Secure and transparent traffic congestion control system for smart city using a federated learning approach

Abstract

This study addresses the increasing problems of traffic congestion in smart cities by introducing a Secure and Transparent Traffic Congestion Control System using federated learning. Traffic congestion control systems face key issues such as data privacy, security vulnerabilities, and the necessity for joint decision-making. Federated learning, a type of distributed machine learning, is effective because it allows for training models on decentralized data while maintaining data privacy. Furthermore, incorporating blockchain technology improves the system’s security, integrity, and transparency. The proposed system uses federated learning to securely gather and analyze local traffic data from different sources within a smart city without moving sensitive data away from its original location. This method minimizes the risk of data breaches and privacy issues. Blockchain technology creates a permanent, transparent record for monitoring and confirming decisions related to traffic congestion control, thereby promoting trust and accountability. The combination of federated learning's decentralized nature and blockchain's secure, transparent features aids in building a strong traffic management system for smart cities. This research contributes to advancements in smart city technology, potentially improving traffic management and urban living standards. Moreover, tests of the new combined model show a high accuracy rate of 97.78% and a low miss rate of 2.22%, surpassing previous methods. The demonstrated efficiency and adaptability of the model to various smart city environments and its scalability in expanding urban areas are crucial for validating its practical use in real-world settings.