Adaptive Scheduling of Traffic Flow and Network Resources for Intelligent Connected Vehicles

This is the authors' abstract. We don't add key points for this paper.

In the context of autonomous driving, low-latency communication is essential for exchanging critical information and rapidly responding to driving control. Intelligent Connected Vehicles (ICVs) can communicate with each other through the Internet of Vehicles (IoV), enabling a tight coupling between IoVs and road traffic resources. Inefficient scheduling of IoV resources can lead to traffic congestion. Inappropriate road traffic flow control schemes may restrict the utilization of IoV resources. Therefore, it is crucial to deeply analyze this coupling relationship and further achieve bidirectional alignment between them. Nevertheless, there is a research gap in the investigation of the potential impact relationship between IoV resource scheduling schemes and road traffic flow control. In this paper, we reveal the correlation between vehicle spacing and road congestion, linking it to Perception-Reaction-Time (PRT). Meanwhile, we elucidate the interaction mechanism between IoV and the transportation network. Utilizing this comprehension, we formulate an adaptive scheduling model to improve the road traffic flow efficiency. We jointly adapt the resource allocation and road traffic control strategies according to the unique resource distribution and traffic conditions of each road. Furthermore, we present a Resource-matched Collaborative Decision-making and Trajectory-planning (RCDT) algorithm aimed at improving the throughput of the road network. Simulation results demonstrate that our proposed approach can significantly enhance traffic network efficiency compared to those strategies focused solely on road traffic control.