车联网中联邦学习模型低时延传输迁移方法研究

王帅; 尹宏博; 江池; 张科; 张引

doi:10.11959/j.issn.2096-3750.2026.00525

您当前的位置：

首页 >

文章列表页 >

车联网中联邦学习模型低时延传输迁移方法研究

智能交通与智能网联 | 更新时间：2026-04-16

- 车联网中联邦学习模型低时延传输迁移方法研究
- Research on low-latency transmission migration method for federated learning models in the Internet of vehicles
- 物联网学报 2026年10卷第1期页码：30-40
- 作者机构：
  
  1.电子科技大学（深圳）高等研究院，广东深圳 518110
  2.电子科技大学信息与通信工程学院，四川成都 611731
  3.广东省智能机器人研究院，广东东莞 523830
- 作者简介：
  
  [ "王帅（2001‒ ），男，电子科技大学信息与通信工程学院硕士生，主要研究方向为算力网络、边缘智能。" ]
  [ "尹宏博（1998‒ ），男，电子科技大学信息与通信工程学院博士生，主要研究方向为算力网络、联邦学习、边缘计算。" ]
  [ "江池（1997‒ ），女，电子科技大学信息与通信工程学院博士生，主要研究方向为区块链、网络安全、生成模型。" ]
  [ "张科（1978‒ ），男，博士，电子科技大学信息与通信工程学院副教授，主要研究方向为边缘智能网络、智慧车联网、边缘计算。" ]
  [ "张引（1986‒ ），男，博士，电子科技大学（深圳）高等研究院研究员，主要研究方向为移动计算、算力网络、边缘智能。" ]
- 基金信息：
  
  广东省重点研发计划项目(2024B1111060001)
- DOI：10.11959/j.issn.2096-3750.2026.00525
  中图分类号： TN915.08
- 收稿：2025-08-28，
  
  修回：2025-09-28，
  
  录用：2025-10-20，
  
  纸质出版：2026-03-30
- 稿件说明：
移动端阅览
王帅,尹宏博,江池等.车联网中联邦学习模型低时延传输迁移方法研究[J].物联网学报,2026,10(01):30-40.

Wang Shuai,Yin Hongbo,Jiang Chi,et al.Research on low-latency transmission migration method for federated learning models in the Internet of vehicles[J].Chinese Journal on Internet of Things,2026,10(01):30-40.
王帅,尹宏博,江池等.车联网中联邦学习模型低时延传输迁移方法研究[J].物联网学报,2026,10(01):30-40. DOI： 10.11959/j.issn.2096-3750.2026.00525.

Wang Shuai,Yin Hongbo,Jiang Chi,et al.Research on low-latency transmission migration method for federated learning models in the Internet of vehicles[J].Chinese Journal on Internet of Things,2026,10(01):30-40. DOI： 10.11959/j.issn.2096-3750.2026.00525.

摘要

联邦学习因其分布式与隐私保护特性，在车联网数据安全领域中引起广泛关注。异步联邦学习机制能够更好地适应车辆算力网络状态的动态变化，在提升全局模型更新效率的同时，实现对本地隐私数据的有效保护。然而，恶意车辆在联邦学习训练中可能进行中毒攻击，上传恶意模型至全局模型，进而影响正常车辆的本地训练。在模型下发时，增加候选模型数量虽可提升规避恶意模型的概率，却会显著增加通信时延，影响系统性能。为了平衡安全性与时延，提出一种联邦学习模型传输迁移方法，对城市道路中移动车辆与路边单元（RSU

roadside unit）的交互过程以及模型下发安全性进行建模，通过强化学习优化车辆对RSU的传输迁移策略，在保证模型下发安全性的同时有效降低通信时延。仿真结果表明，该方法相较于基线方法平均传输时延降低了约7%，验证了其在安全性与通信时延方面的优势。

Abstract

Federated learning

due to its distributed and privacy-preserving characteristics

has attracted widespread attention in the field of data security in vehicular networks. The asynchronous federated learning mechanism can better adapt to the dynamic changes of vehicle computing power and network conditions

and at the same time improve the efficiency of global model updates and realize effective protection of local privacy data. However

the malicious vehicles in federated learning training may perform poisoning attacks by uploading malicious models to the global model

which in turn affects the local training of normal vehicles. During model dissemination

although increasing the number of candidate models can improve the probability of avoiding malicious models

it will significantly increase communication latency and affect system performance. To balance security and latency

a federated learning model transmission migration method was proposed. The interaction process between moving vehicles and roadside units (RSUs) on urban roads were modeled

as well as the security of model dissemination. Through reinforcement learning

the vehicle-to-RSU transmission migration strategy was optimized

ensuring the security of model dissemination while effectively reducing communication latency. Simulation results show that

compared with baseline methods

the proposed method reduces the average transmission latency by about 7%

which verifies its advantages in terms of security and communication latency.

关键词

Keywords

references

江恺 , 曹越 , 周欢 , 等 . 车联网边缘智能: 概念、架构、问题、实施和展望 [J ] . 物联网学报 , 2023 , 7 ( 1 ): 37 - 48 .

Jiang K , Cao Y , Zhou H , et al . Edge intelligence empowered Internet of vehicles: concept, framework, issues, implementation, and prospect [J ] . Chinese Journal on Internet of Things , 2023 , 7 ( 1 ): 37 - 48 .

Alalwany E , Mahgoub I . Security and trust management in the Internet of vehicles (IoV): challenges and machine learning solutions [J ] . Sensors , 2024 , 24 ( 2 ): 368 .

Wang X J , Zhu H L , Ning Z L , et al . Blockchain intelligence for Internet of vehicles: challenges and solutions [J ] . IEEE Communications Surveys & Tutorials , 2023 , 25 ( 4 ): 2325 - 2355 .

Khezri E , Hassanzadeh H , Yahya R O , et al . Security challenges in Internet of vehicles (IoV) for ITS: a survey [J ] . Tsinghua Science and Technology , 2025 , 30 ( 4 ): 1700 - 1723 .

胡海峰 , 张熙 , 赵海涛 , 等 . 移动边缘计算中通信高效的联邦学习模型剪枝算法 [J ] . 物联网学报 , 2024 , 8 ( 3 ): 112 - 126 .

Hu H F , Zhang X , Zhao H T , et al . Communication-efficient model pruning for federated learning in mobile edge computing [J ] . Chinese Journal on Internet of Things , 2024 , 8 ( 3 ): 112 - 126 .

李佳恒 , 吴钦木 . 基于三元联邦学习的车联网数据协同学习与通信优化研究 [J ] . 现代电子技术 , 2024 , 47 ( 15 ): 26 - 33 .

Li J H , Wu Q M . Research on Internet of vehicles data cooperative learning and communication optimization based on tripartite federated learning [J ] . Modern Electronics Technique , 2024 , 47 ( 15 ): 26 - 33 .

Liang F Y , Yang Q L , Liu R Q , et al . Semi-synchronous federated learning protocol with dynamic aggregation in Internet of vehicles [J ] . IEEE Transactions on Vehicular Technology , 2022 , 71 ( 5 ): 4677 - 4691 .

Sharma I , Sharma A , Gupta S K . Asynchronous and synchronous federated learning-based UAVs [C ] // Proceedings of the 2023 Third International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP) . Piscataway : IEEE Press , 2023 : 105 - 109 .

Stripelis D , Thompson P M , Ambite J L . Semi-synchronous federated learning for energy-efficient training and accelerated convergence in cross-silo settings [J ] . ACM Transactions on Intelligent Systems and Technology , 2022 , 13 ( 5 ): 1 - 29 .

Xu C H , Qu Y Y , Xiang Y , et al . Asynchronous federated learning on heterogeneous devices: a survey [J ] . Computer Science Review , 2023 , 50 : 100595 .

Wang Z Y , Zhang Z Y , Wang J . Asynchronous federated learning over wireless communication networks [C ] // Proceedings of the ICC 2021-IEEE International Conference on Communications . Piscataway : IEEE Press , 2021 : 1 - 7 .

Wang Z Y , Xu H L , Liu J C , et al . Resource-efficient federated learning with hierarchical aggregation in edge computing [C ] // Proceedings of the IEEE INFOCOM 2021 IEEE Conference on Computer Communications . Piscataway : IEEE Press , 2021 : 1 - 10 .

Nguyen T D , Rieger P , Chen H , et al . FLAME: taming backdoors in federated learning [C ] // Proceedings of USENIX Security Symposium . Berkeley : USENIX Association , 2022 .

Zhang X R , Chang Z , Hu T , et al . Vehicle selection and resource allocation for federated learning-assisted vehicular network [J ] . IEEE Transactions on Mobile Computing , 2024 , 23 ( 5 ): 3817 - 3829 .

廖岑卉珊 , 陈俊彦 , 梁观平 , 等 . 基于深度强化学习的SDN服务质量智能优化算法 [J ] . 物联网学报 , 2023 , 7 ( 1 ): 73 - 82 .

Liao C H S , Chen J Y , Liang G P , et al . Quality of service optimization algorithm based on deep reinforcement learning in software defined network [J ] . Chinese Journal on Internet of Things , 2023 , 7 ( 1 ): 73 - 82 .

Jiang K , Cao Y , Song Y J , et al . Asynchronous federated and reinforcement learning for mobility-aware edge caching in IoV [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 9 ): 15334 - 15347 .

Wang D , Song B , Lin P , et al . Resource management for edge intelligence (EI)-assisted IoV using quantum-inspired reinforcement learning [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 14 ): 12588 - 12600 .

赵晓焱 , 韩威 , 张俊娜 , 等 . 基于异步深度强化学习的车联网协作卸载策略 [J ] . 计算机应用 , 2024 , 44 ( 5 ): 1501 - 1510 .

Zhao X Y , Han W , Zhang J N , et al . Collaborative offloading strategy in Internet of vehicles based on asynchronous deep reinforcement learning [J ] . Journal of Computer Applications , 2024 , 44 ( 5 ): 1501 - 1510 .

刘冰艺 , 刘煜昊 , 韩玮祯 , 等 . 边缘智能下基于强化学习的车联网路由协议 [J ] . 通信学报 , 2023 , 44 ( 11 ): 110 - 119 .

Liu B Y , Liu Y H , Han W Z , et al . Edge intelligence-assisted routing protocol for Internet of vehicles via reinforcement learning [J ] . Journal on Communications , 2023 , 44 ( 11 ): 110 - 119 .

王为念 , 苏健 , 陈勇 , 等 . 基于多智能体深度强化学习的车联网频谱共享 [J ] . 电子学报 , 2024 , 52 ( 5 ): 1690 - 1699 .

Wang W N , Su J , Chen Y , et al . Multi-agent reinforcement learning enabled spectrum sharing for vehicular networks [J ] . Acta Electronica Sinica , 2024 , 52 ( 5 ): 1690 - 1699 .

Yao L , Xu X L , Bilal M , et al . Dynamic edge computation offloading for Internet of vehicles with deep reinforcement learning [J ] . IEEE Transactions on Intelligent Transportation Systems , 2023 , 24 ( 11 ): 12991 - 12999 .

Tang H J , Wu H M , Qu G J , et al . Double deep Q-network based dynamic framing offloading in vehicular edge computing [J ] . IEEE Transactions on Network Science and Engineering , 2023 , 10 ( 3 ): 1297 - 1310 .

Li H F , Chen C , Shan H G , et al . Deep deterministic policy gradient-based algorithm for computation offloading in IoV [J ] . IEEE Transactions on Intelligent Transportation Systems , 2024 .

Zhang H J , Jiang M H , Liu X N , et al . PPO-based PDACB traffic control scheme for massive IoV communications [J ] . IEEE Transactions on Intelligent Transportation Systems , 2023 , 24 ( 1 ): 1116 - 1125 .

ETSI . 5G; Study on channel model for frequencies from 0.5 to 100 GHz (3GPP TR 38.901 version 18.0.0 Release 18) [R ] . 2024 .

尹宏博 , 王帅 , 张科 , 等 . 车辆算力网络中异步鲁棒联邦学习方法研究 [J ] . 物联网学报 , 2024 , 8 ( 4 ): 14 - 22 .

Yin H B , Wang S , Zhang K , et al . Research on asynchronous robust federated learning method in vehicle computing power network [J ] . Chinese Journal on Internet of Things , 2024 , 8 ( 4 ): 14 - 22 .

Steimle L N , Kaufman D L , Denton B T . Multi-model Markov decision processes [J ] . IISE Transactions , 2021 , 53 ( 10 ): 1124 - 1139 .

Hazarika B , Singh K , Biswas S , et al . DRL-based resource allocation for computation offloading in IoV networks [J ] . IEEE Transactions on Industrial Informatics , 2022 , 18 ( 11 ): 8027 - 8038 .

Attia R , Hassaan A , Rizk R . Advanced greedy hybrid bio-inspired routing protocol to improve IoV [J ] . IEEE Access , 2021 , 9 : 131260 - 131272 .

Wang Y , Hu F J , Xu H C , et al . A multigroups cooperative particle swarm algorithm for optimization of multivehicle path planning in Internet of vehicles [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 22 ): 35839 - 35851 .

Yang C Y , Xu X L , Zhou X K , et al . Deep Q network-driven task offloading for efficient multimedia data analysis in edge computing-assisted IoV [J ] . 2022 , 18 ( 2 s): 1 - 24 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

空天地一体化网络技术：探索与展望

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

面向联邦学习标签翻转攻击的客户端选择防御方法

基于Decision Transformer模型的5G基站节能控制策略优化新范式研究