Q-learning approach to coordinated optimization of passenger inflow control with train skip-stopping on a urban rail transit line

Jiang, Zhibin; Gu, Jinjing; Fan, Wei; Liu, Wei; Zhu, Bingqin

doi:10.1016/j.cie.2018.05.050

Cited by 72 publications

(23 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traffic flow optimization problem can also be modeled as a RL problem in order to reduce traffic congestion (Li, Liu, Xu, Duan, & Wang, 2017; Walraven, Spaan, & Bakker, 2016). Jiang, Gu, Fan, Liu, and Zhu (2019) conducted a coordinated passenger inflow control during peak hours to balance the distribution of passenger demand along a metro line. However, no previous research that used RL in pavement management decision‐making has been found.…”

Section: Introductionmentioning

confidence: 99%

Deep reinforcement learning for long‐term pavement maintenance planning

Yao

Dong

Jiang

et al. 2020

Computer aided Civil Eng

113

View full text Add to dashboard Cite

Inappropriate maintenance and rehabilitation strategies cause many problems such as maintenance budget waste, ineffective pavement distress treatments, and so forth. A method based on a machine learning algorithm called deep reinforcement learning (DRL) was developed in this presented research in order to learn better maintenance strategies that maximize the long-term cost-effectiveness in maintenance decisionmaking through trial and error. In this method, each single-lane pavement segment can have different treatments, and the long-term maintenance cost-effectiveness of the entire section is treated as the optimization goal. In the DRL algorithm, states are embodied by 42 parameters involving the pavement structures and materials, traffic loads, maintenance records, pavement conditions, and so forth. Specific treatments as well as do-nothing are the actions. The reward is defined as the increased or decreased cost-effectiveness after taking corresponding actions. Two expressways, the Ningchang and Zhenli expressways, were selected for a case study. The results show that the DRL model is capable of learning a better strategy to improve the long-term maintenance cost-effectiveness. By implementing the optimized maintenance strategies produced by the developed model, the pavement conditions can be controlled in an acceptable range.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep reinforcement learning for long‐term pavement maintenance planning

Yao

Dong

Jiang

et al. 2020

Computer aided Civil Eng

113

View full text Add to dashboard Cite

show abstract

“…In practice, this method is difficult to implement due to the limited space inside the station, especially when the number of OD pairs is large. Jiang et al [21] applied a Q ‐learning approach to optimise the passenger inflow control with train skip‐stopping, which reduced the penalty value of stranded passengers effectively. Yang et al [22] studied the integration of bus‐bridging service and passenger inflow control.…”

Section: Introductionmentioning

confidence: 99%

Multistation coordinated and dynamic passenger inflow control for a metro line

Wang

Yang

et al. 2020

IET Intelligent Transport Systems

View full text Add to dashboard Cite

“…From reviewing existing literature, direct passenger flow control methods include inbound control and station hall control. Inbound control, which requires passengers to wait outside the station, was taken as the control method in literatures [23][24][25][26][27][28][29]. For instance, Zhao et al [23] established a multiobjective mathematical programming model aiming at minimizing the passenger delay and maximizing the passenger turnover volume.…”

Section: Introductionmentioning

confidence: 99%

“…Jiang et al [26] developed a new reinforcement learning-based method to optimize the inflow volume with the aim of minimizing the safety risks imposed on passengers at the metro stations. Further, Jiang et al [28] proposed a coordinated optimization scheme, which combined both the coordinated passenger inflow control and train rescheduling strategies, to minimize the penalty value of passengers being stranded along the whole line. In addition, the station hall control method, which requires passengers to wait in the station hall, was studied in literatures [30][31][32][33][34].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Multilevel Collaborative Passenger Flow Control in Peak Hours for a Subway Line

Xue

Jia

Guo

2020

Advances in Mathematical Physics

View full text Add to dashboard Cite

Due to contradiction of large-scale passenger demand and limited transportation capacity, the passengers who cannot be transported away in time accumulate and congest in stations. To ensure travel safety, improve travel efficiency, and ameliorate waiting environments for passengers, this paper proposes an adaptive multilevel collaborative passenger flow control strategy integrating the control of station entrance and station hall. An integer linear programming model is constructed, which aims at minimizing the total passenger waiting time and taking the safe capacity of each key area of all stations as the necessary constraints. The model is applied in two scenarios with different scales of passenger demand in the morning peak of the Batong line. The results show that the proposed model can adaptively activate the appropriate control level, limit the amount of accumulated passengers in each key area of the station within its safe capacity, and shorten the total passenger waiting time.

show abstract

Q-learning approach to coordinated optimization of passenger inflow control with train skip-stopping on a urban rail transit line

Cited by 72 publications

References 36 publications

Deep reinforcement learning for long‐term pavement maintenance planning

Deep reinforcement learning for long‐term pavement maintenance planning

Multistation coordinated and dynamic passenger inflow control for a metro line

Adaptive Multilevel Collaborative Passenger Flow Control in Peak Hours for a Subway Line

Contact Info

Product

Resources

About