Reservation-based Network Traffic Management Strategy for Connected and Automated Vehicles: A Multiagent System Approach

Abstract

Due to the increase in population and traffic demand, traffic congestion has become a major concern in urban areas. With the emergence of connected and automated vehicles (CAVs) and vehicle-to-infrastructure (V2I) communication, richer real-time information is becoming available and higher definition control (at the individual vehicle level) can be applied to mitigating traffic congestion. In this paper, we propose an innovative network traffic management (NTM) framework for CAVs using a multiagent system (MAS) approach, where we define the network management agent, vehicle agents and link agents. A link-level reservation-based strategy and optimal route searching algorithms are developed to route individual CAV traversing a given network in terms of minimizing its arrival time, while balancing the flow rate of each link. A numerical example is presented to evaluate the system performance under different scenarios. The results show that our system can reduce travel time in the range of 8 - 12%, compared with the state-of-the-practice strategy. The system can also balance link utilization across the network which is another key feature due to reservation.