TY - JOUR
T1 - Sliding Differential Evolution Scheduling for Federated Learning in Bandwidth-Limited Networks
AU - Luo, Yifan
AU - Xu, Jindan
AU - Xu, Wei
AU - Wang, Kezhi
N1 - Funding information: This work was supported by the NSFC under grants 62022026, 61871109 and 61941115, and the Natural Science Foundation of Jiangsu Province under Grant BK20190012.
PY - 2021/2/1
Y1 - 2021/2/1
N2 - 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.
AB - 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.
KW - Federated learning (FL)
KW - sliding window
KW - differential evolution (DE)
KW - scheduling policy
KW - bandwidth-limited networks
U2 - 10.1109/LCOMM.2020.3032517
DO - 10.1109/LCOMM.2020.3032517
M3 - Article
SN - 1089-7798
VL - 25
SP - 503
EP - 507
JO - IEEE Communications Letters
JF - IEEE Communications Letters
IS - 2
ER -
