A Blockchain-based Privacy Protection Scheme for V2G Interaction

被引:0
作者
Yan, Ziyi [1 ]
Yuan, Xiaodong [2 ]
Guo, Yajuan [2 ]
机构
[1] North China Univ Technol, Beijing, Peoples R China
[2] State Grid Jiangsu Elect Power Co Ltd, Res Inst, Nanjing, Peoples R China
来源
PROCEEDINGS OF THE 2024 3RD INTERNATIONAL CONFERENCE ON NETWORKS, COMMUNICATIONS AND INFORMATION TECHNOLOGY, CNCIT 2024 | 2024年
关键词
V2G Interaction; blockchain; federated learning; homomorphic encryption; secret sharing; secure aggregation; FEDERATED LEARNING FRAMEWORK;
D O I
10.1145/3672121.3672147
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
V2G interaction plays a crucial role in power peak and valley scheduling. Federated learning, as a privacy protection technology, is widely used in the V2G interaction process. However, issues such as the risk of local data leakage during local training, vulnerability of model gradients to reconstruction attacks during aggregation, and instability of central servers remain prevalent. To address these concerns, this paper proposes a blockchain-based privacy protection federated learning model for V2G interaction. By deploying the model on a blockchain, decentralization is achieved. Homomorphic encryption is employed during local training to protect users' temporal privacy without compromising the accuracy of local model training. During the model aggregation phase, a lightweight secure aggregation protocol is used to obscure the true gradient values of local models, ensuring model robustness and fault tolerance.
引用
收藏
页码:143 / 149
页数:7
相关论文
共 18 条
[1]   Federated learning with hierarchical clustering of local updates to improve training on non-IID data [J].
Briggs, Christopher ;
Fan, Zhong ;
Andras, Peter .
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[2]   A generalization of Paillier's public-key system with applications to electronic voting [J].
Damgard, Ivan ;
Jurik, Mads ;
Nielsen, Jesper Buus .
INTERNATIONAL JOURNAL OF INFORMATION SECURITY, 2010, 9 (06) :371-385
[3]   ON SECRET SHARING SYSTEMS [J].
KARNIN, ED ;
GREENE, JW ;
HELLMAN, ME .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1983, 29 (01) :35-41
[4]  
Kaur R., 2012, 2012 International Conference on Computing Sciences (ICCS), P295, DOI 10.1109/ICCS.2012.25
[5]   A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection [J].
Li, Qinbin ;
Wen, Zeyi ;
Wu, Zhaomin ;
Hu, Sixu ;
Wang, Naibo ;
Li, Yuan ;
Liu, Xu ;
He, Bingsheng .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (04) :3347-3366
[6]   A Blockchain-Based Decentralized Federated Learning Framework with Committee Consensus [J].
Li, Yuzheng ;
Chen, Chuan ;
Liu, Nan ;
Huang, Huawei ;
Zheng, Zibin ;
Yan, Qiang .
IEEE NETWORK, 2021, 35 (01) :234-241
[7]   Integration of renewable energy into the transport and electricity sectors through V2G [J].
Lund, Henrik ;
Kempton, Willett .
ENERGY POLICY, 2008, 36 (09) :3578-3587
[8]  
McMahan HB, 2017, PR MACH LEARN RES, V54, P1273
[9]  
Paillier P, 1999, LECT NOTES COMPUT SC, V1592, P223
[10]  
Pappas C, 2021, 2021 IFIP NETWORKING CONFERENCE AND WORKSHOPS (IFIP NETWORKING), DOI [10.23919/IFIPNetworking52078.2021.9472790, 10.23919/IFIPNETWORKING52078.2021.9472790]