Latency-aware semi-synchronous federated learning client resource co-scheduling scheme for IIoT

WANG Ye; SHI Ying; XIA Tianle; LIU Miao; YANG Jie; ZHAO Haitao

doi:10.11959/j.issn.2096-3750.2025.00496

您当前的位置：

首页 >

文章列表页 >

Latency-aware semi-synchronous federated learning client resource co-scheduling scheme for IIoT

Theory and Technology | 更新时间：2026-01-04

- Latency-aware semi-synchronous federated learning client resource co-scheduling scheme for IIoT
- Chinese Journal on Internet of Things Vol. 9, Issue 4, Pages: 194-205(2025)
- 作者机构：
  
  1.江苏移动信息系统集成有限公司，江苏南京 210003
  2.南京邮电大学通信与信息工程学院，江苏南京 210003
  3.南京邮电大学物联网学院，江苏南京 210003
- 作者简介：
- 基金信息：
  
  Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu prevince(BK20202001)
- DOI：10.11959/j.issn.2096-3750.2025.00496
  CLC：
- Received：28 March 2025，
  
  Revised：2025-06-10，
  
  Published：10 December 2025
- 稿件说明：
移动端阅览
王晔,施颖,夏天乐等.面向工业物联网的时延感知半同步联邦学习客户端资源联合调度方案[J].物联网学报,2025,09(04):194-205.

WANG Ye,SHI Ying,XIA Tianle,et al.Latency-aware semi-synchronous federated learning client resource co-scheduling scheme for IIoT[J].Chinese Journal on Internet of Things,2025,09(04):194-205.
王晔,施颖,夏天乐等.面向工业物联网的时延感知半同步联邦学习客户端资源联合调度方案[J].物联网学报,2025,09(04):194-205. DOI： 10.11959/j.issn.2096-3750.2025.00496.

WANG Ye,SHI Ying,XIA Tianle,et al.Latency-aware semi-synchronous federated learning client resource co-scheduling scheme for IIoT[J].Chinese Journal on Internet of Things,2025,09(04):194-205. DOI： 10.11959/j.issn.2096-3750.2025.00496.

摘要

联邦学习作为一种灵活且可扩展的分布式机器学习方法，在工业物联网（IIoT

industrial Internet of things）中得到了广泛应用，在保护数据隐私的同时，实现低时延、低通信开销和高精度的模型训练。然而，由于工业物联网中边缘设备的计算能力和通信能力的异构性，传统同步联邦学习面临“落后者效应”，即服务器需要等待所有客户端完成本地模型参数上传，显著降低训练效率，难以满足工业物联网对低时延服务的需求。为了解决这一问题并降低设备异构性带来的训练时延，提出了一种基于半同步机制的异构工业联邦学习框架，并在此基础上设计了一种基于训练时延效益评分的客户端选择方案，以提升训练效率。此外，为了提高网络频谱资源的利用率，基于全局训练时延均衡的数学关系，提出了一种自适应设备数量的带宽分配机制，优化被选客户端的模型上传策略。大量仿真结果表明，与基于加权平均的联邦学习（FedAvg

federated averaging）和结合客户端选择的联邦学习（FedCS

federated learning with client selection）等基准方案相比，所提方法在模型准确度、系统时延及频谱利用率等方面均具有显著优势。

Abstract

Federated learning (FL)

as a flexible and scalable distributed machine learning approach

has been widely applied in the industrial Internet of things (IIoT) to achieve low-latency

low communication overhead

and high-accuracy model training while preserving data privacy. However

due to the heterogeneity in computing and communication capabilities among edge devices in IIoT

traditional synchronous FL suffers from the "straggler effect"

where the server must wait for all clients to upload their local model parameters

significantly reducing training efficiency and making it difficult to meet the low-latency service requirements of IIoT. To address this issue and mitigate the training delay caused by device heterogeneity

a semi-synchronous heterogeneous industrial FL framework was proposed. Based on this framework

a client selection scheme was designed

leveraging training latency efficiency scores to enhance training efficiency. Furthermore

to improve network spectrum utilization

an adaptive bandwidth allocation mechanism based on a mathematical relationship was proposed that ensured equal global training latency per round

optimizing the model upload strategy of selected clients. Extensive simulation results demonstrate that

compared with benchmark schemes such as FedAvg and FedCS

the proposed approach achieves significant advantages in model accuracy

system latency

and spectrum efficiency.

关键词

Keywords

references

CHOUDHARY A . Internet of things: a comprehensive overview, architectures, applications, simulation tools, challenges and future directions [J ] . Discover Internet of Things , 2024 , 4 ( 1 ): 31 .

SAHA R , MISRA S , CHAKRABORTY A , et al . Data-centric client selection for federated learning over distributed edge networks [J ] . IEEE Transactions on Parallel and Distributed Systems , 2023 , 34 ( 2 ): 675 - 686 .

GE L N , LI H A , WANG X , et al . A review of secure federated learning: privacy leakage threats, protection technologies, challenges and future directions [J ] . Neurocomputing , 2023 , 561 : 126897 .

LO S K , LU Q H , WANG C , et al . A systematic literature review on federated machine learning: from a software engineering perspective [J ] . ACM Computing Surveys , 2021 , 54 ( 5 ): 1 - 39 .

王晓明 , 黄斌枘 . 基于用户选择的鲁棒与隐私保护联邦学习方案 [J ] . 计算机应用研究 , 2025 , 42 ( 6 ): 1859 - 1867 .

WANG X M , HUANG B R . Robust and privacy-preserving federated learning scheme based on user selection [J ] . Application Research of Computers , 2025 , 42 ( 6 ): 1859 - 1867 .

刘淼 , 林婉茹 , 王琴 , 等 . 车联网联邦学习的数据异质性问题及基于个性化的解决方法综述 [J ] . 通信学报 , 2024 , 45 ( 10 ): 207 - 224 .

LIU M , LIN W R , WANG Q , et al . Survey on data heterogeneity problems and personalization based solutions of federated learning in Internet of vehicles [J ] . Journal on Communications , 2024 , 45 ( 10 ): 207 - 224 .

XIA Y J , LIU X J , ZHAO Y X , et al . FCLA-DT: federated continual learning with authentication for distributed digital twin-based industrial IoT [J ] . Journal of Communications and Information Networks , 2024 , 9 ( 4 ): 362 - 373 .

申凌峰 , 王光辉 , 白天水 , 等 . 基于选举策略的低空物联网稳定联邦学习方法 [J ] . 物联网学报 , 2024 , 8 ( 3 ): 55 - 65 .

SHEN L F , WANG G H , BAI T S , et al . Stable federated learning method for low-altitude IoT networks based on election strategy [J ] . Chinese Journal on Internet of Things , 2024 , 8 ( 3 ): 55 - 65 .

范珂欣 , 安丽荣 , 张钦宇 . 业务驱动的空天地海一体化网络技术研究 [J ] . 电信科学 , 2024 , 40 ( 6 ): 25 - 37 .

FAN K X , AN L R , ZHANG Q Y . Research on service-driven network technologies for space-air-ground-sea integration [J ] . Telecommunications Science , 2024 , 40 ( 6 ): 25 - 37 .

MOTHUKURI V , KHARE P , PARIZI R M , et al . Federated-learning-based anomaly detection for IoT security attacks [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 4 ): 2545 - 2554 .

ZHANG W T , YANG D , WU W , et al . Optimizing federated learning in distributed industrial IoT: a multi-agent approach [J ] . IEEE Journal on Selected Areas in Communications , 2021 , 39 ( 12 ): 3688 - 3703 .

郭英芸 , 高博 , 张志飞 , 等 . 一种基于带宽分配的联邦学习激励机制 [J ] . 物联网学报 , 2022 ( 4 ): 82 - 92 .

GUO Y Y , GAO B , ZHANG Z F , et al . An incentive mechanism with bandwidth allocation for federated learning [J ] . Chinese Journal on Internet of Things , 2022 ( 4 ): 82 - 92 .

ZHU C , ZHU G L , YANG J , et al . Quick and good: a DRL based communication-caching-energy joint optimization scheme for prolonging the lifetime of UAV assisted IoE [J ] . Journal of Communications and Information Networks , 2024 , 9 ( 4 ): 1 - 14 .

YANG K , SHI Y M , ZHOU Y , et al . Federated machine learning for intelligent IoT via reconfigurable intelligent surface [J ] . IEEE Network , 2020 , 34 ( 5 ): 16 - 22 .

NING B Y . Federated learning optimisation algorithm based on Non-IID data [C ] // Proceedings of the 2023 IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE) . Piscataway : IEEE Press , 2024 : 1663 - 1669 .

SUN W , LEI S Y , WANG L , et al . Adaptive federated learning and digital twin for industrial Internet of things [J ] . IEEE Transactions on Industrial Informatics , 2021 , 17 ( 8 ): 5605 - 5614 .

ABDULRAHMAN S , TOUT H , MOURAD A , et al . FedMCCS: multicriteria client selection model for optimal IoT federated learning [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 6 ): 4723 - 4735 .

DENG Y H , LYU F , REN J , et al . AUCTION: automated and quality-aware client selection framework for efficient federated learning [J ] . IEEE Transactions on Parallel and Distributed Systems , 2022 , 33 ( 8 ): 1996 - 2009 .

SHEN S , SHEN G J , DAI Z H , et al . Asynchronous federated deep-reinforcement-learning-based dependency task offloading for UAV-assisted vehicular networks [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 19 ): 31561 - 31574 .

CHEN Z Y , LIAO W X , HUA K , et al . Towards asynchronous federated learning for heterogeneous edge-powered Internet of things [J ] . Digital Communications and Networks , 2021 , 7 ( 3 ): 317 - 326 .

XU J , WANG H Q . Client selection and bandwidth allocation in wireless federated learning networks: a long-term perspective [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 2 ): 1188 - 1200 .

刘淼 , 夏雨虹 , 赵海涛 , 等 . 面向6G工业物联网的联邦学习: 从需求、愿景到挑战、机遇 [J ] . 电子与信息学报 , 2024 , 46 ( 12 ): 4335 - 4353 .

LIU M , XIA Y H , ZHAO H T , et al . Federated learning technologies for 6G industrial Internet of things: from requirements, vision to challenges, opportunities [J ] . Journal of Electronics Information Technology , 2024 , 46 ( 12 ): 4335 - 4353 .

SONG Y X , YU F R , ZHOU L , et al . Applications of the Internet of Things (IoT) in smart logistics: a comprehensive survey [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 6 ): 4250 - 4274 .

XU Y , XIAO M J , TAN H S , et al . Incentive mechanism for differentially private federated learning in industrial Internet of things [J ] . IEEE Transactions on Industrial Informatics , 2022 , 18 ( 10 ): 6927 - 6939 .

YU L K , SUN X , ALBELAIHI R , et al . Latency-aware semi-synchronous client selection and model aggregation for wireless federated learning [J ] . Future Internet , 2023 , 15 ( 11 ): 352 .

MCMAHAN H B , MOORE E , RAMAGE D , et al . Communication-efficient learning of deep networks from decentralized data [C ] // Proceedings of the International Conference on Artificial Intelligence and Statistics , 2016 .

WU D X , SHEN G H , HUANG Z Q , et al . A trust-aware task offloading framework in mobile edge computing [J ] . IEEE Access , 2019 , 7 : 150105 - 150119 .

NISHIO T , YONETANI R . Client selection for federated learning with heterogeneous resources in mobile edge [C ] // Proceedings of the ICC 2019-2019 IEEE International Conference on Communications (ICC) . Piscataway : IEEE Press , 2019 : 1 - 7 .

HUANG T S , LIN W W , WU W T , et al . An efficiency-boosting client selection scheme for federated learning with fairness guarantee [J ] . IEEE Transactions on Parallel and Distributed Systems , 2021 , 32 ( 7 ): 1552 - 1564 .

耿光磊 , 高博 , 熊轲 , 等 . 联邦学习赋能6G网络综述 [J ] . 物联网学报 , 2023 ( 2 ): 50 - 66 .

GENG G L , GAO B , XIONG K , et al . A survey of federated learning for 6G networks [J ] . Chinese Journal on Internet of Things , 2023 ( 2 ): 50 - 66 .

齐俏 , 陈晓明 . 面向边缘智能网络的通-感-算融合: 架构、挑战和展望 [J ] . 移动通信 , 2024 , 48 ( 3 ): 40 - 46 .

QI Q , CHEN X M . Integrated sensing, communication, and computing for edge intelligent networks: architecture, challenges, and outlook [J ] . Mobile Communications , 2024 , 48 ( 3 ): 40 - 46 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Joint multi-dimensional resource optimization for model compression in wireless federated learning

Energy-saving computation offloading scheme based on Sarsa algorithm in industrial internet of things

Cross-domain task offloading and computing resource allocation for edge computation in industrial Internet of things

Intent-driven dual-time-scale resource allocation approach for Internet of things

Research on low-latency transmission migration method for federated learning models in the Internet of vehicles

Related Author

ZHU Guangzhao

ZHU Xiaorong

XU Ding

Jun SUN

Shangweikang ZHAO

Peng ZHOU

Jincheng XU

Bo YANG

Related Institution

Department of Automation,Shanghai Jiao Tong University

Key Laboratory of System Control and Information Processing,Ministry of Education

State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications

SINO-PIPELINE International Company

Shenzhen Institute for Advanced Study, UESTC

⁰