Next Article in Journal
Thermal Treatment and High-Intensity Ultrasound Processing to Evaluate the Chemical Profile and Antioxidant Activity of Amazon Fig Juices
Next Article in Special Issue
Deep Transfer Learning Techniques-Based Automated Classification and Detection of Pulmonary Fibrosis from Chest CT Images
Previous Article in Journal
The Effect of Organic Fillers on the Mechanical Strength of the Joint in the Adhesive Bonding
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Processes
Volume 11
Issue 2
10.3390/pr11020407
Review Report
processes-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

Tail Prediction for Heterogeneous Data Center Clusters

Processes 2023, 11(2), 407; https://doi.org/10.3390/pr11020407
by Sharaf Malebary 1,*, Sami Alesawi 2 and Hao Che 3
Reviewer 1:
Manjunath Kounte
Reviewer 2: Anonymous
Processes 2023, 11(2), 407; https://doi.org/10.3390/pr11020407
Submission received: 3 January 2023 / Revised: 20 January 2023 / Accepted: 22 January 2023 / Published: 30 January 2023
(This article belongs to the Special Issue Trends of Machine Learning in Multidisciplinary Engineering Processes)

Round 1

Reviewer 1 Report

The paper has discussed several techniques for modeling clusters of in-homogeneous nodes.

The Design includes nested-event-based simulation model borrowing help from multi-core technologies.

The works focuses on the tail latency can be predicted at high load regions.

I appreciate the contributions focused on budget translation in chapter 6. 

The authors are informed to clarify on the following.

1. Describe the process followed to select Case-Scenarios in chapter 3. (Clarify regarding this process: For the latter, as each node function independently from others, we speculate this case scenario might become the key kernel for any future simulations targeting heterogeneous designs.) 

2.  Regarding the results, kindly clarify how tail prediction in heterogeneous environments is unique? 

3. The authors are informed to justify how the model successfully predicts the light-tailed within the expected window of errors across all load-levels.

Author Response

Kindly find the word file attached

Regards

Author Response File: Author Response.docx

Reviewer 2 Report

1. For self-citation, several papers published by the second and third authors (Sami Alesawi and Hao Che) are cited in References 12, 13, 14, 15, and 22. Such a number of self-citation behaviors should not appear in academic papers, especially the above literature appearing in the literature review section is not appropriate. In addition to the relevant findings of the authors, are there other relevant studies that could prove that the generalized exponential distribution can capture different behaviors for the arrived jobs requests? It is necessary for the authors to review and sort out in detail. Meanwhile, the authors are suggested to replace some of the self-cited papers with works from other authors and supplement similar or related research results to support the findings of this paper better.

2. The paper structure needs to be remodeled. The significance of the authors’ design to show the results of association research in Chapter 7 is not clear. The related works should be summarized before the substantive research work is carried out. It is more appropriate to integrate the content of this chapter with the literature review.

Author Response

Kindly find the word file attached

Regards

Author Response File: Author Response.docx

Back to TopTop