Improving Network Performance in Intelligent Transportation Systems Using Real Traffic Data

This paper focused on developing approaches to improving the intelligent transportation systems network performance by incorporating actual traffic information and optimized computation methods. The course of the investigation entails the assessment of three protocols including the vehicular ad hoc network, 5G and a blend of both at different pool traffic densities. Based on observations made in latency, throughput, and efficiency, the most suitable protocol for intelligent transportation systems implementation is identified. The study is divided into a number of steps comprising the study of network performance under various traffic loads, the absolute comparison of the protocols, and the last step which aims at the simulation of the enhanced algorithms. Analysis shows that the proposed hybrid architecture performs better than regular vehicular ad hoc network and 5G systems in high density traffic conditions. Furthermore, this study shows how real-time data can enhance system interactivity and effectiveness in core processes. The findings advance the understanding of intelligent transportation systems and shed light on future work towards the optimization of intelligent transportation systems to increasingly allow for urban mobility and automated vehicle systems. It also proposes other directions of research on the synergy of machine learning with edge computing for network protocol enhancement.