User Scheduling in Federated Learning over Energy Harvesting Wireless Networks

Rami Hamdi; Mingzhe Chen; Ahmed Ben Said; Marwa Qaraqe; H. Vincent Poor

doi:10.1109/GLOBECOM46510.2021.9685801

User Scheduling in Federated Learning over Energy Harvesting Wireless Networks

Rami Hamdi, Mingzhe Chen, Ahmed Ben Said, Marwa Qaraqe, H. Vincent Poor

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

In this paper, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base station (BS) is equipped with a massive multiple-input multiple-output (MIMO) system and a set of users powered by independent energy harvesting sources to cooperatively perform FL. Since a certain number of users may not be served due to interference and energy constraints, a joint energy management and user scheduling problem is considered. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To determine the effect of various wireless factors (transmit power and number of scheduled users) on training loss, the convergence rate of the FL algorithm is analyzed. Given this analytical result, the original user scheduling and energy management optimization problem can be decomposed, simplified and solved. Simulation results show that the proposed algorithm can reduce training loss compared to a standard FL algorithm.

Original language	English (US)
Title of host publication	2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728181042
DOIs	https://doi.org/10.1109/GLOBECOM46510.2021.9685801
State	Published - 2021
Event	2021 IEEE Global Communications Conference, GLOBECOM 2021 - Madrid, Spain Duration: Dec 7 2021 → Dec 11 2021

Publication series

Name	2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings

Conference

Conference	2021 IEEE Global Communications Conference, GLOBECOM 2021
Country/Territory	Spain
City	Madrid
Period	12/7/21 → 12/11/21

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Hardware and Architecture
Information Systems and Management
Safety, Risk, Reliability and Quality
Health Informatics

Keywords

Federated learning
energy harvesting
resource allocation

Access to Document

10.1109/GLOBECOM46510.2021.9685801

Cite this

Hamdi, R., Chen, M., Ben Said, A., Qaraqe, M., & Poor, H. V. (2021). User Scheduling in Federated Learning over Energy Harvesting Wireless Networks. In 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings (2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GLOBECOM46510.2021.9685801

@inproceedings{c421dc03aba24c769c15b5449582cd1c,

title = "User Scheduling in Federated Learning over Energy Harvesting Wireless Networks",

abstract = "In this paper, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base station (BS) is equipped with a massive multiple-input multiple-output (MIMO) system and a set of users powered by independent energy harvesting sources to cooperatively perform FL. Since a certain number of users may not be served due to interference and energy constraints, a joint energy management and user scheduling problem is considered. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To determine the effect of various wireless factors (transmit power and number of scheduled users) on training loss, the convergence rate of the FL algorithm is analyzed. Given this analytical result, the original user scheduling and energy management optimization problem can be decomposed, simplified and solved. Simulation results show that the proposed algorithm can reduce training loss compared to a standard FL algorithm.",

keywords = "Federated learning, energy harvesting, resource allocation",

author = "Rami Hamdi and Mingzhe Chen and {Ben Said}, Ahmed and Marwa Qaraqe and Poor, {H. Vincent}",

note = "Funding Information: ACKNOWLEDGMENT This research was sponsored in part by the T{\"U}B˙ITAK—QNRF Joint Funding Program grant (AICC03-0324-200005) from the Scientific and Technological Research Council of Turkey and Qatar National Research Fund (QNRF) and in part by the U.S. National Science Foundation under Grant CCF-1908308. The findings achieved herein are solely the responsibility of the authors. Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Global Communications Conference, GLOBECOM 2021 ; Conference date: 07-12-2021 Through 11-12-2021",

year = "2021",

doi = "10.1109/GLOBECOM46510.2021.9685801",

language = "English (US)",

series = "2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings",

address = "United States",

}

Hamdi, R, Chen, M, Ben Said, A, Qaraqe, M & Poor, HV 2021, User Scheduling in Federated Learning over Energy Harvesting Wireless Networks. in 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings. 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE Global Communications Conference, GLOBECOM 2021, Madrid, Spain, 12/7/21. https://doi.org/10.1109/GLOBECOM46510.2021.9685801

User Scheduling in Federated Learning over Energy Harvesting Wireless Networks. / Hamdi, Rami; Chen, Mingzhe; Ben Said, Ahmed et al.
2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - User Scheduling in Federated Learning over Energy Harvesting Wireless Networks

AU - Hamdi, Rami

AU - Chen, Mingzhe

AU - Ben Said, Ahmed

AU - Qaraqe, Marwa

AU - Poor, H. Vincent

N1 - Funding Information: ACKNOWLEDGMENT This research was sponsored in part by the TÜB˙ITAK—QNRF Joint Funding Program grant (AICC03-0324-200005) from the Scientific and Technological Research Council of Turkey and Qatar National Research Fund (QNRF) and in part by the U.S. National Science Foundation under Grant CCF-1908308. The findings achieved herein are solely the responsibility of the authors. Publisher Copyright: © 2021 IEEE.

PY - 2021

Y1 - 2021

N2 - In this paper, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base station (BS) is equipped with a massive multiple-input multiple-output (MIMO) system and a set of users powered by independent energy harvesting sources to cooperatively perform FL. Since a certain number of users may not be served due to interference and energy constraints, a joint energy management and user scheduling problem is considered. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To determine the effect of various wireless factors (transmit power and number of scheduled users) on training loss, the convergence rate of the FL algorithm is analyzed. Given this analytical result, the original user scheduling and energy management optimization problem can be decomposed, simplified and solved. Simulation results show that the proposed algorithm can reduce training loss compared to a standard FL algorithm.

AB - In this paper, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base station (BS) is equipped with a massive multiple-input multiple-output (MIMO) system and a set of users powered by independent energy harvesting sources to cooperatively perform FL. Since a certain number of users may not be served due to interference and energy constraints, a joint energy management and user scheduling problem is considered. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To determine the effect of various wireless factors (transmit power and number of scheduled users) on training loss, the convergence rate of the FL algorithm is analyzed. Given this analytical result, the original user scheduling and energy management optimization problem can be decomposed, simplified and solved. Simulation results show that the proposed algorithm can reduce training loss compared to a standard FL algorithm.

KW - Federated learning

KW - energy harvesting

KW - resource allocation

UR - http://www.scopus.com/inward/record.url?scp=85109962034&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85109962034&partnerID=8YFLogxK

U2 - 10.1109/GLOBECOM46510.2021.9685801

DO - 10.1109/GLOBECOM46510.2021.9685801

M3 - Conference contribution

AN - SCOPUS:85109962034

T3 - 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings

BT - 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE Global Communications Conference, GLOBECOM 2021

Y2 - 7 December 2021 through 11 December 2021

ER -

Hamdi R, Chen M, Ben Said A, Qaraqe M, Poor HV. User Scheduling in Federated Learning over Energy Harvesting Wireless Networks. In 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. (2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings). doi: 10.1109/GLOBECOM46510.2021.9685801

User Scheduling in Federated Learning over Energy Harvesting Wireless Networks

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this