Next Article in Journal
Smart Cities as Hybrid Spaces of Governance: Beyond the Hard/Soft Dichotomy in Cyber-Urbanization
Next Article in Special Issue
Effects of Temperature Rise on Clean Energy-Based Capital Market Investments: Neural Network-Based Granger Causality Analysis
Previous Article in Journal
Spatio-Temporal Variation of Habitat Quality for Bird Species in China Caused by Land Use Change during 1995–2015
Previous Article in Special Issue
The Sustainable Effect of Artificial Intelligence and Parental Control on Children’s Behavior While Using Smart Devices’ Apps: The Case of Saudi Arabia
 
 
Article
Peer-Review Record

A New Deep Learning Restricted Boltzmann Machine for Energy Consumption Forecasting

Sustainability 2022, 14(16), 10081; https://doi.org/10.3390/su141610081
by Aoqi Xu 1, Man-Wen Tian 2, Behnam Firouzi 3, Khalid A. Alattas 4, Ardashir Mohammadzadeh 5 and Ebrahim Ghaderpour 6,*
Reviewer 1: Anonymous
Reviewer 2:
Sustainability 2022, 14(16), 10081; https://doi.org/10.3390/su141610081
Submission received: 27 July 2022 / Revised: 6 August 2022 / Accepted: 12 August 2022 / Published: 15 August 2022
(This article belongs to the Special Issue Artificial Intelligence and Sustainability)

Round 1

Reviewer 1 Report

1. What is the meaning of "programming" in the Introduction Section in Page 1? Should it be "planning" or other meaning?

2. What is the criterion and difference of short-term, mid-term and long-term load forecasting in Page 1? And why is only mid-term load forecasting considered in this study?

3. What is your main contributions and findings in this study? Add a paragraph for relevant discussion in the end of the Introduction Section in Page 2.

4. Some important methodologies for load forecasting are missing in the literature review in Page 2 and should be added, including temporal convolution network used in Deep Learning Based Short‐Term Load Forecasting Incorporating Calendar and Weather Information, Transformer used in Short-Term Load Forecasting Based on the Transformer Model and Transformer-Based Model for Electrical Load Forecasting, et al.

5. The order of Section 3 and Section 4 should be exchanged. State your problem first. Then introduce your methodology.

6. Table 1 in Page 5 is not convincing. Use a validation data subset for comparing the different scenarios, instead of the test data subset.

7. Change "regular days" in Page 6 and Section 6 to "weekdays".

8. What are the baselines? Other forecasting methods should be implemented and their performance should be used to compare with your proposed RBM.

Author Response

Dear Reviewer,

Thank you very much for your time and constructive comments. We tried to address them all in a satisfactory manner, and we believe that our manuscript has been significantly improved. Please see the attached PDF file for the point-by-point responses to your comments.

Please let us know if you have any further comments. Thanks again!

Best regards,

Ebrahim Ghaderpour

On behalf of all the authors

Author Response File: Author Response.pdf

Reviewer 2 Report

The manuscript entitled :A New Deep Learning Restricted Boltzmann Machine for Energy Consumption Forecasting:" is very interesting scientific work. Its structure is well organised and the methodology is sufficient for the study. However it benefits from the revision considering following recommendations:

- In abstract error 5% refer to what? MAPE was about 10 and higher. 

- last paragraph literature review, first of all should be in introduction presenting that in section 2 there is literature review and secondly it should be emphasize the motivation of the study because it is not visible in introduction neither in the literature review (because it is literature review not research significance).

- Methodology used in the study is sufficient for this study however MAPE as the only one accuracy parametr is not the bets one. Imagine the set of numbers containing two classes 0.8 and 1.2 If the model predicts 0.99 for 0.8 and 1.01 for 1.2 MAPE is OK but the R coefficient of determination is not. Therefore it is beneficial to use also other parameters

-The authors have not compare their results with other studies e.g. presented in the literature review. 

- Conclusions section need to be rewritten presenting the contribution to the body of knowledge in the field as well as the limitations of the study and perspectives for future research.

- editorial thing: lack of contribution and other statements at the end of the Manuscript  

Author Response

Dear Reviewer,

Thank you very much for your time and constructive comments. We tried to address them all in a satisfactory manner, and we believe that our manuscript has been significantly improved. Please see the attached PDF file for the point-by-point responses to your comments.

Please let us know if you have any further comments. Thanks again!

Best regards,

Ebrahim Ghaderpour

On behalf of all the authors

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Dear authors, thanks for revising and resubmitting the manuscript. My previous concerns are resolved.

Reviewer 2 Report

I accept now

Back to TopTop