Cyberattacks in Smart Grids: Challenges and Solving the Multi-Criteria Decision-Making for Cybersecurity Options, Including Ones That Incorporate Artificial Intelligence, Using an Analytical Hierarchy Process
Round 1
Reviewer 1 Report
This study on solving cyber security solutions with multi-criteria decision making using the AHP method for the security of smart grids is interesting in general terms and can contribute to the literature. Below I would like to make a few recommendations regarding the study.
-The study contains too many pages than a general article format and complete fluency has not been established. This does not adversely affect the originality, quality and intelligibility of the study.
-General information (smart grid, definitions of attack methods, emission values, etc.) takes up a lot of space in the article, these areas should be seriously shortened and rearranged in a maximum of 1-2 paragraphs so as not to spoil the whole.
-In the introduction, the requirements of using a lot of smart grids (carbon emissions, usage statistics, etc.) are mentioned. The length of this section leaves the main purpose of the study, smart grid security, in the background. The introduction part can be arranged in a more concise manner under 3 main headings as motivation, limitation and contribution.
-The methodology part is explained clearly, but the comparison of the proposed method with other ML algorithms or different methods in the literature is not presented. It would be more appropriate to support this part with graphics.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
1. Section 1.1 is too long. The introductory part (first 7 pages) is too broad. Climate change seems to be too far away from smart grid cybersecurity. The motivation can focus more on cybersecurity of smart grid.
2. The motivation about MCDM-AHP is not enough.
3. How the weight is decided, better to explain all the weights originated in the tables from Table 4. What about dynamic and evolving system? The weight will be modified manually with the system evolution?
4. Suggest the figure titles and table titles should be short and in one line. Some titles are almost a paragraph long.
5. ML is a subset of AI, but the author seems to distinguish the two in some sections. I would suggest using only AI.
6. page 15, formula (4), n_{i}j --> n_{ij}, maybe similar typo in formula (6), o_{kn}
7. page 16, 3. Results, seems to be part of the introduction, but is listed here as results.
8. Future directions can be mentioned, how to improve the MCDM-AHP for smart grid cybersecurity.
9. Some reference information is not complete, the reference should include the year, volume, and page numbers, etc.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The authors rearranged their work taking into account all the edits recommended to them in the previous version of the study. The study has become more academic, fluent and clear in its new form. I support that this study, which can contribute to the literature, can be interesting for the readers.
Author Response
Thank you very much for taking the time to review our manuscript and for your thoughtful feedback. We greatly appreciate your positive assessment of the revisions we made based on your recommendations from the previous version.
Reviewer 2 Report
Most of my comments are properly addressed.
Author Response
Thank you for your feedback and for acknowledging the adjustments made in response to your comments. We appreciate your thorough review and are pleased to hear that most of your concerns have been appropriately addressed.
