Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management
Unmanned aerial vehicles (UAVs) are capable of serving as flying base stations (BSs) for supporting data collection, machine learning (ML) model training, and wireless communications. However, due to the privacy concerns of devices and limited computation or communication resource of UAVs, it is imp...
Saved in:
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/157149 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-157149 |
---|---|
record_format |
dspace |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Computational Modeling Unmanned Aerial Vehicle |
spellingShingle |
Engineering::Computer science and engineering Computational Modeling Unmanned Aerial Vehicle Yang, Helin Zhao, Jun Xiong, Zehui Lam, Kwok-Yan Sun, Sumei Xiao, Liang Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management |
description |
Unmanned aerial vehicles (UAVs) are capable of serving as flying base stations (BSs) for supporting data collection, machine learning (ML) model training, and wireless communications. However, due to the privacy concerns of devices and limited computation or communication resource of UAVs, it is impractical to send raw data of devices to UAV servers for model training. Moreover, due to the dynamic channel condition and heterogeneous computing capacity of devices in UAV-enabled networks, the reliability and efficiency of data sharing require to be further improved. In this paper, we develop an asynchronous federated learning (AFL) framework for multi-UAV-enabled networks, which can provide asynchronous distributed computing by enabling model training locally without transmitting raw sensitive data to UAV servers. The device selection strategy is also introduced into the AFL framework to keep the low-quality devices from affecting the learning efficiency and accuracy. Moreover, we propose an asynchronous advantage actor-critic (A3C) based joint device selection, UAVs placement, and resource management algorithm to enhance the federated convergence speed and accuracy. Simulation results demonstrate that our proposed framework and algorithm achieve higher learning accuracy and faster federated execution time compared to other existing solutions. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Yang, Helin Zhao, Jun Xiong, Zehui Lam, Kwok-Yan Sun, Sumei Xiao, Liang |
format |
Article |
author |
Yang, Helin Zhao, Jun Xiong, Zehui Lam, Kwok-Yan Sun, Sumei Xiao, Liang |
author_sort |
Yang, Helin |
title |
Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management |
title_short |
Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management |
title_full |
Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management |
title_fullStr |
Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management |
title_full_unstemmed |
Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management |
title_sort |
privacy-preserving federated learning for uav-enabled networks: learning-based joint scheduling and resource management |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/157149 |
_version_ |
1734310177645002752 |
spelling |
sg-ntu-dr.10356-1571492022-05-14T20:11:45Z Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management Yang, Helin Zhao, Jun Xiong, Zehui Lam, Kwok-Yan Sun, Sumei Xiao, Liang School of Computer Science and Engineering Nanyang Technopreneurship Center Strategic Centre for Research in Privacy-Preserving Technologies & Systems (SCRIPTS) Engineering::Computer science and engineering Computational Modeling Unmanned Aerial Vehicle Unmanned aerial vehicles (UAVs) are capable of serving as flying base stations (BSs) for supporting data collection, machine learning (ML) model training, and wireless communications. However, due to the privacy concerns of devices and limited computation or communication resource of UAVs, it is impractical to send raw data of devices to UAV servers for model training. Moreover, due to the dynamic channel condition and heterogeneous computing capacity of devices in UAV-enabled networks, the reliability and efficiency of data sharing require to be further improved. In this paper, we develop an asynchronous federated learning (AFL) framework for multi-UAV-enabled networks, which can provide asynchronous distributed computing by enabling model training locally without transmitting raw sensitive data to UAV servers. The device selection strategy is also introduced into the AFL framework to keep the low-quality devices from affecting the learning efficiency and accuracy. Moreover, we propose an asynchronous advantage actor-critic (A3C) based joint device selection, UAVs placement, and resource management algorithm to enhance the federated convergence speed and accuracy. Simulation results demonstrate that our proposed framework and algorithm achieve higher learning accuracy and faster federated execution time compared to other existing solutions. AI Singapore Info-communications Media Development Authority (IMDA) Ministry of Education (MOE) Nanyang Technological University National Research Foundation (NRF) Submitted/Accepted version This work was supported in part by the National Research Foundation, Singapore through the Strategic Capability Research Centre’s Funding Initiative; in part by Nanyang Technological University (NTU) Startup Grant, Alibaba-NTU Singapore Joint Research Institute, Singapore Ministry of Education Academic Research Fund under Grant Tier 1 RG128/18, Grant Tier 1 RG115/19, Grant Tier 1 RT07/19, Grant Tier 1 RT01/19, and Grant Tier 2 MOE2019-T2-1-176; in part by the NTU-Wallenberg AI, Autonomous Systems and Software Program (WASP) Joint Project, Energy Research Institute, NTU, Singapore through the NRF National Satellite of Excellence (NSoE) in Design Science and Technology for Secure Critical Infrastructure under Grant DeST-SCI2019-0012; in part by the AI Singapore 100 Experiments (100E) Program through the NTU Project for Large Vertical Take-Off and Landing Research Platform by the Singapore University of Technology and Design (SUTD) under Grant SRG-ISTD-2021-165; and in part by the National Natural Science Foundation of China under Grant 61971366. 2022-05-09T05:00:52Z 2022-05-09T05:00:52Z 2021 Journal Article Yang, H., Zhao, J., Xiong, Z., Lam, K., Sun, S. & Xiao, L. (2021). Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management. IEEE Journal On Selected Areas in Communications, 39(10), 3144-3159. https://dx.doi.org/10.1109/JSAC.2021.3088655 0733-8716 https://hdl.handle.net/10356/157149 10.1109/JSAC.2021.3088655 2-s2.0-85112245408 10 39 3144 3159 en RG128/18 RG115/19 RT07/19 RT01/19 MOE2019-T2-1-176 DeST-SCI2019-0012 SRG-ISTD-2021-165 IEEE Journal on Selected Areas in Communications © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/JSAC.2021.3088655. application/pdf |