A decision support system for predicting and relieving traffic congestion in urban road networks from the perspective of connected vehicles.

This paper proposed a decision support system for predicting and alleviating urban road network traffic congestion from the perspective of the Internet of Vehicles. Firstly, the Internet of Vehicles utilizes GPS and OBU to collect urban road network data, which is then fused through Kalman filtering to extract congestion features and predicted using a CNN model. Secondly, design a decision support system for traffic congestion management, covering multiple modules such as data collection and preprocessing. Finally, a decision model is constructed with the goal of minimizing congestion time and maximizing traffic capacity, and solved using particle swarm optimization algorithm to achieve decision support for traffic congestion mitigation. The experimental results show that the proposed method has low traffic congestion time and road capacity utilization, indicating that it can provide scientific decision support for traffic congestion alleviation. [ABSTRACT FROM AUTHOR]