An Integrated Approach for Freeway and Arterial Traffic Control Using Q-Learning Framework

The lack of communication between freeway and arterial road networks leads to sub-optimal traffic operation efficiency and frequent congestion at on-ramps and off-ramps in urban transportation systems. To address the issue, we propose an integrated freeway and arterial traffic control strategy using a Q-learning (QL) framework, which consists of a freeway traffic control (FTC) agent, an arterial traffic signal control (TSC) agent, and a dynamic speed offset (DSO) agent. The FTC agent exploits adjacent arterial signal timing and intersection demands to estimate on-ramp demands and takes proactive control actions. The TSC agent is able to adjust the signal timing to assist queue dissipation for nearest ramps. The DSO agent computes the relative offset and provides speed recommendations for adjacent arterial intersections. The states of each agent include the control action from other agents or real-time measurements from the neighboring environment, which facilitates the communication and coordination between different control components within the network. We compare the proposed approach with two under-coordinated approaches to quantify the benefit of the coordination mechanism using microscopic traffic simulations in various scenarios. As a result, the proposed approach significantly reduces ramp queues and freeway travel time in high-demand scenarios, albeit with a marginal trade-off in arterial travel time. Furthermore, it demonstrates consistent performance across different freeway incident locations.