Simulation Optimization of Station-Level Control of Large-Scale Passenger Flow Based on Queueing Network and Surrogate Model

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper investigates how to optimize passenger flow control measures at subway stations through simulation optimization methods, in order to address congestion and safety issues arising from the influx of large numbers of passengers during peak hours. Through a case study of an actual station, the effectiveness of the proposed method is validated. The method presented demonstrates a certain degree of innovation and practicality. Nevertheless, the paper still exhibits shortcomings in areas such as literature review, theoretical derivation, experimental design, and conclusion presentation, which require further improvement and refinement.

 

1. In the Introduction section, the content of the first paragraph leaves me quite perplexed. Could it be that the author employed AI tools akin to ChatGPT to author that section !?

 

2. In the Relative works section, the majority of the references cited by the author are overly outdated, lacking in recent literature from the past five years. It is recommended to further comb through and analyze the research progress in the relevant field to ensure the comprehensiveness, accuracy, and advancement of the literature review.

 

3. The overall framework has a clear logical structure, but the connections and transitions between sections appear somewhat abrupt, lacking sufficient theoretical foundations and logical connections.

 

4. The paper provides a detailed description of subway station environment modeling, pedestrian agent modeling, and simulation scheduling methods. The environment modeling section comprehensively considers both corridor facilities and service facilities. In the pedestrian agent modeling section, passenger characteristics are simplified, with a focus on actions and state changes, which is reasonable in a mesoscopic model. However, regarding the selection of the simulation scheduling method (FIFO), the article fails to adequately justify its advantages over other scheduling methods, lacking the necessary comparative analysis.

 

5. The optimization method proposed in the article combines the Kriging model with the Particle Swarm Optimization (PSO) algorithm, which is theoretically feasible. However, during the construction of the Kriging model, the selection of the variogram function and the parameter estimation method lack detailed theoretical derivation and validation, which may lead to uncertainty in the model's prediction accuracy. Additionally, the parameter settings and convergence analysis of the PSO algorithm are also relatively brief and require further elaboration.

 

6. The paper conducts a case study using the Zhongguancun subway station in Beijing to validate the effectiveness of the proposed method. However, the case study section has the following shortcomings: the article fails to clearly state the data sources and collection methods, which affects the reliability of the results; furthermore, the experimental parameter settings lack a theoretical basis, potentially leading to deviations in the experimental results.

 

7. The conclusions drawn in the article are generally reasonable, but the expression is somewhat vague, failing to adequately highlight the unique contributions and innovative aspects of the proposed method.

 

8. The paper contains some inappropriate expressions, such as "both domestic and international" (Page 3, Line 116) and "at home and abroad" (Page 6, Line 267).

 

9. The data in Table 1 needs to be verified as the total exceeds 100%.

 

10. The citation format of the references is not standardized.

Comments on the Quality of English Language

OK

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Dear Authors!

I want to congratulate you on your work, especially on the mathematical or methodological part. Maybe this part is too long for readers of the Sustainability Journal.

I have some questions/comments to improve the quality of your article. Please see the attachment.

Regards.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

Please see in the attachment

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

Please see the attached review report!

Comments for author File: Comments.pdf

Comments on the Quality of English Language

Moderate editing of English language required!

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The revised manuscript is much improved and the paper may be published.

Author Response

Comment: The revised manuscript is much improved and the paper may be published.

Response：Thank you for your comments and appreciation. 

Reviewer 2 Report

Comments and Suggestions for Authors

Dear Authors!

General article is better now, but in my opinion, it is still too long. A longer reference sheet could be used at the expense of the long text in the methodology chapter.

As I said, there is no need to mention the “Kriging model, and the particle swarm optimization algorithm” twice in the Abstract. Please, simplify and shorten the text.

There are small remarks in Tables 4-6 and Figures 7-9, please correct “sampling points” or “-“ or “samping points” to “sampling point”. In Table 3, there is no need to repeat “sampling point 1, sampling point 2”, etc. just “1”,”2”, etc.

Regards.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

While the authors tried to address most of the comments, they failed to improve the Introduction and provide enough knowledge for the readers to support the concepts of passenger flow for urban rail transit stations during peak hours, which is an essential concept of Transit Oriented Development (TOD) and should be discussed in the Introduction section. In lines 10 to 14, the authors mentioned: "Urban rail transit encounters supply-demand contradictions during peak hours, seriously affecting passenger experience. Therefore, it is necessary to explore and optimize passenger flow control strategies for urban rail transit stations during peak hours. However, current research mostly focuses on passenger flow control at the network level, and there is insufficient exploration of specific operational strategies at the station level." But unfortunately, the current Introduction text doesn't seem informative enough to support this TOD concept. So please open a paragraph and explain the optimization methods as a TOD concept and how this pattern affects overall urban rail transit stations. Please provide at least ten recent research works in this field to improve the quality of the literature review. Five of the recommended works that should be added are provided below:

·         The Integrated ANN-NPRT-HUB Algorithm for Rail-Transit Networks of Smart Cities: A TOD Case Study in Chengdu. Buildings 2023, 13, 1944. https://doi.org/10.3390/buildings13081944

·         Transit-oriented development (TOD) typologies around metro station areas in urban China: A comparative analysis of five typical megacities for planning implications. Journal of Transport Geography 90 (2021) 102939. https://doi.org/10.1016/j.jtrangeo.2020.102939

·         Relationship between built environment characteristics of TOD and subway ridership: A causal inference and regression analysis of the Beijing subway. Journal of Rail Transport Planning & Management, Volume 24, 2022, 100341. https://doi.org/10.1016/j.jrtpm.2022.100341.

·         Node, Place, Ridership, and Time model for Rail-Transit Stations: A Case Study; Scientific Report; (2022) 12:16120; https://doi.org/10.1038/s41598-022-20209-4

·         Relationship analysis of short-term origin–destination prediction performance and spatiotemporal characteristics in urban rail transit. Transportation Research Part A: Policy and Practice. Volume 164, October 2022, Pages 206-223. https://doi.org/10.1016/j.tra.2022.08.006

Comments on the Quality of English Language

Minor editing of English language required.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 3

Reviewer 4 Report

Comments and Suggestions for Authors

Accept in present form!