TY - JOUR

T1 - Resource Allocation for Latency-aware Federated Learning in Industrial Internet-of-Things

AU - Gao, W.

AU - Zhao, Z.

AU - Min, G.

AU - Ni, Q.

AU - Jiang, Y.

N1 - ©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2021/12/31

Y1 - 2021/12/31

N2 - Federated Learning (FL) has been employed for tremendous privacy-sensitive applications, where distributed devices collaboratively train a global model. In Industrial Internet-of-Things (IIoT) systems, training latency is the key performance metric as the automated manufacture usually requires timely processing. The existing works increase the number of effective devices to accelerate the training. However, devices in IIoT systems are usually densely deployed, increasing the number of clients can potentially cause serious interference and prolonged training latency. In this paper, we propose RaFed, a resource allocation scheme for FL. We formulate the problem of reducing training latency as an optimization problem, which is proved to be NP-hard. We propose a heuristic to select appropriate devices to achieve a good trade-off between the interference and convergence time. We conduct experiments using an RGB-D dataset in an IIoT system. The results show that compared to the state-of-the-art works, Rafed significantly reduces the latency by 29.9%.

AB - Federated Learning (FL) has been employed for tremendous privacy-sensitive applications, where distributed devices collaboratively train a global model. In Industrial Internet-of-Things (IIoT) systems, training latency is the key performance metric as the automated manufacture usually requires timely processing. The existing works increase the number of effective devices to accelerate the training. However, devices in IIoT systems are usually densely deployed, increasing the number of clients can potentially cause serious interference and prolonged training latency. In this paper, we propose RaFed, a resource allocation scheme for FL. We formulate the problem of reducing training latency as an optimization problem, which is proved to be NP-hard. We propose a heuristic to select appropriate devices to achieve a good trade-off between the interference and convergence time. We conduct experiments using an RGB-D dataset in an IIoT system. The results show that compared to the state-of-the-art works, Rafed significantly reduces the latency by 29.9%.

KW - Computational modeling

KW - Federated learning

KW - Industrial Internet of Things

KW - Optimization

KW - Resource allocation

KW - Resource management

KW - Servers

KW - Training

KW - Wireless communication

KW - Economic and social effects

KW - NP-hard

KW - Processing

KW - Automated manufacture

KW - Convergence time

KW - Distributed devices

KW - Optimization problems

KW - Performance metrices

KW - Resource allocation schemes

KW - Sensitive application

KW - State of the art

KW - Industrial internet of things (IIoT)

U2 - 10.1109/TII.2021.3073642

DO - 10.1109/TII.2021.3073642

M3 - Journal article

VL - 17

SP - 8505

EP - 8513

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

IS - 12

ER -