User Scheduling in Federated Learning over Energy Harvesting Wireless Networks

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

doi:10.1109/GLOBECOM46510.2021.9685801

Back

Conference proceeding

User Scheduling in Federated Learning over Energy Harvesting Wireless Networks

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

2021 IEEE Global Communications Conference (GLOBECOM), pp.1-6

2021-12

DOI: https://doi.org/10.1109/GLOBECOM46510.2021.9685801

Abstract

Collaborative work

Energy harvesting

Energy management

Federated learning

resource allocation

Scheduling

Simulation

Training

Wireless networks

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.

Metrics

1 Record Views

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites

Details

Title: User Scheduling in Federated Learning over Energy Harvesting Wireless Networks
Creators: Rami Hamdi - Hamad bin Khalifa University
Mingzhe Chen - Princeton University
Ahmed Ben Said - Qatar University
Marwa Qaraqe - Hamad bin Khalifa University
H. Vincent Poor - Princeton University
IEEE
Publication Details: 2021 IEEE Global Communications Conference (GLOBECOM), pp.1-6
Publisher: IEEE
Grant note: Qatar National Research Fund (10.13039/100008982) Scientific and Technological Research Council of Turkey (10.13039/501100004410)
Academic Unit: CoE - Electrical & Computer Engineering; College of Engineering
Language: English
Resource Type: Conference proceeding
Record Identifier: 991031934005002976