In the urban rail transit system, in order to deal with the problems of station congestion and excessive waiting time for passengers caused by train delays, it is necessary to adopt strategies such as skip-stopping and inbound passenger flow control. This paper proposes a train skip-stopping and inbound passenger flow control model based on reinforcement learning deep Q network, which optimizes the amount of inbound and train stops at the station in various time periods. So as to minimize the comprehensive benefits of station passenger platform overrun, average waiting time and passenger flow control intensity. Taking an example of postponement delays during rail transit operation, the deep Q network based on reinforcement learning is used to optimize the solution, which verifies the effectiveness of the method. The simulation results of using train skip-stopping and inbound passenger flow control are good. It can effectively reduce passenger waiting time under the condition of low passenger flow control intensity, improve passenger travel efficiency, and help alleviate passenger congestion at stations and gradually restore train operation order.
Coordinated Control of Urban Rail Train Skip-Stopping and Inbound Passenger Flow Based on Deep Q-network
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021
Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021 ; Kapitel : 57 ; 545-557
2022-02-19
13 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
British Library Conference Proceedings | 2022
|Urban Rail Train Diagram Compilation for Unbalanced Passenger Flow
Springer Verlag | 2024
|