Online Optimization for Over-the-Air Federated Learning with Energy Harvesting

doi:10.1109/TWC.2023.3339298

	Online Optimization for Over-the-Air Federated Learning with Energy Harvesting
	Qiaochu An1 ; Yong Zhou1 ; Zhibin Wang1 ; Hangguan Shan 2; Yuanming Shi1 ; Mehdi Bennis 3
	2023
发表期刊	IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (IF:8.9[JCR-2023],8.6[5-Year])
ISSN	1558-2248
EISSN	1558-2248
卷号	PP 期号:99 页码:7291-7306
发表状态	已发表
DOI	10.1109/TWC.2023.3339298
摘要	Federated learning (FL) is recognized as a promising privacy-preserving distributed machine learning paradigm, given its potential to enable collaborative model training among distributed devices without sharing their raw data. However, supporting FL over wireless networks confronts the critical challenges of periodically executing power-hungry training tasks on energy-constrained devices and transmitting high-dimensional model updates over spectrum-limited channels. In this paper, we reap the benefits of both energy harvesting (EH) and over-the-air computation (AirComp) to alleviate the battery limitation by harvesting ambient energy to support both the training and transmission of local models, and to achieve low-latency model aggregation by concurrently transmitting local gradients via AirComp. We characterize the convergence of the proposed FL by deriving an upper bound of the expected optimality gap, revealing that the convergence depends on the accumulated errors due to partial device participation and model distortion, both of which further depend on dynamic energy levels. To accelerate the convergence, we formulate a joint AirComp transceiver design and device scheduling problem, which is then tackled by developing an efficient Lyapunov-based online optimization algorithm. Simulations demonstrate that, by appropriately scheduling devices and allocating energy across multiple communication rounds, our proposed algorithm achieves a much better learning performance than benchmarks.
关键词	Federated learning Lyapunov optimization energy harvesting over-the-air computation
URL	查看原文
收录类别	SCI ; EI
语种	英语
资助项目	National Natural Science Foundation of China["62001294","U20A20159","61971286","U21B2029","U21A20456","62271318"] ; Natural Science Foundation of Shanghai["23ZR1442800","21ZR1442700"] ; Zhejiang Provincial Natural Science Foundation of China[LR23F010006] ; Shanghai Rising-Star Program[22QA1406100]
WOS研究方向	Engineering ; Telecommunications
WOS类目	Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:001267002700018
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号	20235215271111
EI主题词	Energy harvesting
EI分类号	525.5 Energy Conversion Issues ; 716 Telecommunication ; Radar, Radio and Television ; 716.3 Radio Systems and Equipment ; 718 Telephone Systems and Related Technologies ; Line Communications ; 723.2 Data Processing and Image Processing
原始文献类型	Journal article (JA)
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354966
专题	信息科学与技术学院信息科学与技术学院_PI研究组_石远明组信息科学与技术学院_PI研究组_周勇组信息科学与技术学院_博士生
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 2.College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China 3.Centre for Wireless Communication, University of Oulu, Finland
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Qiaochu An,Yong Zhou,Zhibin Wang,et al. Online Optimization for Over-the-Air Federated Learning with Energy Harvesting[J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS,2023,PP(99):7291-7306.
APA	Qiaochu An,Yong Zhou,Zhibin Wang,Hangguan Shan,Yuanming Shi,&Mehdi Bennis.(2023).Online Optimization for Over-the-Air Federated Learning with Energy Harvesting.IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS,PP(99),7291-7306.
MLA	Qiaochu An,et al."Online Optimization for Over-the-Air Federated Learning with Energy Harvesting".IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS PP.99(2023):7291-7306.