Sliding Differential Evolution Scheduling for Federated Learning in Bandwidth-Limited Networks

Luo, Yifan, Xu, Jindan, Xu, Wei and Wang, Kezhi (2020) Sliding Differential Evolution Scheduling for Federated Learning in Bandwidth-Limited Networks. IEEE Communications Letters. ISSN 1089-7798 (In Press)

2010.08991.pdf - Accepted Version

Download (725kB) | Preview
Official URL:


Federated learning (FL) in a bandwidth-limited network with energy-limited user equipments (UEs) is underexplored. In this paper, to jointly save energy consumed by the battery-limited UEs and accelerate the convergence of the global model in FL for the bandwidth-limited network, we propose the sliding differential evolution-based scheduling (SDES) policy. To this end, we first formulate an optimization that aims to minimize a weighted sum of energy consumption and model training convergence. Then, we apply the SDES with parallel differential evolution (DE) operations in several small-scale windows, to address the above proposed problem effectively. Compared with existing scheduling policies, the proposed SDES performs well in reducing energy consumption and the model convergence with lower computational complexity.

Item Type: Article
Uncontrolled Keywords: Federated learning (FL), sliding window, differential evolution (DE), scheduling policy, bandwidth-limited networks
Subjects: G400 Computer Science
G900 Others in Mathematical and Computing Sciences
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: John Coen
Date Deposited: 01 Dec 2020 09:49
Last Modified: 01 Dec 2020 10:00

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics