A Novel Strategy for VNF Placement in Edge Computing Environments
, Evandro Luiz Cardoso Macedo 2,*, Marina Ivanov Pereira Josué 1, Hugo Barbalho 3, Flávia C. Delicato 1, Débora Christina Muchaluat-Saade 1, Paulo F. Pires 1, Douglas Paulo de Mattos 1 and Ana Cristina Bernardo de Oliveira 3
Round 1
Reviewer 1 Report
The paper describes an approach to solving the VNF placement problem in edge computing environments. A model and an optimization problem solved through a heuristic-based approach are presented. The implementation of the proposed approach is described at an architectural level. Experimental results through scenario validation are presented for the multi-objective optimization platform implementation.
This reviewer has the following technical comments that may help the authors to enhance the technical content of the manuscript:
The problem is widely studied in the past, however, a clear differentiation with respect to the state of the art is required to justify a new model and in general a new optimization approach for the above problem. More importantly, the performance of the proposed approach is not compared with heuristic, meta-heuristic or learning-based approaches presented in the literature. The above is a critical aspect that should be addressed.
Author Response
"Please see the attachment."
Author Response File: 
Author Response.pdf
Reviewer 2 Report
1. The phrase “To the best of our knowledge” which you used in the abstract and contributions does not guarantee that this solution is the first. So, please try to rephrase it, or remove it completely.
2. The contributions need rewriting as they are currently not highlighting what is novel in them. Also, building an assumption on one reference, as in the case of contribution 2, [13], is not adequate.
3. The related work section is verbose with a lot of redundant text.
4. The conceptual model of the proposed solution is poor and needs further enhancement.
5. Discussion the problem statement in Sec4 is deemed too late. It should be earlier in the paper.
6. I feel am confused as whether the nodes used are traditional servers, or real edge. How can you convince the reader that you used edge nodes?
7. What is the software you used to produce the graphs of the results?
Author Response
"Please see the attachment."
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
The authors have done a great job and addressed the comments appropriately. The paper has clear impact and justified contributions. I have no other comments related to this paper, hence the paper can be accepted for publication in my opinion.
