Securing real-time traffic analytics with a privacy-preserving edge and cloud computing framework

The recent demand for real-time traffic management in urban environments has led to the adoption of edge and cloud computing, which improve the efficiency, scalability, and security of traffic analytics. Nevertheless, the privacy and confidentiality of traffic data remain important issues. In this study, a privacy-sensitive real-time traffic analytics system is proposed that combines edge computing for local-area data processing and cloud computing for large-scale analytics. This system uses blockchain, encryption, and differential privacy to safeguard sensitive traffic information and ensure information integrity and confidentiality. The proposed system was evaluated through a set of simulation experiments and compared with existing models, namely BFRT, FedTSE, FLAGCN, and VehiCast. The results indicate that the suggested system is more successful at reducing latency, power consumption, and load balancing, and at improving data security, achieving 30% latency reduction and 15-30% power reduction. In addition, the system was highly scalable, able to process an increasing number of edge devices and cloud servers without significant performance impairment. The work overall offers a scalable, robust real-time traffic control platform and insight into integrating the edge-cloud computing system into intelligent transportation systems (ITS) with privacy-preserving technologies.