Open AccessCloudlet Federation Based Context-Aware Federated Learning Approach
Author(s) -
Sana Latif,
Muhammad Ziad Nayyer,
Imran Raza,
Syed Asad Hussain,
M. Hasan Jamal,
Soojung Hur,
Imran Ashraf
Publication year - 2022
Publication title -
ieee access
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.587
H-Index - 127
ISSN - 2169-3536
DOI - 10.1109/access.2022.3212550
Subject(s) - aerospace , bioengineering , communication, networking and broadcast technologies , components, circuits, devices and systems , computing and processing , engineered materials, dielectrics and plasmas , engineering profession , fields, waves and electromagnetics , general topics for engineers , geoscience , nuclear engineering , photonics and electrooptics , power, energy and industry applications , robotics and control systems , signal processing and analysis , transportation
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.