高速车联网场景下分簇式无线联邦学习算法

doi:10.11772/j.issn.1001-9081.2020121912

计算机应用 ›› 2021, Vol. 41 ›› Issue (6): 1546-1550.DOI: 10.11772/j.issn.1001-9081.2020121912

所属专题： 2020年全国开放式分布与并行计算学术年会（DPCS 2020）

• 2020年全国开放式分布与并行计算学术年会（DPCS 2020） • 上一篇下一篇

高速车联网场景下分簇式无线联邦学习算法

王家瑞^1,2, 谭国平^1,2, 周思源^1,2

1. 河海大学计算机与信息学院南京 211100;
2. 江苏智能交通及智能驾驶研究院南京 210019

收稿日期:2020-11-04 修回日期:2021-03-31 出版日期:2021-06-10 发布日期:2021-06-23
通讯作者: 谭国平
作者简介:王家瑞(1998-),男,山东威海人,硕士研究生,主要研究方向:无线网络;谭国平(1975-),男,湖南澧县人,教授,博士,CCF会员,主要研究方向:无线通信系统与网络;周思源(1985-),男,江苏南京人,副教授,博士,CCF会员,主要研究方向:无线通信。
基金资助:
国家自然科学基金资助项目（61701168，61832005，61571303）；中国博士后科学基金资助项目（2019M651546）；江苏省交通技术改造项目（2018Y45）。

Clustered wireless federated learning algorithm in high-speed internet of vehicles scenes

WANG Jiarui^1,2, TAN Guoping^1,2, ZHOU Siyuan^1,2

1. School of Computer and Information, Hohai University, Nanjing Jiangsu 211100, China;
2. Jiangsu Intelligent Transportation and Intelligent Driving Research Institute, Nanjing Jiangsu 210019, China

Received:2020-11-04 Revised:2021-03-31 Online:2021-06-10 Published:2021-06-23
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61701168, 61832005, 61571303), the China Postdoctoral Science Foundation (2019M651546), the Jiangsu Province Transportation Technology Transformation Project (2018Y45).

摘要/Abstract

摘要： 现有无线联邦学习框架缺乏对实际的分布式高速车联网（IoV）场景的有效支持。针对该场景下的分布式学习问题，提出了一种基于随机网络拓扑模型的分布式训练算法——分簇式无线联邦学习算法（C-WFLA）。首先，该算法基于高速公路场景下的车辆分布情况设计网络模型；其次，该算法考虑了用户端进行上行数据传输时的路径衰落、瑞利衰落等因素；最后，该算法设计了基于分簇式训练的无线联邦学习方法。利用所提算法对手写体识别模型进行了训练与测试，仿真结果表明：在信道状态较好、用户发射功率受限较小的情况下，传统无线联邦学习算法与C-WFLA在相同的训练条件下损失函数均能收敛至相近的数值，且C-WFLA收敛更快；而在信道状态较差、用户发射功率受限较大的情况下，C-WFLA损失函数收敛值相较于传统的集中式算法可以降低10%~50%。可见，C-WFLA更有助于高速IoV场景下的模型训练。

关键词: 无线联邦学习, 随机拓扑, 车联网, 分布式学习, 分簇算法

Abstract: Existing wireless federated learning frameworks lack the effective support for the actual distributed high-speed Internet of Vehicles (IoV) scenes. Aiming at the distributed learning problem in such scenes, a distributed training algorithm based on the random network topology model named Clustered-Wireless Federated Learning Algorithm (C-WFLA) was proposed. In this algorithm, firstly, a network model was designed on the basis of the distribution situation of vehicles in the highway scene. Secondly, the path fading, Rayleigh fading and other factors during the uplink data transmission of the users were considered. Finally, a wireless federated learning method based on clustered training was designed. The proposed algorithm was used to train and test the handwriting recognition model. The simulation results show that under the situations of good channel state and little user transmit power limit, the loss functions of traditional wireless federated learning algorithm and C-WFLA can converge to similar values under the same training condition, but C-WFLA converges faster; under the situations of poor channel state and much user transmit power limit, C-WFLA can reduce the convergence value of loss function by 10% to 50% compared with the traditional centralized algorithm. It can be seen that C-WFLA is more helpful for model training in high-speed IoV scenes.

Key words: wireless federated learning, random topology, Internet of Vehicles (IoV), distributed learning, clustering algorithm

中图分类号:

TN929.5

王家瑞, 谭国平, 周思源. 高速车联网场景下分簇式无线联邦学习算法[J]. 计算机应用, 2021, 41(6): 1546-1550.

WANG Jiarui, TAN Guoping, ZHOU Siyuan. Clustered wireless federated learning algorithm in high-speed internet of vehicles scenes[J]. Journal of Computer Applications, 2021, 41(6): 1546-1550.

参考文献

[1] DWORK C. Differential privacy:a survey of results[C]//Proceedings of the 2008 International Conference on Theory and Applications of Models of Computation, LNCS 4978. Berlin:Springer,2008:1-19.
[2] SWEENY L. k-anonymity:a model for protecting privacy[J]. International Journal of Uncertainty,Fuzziness and KnowledgeBased Systems,2002,10(5):557-570.
[3] KANG J,YU R,HUANG X,et al. Privacy-preserved pseudonym scheme for fog computing supported internet of vehicles[J]. IEEE Transactions on Intelligent Transportation Systems,2018,19(8):2627-2637.
[4] SUN Y,WU L,WU S,et al. Security and privacy in the internet of vehicles[C]//Proceedings of the 2015 International Conference on Identification, Information, and Knowledge in the Internet of Things. Piscataway:IEEE,2015:116-121.
[5] KANG J,YU R,HUANG X,et al. Location privacy attacks and defenses in cloud-enabled internet of vehicles[J]. IEEE Wireless Communications,2016,23(5):52-59.
[6] SUN G,SUN S,SUN J,et al. Security and privacy preservation in fog-based crowd sensing on the internet of vehicles[J]. Journal of Network and Computer Applications,2019,134:89-99.
[7] JOY J,GERLA M. Internet of Vehicles and autonomous connected car-privacy and security issues[C]//Proceedings of the 26th International Conference on Computer Communication and Networks. Piscataway:IEEE,2017:1-9.
[8] AMIRI M M,GÜNDÜZ D. Federated learning over wireless fading channels[J]. IEEE Transactions on Wireless Communications, 2020,19(5):3546-3557.
[9] YANG Q,LIU Y,CHENG Y,et al. Federated Learning[M]. San Rafael:Morgan & Claypool Publishers,2020:1-207.
[10] ZHAO Y,LI M,LAI L,et al. Federated learning with non-ⅡD data[EB/OL].[2019-06-29]. https://arxiv.org/pdf/1806.00582.pdf.
[11] SAMARAKOON S,BENNIS M,SAAD W,et al. Distributed federated learning for ultra-reliable low-latency vehicular communications[J]. IEEE Transactions on Communications, 2020,68(2):1146-1159.
[12] KONEČNÝ J,MCMAHAN H B,YU F X,et al. Federated learning:strategies for improving communication efficiency[EB/OL].[2019-06-29]. https://arxiv.org/pdf/1610.05492.pdf.
[13] JIANG R,ZHOU S. Cluster-based cooperative digital over-the-air aggregation for wireless federated edge learning[C]//Proceedings of the 2020 IEEE/CIC International Conference on Communications in China. Piscataway:IEEE,2020:887-892
[14] SATTLER F,WIEDEMANN S,SAMEK W,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.
[15] 牛志升, SHEN S, 张钦宇, 等. 面向沉浸式体验的空天地一体化车联网体系架构与关键技术[J]. 物联网学报, 2017, 1(2):17-27.(NIU Z S,SHEN S,ZHANG Q Y,et al. Space-air-ground integrated vehicular network for immersive driving experience[J]. Chinese Journal on Internet of Things,2017,1(2):17-27.)
[16] 尉志青, 马昊, 张奇勋, 等. 感知-通信-计算融合的智能车联网挑战与趋势[J]. 中兴通讯技术, 2020, 26(1):45-49.(WEI Z Q, MA H,ZHANG Q X,et al. Challenge and trend of sensing, communication and computing integrated intelligent internet of vehicle[J]. ZTE Technology Journal,2020,26(1):45-49.)
[17] 许瑞琛, 王俊峰, 张莎. LTE-V2X测试与仿真从入门到精通[M]. 北京:人民邮电出版社, 2018:127-128.(XU R C,WANG J F,ZHANG S. LTE-V2X Testing and Simulation:From Initiation to Mastery[M]. Beijing:Posts & Telecom Press, 2018:127-128.)

高速车联网场景下分簇式无线联邦学习算法

Clustered wireless federated learning algorithm in high-speed internet of vehicles scenes

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[2]	陈葳葳, 曹利, 顾翔. 基于区块链的车联网电子取证模型[J]. 计算机应用, 2021, 41(7): 1989-1995.
[3]	巫光福, 王影军. 基于区块链与云-边缘计算混合架构的车联网数据安全存储与共享方案[J]. 计算机应用, 2021, 41(10): 2885-2892.
[4]	陈锦宇, 刘兆伟. 基于改进投票证明共识协议的车联网系统[J]. 计算机应用, 2021, 41(1): 170-176.
[5]	胡润彦, 李翠然. 基于模糊控制的自供能无线传感器网络分簇算法[J]. 计算机应用, 2020, 40(9): 2691-2697.
[6]	黄辰, 曹建农, 王时绘, 张龑. 基于协作反馈控制算法的车联网行车安全动态强化模型[J]. 计算机应用, 2020, 40(4): 1209-1214.
[7]	陈葳葳, 曹利, 邵长虹. 基于区块链技术的车联网高效匿名认证方案[J]. 计算机应用, 2020, 40(10): 2992-2999.
[8]	樊娜, 朱光源, 康军, 唐蕾, 朱依水, 王路阳, 段嘉欣. 车联网环境下基于节点认知交互的路由算法[J]. 计算机应用, 2019, 39(2): 518-522.
[9]	陈镜任, 吴业福, 吴冰. 基于车辆行驶数据的驾驶人行为谱分析方法[J]. 计算机应用, 2018, 38(7): 1916-1922.
[10]	袁娜, 史昕, 赵祥模. 基于改进人工鱼群算法的车辆轨迹规划方法[J]. 计算机应用, 2018, 38(10): 3030-3035.
[11]	董柏宏, 邓健, 张定杰, 吴维刚. 软件定义车联网的数据转发策略和路由选择技术[J]. 计算机应用, 2018, 38(1): 26-30.
[12]	张春花, 臧海娟, 薛小平, 张芳, 陈康强, 冯丽娟. 车联网轨迹隐私保护研究进展[J]. 计算机应用, 2017, 37(7): 1921-1925.
[13]	左雨星, 郭爱煌, 黄博, 王露. 基于网络效用最大化的车联网功率控制算法[J]. 计算机应用, 2017, 37(12): 3345-3350.
[14]	杨志伟, 陈昊亮, 张波, 吴丽娟, 吴维刚. 软件定义车联网的数据转发机制[J]. 计算机应用, 2017, 37(1): 84-89.
[15]	王永胜, 谭国真, 刘明剑, 丁男. 车联网环境下的公交自适应优先方法[J]. 计算机应用, 2016, 36(8): 2181-2186.