Evaluating the Effectiveness and Transferability of a Data-Driven Two-Region Perimeter Control Method Using Microsimulation

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.