Resource-Aware Federated Hybrid Profiling for Edge Node Selection in Federated Patient Similarity Network
The widespread adoption of edge computing for resource-constrained devices presents challenges in computational straggler issues, primarily due to the heterogeneity of edge node resources. This research addresses these issues by introducing a novel resource-aware federated hybrid profiling approach....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/24/13114 |
| _version_ | 1797382210258468864 |
|---|---|
| author | Alramzana Nujum Navaz Hadeel T. El Kassabi Mohamed Adel Serhani Ezedin S. Barka |
| author_facet | Alramzana Nujum Navaz Hadeel T. El Kassabi Mohamed Adel Serhani Ezedin S. Barka |
| author_sort | Alramzana Nujum Navaz |
| collection | DOAJ |
| description | The widespread adoption of edge computing for resource-constrained devices presents challenges in computational straggler issues, primarily due to the heterogeneity of edge node resources. This research addresses these issues by introducing a novel resource-aware federated hybrid profiling approach. This approach involves classifying edge node resources with relevant performance metrics and leveraging their capabilities to optimize performance and improve Quality of Service (QoS), particularly in real-time eHealth applications. Such paradigms include Federated Patient Similarity Network (FPSN) models that distribute processing at each edge node and fuse the built PSN matrices in the cloud, presenting a unique challenge in terms of optimizing training and inference times, while ensuring efficient and timely updates at the edge nodes. To address this concern, we propose a resource-aware federated hybrid profiling approach that measures the available static and dynamic resources of the edge nodes. By selecting nodes with the appropriate resources, we aim to optimize the FPSN to ensure the highest possible Quality of Service (QoS) for its users. We conducted experiments using edge performance metrics, i.e., accuracy, training convergence, memory and disk usage, execution time, and network statistics. These experiments uniquely demonstrate our work’s contribution to optimizing resource allocation and enhancing the performance of eHealth applications in real-time contexts using edge computing. |
| first_indexed | 2024-03-08T21:02:08Z |
| format | Article |
| id | doaj.art-f02b450e47c74683ba6431a39159ba2a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T21:02:08Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f02b450e47c74683ba6431a39159ba2a2023-12-22T13:51:29ZengMDPI AGApplied Sciences2076-34172023-12-0113241311410.3390/app132413114Resource-Aware Federated Hybrid Profiling for Edge Node Selection in Federated Patient Similarity NetworkAlramzana Nujum Navaz0Hadeel T. El Kassabi1Mohamed Adel Serhani2Ezedin S. Barka3Department of Computer Science and Software Engineering, College of Information Technology, UAE University, Al Ain P.O. Box 15551, United Arab EmiratesFaculty of Applied Sciences & Technology, Humber College Institute of Technology & Advanced Learning, Toronto, ON M9W 5L7, CanadaCollege of Computing and Informatics, Sharjah University, Sharjah P.O. Box 27272, United Arab EmiratesDepartment of Information Systems and Security, College of Information Technology, UAE University, Al Ain P.O. Box 15551, United Arab EmiratesThe widespread adoption of edge computing for resource-constrained devices presents challenges in computational straggler issues, primarily due to the heterogeneity of edge node resources. This research addresses these issues by introducing a novel resource-aware federated hybrid profiling approach. This approach involves classifying edge node resources with relevant performance metrics and leveraging their capabilities to optimize performance and improve Quality of Service (QoS), particularly in real-time eHealth applications. Such paradigms include Federated Patient Similarity Network (FPSN) models that distribute processing at each edge node and fuse the built PSN matrices in the cloud, presenting a unique challenge in terms of optimizing training and inference times, while ensuring efficient and timely updates at the edge nodes. To address this concern, we propose a resource-aware federated hybrid profiling approach that measures the available static and dynamic resources of the edge nodes. By selecting nodes with the appropriate resources, we aim to optimize the FPSN to ensure the highest possible Quality of Service (QoS) for its users. We conducted experiments using edge performance metrics, i.e., accuracy, training convergence, memory and disk usage, execution time, and network statistics. These experiments uniquely demonstrate our work’s contribution to optimizing resource allocation and enhancing the performance of eHealth applications in real-time contexts using edge computing.https://www.mdpi.com/2076-3417/13/24/13114federated learningfederated resource profilingdeep learningedge computingworkload profilePSN |
| spellingShingle | Alramzana Nujum Navaz Hadeel T. El Kassabi Mohamed Adel Serhani Ezedin S. Barka Resource-Aware Federated Hybrid Profiling for Edge Node Selection in Federated Patient Similarity Network Applied Sciences federated learning federated resource profiling deep learning edge computing workload profile PSN |
| title | Resource-Aware Federated Hybrid Profiling for Edge Node Selection in Federated Patient Similarity Network |
| title_full | Resource-Aware Federated Hybrid Profiling for Edge Node Selection in Federated Patient Similarity Network |
| title_fullStr | Resource-Aware Federated Hybrid Profiling for Edge Node Selection in Federated Patient Similarity Network |
| title_full_unstemmed | Resource-Aware Federated Hybrid Profiling for Edge Node Selection in Federated Patient Similarity Network |
| title_short | Resource-Aware Federated Hybrid Profiling for Edge Node Selection in Federated Patient Similarity Network |
| title_sort | resource aware federated hybrid profiling for edge node selection in federated patient similarity network |
| topic | federated learning federated resource profiling deep learning edge computing workload profile PSN |
| url | https://www.mdpi.com/2076-3417/13/24/13114 |
| work_keys_str_mv | AT alramzananujumnavaz resourceawarefederatedhybridprofilingforedgenodeselectioninfederatedpatientsimilaritynetwork AT hadeeltelkassabi resourceawarefederatedhybridprofilingforedgenodeselectioninfederatedpatientsimilaritynetwork AT mohamedadelserhani resourceawarefederatedhybridprofilingforedgenodeselectioninfederatedpatientsimilaritynetwork AT ezedinsbarka resourceawarefederatedhybridprofilingforedgenodeselectioninfederatedpatientsimilaritynetwork |