Cloudlet Federation Based Context-Aware Federated Learning Approach

A Cloudlet federation can be beneficial to overcome the latency and resource scarcity challenges in a cloudlet deployment altogether, as a task can run on a cloudlet within the federation, sharing resources of member cloudlets. Nonetheless, the cloudlet federation is not context-aware in terms of la...

Full description

Saved in:
Bibliographic Details
Main Authors: Sana Latif, Muhammad Ziad Nayyer, Imran Raza, Syed Asad Hussain, M. Hasan Jamal, Soojung Hur, Imran Ashraf
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9912422/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850209140614365184
author Sana Latif
Muhammad Ziad Nayyer
Imran Raza
Syed Asad Hussain
M. Hasan Jamal
Soojung Hur
Imran Ashraf
author_facet Sana Latif
Muhammad Ziad Nayyer
Imran Raza
Syed Asad Hussain
M. Hasan Jamal
Soojung Hur
Imran Ashraf
author_sort Sana Latif
collection DOAJ
description A Cloudlet federation can be beneficial to overcome the latency and resource scarcity challenges in a cloudlet deployment altogether, as a task can run on a cloudlet within the federation, sharing resources of member cloudlets. Nonetheless, the cloudlet federation is not context-aware in terms of latency, so to perform federated learning in cloudlet federation, the selection of a resource-efficient deep learning model is challenging. Additionally, the accuracy of a deep learning model can be affected if end-user devices are unreliable and provide incorrect data for training deep learning models at the cloudlets. Thus, resource and context-aware federated learning solutions are required for accurate and latency-critical applications such as COVID-19 detection using X-ray images. This paper presents a novel context-aware cloudlet federated learning solution for COVID-19 detection that monitors the resources of a cloudlet using a broker thereby minimizing latency without any impact on the accuracy of the deep learning model. Results show that the proposed model reduces the latency by 5% and increases the accuracy by 5% as compared to the state-of-the-art conventional federated learning approach.
format Article
id doaj-art-aa2d9193a73546f7b60bc99d6a394a50
institution OA Journals
issn 2169-3536
language English
publishDate 2022-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-aa2d9193a73546f7b60bc99d6a394a502025-08-20T02:10:06ZengIEEEIEEE Access2169-35362022-01-011010915310916610.1109/ACCESS.2022.32125509912422Cloudlet Federation Based Context-Aware Federated Learning ApproachSana Latif0https://orcid.org/0000-0002-6213-3576Muhammad Ziad Nayyer1https://orcid.org/0000-0001-6014-4397Imran Raza2https://orcid.org/0000-0003-3118-4634Syed Asad Hussain3https://orcid.org/0000-0002-8264-7857M. Hasan Jamal4https://orcid.org/0000-0002-0114-0887Soojung Hur5Imran Ashraf6https://orcid.org/0000-0002-8271-6496Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Lahore, PakistanDepartment of Computer Science, GIFT University, Gujranwala, PakistanDepartment of Computer Science, COMSATS University Islamabad, Lahore Campus, Lahore, PakistanDepartment of Computer Science, COMSATS University Islamabad, Lahore Campus, Lahore, PakistanDepartment of Computer Science, COMSATS University Islamabad, Lahore Campus, Lahore, PakistanDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan, South KoreaDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan, South KoreaA Cloudlet federation can be beneficial to overcome the latency and resource scarcity challenges in a cloudlet deployment altogether, as a task can run on a cloudlet within the federation, sharing resources of member cloudlets. Nonetheless, the cloudlet federation is not context-aware in terms of latency, so to perform federated learning in cloudlet federation, the selection of a resource-efficient deep learning model is challenging. Additionally, the accuracy of a deep learning model can be affected if end-user devices are unreliable and provide incorrect data for training deep learning models at the cloudlets. Thus, resource and context-aware federated learning solutions are required for accurate and latency-critical applications such as COVID-19 detection using X-ray images. This paper presents a novel context-aware cloudlet federated learning solution for COVID-19 detection that monitors the resources of a cloudlet using a broker thereby minimizing latency without any impact on the accuracy of the deep learning model. Results show that the proposed model reduces the latency by 5% and increases the accuracy by 5% as compared to the state-of-the-art conventional federated learning approach.https://ieeexplore.ieee.org/document/9912422/Cloudlet federationfederated learningedge computingcloud computing
spellingShingle Sana Latif
Muhammad Ziad Nayyer
Imran Raza
Syed Asad Hussain
M. Hasan Jamal
Soojung Hur
Imran Ashraf
Cloudlet Federation Based Context-Aware Federated Learning Approach
IEEE Access
Cloudlet federation
federated learning
edge computing
cloud computing
title Cloudlet Federation Based Context-Aware Federated Learning Approach
title_full Cloudlet Federation Based Context-Aware Federated Learning Approach
title_fullStr Cloudlet Federation Based Context-Aware Federated Learning Approach
title_full_unstemmed Cloudlet Federation Based Context-Aware Federated Learning Approach
title_short Cloudlet Federation Based Context-Aware Federated Learning Approach
title_sort cloudlet federation based context aware federated learning approach
topic Cloudlet federation
federated learning
edge computing
cloud computing
url https://ieeexplore.ieee.org/document/9912422/
work_keys_str_mv AT sanalatif cloudletfederationbasedcontextawarefederatedlearningapproach
AT muhammadziadnayyer cloudletfederationbasedcontextawarefederatedlearningapproach
AT imranraza cloudletfederationbasedcontextawarefederatedlearningapproach
AT syedasadhussain cloudletfederationbasedcontextawarefederatedlearningapproach
AT mhasanjamal cloudletfederationbasedcontextawarefederatedlearningapproach
AT soojunghur cloudletfederationbasedcontextawarefederatedlearningapproach
AT imranashraf cloudletfederationbasedcontextawarefederatedlearningapproach