Queuing-Based Federation and Optimization for Cloud Resource Sharing

Round 1

Reviewer 1 Report

In this manuscript, the authors propose two queuing-based models for optimization of resource allocation in a cloud federation. The topic is interesting and worth investigating. The manuscript is well-structured and well-written. The research goals are clearly formulated. The experimental results show that the proposed models demonstrate that the new models can: 1) decrease the number of dropped jobs; 2) increase the total utility and 3) improve the overall effectiveness of cloud system. The analysis of the obtained results is thorough.

 

My remarks are as follows:

Please, add a discussion or comparison with results obtained from similar previous studies, described in “2. Related work” section.

What are the limitations of your study?

In “6. Conclusions” section, future plans are missing.

 

Technical remarks:

In my opinion, the title “Federations and Optimisations Inspired by Human Economics for Cloud Resource Sharing” is verbose and should be edited, for example: “Queuing-based Optimisation for Cloud Federation”.

p. 2: “cloud federation institutes” -> “cloud federation institutions”

p. 8: “is convergence.” – Please, edit this fragment.

p. 8: “in federation is no less than the utility” – Please, edit this fragment.

Figure 2(b) – Figure 5(b): ‘utilities’ -> ‘utility’.

p. 12, 14: “1000-player” -> “1000-players”.

Author Response

Dear Reviewer,

Thank you for your comment. The advises are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. Revised portion are marked in red in the paper.

Author Response File: Author Response.docx

Reviewer 2 Report

The paper addresses the topic of federating cloud computing by offering two potential solutions: a Cloud Light-Federation Sharing and a Cloud Cooperative-Federation Sharing, with different objectives - the first one achieves the highest profit and the second one achieved the highest number of satisfied customers. The approach is interesting and the authors claim it is the first research to address the problem of maximizing the net utility of cloud federation based on queueing theory where the cost of users’ time is considered, although federating clouds is not new and practical solutions already exist. Therefore, the authors need to delve more into the novelty of their approach and their research objectives to differentiate themselves from the existing literature (here, please eliminate "literatures" from the paper, in academic terms we refer to "literature"!)

The authors begin by discussing Figure 1, which shows the Job arrival rate of Gaia cluster and MetaCentrum back in 2014. I wonder why data from 2014 was used and not more recent data, considering that progress in federating clouds has been made recently. Moreover, I find the explanations accompanying this figure rather poor and unfit for what the figure shows, so I advise the authors to elaborate more on them.

Methodologically, I think the paper is sound.

Conclusions need to be reinforced: they do not discuss much the results, do not address research limitations, do not propose further research avenues and do not mention the practical implications of the findings.

Author Response

Dear Reviewer,

Thank you for your comment. The advises are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. Revised portion are marked in red in the paper.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

The authors have performed the needed changes. I still believe the Conclusions have to discuss the implications and usefulness of the results, otherwise, the paper is fine.

Author Response

Dear Reviewer,

Thank you very much for your valuable suggestion. I have added the implications and usefulness of the results in the conclusion. The added description is as following:

 “Therefore, the work provides two alternative solutions for cloud resource sharing which are different in cooperation rules. If there are only a few cloud computing centers participating in the federation, a fair resource sharing method can be selected. When the number of  participants is large, it also provide a simplified and efficient way of cooperation.”

Best Regards,

Xiaohong Wu et al.