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

Abstract

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

Passenger‐based adaptive transit signal priority for BRT systems with multiple loading areas

“…Another ATSP strategy was proposed by Zhang et al taking advantage of V2I communications to improve the PT vehicle travel time prediction and subsequently passenger delay [29]. Regarding the novel solution methods, fuzzy logic [30,31], Q-learning [32], deep reinforcement learning [33,34], and metaheuristics [25,29,35,36] are among the methods used in the ATSP strategies to empower the optimization process. The maximization of passenger throughput has been also targeted in some of the ATSP strategies showing superior performance compared to the delay-based strategies, especially at high congestion levels [37][38][39].…”

“…These changes to green time can take the form of the optimal adoption of active strategies [55][56][57][58], reallocation of green time [21][22][23][24], or calculation of green times based on optimization [14, 17-19, 20, 28]. However, by equipping the ATSP strategy with the ability to additionally optimize phase sequence, higher benefits for PT vehicles could be achievable [20,32]. The rotation of the phase sequence in favour of PT vehicles provides the opportunity to change the order of the PT vehicle phase and to avoid extra delay.…”