Abstract
Traffic congestion has become common in urban areas worldwide. To solve this problem, the method of searching a solution using artificial intelligence has recently attracted widespread attention because it can solve complex problems such as traffic signal control. This study developed two traffic signal control models using reinforcement learning and a microscopic simulation-based evaluation for an isolated intersection and two coordinated intersections. To develop these models, a deep Q-network (DQN) was used, which is a promising reinforcement learning algorithm. The performance was evaluated by comparing the developed traffic signal control models in this research with the fixed-time signal optimized by Synchro model, which is a traffic signal optimization model. The evaluation showed that the developed traffic signal control model of the isolated intersection was validated, and the coordination of intersections was superior to that of the fixed-time signal control method.
Highlights
Background and purposeTraffic congestion in urban areas is a chronic social problem in modern society, and many urbanized areas suffer from chronic socioeconomic damage due to growing traffic congestion [1]
In the case of the microscopic traffic simulation, as the measures of effectiveness (MOEs) values calculated according to random numbers are measured differently, this study attempted to improve the accuracy of the analysis through five multi-runs for each scenario
It was found that the performance of the isolated intersection traffic signal control model developed in this study guarantee the performance of the optimized signal timing plan using Synchro
Summary
Background and purposeTraffic congestion in urban areas is a chronic social problem in modern society, and many urbanized areas suffer from chronic socioeconomic damage due to growing traffic congestion [1]. To solve the traffic congestion problem in urban areas, road capacity can be increased by the construction and expansion of roads, but these alternatives require enormous resources and time. The reduction in road capacity owing to the operation of traffic signals, which are major traffic control devices in urban areas, may be one of the main causes of traffic congestion in urban areas. For the efficient operation of traffic signals, actuated traffic signal controls and various types of adaptive traffic signal control systems, such as SCATS, SCOOT, and COSMOS, have been developed [2, 3].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
