Machine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)

Round 1

Reviewer 1 Report

In my opinion, this manuscript can be considered for publication after appropriate revisions. My comment is as follows.

1、How did the authors apply the train-validate strategy? 3 or 5 or 10 fold cross validation, or heldout validation? And state the reasons that took this strategy, please.
2、Neurons between three hidden layers are supposed to be fully connected, but this structure is not depicted in the figure 6.

3、The figures in the manuscript should be marked with coordinates.

Author Response

Please see attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

This paper is well organized, and the results are promising. I think it is acceptable in its present form.

Author Response

The authors appreciate the time and effort expended by the reviewer for helping us refine the manuscript. We thank the reviewer for the encouraging and positive comments.

Reviewer 3 Report

1. The authors suggested rewriting the abstract with the observed data, especially discussing the error variation with the prediction and real-time data.
2. The conclusion needs to be a summarise of the overall work. It should be precise and effective to highlight the outcome and usefulness of the work. Need to rewrite the conclusion part.
3. 1 was not clear, and the way it was presented was very substandard. Provide a better quality image with a good illustration.
4. What kind of heaters are used for experiments. What is the reason for selecting the mentioned input voltage and power ratings for the heater?
5. How do the authors perform the repeatability test? Is there any time gap between experiments 1 and 2? Provide at least five cycles to show the repeatability of the experiments?
6. Why does the temperature profile vary (Fig.8 to 10) in each melting condition?
7. Why does the huge error variant in each applied voltage and testing conditions? Provide the error percentage.
8. How to reduce the overall error variation between the predicted and experimental values?

Author Response

Please see attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The revised manuscript has met the requirements and can be considered for publication.

Reviewer 3 Report

The present form of the revised version is improved and it suitable for publication.