Publication:
Reinforced-LSTM Trajectory Prediction-driven Dynamic Service Migration: A Case Study

Simple item page
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid0000-0002-3189-0291
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid0000-0002-1949-6857
cris.virtual.author-orcid0000-0001-5968-7108
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcidd4643203-2136-49f3-a65b-e52a2e1f8301
cris.virtualsource.author-orcid79944c71-55bf-455d-a804-1a3d357bd5a8
cris.virtualsource.author-orcidabad467d-6241-4f58-a678-d34aa725ac00
cris.virtualsource.author-orcida6cc6f29-3c96-4654-9d50-c1ead6d018bb
cris.virtualsource.author-orcidde7b830f-bace-491e-b726-2d89bc625261
cris.virtualsource.author-orcid65f054ad-ee65-4a22-a3be-990293fcb596
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
dc.contributor.authorZhao, Zhongliang
dc.contributor.authorEmami, Negar
dc.contributor.authorMelo dos Santos, Hugo Leonardo
dc.contributor.authorde Sousa Pacheco, Lucas
dc.contributor.authorKarimzadeh Motallebiazar, Mostafa
dc.contributor.authorBraun, Torsten
dc.contributor.authorBraud, Arnaud
dc.contributor.authorRadier, Benoit
dc.contributor.authorTamagnan, Philippe
dc.date.accessioned2024-10-05T12:11:54Z
dc.date.available2024-10-05T12:11:54Z
dc.date.issued2022-04-25
dc.description.abstractMobility prediction is an essential enabler to provide intelligent network systems and services in the upcoming B5G/6G era. Artificial Intelligence (AI) models such as Long Short Term Memory (LSTM) offer great performance at predicting users’ locations. However, model training can be time-consuming, which brings obstacles to practical applications. In this article, we present a mobility predictor based on Long Short Term Memory (LSTM), which is a variant of Recurrent Neural Networks (RNN) to reduce the network traffic for the sake of service migration improvement and handover (HO) optimization. To speed up the model convergence rate, we employ a Reinforcement Learning (RL) technique to automate the selection procedure of the best neural network architecture. To further accelerate the RL environmental search procedure, we transfer the architecture knowledge learned from a teacher LSTM to a student LSTM via a Transfer Learning (TL) framework. We propose a HO algorithm and a service migration algorithm based on the proposed LSTM predictor. We deploy the AI models on a mobile edge computing architecture using a real-world dataset collected from Paris, and evaluation results prove the efficiency of the predictor, and its impacts on improving ping-pong handover, and the service migration performance.
dc.description.numberOfPages15
dc.description.sponsorshipInstitut für Informatik (INF)
dc.identifier.doi10.48350/155232
dc.identifier.publisherDOI10.1109/TNSE.2022.3169786
dc.identifier.urihttps://boris-portal.unibe.ch/handle/20.500.12422/56574
dc.language.isoen
dc.publisherIEEE
dc.relation.ispartofTransactions on Network Science and Engineering
dc.relation.organizationDCD5A442BE95E17DE0405C82790C4DE2
dc.relation.organizationDCD5A442C2AFE17DE0405C82790C4DE2
dc.subjectService migration
dc.subjecthandover optimization
dc.subjecttrajectory prediction
dc.subjectrecurrent neural network
dc.subjectreinforcement learning
dc.subjecttransfer learning
dc.subject.ddc000 - Computer science, knowledge & systems
dc.subject.ddc500 - Science::510 - Mathematics
dc.subject.ddc600 - Technology
dc.titleReinforced-LSTM Trajectory Prediction-driven Dynamic Service Migration: A Case Study
dc.typearticle
dspace.entity.typePublication
dspace.file.typetext
dspace.file.typetext
oaire.citation.endPage2802
oaire.citation.issue4
oaire.citation.startPage2786
oaire.citation.volume9
oairecerif.author.affiliationInstitut für Informatik (INF)
oairecerif.author.affiliationInstitut für Informatik (INF)
oairecerif.author.affiliationInstitut für Informatik (INF)
oairecerif.author.affiliationInstitut für Informatik (INF)
oairecerif.author.affiliationInstitut für Informatik (INF)
oairecerif.author.affiliationInstitut für Informatik (INF)
oairecerif.author.affiliation#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation2#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation2#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation2#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation2#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation2#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation2#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation2#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation2#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation2#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation3#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation3#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation3#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation3#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation3#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation3#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation3#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation3#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation3#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation4#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation4#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation4#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation4#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation4#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation4#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation4#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation4#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.author.affiliation4#PLACEHOLDER_PARENT_METADATA_VALUE#
oairecerif.identifier.urlhttps://ieeexplore.ieee.org/document/9762557
unibe.contributor.rolecreator
unibe.contributor.rolecreator
unibe.contributor.rolecreator
unibe.contributor.rolecreator
unibe.contributor.rolecreator
unibe.contributor.rolecreator
unibe.contributor.rolecreator
unibe.contributor.rolecreator
unibe.contributor.rolecreator
unibe.date.licenseChanged2023-09-20 08:08:58
unibe.description.ispublishedpub
unibe.eprints.legacyId155232
unibe.refereedTRUE
unibe.subtype.articlejournal

Files

Original bundle
Now showing 1 - 2 of 2
Name:
IEEE_TNSE_Orange.pdf
Size:
706.35 KB
Format:
Adobe Portable Document Format
File Type:
text
License:
publisher
Content:
accepted
Download
Name:
Reinforced-LSTM_Trajectory_Prediction-Driven_Dynamic_Service_Migration_A_Case_Study__preprint_.pdf
Size:
1.95 MB
Format:
Adobe Portable Document Format
File Type:
text
License:
publisher
Content:
submitted
Download

Collections

Publications