Time-Sensitive Network Simulation for In-Vehicle Ethernet Using SARSA Algorithm

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

In this text, an improved approach is proposed for the analysis and calculation of delays in the simulation of time-sensitive networks (TSNs) of Vehicular Ethernet. The authors propose a delay analysis model for reserved data in the TSN network, which is improved by using the SARSA reinforcement learning algorithm. First, the models for the data transmission delay in the TSN queue and the intelligent data delay analysis of the reservation class are established. Then, the TSN traffic scheduling mechanism is improved by the SARSA reinforcement learning algorithm, and the improved data analysis model for the reservation class in the TSN network is established to handle the uncertainty of network traffic scheduling. Finally, the performance of the proposed method is verified by simulation and experimental validation. The results show that the deviation between the two is less than 5% under different traffic loads, which means that the delay analysis model for reserved data in the TSN network can correctly match the scheduling mechanism of the TSN vehicular network, thus proving the rationality of the model simulation.

- The article should follow the same narrative thread and at the end produce some experience regarding the level of actuality and how it highlights what has developed.

- The article needs solid support for the aspects related to novelty, development, and contribution in the field,

- Please detail the purpose of this work and some other new aspects from the literature.

- You have some paragraphs that need to be adjusted in the area of results and explanations regarding measurements (figures, tables).

- You should highlight much better those aspects that relate to the direct comparison between the specialized literature and your article.

- Does the architecture belong to you? Give examples and details (code structure, algorithm)

- The program/programs used, implementation but also other aspects?

- The classification table also needs other information, try to highlight what you want to score.

- The conclusions require a much more detailed approach, trying to develop much better, and outlining as scientifically as possible what has been achieved, at the moment they are extremely lacking in nuance.

 

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The paper Time-sensitive Network Simulation for In-vehicle Ethernet Using SARSA algorithm is focused on simulations and evaluations of timing and delays in time-sensitive network (TSN) of vehicular Ethernet. First, authors created and provided TSN data queue forwarding delay model and reservation class data delay analysis, followed by TSN traffic scheduling mechanism improved by the SARSA. The results demonstrate accurate and reasonableness of the model simulation.

First, the level of English language needs some improvements. I was able to notice several mistakes, typos and errors, which should be corrected. Therefore, I recommend to perform intensive proof reading. I also feel that some acronyms and abbreviations are not properly described in the text.

Next, I recommend to improve the overall organization of the paper. I recommend to separate the Introduction section with just short description of the topic and what has been done and why and the section with the review of existing methods and approaches. Mixing both together is not very favorable.

Equations (8) and (19) contains some Chinese symbol.

Does the presented model somehow involve environmental conditions? I mean, both simulations as well as experimentation are performed in a laboratory like conditions without any environmental impacts, such as various signal noises, mechanical noises, vibrations, tensions and deformations caused by a moving cars, temperature and humidity fluctuations, dusty environment etc. In my opinion, these realistic conditions would also influence the overall performance of the system as well as the performance of a simulated networks. I understand that it would be quite hard to quantify and simulate all such conditions and scenario, however, at least some short paragraph with some theoretical elaboration could be perhaps included in the paper.

The captions and texts in all of the graphs and pictures with the results of simulations and measurements are very hard to read. I recommend to increase the font size.

The paper does not contain any comparison with some other existing simulation approach.

Comments on the Quality of English Language

English language needs some improvements.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

1.The first appearance of SARSA in the abstract should have the full name

2.On the first page, "Ethernet time-sensitive networking (AVB)" should be modified to  "Ethernet time-sensitive networking (ESN)" .

3.On the second page, CB should have its full name for the first time

4.Page two, the first time the CDT appears is to have the full name

 

5.After, the abbreviation must have the full name when it first appears

6.In equation (3), some parameters are not specified.

7.Picture name should be in center.

8.The legend of the picture is not clear.

 

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 2 Report

Comments and Suggestions for Authors

I recommend to accept the article now.

Comments on the Quality of English Language

English language is fine, just some minor corrections.