Service Composition and Optimal Selection of Low-Carbon Cloud Manufacturing Based on NSGA-II-SA Algorithm
![](/bundles/mdpisciprofileslink/img/unknown-user.png)
Round 1
Reviewer 1 Report
The manuscript focuses on a popular topic about low carbon in the context of cloud manufacturing optimization with a proposed algorithm, which is interesting. However, there are still some questions to be answered, maybe, for further improvements.
1. The title of the manuscript highlights low-carbon manufacturing, but the problem itself is about multi-objective optimization from the description in the manuscript. From the authors’ literature review and problem description, it can be seen that low-carbon is one of the objects paralleling with others, such as time, cost, and reliability. For such a multi-objective optimization problem, why only emphasize on low carbon in the title? What is the relationship among the objects? There are no statements for this problem in the manuscript. If it is parallel relationship among multiple objectives, it should be focused on multi-objective optimization itself but not emphasizing on low carbon, although it is popular in recent years.
2.For the references of [12-21], most of the authors seem from China or are Chinese. Usually, if a topic is attractive, the authors are from multiple countries or regions with different perspectives and different contributions; if most of the authors are from a single area, no problem, maybe, the topic is a typical one related with a certain area. However, it is not sufficiently discussed in the manuscript, which will weaken the value of the research. So, probably, the work of literature review is not enough…
3. In fact, for most optimization algorithms dealing with complex problems, it is a common problem to fall into a local optimal solution. And there are many solutions and technical approaches for this problem in existing literatures. The manuscript proposed an algorithm based on NSGA-II, and there is not enough discussion on why NSGA-II is an algorithm suitable for current problems only stating with a sentence of “The traditional Non-dominated Sorting Genetic Algorithm (NSGA-II) is one of the best multi-objective genetic algorithms for current NP-Hard problems.” in line 314 of page 9, with no reference no argumentation. In the part of literature review, NSGA-II is just one of the many techniques in previous literatures. If no further argumentation on why it is NSGA-II to be improved but not others, the value of contributions of this research will be weakened.
4. In Table 1, a uniform format for the algorithm names, such as first letter capitalized is suggested to be used, for example, in line 3 of table 1, the reference of Jiang et al., the name of the algorithm is “genetic algorithm”, but states as “Genetic Algorithm” in the line of Liu et al. The same for the introduction section.
5. Is i-NSGA-II in Figure 8 and Figure 9 the proposed NSGA-II-SA and why is it named i-NSGA-II and is there a clerical error here? BTW, “i-NSGA-II” can not be found in the manuscript, which makes the experiment hard to follow. Further proofreading should be done before the submission.
6. There are multiple evaluation metrics for multi-objective optimization algorithms in existing literatures that can evaluate the performance of an algorithm, why not employ a multi-objective algorithm evaluation metric commonly used in existing literatures to evaluate the algorithm performance in this manuscript?
Comments for author File: Comments.docx
Author Response
Thank you very much for your careful comments. We have revised the manuscript carefully and given a detailed response to your comments.
Author Response File: Author Response.docx
Reviewer 2 Report
This paper studied the optimal composition and selection in CMfg environment for customer demand. A hybrid multi-objective evolutionary algorithm incorperating SA was proposed, and an algorithm result optimization strategy based on the combination of TFNAHP and EWM was designed to select the final execution scheme. The optimization strategy is meaningful. But this paper needs to be well revised.
1. The contributions should be clarified clearly in the introduction.
2. After Table 1, the points to be improved in existing research should be clearly pointed out.
3. What is the relationship between ‘carbon emissions’ and ‘service quality’. In lines 12-13, the sentence ‘the impact of carbon emissions on service quality’ confused me.
4. Explain the NSGA-II-SA abbreviation. I don't see how it is related to the name of the proposed algorithm.
5. What is ‘eliminate undesirable individuals’ in line 337?
6. The difference of ‘point exchange’ and ‘two exchanges’ is unclear.
7. What is the ‘the advantages and disadvantages of old and new solution” in line 385.
8. The effectiveness of ‘local search strategy’ should be demonstrated in the Section 6.
9. There are many notation errors.
l The meaning of ‘Mj’ in line 170 is not given;
l ‘α1’ ‘α2’ is not consistent with them in Equation (12)? Many other notations have similar problems.
10. The paper needs thorough proofreading because there are many grammatical issues.
l In line 485, ‘formula’ should be ‘formulas’.
l In line 492, ‘then’ should be ‘and then’.
l In lines 514 and 522, ‘The’ should be ‘the’.
Author Response
Thank you very much for your careful comments. We have revised the manuscript carefully and given a detailed response to your comments.
Author Response File: Author Response.docx
Reviewer 3 Report
Thank you for the interesting paper.
Could you write more examples where a Hybrid Multi-Objective Evolutionary Algorithm (NSGA-II-SA) could also be applied?
Author Response
Thank you very much for your careful comments. We have revised the manuscript carefully and given a detailed response to your comments.
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
The authors have answered my questions very well. Therefore, I accept the publication of this article.