Dual-Layer Federated Learning Based Edge Collaborative Computing Mechanism for High Dynamic Internet of Vehicle Businesses

XU Si-ya; GUO Jia-hui

doi:10.12263/DZXB.20230065

您当前的位置：

首页 >

文章列表页 >

Dual-Layer Federated Learning Based Edge Collaborative Computing Mechanism for High Dynamic Internet of Vehicle Businesses

PAPERS | 更新时间：2025-12-24

- Dual-Layer Federated Learning Based Edge Collaborative Computing Mechanism for High Dynamic Internet of Vehicle Businesses
- ACTA ELECTRONICA SINICA Vol. 52, Issue 7, Pages: 2228-2241(2024)
- 作者机构：
  
  北京邮电大学网络与交换技术全国重点实验室，北京 100876
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62201074);Innovation and Development Project of Industrial Internet
- DOI：10.12263/DZXB.20230065
  CLC： TN92;
- Received：20 January 2023，
  
  Revised：2023-06-13，
  
  Published：25 July 2024
- 稿件说明：
移动端阅览
徐思雅,郭佳惠. 基于双层联邦学习的高动态车联网业务边缘协作计算机制[J]. 电子学报,2024,52(07):2228-2241.

XU Si-ya, GUO Jia-hui. Dual-Layer Federated Learning Based Edge Collaborative Computing Mechanism for High Dynamic Internet of Vehicle Businesses[J]. Acta Electronica Sinica, 2024, 52(07): 2228-2241.
徐思雅,郭佳惠. 基于双层联邦学习的高动态车联网业务边缘协作计算机制[J]. 电子学报,2024,52(07):2228-2241. DOI：10.12263/DZXB.20230065

XU Si-ya, GUO Jia-hui. Dual-Layer Federated Learning Based Edge Collaborative Computing Mechanism for High Dynamic Internet of Vehicle Businesses[J]. Acta Electronica Sinica, 2024, 52(07): 2228-2241. DOI：10.12263/DZXB.20230065

摘要

联邦学习作为一种新兴的分布式机器学习架构，允许车联网中多个车辆终端进行本地模型训练，并在兼顾数据隐私保护的条件下实现模型的全局聚合，从而提供可靠的车联网服务.然而，在联邦学习训练过程中，车辆终端往往因其高移动性在不同区域间切换训练，导致全局模型精度低.此外，恶意终端频繁上传无效或错误模型数据将导致车联网服务可靠性差.因此，本文提出了一种基于双层联邦学习的高动态车联网业务边缘协作计算机制.首先，综合考虑车辆终端的移动性、计算能力和可靠性，构建了终端服务能力模型，并提出了基于深度强化学习的边缘协作计算域构建算法，通过将多个边缘节点覆盖下的车辆终端进行聚簇训练，降低了终端本地模型的切换概率，从而保证联邦学习模型训练的持续性.进而，构建了包含边缘协作计算域内聚合层和域间聚合层的双层联邦学习框架，分别采用基于自适应聚合因子的本地模型半异步聚合机制和基于数据量的区域模型异步聚合机制，提升了联邦学习系统的聚合效率.特别地，考虑终端高速移动引起的跨域问题，引入了本地模型部分条件更新机制，避免了高质量模型被低质量模型覆盖的情况，进一步提高了全局模型准确率和系统资源利用率.仿真结果表明，本文所提机制在模型精度和服务可靠性等方面均优于本地计算、同步联邦学习和异步联邦学习算法.

Abstract

As an emerging distributed machine learning architecture

federated learning (FL) allows multiple users to train local models and achieve global aggregation of models with data privacy protection

thus providing reliable Internet of Vehicle (IoV) services. However

in the training process of FL

many training terminals may switch among domains due to the high mobility

resulting in low accuracy of the global model. Besides

malicious terminals may frequently upload invalid or incorrect model data which leads to low service reliability. Therefore

we build the dual-layer FL based edge collaborative computing mechanism for high dynamic IoV businesses. Firstly

we comprehensively consider the mobility

computing ability and reliability to construct the service capability model for the terminal

and then propose the edge collaborative computing domain (ECCD) construction algorithm based on deep reinforcement learning. By clustering the vehicle terminals covered by multiple edge nodes

the switching probability of the terminal local model will be reduced

and the sustainability of the FL model training can be guaranteed. Furthermore

we design a dual-layer FL framework including the inter-ECCD aggregation layer and cross-ECCD aggregation layer

respectively. It adopts the semi-asynchronous aggregation mechanism for local models based on the adaptive aggregation factor in the inter-ECCD aggregation layer

and the asynchronous aggregation mechanism for domain’s regional model based on data volume in the cross-ECCD aggregation layer

which jointly improve the aggregation efficiency of the FL system. In particular

considering that the high speed terminals may cause the cross-domain problem

we introduce the partial conditional update mechanism for the local model to avoid the situation that the high-quality models are covered by the low-quality models

which further improves the accuracy of the global model and the utilization of FL system resources. The simulation results verify that the proposed framework outperforms the local computing and asynchronous/synchronous FL algorithms in terms of model accuracy and service reliability.

关键词

Keywords

references

GAO Y J , LIU L , HU B X , et al . Federated region-learning for environment sensing in edge computing system [J ] . IEEE Transactions on Network Science and Engineering , 2020 , 7 ( 4 ): 2192 - 2204 .

QUANG HIEU N , TRAN T A , NGUYEN C L , et al . Deep reinforcement learning for resource management in blockchain-enabled federated learning network [J ] . IEEE Networking Letters , 2022 , 4 ( 3 ): 137 - 141 .

BOTTOU L , CURTIS F E , NOCEDAL J . Optimization methods for large-scale machine learning [J ] . SIAM Review , 2018 , 60 ( 2 ): 223 - 311 .

BONAWITZ K , EICHNER H , GRIESKAMP W , et al . Towards federated learning at scale: System design [EB/OL ] . ( 2019 )[2023 ] . http://arxiv.org/abs/1902.01046.pdf http://arxiv.org/abs/1902.01046.pdf .

LU Y L , HUANG X H , DAI Y Y , et al . Blockchain and federated learning for privacy-preserved data sharing in industrial IoT [J ] . IEEE Transactions on Industrial Informatics , 2020 , 16 ( 6 ): 4177 - 4186 .

ALOTAIBI J , ALAZZAWI L . PPIoV: A privacy preserving-based framework for IoV- fog environment using federated learning and blockchain [C ] // 2022 IEEE World AI IoT Congress (AIIoT) . Piscataway : IEEE , 2022 : 597 - 603 .

AHMED K M , IMTEAJ A , AMINI M H . Federated deep learning for heterogeneous edge computing [C ] // 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) . Piscataway : IEEE , 2021 : 1146 - 1152 .

CHEN M Z , YANG Z H , SAAD W , et al . A joint learning and communications framework for federated learning over wireless networks [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 1 ): 269 - 283 .

YU Z X , HU J , MIN G Y , et al . Mobility-aware proactive edge caching for connected vehicles using federated learning [J ] . IEEE Transactions on Intelligent Transportation Systems , 2021 , 22 ( 8 ): 5341 - 5351 .

MCMAHAN H B , MOORE E , RAMAGE D , et al . Communication-efficient learning of deep networks from decentralized data [EB/OL ] . ( 2016 )[2023 ] . http://arxiv.org/abs/1602.05629.pdf http://arxiv.org/abs/1602.05629.pdf .

SAMARAKOON S , BENNIS M , SAAD W , et al . Federated learning for ultra-reliable low-latency V2V communications [C ] // 2018 IEEE Global Communications Conference (GLOBECOM) . Piscataway : IEEE , 2018 : 1 - 7 .

FEYZMAHDAVIAN H R , AYTEKIN A , JOHANSSON M . An asynchronous mini-batch algorithm for regularized stochastic optimization [J ] . IEEE Transactions on Automatic Control , 2016 , 61 ( 12 ): 3740 - 3754 .

LU Y L , HUANG X H , ZHANG K , et al . Blockchain empowered asynchronous federated learning for secure data sharing in Internet of vehicles [J ] . IEEE Transactions on Vehicular Technology , 2020 , 69 ( 4 ): 4298 - 4311 .

WANG Z H , XIA G M , CHEN J , et al . Adaptive asynchronous federated learning for edge intelligence [C ] // 2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) . Piscataway : IEEE , 2021 : 285 - 289 .

PAN C , WANG Z , LIAO H J , et al . Asynchronous federated deep reinforcement learning-based URLLC-aware computation offloading in space-assisted vehicular networks [J ] . IEEE Transactions on Intelligent Transportation Systems , 2023 , 24 ( 7 ): 7377 - 7389 .

WU W T , HE L G , LIN W W , et al . SAFA: A semi-asynchronous protocol for fast federated learning with low overhead [J ] . IEEE Transactions on Computers , 2021 , 70 ( 5 ): 655 - 668 .

CHEN S , WANG X M , ZHOU P , et al . Heterogeneous semi-asynchronous federated learning in Internet of Things: A multi-armed bandit approach [J ] . IEEE Transactions on Emerging Topics in Computational Intelligence , 2022 , 6 ( 5 ): 1113 - 1124 .

XIAO H Z , ZHAO J , PEI Q Q , et al . Vehicle selection and resource optimization for federated learning in vehicular edge computing [J ] . IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 8 ): 11073 - 11087 .

熊小峰 , 黄淳岚 , 乐光学 , 等 . 边缘计算中基于综合信任评价的任务卸载策略 [J ] . 电子学报 , 2022 , 50 ( 9 ): 2134 - 2145 .

XIONG X F , HUANG C L , YUE G X , et al . Task offloading scheme based on comprehensive trust evaluation in edge computing [J ] . Acta Electronica Sinica , 2022 , 50 ( 9 ): 2134 - 2145 . (in Chinese)

WANG H , HUANG Y J , KHAJEPOUR A , et al . Local path planning for autonomous vehicles: Crash mitigation [C ] // 2018 IEEE Intelligent Vehicles Symposium (IV) . Piscataway : IEEE , 2018 : 1602 - 1606 .

BURD T D , BRODERSEN R W . Processor design for portable systems [J ] . Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology , 1996 , 13 ( 2 ): 203 - 221 .

ZHOU Z , CHEN X , LI E , et al . Edge intelligence: Paving the last mile of artificial intelligence with edge computing‍ [J ] . Proceedings of the IEEE , 2019 , 107 ( 8 ): 1738 - 1762 .

HE Y , ZHAO N , YIN H X . Integrated networking, caching, and computing for connected vehicles: A deep reinforcement learning approach [J ] . IEEE Transactions on Vehicular Technology , 2018 , 67 ( 1 ): 44 - 55 .

ZHANG K , ZHU Y X , LENG S P , et al . Deep learning empowered task offloading for mobile edge computing in urban informatics [J ] . IEEE Internet of Things Journal , 2019 , 6 ( 5 ): 7635 - 7647 .

刘全 , 翟建伟 , 章宗长 , 等 . 深度强化学习综述 [J ] . 计算机学报 , 2018 , 41 ( 1 ): 1 - 27 .

LIU Q , ZHAI J W , ZHANG Z Z , et al . A survey on deep reinforcement learning [J ] . Chinese Journal of Computers , 2018 , 41 ( 1 ): 1 - 27 . (in Chinese)

XIN F , ZHANG J H , LUO J Z , et al . Federated learning client selection mechanism under system and data heterogeneity [C ] // 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD) . Piscataway : IEEE , 2022 : 1239 - 1244 .

LU Y L , HUANG X H , DAI Y Y , et al . Differentially private asynchronous federated learning for mobile edge computing in urban informatics [J ] . IEEE Transactions on Industrial Informatics , 2020 , 16 ( 3 ): 2134 - 2143 .

KONEČNÝ J , MCMAHAN H B , RAMAGE D , et al . Federated optimization: Distributed machine learning for on-device intelligence [EB/OL ] . ( 2016 )[2023 ] . http://arxiv.org/abs/1610.02527.pdf http://arxiv.org/abs/1610.02527.pdf .

XIE C , KOYEJO S , GUPTA I . Asynchronous federated optimization [EB/OL ] . ( 2019 )[2023 ] . http://arxiv.org/abs/1903.03934.pdf http://arxiv.org/abs/1903.03934.pdf .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Blockchain-Based Hierarchical Federated Learning System

Research on Network Attack Detection Method Based on Federated Large Model

Adaptive Federated Learning Based Crowd Sensing Algorithm for Environmental Monitoring

Low-Cost Federated Learning Based on Lightweight Self-Distillation

Related Author

XU Si-ya

GUO Jia-hui

HU Rong-lei

LIU Si-hui

DUAN Xiao-yi

ZUO Pei-liang

ZHANG Yan-shuo

KANG Hai-yan

Related Institution

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

Department of Electronics and Information Engineering, Beijing Electronic Science and Technology Institute

Computer School, Beijing Information Science and Technology University

Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing

School of Computer Science, Hunan University of Technology and Business

⁰