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

10/18/2020 ∙ by Yifan Luo, et al. ∙ 0 ∙ share

Federated learning (FL) in a bandwidth-limited network with energy-limited user equipments (UEs) is under-explored. 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.

READ FULL TEXT

Device Scheduling with Fast Convergence for Wireless Federated Learning

Owing to the increasing need for massive data analysis and model trainin...
11/03/2019 ∙ by Wenqi Shi, et al. ∙ 0 ∙ share

read it
Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networks

Federated learning (FL) is a machine learning model that preserves data ...
10/31/2019 ∙ by Howard H. Yang, et al. ∙ 0 ∙ share

read it
Energy Efficient Federated Learning Over Wireless Communication Networks

In this paper, the problem of energy efficient transmission and computat...
11/06/2019 ∙ by Zhaohui Yang, et al. ∙ 13 ∙ share

read it
Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning

In federated learning (FL), devices contribute to the global training by...
07/14/2020 ∙ by Wenqi Shi, et al. ∙ 0 ∙ share

read it
Scheduling Policies for Federated Learning in Wireless Networks

Motivated by the increasing computational capacity of wireless user equi...
08/17/2019 ∙ by Howard H. Yang, et al. ∙ 0 ∙ share

read it
Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective

This paper studies federated learning (FL) in a classic wireless network...
04/09/2020 ∙ by Jie Xu, et al. ∙ 0 ∙ share

read it
Key technologies to accelerate the ICT Green evolution -- An operator's point of view

The exponential growth in networks' traffic accompanied by the multiplic...
03/22/2019 ∙ by Azeddine Gati, et al. ∙ 0 ∙ share

read it

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

Authors

Device Scheduling with Fast Convergence for Wireless Federated Learning

Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networks

Energy Efficient Federated Learning Over Wireless Communication Networks

Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning

Scheduling Policies for Federated Learning in Wireless Networks

Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective

Key technologies to accelerate the ICT Green evolution -- An operator's point of view

This week in AI