Deep Q-Learning Network Model for Optimizing Transit Bus Priority at Multiphase Traffic Signal Controlled Intersection

When multiple bus vehicles send priority requests at a single intersection, the existing fixed-phase sequence control methods cannot provide traffic request services for multiphase vehicles. In view of conflict intersections, vehicle is determined, which focus this study. paper, connected vehicle-enabled transit signal system (CV-TSPS) has been proposed, uses vehicle-infrastructure communication function (V2I) technology to obtain real-time movement, road states, and light phase information. By developing deep Q-learning neural network (DQNN), especially optimizing strategy, public will be prioritized improve their travel efficiency, while overall delay flow balanced ensure safe orderly passage intersections. order verify validity model, SUMO analysis software applied simulate control, experimental results show that compared with traditional timing loss time reduced by nearly 40%, cumulative per capita 43.5%, good effect achieved. case medium low densities, it better than solid scheduled scheme.