiposka1Salvador Alcaraz2Department of Computer Engineering, Miguel Hernandez University of Elche, 03202 Elche, SpainFaculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Rugjer Boshkovikj 16, 1000 Skopje, North MacedoniaDepartment of Computer Engineering, Miguel Hernandez University of Elche, 03202 Elche, SpainAdvanced learning algorithms for autonomous driving require lots of processing and storage power, which puts a strain on vehicles’ computing resources. Using a combination of 5G network connectivity with ultra-high bandwidth and low latency together with extra computing power located at the edge of the network can help extend the capabilities of vehicular networks. However, due to the high mobility, it is essential that the offloaded services are migrated so that they are always in close proximity to the requester. Using proactive migration techniques ensures minimum latency for high service quality. However, predicting the next edge server to migrate comes with an error that can have deteriorating effects on the latency. In this paper, we examine the influence of mobility prediction errors on edge service migration performances in terms of latency penalty using a large-scale urban vehicular simulation. Our results show that the average service delay increases almost linearly with the migration prediction error, with 20% error yielding almost double service latency.https://www.mdpi.com/2076-3417/11/3/944edge computingmigrationspredictive modellingurban vehicular scenarios |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Katja Gilly Sonja Filiposka Salvador Alcaraz |
spellingShingle |
Katja Gilly Sonja Filiposka Salvador Alcaraz Predictive Migration Performance in Vehicular Edge Computing Environments Applied Sciences edge computing migrations predictive modelling urban vehicular scenarios |
author_facet |
Katja Gilly Sonja Filiposka Salvador Alcaraz |
author_sort |
Katja Gilly |
title |
Predictive Migration Performance in Vehicular Edge Computing Environments |
title_short |
Predictive Migration Performance in Vehicular Edge Computing Environments |
title_full |
Predictive Migration Performance in Vehicular Edge Computing Environments |
title_fullStr |
Predictive Migration Performance in Vehicular Edge Computing Environments |
title_full_unstemmed |
Predictive Migration Performance in Vehicular Edge Computing Environments |
title_sort |
predictive migration performance in vehicular edge computing environments |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-01-01 |
description |
Advanced learning algorithms for autonomous driving require lots of processing and storage power, which puts a strain on vehicles’ computing resources. Using a combination of 5G network connectivity with ultra-high bandwidth and low latency together with extra computing power located at the edge of the network can help extend the capabilities of vehicular networks. However, due to the high mobility, it is essential that the offloaded services are migrated so that they are always in close proximity to the requester. Using proactive migration techniques ensures minimum latency for high service quality. However, predicting the next edge server to migrate comes with an error that can have deteriorating effects on the latency. In this paper, we examine the influence of mobility prediction errors on edge service migration performances in terms of latency penalty using a large-scale urban vehicular simulation. Our results show that the average service delay increases almost linearly with the migration prediction error, with 20% error yielding almost double service latency. |
topic |
edge computing migrations predictive modelling urban vehicular scenarios |
url |
https://www.mdpi.com/2076-3417/11/3/944 |
work_keys_str_mv |
AT katjagilly predictivemigrationperformanceinvehicularedgecomputingenvironments AT sonjafiliposka predictivemigrationperformanceinvehicularedgecomputingenvironments AT salvadoralcaraz predictivemigrationperformanceinvehicularedgecomputingenvironments |
_version_ |
1724329576851570688 |