Details

Autor(en) / Beteiligte

• Latif, Sana
• Nayyer, Muhammad Ziad
• Raza, Imran
• Hussain, Syed Asad
• Jamal, M. Hasan
• Hur, Soojung
• Ashraf, Imran

Titel

Cloudlet Federation Based Context-Aware Federated Learning Approach

Ist Teil von

• IEEE access, 2022, Vol.10, p.109153-109166

Ort / Verlag

Piscataway: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)

Erscheinungsjahr

2022

Quelle

EZB Electronic Journals Library

Beschreibungen/Notizen

• 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.