Transformer-Based Macroscopic Regulation for High-Speed Railway Timetable Rescheduling  

作　　者：Wei Xu Chen Zhao Jie Cheng Yin Wang Yiqing Tang Tao Zhang Zhiming Yuan Yisheng Lv Fei-Yue Wang 

机构地区：[1]Faculty of Innovation Engineering,Macao University of Science and Technology,Macao 999078,China [2]Signal&Communication Research Institute,China Academy Railway Sciences,Beijing 100081,China [3]School of Artificial Intelligence,University of Chinese Academy of Sciences,Beijing 100049 [4]State Key Laboratory for Management and Control of Complex Systems,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China [5]IEEE [6]State Key Laboratory for Management and Control of Complex Systems,Chinese Academy of Sciences,Beijing 100190 [7]Macao Institute of Systems Engineering,Macao University of Science and Technology,Macao 999078,China

出　　处：《IEEE/CAA Journal of Automatica Sinica》2023年第9期1822-1833,共12页自动化学报（英文版）

基　　金：supported partially by the National Natural Science Foundation of China(61790573,61790575);the Center of National Railway Intelligent Transportation System Engineering and Technology(RITS2019KF03);China Academy of Railway Sciences Corporation Limited;China Railway Project(N2019G020);China Railway Project(L2022X002);the Key Project of Science and Technology Research Plan of China Academy of Railway Sciences Group Co.Ltd.(2022YJ326)。

摘　　要：Unexpected delays in train operations can cause a cascade of negative consequences in a high-speed railway system.In such cases,train timetables need to be rescheduled.However,timely and efficient train timetable rescheduling is still a challenging problem due to its modeling difficulties and low optimization efficiency.This paper presents a Transformer-based macroscopic regulation approach which consists of two stages including Transformer-based modeling and policy-based decisionmaking.Firstly,the relationship between various train schedules and operations is described by creating a macroscopic model with the Transformer,providing the better understanding of overall operation in the high-speed railway system.Then,a policy-based approach is used to solve a continuous decision problem after macro-modeling for fast convergence.Extensive experiments on various delay scenarios are conducted.The results demonstrate the effectiveness of the proposed method in comparison to other popular methods.

关 键 词：High-speed railway reinforcement learning train timetable rescheduling TRANSFORMER 

分 类 号：U292.4[交通运输工程—交通运输规划与管理] TP18[交通运输工程—道路与铁道工程]