Research on Application of Federated Learning of Blockchain Technology System under Computer Networking Technology
- Resource Type
- Conference
- Authors
- Li, Qiong
- Source
- 2022 IEEE 5th International Conference on Information Systems and Computer Aided Education (ICISCAE) Information Systems and Computer Aided Education (ICISCAE), 2022 IEEE 5th International Conference on. :471-474 Sep, 2022
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Training
Data privacy
Privacy
Federated learning
Computational modeling
Simulation
Scalability
Computer
vehicle network
federated learning
edge computing
- Language
- ISSN
- 2770-663X
This paper proposes an edge computing privacy protection method based on blockchain and federated learning to address the efficiency problem of privacy data sharing on the Internet of Vehicles. This paper uses blockchain to endow edge computing with anti-tampering and single-point-of-failure attacks and integrates gradient verification and incentive mechanisms into the consensus protocol. This encourages more local devices to contribute computing power and data honestly to federated learning. In this paper, the distributed model is safely shared by building a master-slave chain architecture between vehicles, roadside units, and base stations. At the same time, the paper proposes an asynchronous federated learning algorithm based on an incentive mechanism. The research results show that the proposed mechanism can improve the efficiency of data sharing and has sure scalability.