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

ZHU Guangzhao; ZHU Xiaorong; XU Ding

doi:10.11959/j.issn.2096-3750.2025.00391

您当前的位置：

首页 >

文章列表页 >

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

Theory and Technology | 更新时间：2025-09-12

- Joint multi-dimensional resource optimization for model compression in wireless federated learning
- Chinese Journal on Internet of Things Vol. 9, Issue 2, Pages: 190-201(2025)
- 作者机构：
  
  南京邮电大学通信与信息工程学院，江苏南京 210003
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(92367102);The Key Research and Development Plan of Jiangsu Province(BE2020084-3;BE2021013-3)
- DOI：10.11959/j.issn.2096-3750.2025.00391
  CLC： TN929.5
- Received：26 January 2024，
  
  Revised：2024-04-14，
  
  Published：10 June 2025
- 稿件说明：
移动端阅览
朱光照,朱晓荣,徐鼎.面向无线联邦学习模型压缩的多维资源联合优化研究[J].物联网学报,2025,09(02):190-201.

ZHU Guangzhao,ZHU Xiaorong,XU Ding.Joint multi-dimensional resource optimization for model compression in wireless federated learning[J].Chinese Journal on Internet of Things,2025,09(02):190-201.
朱光照,朱晓荣,徐鼎.面向无线联邦学习模型压缩的多维资源联合优化研究[J].物联网学报,2025,09(02):190-201. DOI： 10.11959/j.issn.2096-3750.2025.00391.

ZHU Guangzhao,ZHU Xiaorong,XU Ding.Joint multi-dimensional resource optimization for model compression in wireless federated learning[J].Chinese Journal on Internet of Things,2025,09(02):190-201. DOI： 10.11959/j.issn.2096-3750.2025.00391.

摘要

针对边缘计算场景中，资源受限和网络动态的终端设备参与联邦学习产生的巨大时延和能耗问题，基于云-边-端三层联邦学习架构提出了一种高效训练和绿色节能的联邦学习算法。首先，将模型压缩技术引入三层联邦学习结构中，对三层联邦学习的模型收敛速率、训练时延和能耗进行理论分析。然后，根据理论分析结果进行问题建模，在一定的模型收敛速率下最小化全局模型训练时延和能耗，通过联合优化终端设备的发射功率、算力和模型压缩率，提高联邦学习的资源利用率。最后，将问题分解为3个优化子问题分别求解，设计了一种联合交替优化算法来获得原始问题的最优解。仿真结果表明，该算法可以适应大规模的边缘计算场景，在保证模型收敛速率的同时，与传统三层联邦学习算法相比，产生的时延和能耗分别减少了71.54%和48.76%，有效地降低了全局模型训练产生的时延和能耗。

Abstract

In the edge computing scenarios

resource-constrained and particiption of the dynamically terminal devices of network in federated learning cause high latency and high energy consumption. An efficient and environmentally friendly federated learning algorithm based on a three-tier cloud-edge-terminal architecture was proposed. Firstly

by introducing model compression techniques into the three-tier federated learning structure

a theoretical analysis was conducted on the model convergence rate

training latency

and energy consumption. Subsequently

based on the theoretical analysis

a problem was formulated to minimize the global model training latency and energy consumption under a certain model convergence rate by jointly optimizing the terminal devices' transmission power

computing power

and model compression rate. Finally

by decomposing the problem into three sub-optimization problems and solving them alternately

a joint alternating optimization algorithm was designed to obtain the optimal solution for the original problem. Experimental results demonstrate that the proposed algorithm is adaptable to large-scale edge computing scenarios. It achieves reductions of 71.54% and 48.76%

respectively

in latency and energy consumption compared with traditional three-layer federated learning algorithms

while ensuring the convergence rate of the model

and effectively reduces the latency and energy consumption generated by global model training.

关键词

Keywords

references

SHAHRAKI A , ABBASI M , PIRAN M J , et al . A comprehensive survey on 6G networks: applications, core services, enabling technologies, and future challenges [J ] . arXiv preprint , 2021 , arXiv: 2101.12475 .

栾宁 , 熊轲 , 张煜 , 等 . 6G: 典型应用、关键技术与面临挑战 [J ] . 物联网学报 , 2022 , 6 ( 1 ): 29 - 43 .

LUAN N , XIONG K , ZHANG Y , et al . 6G: typical applications, key technologies and challenges [J ] . Chinese Journal on Internet of Things , 2022 , 6 ( 1 ): 29 - 43 .

李文璟 , 喻鹏 , 张平 . 6G智能内生网络架构及关键技术分析 [J ] . 中兴通讯技术 , 2023 , 29 ( 5 ): 2 - 8 .

LI W J , YU P , ZHANG P . Analysis of the architecture and key technologies of 6G intelligent [J ] . ZTE Technology Journal , 2023 , 29 ( 5 ): 2 - 8 .

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 , 7 ( 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 , 7 ( 2 ): 50 - 66 .

AL-QURAAN M , MOHJAZI L , BARIAH L , et al . Edge-native intelligence for 6G communications driven by federated learning: a survey of trends and challenges [J ] . IEEE Transactions on Emerging Topics in Computational Intelligence , 2023 , 7 ( 3 ): 957 - 979 .

XIAO Y , SHI G M , KRUNZ M . Towards ubiquitous AI in 6G with federated learning [J ] . arXiv preprint , 2020 , arXiv: 2004.13563 .

ZHU G X , LYU Z H , JIAO X , et al . Pushing AI to wireless network edge: an overview on integrated sensing, communication, and computation towards 6G [J ] . Science China Information Sciences , 2023 , 66 ( 3 ): 130301 .

刘胜利 . 无线分布式学习系统的模型优化与资源管理 [D ] . 杭州 : 浙江大学 , 2022 .

LIU S L . Model optimization and resource management of wireless distributed learning system [D ] . Hangzhou : Zhejiang University , 2022 .

BOUZINIS P S , DIAMANTOULAKIS P D , KARAGIANNIDIS G K . Wireless federated learning (WFL) for 6G Networks⁴Part I: research challenges and future trends [J ] . IEEE Communications Letters , 2022 , 26 ( 1 ): 3 - 7 .

YANG Z H , CHEN M Z , WONG K K , et al . Federated learning for 6G: applications, challenges, and opportunities [J ] . Engineering , 2022 , 8 : 33 - 41 .

MCMAHAN H B , MOORE E , RAMAGE D , et al . Communication-efficient learning of deep networks from decentralized data [J ] . arXiv preprint , 2016 , arXiv: 1602.05629 .

LI T , SAHU A K , TALWALKAR A , et al . Federated learning: challenges, methods, and future directions [J ] . IEEE Signal Processing Magazine , 2020 , 37 ( 3 ): 50 - 60 .

LIU Y , YUAN X L , XIONG Z H , et al . Federated learning for 6G communications: challenges, methods, and future directions [J ] . China Communications , 2020 , 17 ( 9 ): 105 - 118 .

QIN Z J , LI G Y , YE H . Federated learning and wireless communications [J ] . IEEE Wireless Communications , 2021 , 28 ( 5 ): 134 - 140 .

SHI W Q , ZHOU S , NIU Z S . Device scheduling with fast convergence for wireless federated learning [C ] // Proceedings of the ICC 2020 - 2020 IEEE International Conference on Communications (ICC) . Piscataway : IEEE Press , 2020 : 1 - 6 .

LI Q B , DIAO Y Q , CHEN Q , et al . Federated learning on non-IID data silos: an experimental study [C ] // Proceedings of the 2022 IEEE 38th International Conference on Data Engineering (ICDE) . Piscataway : IEEE Press , 2022 : 965 - 978 .

YAMASAKI Y , TAKASE H . F2MKD: fog-enabled federated learning with mutual knowledge distillation [C ] // Proceedings of the 2023 IEEE 20th Consumer Communications & Networking Conference (CCNC) . Piscataway : IEEE Press , 2023 : 682 - 683 .

ALISTARH D , HOEFLER T , JOHANSSON M , et al . The convergence of sparsified gradient methods [C ] // Proceedings of the 32nd International Conference on Neural Information Processing Systems . New York : Curran Associates Inc , 2018 : 5977 - 5987 .

SHI S H , WANG Q , ZHAO K Y , et al . A distributed synchronous SGD algorithm with global Top- K sparsification for low bandwidth networks [C ] // Proceedings of the 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS) . Piscataway : IEEE Press , 2019 : 2238 - 2247 .

SATTLER F , WIEDEMANN S , MULLER K R , et al . Robust and communication-efficient federated learning from non-i.i.d. data [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2020 , 31 ( 9 ): 3400 - 3413 .

JIANG Z D , XU Y , XU H L , et al . Adaptive control of client selection and gradient compression for efficient federated learning [J ] . arXiv preprint , 2022 , arXiv: 2212.09483 .

XU Y , LIAO Y M , XU H L , et al . Adaptive control of local updating and model compression for efficient federated learning [J ] . IEEE Transactions on Mobile Computing , 2023 , 22 ( 10 ): 5675 - 5689 .

唐伦，汪智平，蒲昊，等 . 基于自适应梯度压缩的高效联邦学习通信机制研究 [J ] . 电子与信息学报， 2023 ， 45 ( 1 ): 227 - 234 .

TANG L , WANG Z P , PU H , et al . Research on efficient federated learning communication mechanism based on adaptive gradient compression [J ] . Journal of Electronics & Information Technology , 2023 , 45 ( 1 ): 227 - 234 .

LIU S L , YU G D , YIN R , et al . Communication and computation efficient federated learning for Internet of vehicles with a constrained latency [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 1 ): 1038 - 1052 .

MO X P , XU J . Energy-efficient federated edge learning with joint communication and computation design [J ] . Journal of Communications and Information Networks , 2021 , 6 ( 2 ): 110 - 124 .

TRAN N H , BAO W , ZOMAYA A , et al . Federated learning over wireless networks: optimization model design and analysis [C ] // Proceedings of the IEEE INFOCOM 2019 - IEEE Conference on Computer Communications . Piscataway : IEEE Press , 2019 : 1387 - 1395 .

LI P C , CHENG G L , HUANG X M , et al . Snowball: energy efficient and accurate federated learning with coarse-to-fine compression over heterogeneous wireless edge devices [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 10 ): 6778 - 6792 .

HONG W , LUO X T , ZHAO Z Y , et al . Optimal design of hybrid federated and centralized learning in the mobile edge computing systems [C ] // Proceedings of the 2021 IEEE International Conference on Communications Workshops (ICC Workshops) . Piscataway : IEEE Press , 2021 : 1 - 6 .

LIU L M , ZHANG J , SONG S H , et al . Client-edge-cloud hierarchical federated learning [C ] // Proceedings of the ICC 2020 - 2020 IEEE International Conference on Communications (ICC) . Piscataway : IEEE Press , 2020 : 1 - 6 .

SHI S H , ZHAO K Y , WANG Q , et al . A convergence analysis of distributed SGD with communication-efficient gradient sparsification [C ] // Proceedings of the 28th International Joint Conference on Artificial Intelligence . Menlo Park : AAAI Press , 2019 : 3411 - 3417 .

LIU S L , YU G D , CHEN X F , et al . Joint user association and resource allocation for wireless hierarchical federated learning with Non-IID data [C ] // Proceedings of ICC 2022 - IEEE International Conference on Communications . Piscataway : IEEE Press , 2022 : 74 - 79 .

PAN Y J , CHEN M , YANG Z H , et al . Energy-efficient NOMA-based mobile edge computing offloading [J ] . IEEE Communications Letters , 2019 , 23 ( 2 ): 310 - 313 .

TUN Y K , PARK Y M , TRAN N H , et al . Energy-efficient resource management in UAV-assisted mobile edge computing [J ] . IEEE Communications Letters , 2021 , 25 ( 1 ): 249 - 253 .

Views

163

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

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

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

Resource allocation based on optimal transport theory in IoT edge computing

An efficient training optimization method for federated learning in 6G networks

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

Related Author

WANG Ye

SHI Ying

XIA Tianle

LIU Miao

YANG Jie

ZHAO Haitao

Jun SUN

Shangweikang ZHAO

Related Institution

Jiangsu Mobile Information System Integration Co., Ltd.

School of Internet of Things, Nanjing University of Posts and Telecommunications

Huazhong University of Science and Technology

The University of Sydney

Jiangsu Vocational College of Business

⁰