Research on Collaborative Optimization of Passenger Flow Control and Train Skip-Stopping in Urban Rail Transit

Considering passenger flow will be stranded on the platform during the peak hours of urban rail transit, passenger flow congestion will be caused when the safety threshold is exceeded. A collaborative optimization model of station passenger flow control and train skip-stopping is established with the goal of minimizing the number of people exceeding the platform safety threshold and the average waiting time of passengers. A double deep Q network is used to solve it. A case study of Beijing Metro Line 13 and Changping Line is carried out with comparative analysis. In the morning peak station platform, there is a situation where the safety threshold is exceeded, and this safety problem is solved after optimization and the average waiting time of passengers is smaller than that before optimization. The case verifies the optimization effect of the model.