Resource Allocation on Blockchain Enabled Mobile Edge Computing System
Round 1
Reviewer 1 Report
The connection between the problem and the solution proposed is also not pointed out clearly. Above all, emphasize the novelty introduced.
The proposed methodology and what was found better as compared to existing ones (in the Introduction) should be highlighted.
Also highlight the research gap in existing research and in literature. The importance of the proposed integrated approach with respect to the problem statement should have been in focus.
About the literature review, add some papers and each paper should clearly specify what is the proposed methodology, novelty and results with experimentation. At the end of related works, highlight in some lines what overall technical gaps are observed in existing works, that led to the design of the proposed approach. To better delineate the context and the different possible solutions, you can consider the following papers as references: https://www.mdpi.com/2079-9292/10/18/2250 and https://ieeexplore.ieee.org/abstract/document/9409962/.
The future scope of the methodology should be extended/highlighted. Improve the conclusion, and clarify the conclusion of this article with its significance for follow-up research.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
The paper Resource Allocation on Blockchain Enabled Mobile Edge is relevant and interesting. The authors have a good idea.
Details to be corrected:
More recent (2021, 2022) literature sources from prestigious journals such as Symmetry, Sustainability and others need to be added.
Some literature sources are too old, e.g., at positions 42.
Page 7 provides that time approximation formula raised by Boxma [42]. However, the author of 42 literature sources is Kimura.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
The authors addressed all my comments, therefore, in my opinion, the paper can be accepted.
This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.
Round 1
Reviewer 1 Report
The article studies a RL based resource allocation problem in Blockchain-assisted MEC system, which is innovative. But there are some suggestion for the article from my side:
1) The relationship between blockchain, MEC system and resource allocation is not clear. Please clarify it.
2) The A3C and SA2C algorithm are quite common reforcement learning algorithms recently, so the introduction of these algorithms should be briefly and concise.
3) For the simulation part, the analysis of performance on different weight parameter groups is lengthy and meaningless, it is suggest to analyse the optimal weight group after simulation.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
This paper proposed a blockchain-based MEC service system. It seems that this work is a simple application, the authors did not explain the pros and cons of this paper.Several questions to ask the authors:
- "The blockchain technology can guarantee data security during transporting and processing relying based on the characteristics of safety and credibility" How can your blockchain guarantee these? Where is the design or implementation of your blockchain? Why the traditional solutions cannot do this?
- "The decentralized infrastructure of blockchain can enhance the robustness of the system" Similarly, you need to explain it if you say so. Not all blockchain has this kind of ability. The blockchain can destroy your system in some critical situations.
Need to be improved:
- Experiments to prove the blockchain-based system is better than traditional ones. - Figures in the experiments are unclear. - Empty pages must be removed.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
The topic of the article Resource Allocation Policy of Blockchain Enabled Mobile Edge Computing System Based on Distributed Reinforcement Learning is relevant and interesting. However, it is presented a bit chaotically. The authors have a good idea, but the elaboration of the article is not good.
Details to be corrected:
First of all, I want to say that the title of the article is too long, it should be specified and shortened.
Reading the article gives the impression that the Bockchain system is artificially linked to the subject matter of the article. The essence and applicability of the Bockchain system should be further emphasized. About this system is presented only at the beginning of the article. Furthermore, the purpose of the article is not clear.
As for the structure of the article, it can be said that one more section is needed – Discussions (before the Conclusion section).
More literature sources from prestigious journals such as Symmetry, Sustainability and others need to be added.
Some literature sources are too old, e.g., at positions 28, 33.
Page 5 (line 168) provides that time approximation formula raised by Boxma [28]. However, the author of 28 literature sources is Kimura.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
Dear Authors,
I am not satisfied with your explanation about blockchain design. In my view, the “food supply chain” is just for the topic of this special issue. Here are some questions for the authors.
- As shown in Figure 1, you need each IoT device (e.g., temperature or humidity sensor) to have a wallet node. I wonder where to place the wallet node? Why not use a gateway just like other blockchain-based IoT implementations?
- The watcher node in your design is in charge of monitoring the service nodes’ operation. How can it judge if a service node is “normal” or “malicious”? If a watcher finds a node is malicious in your design, the block will be rejected by the network. In this situation, how to avoid the congestion collapse?
- From Section 3.2, the authors believe the mining process is the validation of a service node after generating a block, which is absolutely wrong. This description is for confirmation rather than mining, which makes me believe that the authors are unfamiliar with blockchains.
- Due to the confirmation requirements, the results of one service node need to be confirmed by N other nodes. The cost will be extremely high. How to deal with this problem?
Reviewer 3 Report
The authors improved the work based on comments from me and other reviewers. Just the only thing not done - more literature sources from prestigious journals such as Symmetry, Sustainability and others need to be added. So, in my opinion, paper can be published after minor corrections.
