一种基于区块链和联邦学习融合的交通流预测方法

智慧; 段苗苗; 杨利霞; 黄彧; 费洁; 王雅宁

doi:10.11999/JEIT240030

一种基于区块链和联邦学习融合的交通流预测方法

doi: 10.11999/JEIT240030

智慧^{1, 2, ,},
段苗苗^{1, 2},
杨利霞¹,
黄彧^{1, 2},
费洁^{1, 2},
王雅宁^{1, 2}

1.
安徽大学电子信息工程学院合肥 230601
2.
安徽大学智能计算与信号处理教育部重点实验室合肥 230601

基金项目: 国家自然科学基金(62001001, U21A20457, 62071003, 41874174, 61901004)，安徽省高新领域重点研发计划(202304a05020011)，安徽省研究生教育质量工程项目(2023qygzz005)，安徽省高校自然学科研究项目(2022AH050109)；安徽省自然科学基金项目(2008085MF186)，安徽省高校协同创新项目(GXXT-2020-050)；安徽省高校国防科技与协同创新项目(GXXT-2021-028)

详细信息

作者简介:
智慧：女，副教授，研究方向为区块链、协作通信、网络编码和无线传感器网络

段苗苗：女，硕士生，研究方向为交通流预测、联邦学习、区块链和接入点选择

杨利霞：男，教授，研究方向为电磁散射与逆散射、无线通信系统中的电波传播及天线理论与设计和计算电磁学等

黄彧：男，硕士生，研究方向为区块链、设备对设备通信、移动边缘计算和物联网通信

费洁：女，硕士生，研究方向为中继选择、机器学习和强化学习

王雅宁：女，硕士生，研究方向为无线网络中的网络、资源和服务管理以及网络资源分配

通讯作者:
智慧　zhihui_0902@163.com

中图分类号: TN915.41
计量
- 文章访问数: 165
- HTML全文浏览量: 59
- PDF下载量: 30
- 被引次数: 0
出版历程
- 收稿日期: 2024-01-19
- 修回日期: 2024-07-14
- 网络出版日期: 2024-08-02
- 刊出日期: 2024-09-26

A Traffic Flow Prediction Method Based on the Fusion of Blockchain and Federated Learning

ZHI Hui^{1, 2
, ,},
DUAN Miaomiao^{1, 2},
YANG Lixia¹,
HUANG Yu^{1, 2},
FEI Jie^{1, 2},
WANG Yaning^{1, 2}

1.
School of Electronic and Information Engineering, Anhui University, Hefei 230601, China
2.
Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei 230601, China

Funds: The National Natural Science Foundation of China (62001001, U21A20457, 62071003, 41874174, 61901004), Anhui Province high-tech Field Key Research and Development Program (202304a05020011), Anhui Graduate Education Quality Project (2023qygzz005), The Natural Science Research Project of Anhui University (2022AH050109), The Natural Science Foundation of Anhui Province (2008085MF186), Anhui University Collaborative Innovation Project (GXXT-2020-050), The National Defense Technology and Collaborative Innovation Project of Anhui University (GXXT-2021-028)

摘要

摘要: 智能交通领域中实时准确地交通流预测一直是城市发展中的重中之重，这对提高路网运行效率起着至关重要的作用。现有的交通流预测方法大多是基于机器学习的，忽略了客户端不愿意参与预测任务或者为获得高奖励而撒谎的情况，从而在模型聚合时导致交通流预测的准确率下降。该文提出一种基于区块链和联邦学习融合的交通流预测方法(TFPM-BFL)来解决这一问题。在该方法中，利用加入了注意机制的长短期记忆网络(LSTM)模型进行本地预测，提高预测准确率；设计了基于信誉评定的激励机制，通过评估客户端上传的模型质量得到本地和局部信誉值，根据信誉值评定结果进行奖励分配，从而激励客户端参与联邦学习(FL)；边缘服务器(ES)采用基于信誉值和压缩率的模型聚合方法来提高模型聚合质量。仿真结果表明，TFPM-BFL能够实现准确、及时地交通流预测，在保证底层数据私密的同时可以有效地激励客户端参与联邦学习任务，而且可以实现高质量的模型聚合。
- 交通流预测 /
- 联邦学习 /
- 区块链 /
- 激励机制
Abstract: In the field of intelligent transportation, real-time and accurate traffic flow prediction has always been the top priority in urban development, which plays a crucial role in improving the operation efficiency of the road network. Most of the existing traffic flow prediction methods are based on machine learning, ignoring cases where the client is unwilling to participate in the prediction task or lies in order to obtain high rewards, resulting in a decline in the accuracy of traffic flow prediction when the model is aggregated. This paper proposes a Traffic Flow Prediction Method Based on Blockchain and Federated Learning (TFPM-BFL) to solve this problem. In this method, the client uses the Long Short-Term Memory (LSTM) model with attention mechanism to make local prediction and improve the prediction accuracy. An incentive mechanism based on credit rating is designed. Local and local credit values are obtained by evaluating the quality of the model uploaded by the client, and rewards are distributed according to the credit rating results, so as to encourage the client to participate in federal learning. Edge Server (ES) uses the model aggregation method based on credit value and compression rate to improve the model aggregation quality. The simulation results show that TFPM-BFL can achieve accurate and timely traffic flow prediction, effectively motivate clients to participate in Federated Learning (FL) tasks while ensuring the privacy of underlying data, and realize high-quality model aggregation.
- Traffic flow prediction /
- Federated learning /
- Blockchain /
- Incentive mechanism

HTML全文

图 1 TFPM-BFL的系统模型

下载: 全尺寸图片幻灯片

图 2 TFPM-BFL的工作流程

下载: 全尺寸图片幻灯片

图 3 改进的LSTM与LSTM模型预测对比

下载: 全尺寸图片幻灯片

图 4 不同模型质量情况下的信誉值对比

下载: 全尺寸图片幻灯片

图 5 说谎程度对全局信誉值的影响

下载: 全尺寸图片幻灯片

图 6 不同压缩率对客户端交通流预测的影响

下载: 全尺寸图片幻灯片

参考文献(30)

[1]	MEDINA-SALGADO B, SÁNCHEZ-DELACRUZ E, POZOS-PARRA P, et al. Urban traffic flow prediction techniques: A review[J]. Sustainable Computing: Informatics and Systems, 2022, 35: 100739. doi: 10.1016/j.suscom.2022.100739.
[2]	LIU Yi, YU J J Q, KANG Jiawen, et al. Privacy-preserving traffic flow prediction: A federated learning approach[J]. IEEE Internet of Things Journal, 2020, 7(8): 7751–7763. doi: 10.1109/JIOT.2020.2991401.
[3]	LI Cong and XU Pei. Application on traffic flow prediction of machine learning in intelligent transportation[J]. Neural Computing and Applications, 2021, 33(2): 613–624. doi: 10.1007/s00521-020-05002-6.
[4]	RAZALI N A M, SHAMSAIMON N, ISHAK K K, et al. Gap, techniques and evaluation: Traffic flow prediction using machine learning and deep learning[J]. Journal of Big Data, 2021, 8(1): 152. doi: 10.1186/s40537-021-00542-7.
[5]	ZHANG Hongyi, DAKKAK A, MATTOS D I, et al. Towards federated learning: A case study in the telecommunication domain[C]. The 12th International Conference on Software Business (ICSOB), Drammen, Norway, 2021: 238–253.
[6]	JIMÉNEZ-LOSADA A and ORDÓÑEZ M. Sharing profits in formal fuzzy contexts[J]. Fuzzy Sets and Systems, 2023, 466: 108452. doi: 10.1016/j.fss.2022.12.008.
[7]	YANG Shuo, WU Fan, TANG Shaojie, et al. On designing data quality-aware truth estimation and surplus sharing method for mobile crowdsensing[J]. IEEE Journal on Selected Areas in Communications, 2017, 35(4): 832–847. doi: 10.1109/JSAC.2017.2676898.
[8]	JUAREZ R, NITTA K, and VARGAS M. Coalitional efficient profit-sharing[J]. Economics Letters, 2021, 204: 109875. doi: 10.1016/j.econlet.2021.109875.
[9]	WUMAIER H, GAO Jian, and ZHOU Jin. Short-term forecasting method for dynamic traffic flow based on stochastic forest algorithm[J]. Journal of Intelligent & Fuzzy Systems, 2020, 39(2): 1501–1513. doi: 10.3233/JIFS-179924.
[10]	ZHOU Teng, HAN Guoqiang, XU Xuemiao, et al. A learning-based multimodel integrated framework for dynamic traffic flow forecasting[J]. Neural Processing Letters, 2019, 49(1): 407–430. doi: 10.1007/s11063-018-9804-x.
[11]	ZHENG Jianhu and HUANG Mingfang. Traffic flow forecast through time series analysis based on deep learning[J]. IEEE Access, 2020, 8: 82562–82570. doi: 10.1109/ACCESS.2020.2990738.
[12]	ZHANG Chuanting, DANG Shuping, SHIHADA B, et al. Dual attention-based federated learning for wireless traffic prediction[C]. The 2021 IEEE Conference on Computer Communications (IEEE INFOCOM), Vancouver, Canada, 2021: 1–10. doi: 10.1109/INFOCOM42981.2021.9488883.
[13]	ZHANG Pengfei, CHENG Xiang, SU Sen, et al. Effective truth discovery under local differential privacy by leveraging noise-aware probabilistic estimation and fusion[J]. Knowledge-Based Systems, 2023, 261: 110213. doi: 10.1016/j.knosys.2022.110213.
[14]	FENG Jun, YANG L T, ZHU Qing, et al. Privacy-preserving tensor decomposition over encrypted data in a federated cloud environment[J]. IEEE Transactions on Dependable and Secure Computing, 2020, 17(4): 857–868. doi: 10.1109/TDSC.2018.2881452.
[15]	FENG Jun, YANG L T, REN Bocheng, et al. Tensor recurrent neural network with differential privacy[J]. IEEE Transactions on Computers, 2024, 73(3): 683–693. doi: 10.1109/TC.2023.3236868.
[16]	GUO Hao, MEESE C, LI Wanxin, et al. B²SFL: A Bi-level blockchained architecture for secure federated learning-based traffic prediction[J]. IEEE Transactions on Services Computing, 2023, 16(6): 4360–4374. doi: 10.1109/TSC.2023.3318990.
[17]	QI Yuanhang, HOSSAIN M S, NIE Jiangtian, et al. Privacy-preserving blockchain-based federated learning for traffic flow prediction[J]. Future Generation Computer Systems, 2021, 117: 328–337. doi: 10.1016/j.future.2020.12.003.
[18]	MEESE C, CHEN Hang, ASIF S A, et al. BFRT: Blockchained federated learning for real-time traffic flow prediction[C]. The 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid), Taormina, Italy, 2022: 317–326. doi: 10.1109/CCGrid54584.2022.00041.
[19]	YU Han, LIU Zelei, LIU Yang, et al. A sustainable incentive scheme for federated learning[J]. IEEE Intelligent Systems, 2020, 35(4): 58–69. doi: 10.1109/MIS.2020.2987774.
[20]	LIU Zelei, CHEN Yuanyuan, YU Han, et al. GTG-Shapley: Efficient and accurate participant contribution evaluation in federated learning[J]. ACM Transactions on Intelligent Systems and Technology, 2022, 13(4): 60. doi: 10.1145/3501811.
[21]	NG J S, LIM W Y B, XIONG Zehui, et al. A hierarchical incentive design toward motivating participation in coded federated learning[J]. IEEE Journal on Selected Areas in Communications, 2022, 40(1): 359–375. doi: 10.1109/JSAC.2021.3126057.
[22]	KILIÇ D K and UĞUR Ö. Hybrid wavelet-neural network models for time series[J]. Applied Soft Computing, 2023, 144: 110469. doi: 10.1016/j.asoc.2023.110469.
[23]	PENG Le, LUO Gaoxiang, WALKER A, et al. Evaluation of federated learning variations for COVID-19 diagnosis using chest radiographs from 42 US and European hospitals[J]. Journal of the American Medical Informatics Association, 2023, 30(1): 54–63. doi: 10.1093/jamia/ocac188.
[24]	WANG Tianxiang, ZHENG Zhonglong, TANG Changbing, et al. Aggregation rules based on stochastic gradient descent in Byzantine consensus[C]. The IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), Chongqing, China, 2019: 317–324. doi: 10.1109/ITAIC.2019.8785560.
[25]	BONAWITZ K, IVANOV V, KREUTER B, et al. Practical secure aggregation for privacy-preserving machine learning[C]. The 24th ACM SIGSAC Conference on Computer and Communications Security (ACM CCS), Dallas, USA, 2017: 1175–1191. doi: 10.1145/3133956.3133982.
[26]	LI Dun, HAN Dezhi, WENG T H, et al. Blockchain for federated learning toward secure distributed machine learning systems: A systemic survey[J]. Soft Computing, 2022, 26(9): 4423–4440. doi: 10.1007/s00500-021-06496-5.
[27]	ZHU Shanliang, ZHAO Yu, ZHANG Yanjie, et al. Short-term traffic flow prediction with wavelet and multi-dimensional Taylor network model[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(5): 3203–3208. doi: 10.1109/TITS.2020.2977610.
[28]	CUI Laizhong, SU Xiaoxin, and ZHOU Yipeng. A fast blockchain-based federated learning framework with compressed communications[J]. IEEE Journal on Selected Areas in Communications, 2022, 40(12): 3358–3372. doi: 10.1109/JSAC.2022.3213345.
[29]	CHEN Chao. Freeway performance measurement system (PeMS)[D]. [Ph. D. dissertation], University of California, 2002.
[30]	LÜ Yisheng, DUAN Yanjie, KANG Wenwen, et al. Traffic flow prediction with big data: A deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2): 865–873. doi: 10.1109/TITS.2014.2345663.