Optimization algorithm of UAV‐assisted federated learning resources based on wireless energy harvesting
Abstract Federated learning (FL) enhances data privacy and security by enabling multiple terminals to collaboratively train a global model without transferring data to a central location. To tackle the challenges of limited terrestrial communication resources and device energy in FL, a UAV‐assisted...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | IET Communications |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cmu2.12857 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846145932435914752 |
|---|---|
| author | Youhan Yuan Qi Zhu |
| author_facet | Youhan Yuan Qi Zhu |
| author_sort | Youhan Yuan |
| collection | DOAJ |
| description | Abstract Federated learning (FL) enhances data privacy and security by enabling multiple terminals to collaboratively train a global model without transferring data to a central location. To tackle the challenges of limited terrestrial communication resources and device energy in FL, a UAV‐assisted federated learning and energy collection resource optimization algorithm is proposed. This algorithm harvests the working energy of FL terminals from radio frequency signals transmitted by the UAV via wireless energy collection. Considering energy causality and limited resources, we formulate a problem aimed at minimizing the completion time of FL training tasks. As this problem is NP‐hard, we initially employ a greedy algorithm to optimize the UAV's position, then decompose it into three sub‐problems: computing resources, power control, and bandwidth allocation. We derive and establish the optimization objective function for computing resources as convex, obtaining the expression for optimal computing resources. The Brent algorithm, based on golden section interpolation, iteratively solves the power distribution sub‐problem, while the Lagrange‐quasi‐Newton algorithm optimizes bandwidth allocation for each user. Simulation results demonstrate that the proposed algorithm effectively reduces training completion time while maintaining training quality. |
| format | Article |
| id | doaj-art-fcc11f7adf77461bac094a094875d890 |
| institution | Kabale University |
| issn | 1751-8628 1751-8636 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Communications |
| spelling | doaj-art-fcc11f7adf77461bac094a094875d8902024-12-02T05:06:40ZengWileyIET Communications1751-86281751-86362024-12-0118191621163110.1049/cmu2.12857Optimization algorithm of UAV‐assisted federated learning resources based on wireless energy harvestingYouhan Yuan0Qi Zhu1College of Telecommunications and Information Engineering NJUPT Nanjing ChinaCollege of Telecommunications and Information Engineering NJUPT Nanjing ChinaAbstract Federated learning (FL) enhances data privacy and security by enabling multiple terminals to collaboratively train a global model without transferring data to a central location. To tackle the challenges of limited terrestrial communication resources and device energy in FL, a UAV‐assisted federated learning and energy collection resource optimization algorithm is proposed. This algorithm harvests the working energy of FL terminals from radio frequency signals transmitted by the UAV via wireless energy collection. Considering energy causality and limited resources, we formulate a problem aimed at minimizing the completion time of FL training tasks. As this problem is NP‐hard, we initially employ a greedy algorithm to optimize the UAV's position, then decompose it into three sub‐problems: computing resources, power control, and bandwidth allocation. We derive and establish the optimization objective function for computing resources as convex, obtaining the expression for optimal computing resources. The Brent algorithm, based on golden section interpolation, iteratively solves the power distribution sub‐problem, while the Lagrange‐quasi‐Newton algorithm optimizes bandwidth allocation for each user. Simulation results demonstrate that the proposed algorithm effectively reduces training completion time while maintaining training quality.https://doi.org/10.1049/cmu2.12857bandwidth allocationenergy consumptionfederated learningfrequency allocationpower control |
| spellingShingle | Youhan Yuan Qi Zhu Optimization algorithm of UAV‐assisted federated learning resources based on wireless energy harvesting IET Communications bandwidth allocation energy consumption federated learning frequency allocation power control |
| title | Optimization algorithm of UAV‐assisted federated learning resources based on wireless energy harvesting |
| title_full | Optimization algorithm of UAV‐assisted federated learning resources based on wireless energy harvesting |
| title_fullStr | Optimization algorithm of UAV‐assisted federated learning resources based on wireless energy harvesting |
| title_full_unstemmed | Optimization algorithm of UAV‐assisted federated learning resources based on wireless energy harvesting |
| title_short | Optimization algorithm of UAV‐assisted federated learning resources based on wireless energy harvesting |
| title_sort | optimization algorithm of uav assisted federated learning resources based on wireless energy harvesting |
| topic | bandwidth allocation energy consumption federated learning frequency allocation power control |
| url | https://doi.org/10.1049/cmu2.12857 |
| work_keys_str_mv | AT youhanyuan optimizationalgorithmofuavassistedfederatedlearningresourcesbasedonwirelessenergyharvesting AT qizhu optimizationalgorithmofuavassistedfederatedlearningresourcesbasedonwirelessenergyharvesting |