Resource Allocation for Federated Learning with Heterogeneous Computing Capability in Cloud–Edge–Client IoT Architecture

A federated learning (FL) framework for cloud–edge–client collaboration performs local aggregation of model parameters through edges, reducing communication overhead from clients to the cloud. This framework is particularly suitable for Internet of Things (IoT)-based secure computing scenarios that...

Full description

Saved in:
Bibliographic Details
Main Authors: Xubo Zhang, Yang Luo
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/17/6/243
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849431912760737792
author Xubo Zhang
Yang Luo
author_facet Xubo Zhang
Yang Luo
author_sort Xubo Zhang
collection DOAJ
description A federated learning (FL) framework for cloud–edge–client collaboration performs local aggregation of model parameters through edges, reducing communication overhead from clients to the cloud. This framework is particularly suitable for Internet of Things (IoT)-based secure computing scenarios that require extensive computation and frequent parameter updates, as it leverages the distributed nature of IoT devices to enhance data privacy and reduce latency. To address the issue of high-computation-capability clients waiting due to varying computing capabilities under heterogeneous device conditions, this paper proposes an improved resource allocation scheme based on a three-layer FL framework. This scheme optimizes the communication parameter volume from clients to the edge by implementing a method based on random dropout and parameter completion before and after communication, ensuring that local models can be transmitted to the edge simultaneously, regardless of different computation times. This scheme effectively resolves the problem of high-computation-capability clients experiencing long waiting times. Additionally, it optimizes the similarity pairing method, the Shapley Value (SV) aggregation strategy, and the client selection method to better accommodate heterogeneous computing capabilities found in IoT environments. Experiments demonstrate that this improved scheme is more suitable for heterogeneous IoT client scenarios, reducing system latency and energy consumption while enhancing model performance.
format Article
id doaj-art-44aaed865e874709a40bcd65a7809e45
institution Kabale University
issn 1999-5903
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-44aaed865e874709a40bcd65a7809e452025-08-20T03:27:29ZengMDPI AGFuture Internet1999-59032025-05-0117624310.3390/fi17060243Resource Allocation for Federated Learning with Heterogeneous Computing Capability in Cloud–Edge–Client IoT ArchitectureXubo Zhang0Yang Luo1The 30th Research Institute of China Electronics Technology Group Corporation, Chengdu 610041, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaA federated learning (FL) framework for cloud–edge–client collaboration performs local aggregation of model parameters through edges, reducing communication overhead from clients to the cloud. This framework is particularly suitable for Internet of Things (IoT)-based secure computing scenarios that require extensive computation and frequent parameter updates, as it leverages the distributed nature of IoT devices to enhance data privacy and reduce latency. To address the issue of high-computation-capability clients waiting due to varying computing capabilities under heterogeneous device conditions, this paper proposes an improved resource allocation scheme based on a three-layer FL framework. This scheme optimizes the communication parameter volume from clients to the edge by implementing a method based on random dropout and parameter completion before and after communication, ensuring that local models can be transmitted to the edge simultaneously, regardless of different computation times. This scheme effectively resolves the problem of high-computation-capability clients experiencing long waiting times. Additionally, it optimizes the similarity pairing method, the Shapley Value (SV) aggregation strategy, and the client selection method to better accommodate heterogeneous computing capabilities found in IoT environments. Experiments demonstrate that this improved scheme is more suitable for heterogeneous IoT client scenarios, reducing system latency and energy consumption while enhancing model performance.https://www.mdpi.com/1999-5903/17/6/243federated learningheterogeneous clientsmodel dropout
spellingShingle Xubo Zhang
Yang Luo
Resource Allocation for Federated Learning with Heterogeneous Computing Capability in Cloud–Edge–Client IoT Architecture
Future Internet
federated learning
heterogeneous clients
model dropout
title Resource Allocation for Federated Learning with Heterogeneous Computing Capability in Cloud–Edge–Client IoT Architecture
title_full Resource Allocation for Federated Learning with Heterogeneous Computing Capability in Cloud–Edge–Client IoT Architecture
title_fullStr Resource Allocation for Federated Learning with Heterogeneous Computing Capability in Cloud–Edge–Client IoT Architecture
title_full_unstemmed Resource Allocation for Federated Learning with Heterogeneous Computing Capability in Cloud–Edge–Client IoT Architecture
title_short Resource Allocation for Federated Learning with Heterogeneous Computing Capability in Cloud–Edge–Client IoT Architecture
title_sort resource allocation for federated learning with heterogeneous computing capability in cloud edge client iot architecture
topic federated learning
heterogeneous clients
model dropout
url https://www.mdpi.com/1999-5903/17/6/243
work_keys_str_mv AT xubozhang resourceallocationforfederatedlearningwithheterogeneouscomputingcapabilityincloudedgeclientiotarchitecture
AT yangluo resourceallocationforfederatedlearningwithheterogeneouscomputingcapabilityincloudedgeclientiotarchitecture