Optimal Electric Vehicle Battery Management Using Q-learning for Sustainability
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsDear Authors, this paper investigates the optimal electric vehicle battery management Using Q-Learning. The paper is well written. However, there are some comments and suggestions to improve the quality of the manuscript. The comments are as follows:
· The introduction lacks a clear problem statement. Adding a succinct problem statement early in the introduction would help clarify the specific challenges the study aims to address.
· The introduction cites numerous sources to establish the background, but the integration of these references can be more cohesive. In particular you should mention more exactly the contribution of the works you are citing. Suggested literature:
o https://doi.org/10.1016/j.egyai.2022.100217
o https://doi.org/10.3390/en13225858
· Furtremore, consolidate the objectives into a single, concise paragraph to enhance clarity.
· The methodology can benefit from a more detailed justification of why the Q-learning approach is superior to other machine learning techniques.
· While the state variables for the Q-learning model are listed, the rationale for selecting each variable needs to be more explicit. Explain why each parameter (e.g., SoC, SoH, temperature) is critical for the model.
· In the experimental results, expand on the computational time comparison and discuss any potential trade-offs between accuracy and computational cost.
· A dedicated subsection on the limitations of the study is missing.
· Emphasize the practical implications of the research for EV battery management and sustainable transportation. This can include potential impacts on industry practices or policy recommendations.
Author Response
Dear Authors, this paper investigates the optimal electric vehicle battery management Using Q-Learning. The paper is well written. However, there are some comments and suggestions to improve the quality of the manuscript. The comments are as follows:
Answer: Dear Reviewer, the author extends sincere appreciation to the reviewers for their kindness, valuable suggestions, and constructive feedback, which have significantly enhanced the quality of our paper. In response to your recommendations, we have thoroughly revised and amended the manuscript. The changes are highlighted in blue, with additional information indicated in red within these highlights.
- The introduction lacks a clear problem statement. Adding a succinct problem statement early in the introduction would help clarify the specific challenges the study aims to address.
Answer: Thank you for your recommendation. We have added a 'Problem Statement' subsection to clarify the issue and outline the specific challenges addressed in this study. Additionally, we have refined the 'Research Gap' and 'Objective' subsections to provide further clarity. (Lines 73-96, 143-177, 194-202)
- The introduction cites numerous sources to establish the background, but the integration of these references can be more cohesive. In particular you should mention more exactly the contribution of the works you are citing. Suggested literature:
- https://doi.org/10.1016/j.egyai.2022.100217
- https://doi.org/10.3390/en13225858
Answer: Thank you very much for your suggestions. We have revised the 'Contribution' section to improve its cohesion. Additionally, we have summarized the key points from the two papers you recommended [20-21] that are relevant to our study. (Lines 143-149, 187-202)
- Furthermore, consolidate the objectives into a single, concise paragraph to enhance clarity.
Answer: Thank you so much. We have consolidated the objectives into a single concise paragraph to enhance clarity. (Lines 185-181)
- The methodology can benefit from a more detailed justification of why the Q-learning approach is superior to other machine learning techniques.
Answer: Once again, we would like to thank the Reviewer for recommending that we provide a justification in the methodology for choosing Q-Learning over other machine learning techniques. Q-Learning offers a balance between performance and interpretability, making it a suitable choice for a reinforcement learning framework that is both comprehensible and practical for real-world deployment. This balance is essential for developing an accessible and effective solution for managing EV batteries, which aligns with our goals of improving energy efficiency, extending battery life, and ensuring vehicle reliability. By using Q-Learning, we can create a robust and adaptive EV battery management system that continuously improves based on real-world data and evolving conditions. (Lines 516-558)
- While the state variables for the Q-learning model are listed, the rationale for selecting each variable needs to be more explicit. Explain why each parameter (e.g., SoC, SoH, temperature) is critical for the model.
Answer: Thank you very much for your suggestions. We have added explanations for each variable in the Q-learning model, including the rationale behind their selection. Additionally, we have clarified the importance of each parameter (e.g., SoC, SoH, temperature) and discussed the parameters used in this study. (Lines 1012-1053, 1190-1213)
- In the experimental results, expand on the computational time comparison and discuss any potential trade-offs between accuracy and computational cost.
Answer: We have added a subsection titled ‘Computational Time’ to explain the comparison and discuss potential trade-offs between accuracy and computational cost. This subsection includes 3.1 Computational Time Comparison and 3.2 Analysis of Trade-offs Between Accuracy and Computational Cost. (Lines 1663-1721)
- A dedicated subsection on the limitations of the study is missing.
Answer: Thank you so much for your recommendation to include a dedicated subsection on the limitations of this study. We have added a subsection titled ‘5.4 Limitations and Future Research Directions,’ which discusses the details of the study's limitations and outlines potential future research directions. (Lines 1867-1919, 1962-1970)
- Emphasize the practical implications of the research for EV battery management and sustainable transportation. This can include potential impacts on industry practices or policy recommendations.
Answer: We would like to extend our special thanks to the Reviewer for recommending enhancements to clarify the practical implications of our research for EV battery management and sustainable transportation. In response, we have included detailed information on the potential impacts on industry practices, highlighting how the knowledge presented in this paper can be implemented to drive sustainability in the industry. (Lines 1982-1996)
The authors would like to extend their sincere gratitude to Reviewer for the invaluable suggestions to enhance the quality of this paper further. We also deeply appreciate the encouragement provided to the authors in presenting research on the application of advanced technologies in tourism. The suggested enhancements in the aforementioned areas will strengthen the scientific rigor and practical significance of our research. ?❤️?
Reviewer 2 Report
Comments and Suggestions for AuthorsThis work presents a comprehensive investigation on the optimization of Electric Vehicle (EV) battery management using Q-learning technique. Overall, this work is well organized and interest to researchers in this field. I think this work can be accepted after a minor revison.
The quality of Figure 6 should be improved.
What can Q-learning technique do to predict the cycle lifespan of EVs?
How to gain the data on material structure changes using Q-learning technique?
Author Response
This work presents a comprehensive investigation on the optimization of Electric Vehicle (EV) battery management using Q-learning technique. Overall, this work is well organized and interest to researchers in this field. I think this work can be accepted after a minor revision.
Answer: Dear Reviewer, the author extends sincere appreciation to the reviewers for their kindness, valuable suggestions, and constructive feedback, which have significantly enhanced the quality of our paper. In response to your recommendations, we have thoroughly revised and amended the manuscript. The changes are highlighted in blue, with additional information indicated in red within these highlights.
- The quality of Figure 6 should be improved.
Answer: Thank you very much for your suggestions. We have improved the quality of Figure 6 by increasing its resolution, making it clearer, more readable, and easier to understand. (Lines 1119-1120)
- What can Q-learning technique do to predict the cycle lifespan of EVs?
Answer: Thank you so much for your suggestions. We have added information in the subsection "Q-Learning Technique for Predicting the Cycle Lifespan of EVs" to explain how the Q-Learning technique is used to predict the cycle lifespan of EVs. (Lines 893--950)
- How to gain data on material structure changes using Q-learning technique?
Answer: Once again, we would like to thank you for your recommendation to clarify the method for obtaining data on material structure changes using the Q-Learning technique. We have added a subsection titled ‘Gain Data’ to explain in detail how data on material structure changes is acquired using the Q-Learning technique. (Lines 1359-1405)
The authors would like to extend their sincere gratitude to Reviewer for the invaluable suggestions to enhance the quality of this paper further. We also deeply appreciate the encouragement provided to the authors in presenting research on the application of advanced technologies in tourism. The suggested enhancements in the aforementioned areas will strengthen the scientific rigor and practical significance of our research. ?❤️?
