Search for: All records

Regional perimeter control based on the existence of macroscopic fundamental diagrams has been widely studied as an effective tool to regulate traffic and prevent oversaturation in dense urban areas. Significant research efforts have been performed concerning the modeling aspects of perimeter control. More recently, data-driven techniques for perimeter control have shown remarkable promise; however, few studies have examined the transferability of these techniques. While it is surely of the highest priority to devise effective perimeter control methods, the ability of such methods to transfer the learned knowledge and quickly adapt control policies to a new setting is critical, particularly in real-life situations where training a method from scratch is intractable. This work seeks to bridge this research gap by comprehensively examining the effectiveness and transferability of a reinforcement-learning-based perimeter control method for a two-region urban network in a microsimulation setting. The results suggest: 1) the presented data-driven method demonstrates promising control effectiveness in comparison with no perimeter control and an extended greedy controller and 2) the method can readily transfer its learned knowledge and adapt its control policy with newly collected data to simulation settings with different traffic demands, driving behaviors, or both. 

Perimeter metering control has long been an active research topic since well-defined relationships between network productivity and usage, that is, network macroscopic fundamental diagrams (MFDs), were shown to be capable of describing regional traffic dynamics. Numerous methods have been proposed to solve perimeter metering control problems, but these generally require knowledge of the MFDs or detailed equations that govern traffic dynamics. Recently, a study applied model-free deep reinforcement learning (Deep-RL) methods to two-region perimeter control and found comparable performances to the model predictive control scheme, particularly when uncertainty exists. However, the proposed methods therein provide very low initial performances during the learning process, which limits their applicability to real life scenarios. Furthermore, the methods may not be scalable to more complicated networks with larger state and action spaces. To combat these issues, this paper proposes to integrate the domain control knowledge (DCK) of congestion dynamics into the agent designs for improved learning and control performances. A novel agent is also developed that builds on the Bang-Bang control policy. Two types of DCK are then presented to provide knowledge-guided exploration strategies for the agents such that they can explore around the most rewarding part of the action spaces. The results from extensive numerical experiments on two- and three-region urban networks show that integrating DCK can (a) effectively improve learning and control performances for Deep-RL agents, (b) enhance the agents’ resilience against various types of environment uncertainties, and (c) mitigate the scalability issue for the agents.