CLSTM-AR-Based Multi-Dimensional Feature Fusion for Multi-Energy Load Forecasting
, Cunqiang Huang 2, Laijun Chen 1, Shengwei Mei 1, Juan An 2, Xingwen Liu 2 and Hengrui Ma 1,*Round 1
Reviewer 1 Report
1. Please define CLSTM-AR in the abstract.
2. It is not clear that what data was used to plot figure 2? Moreover, it is important to correlate your data with the published data. Because the statements like “Obviously, the electricity load has an extremely high correlation with the heat 122 load during the heating season and the electricity load with the cold load during the cooling 123 season, which is related to the use of thermo-electrical device and heat-pump equipment in 124 the building.” need some reference.
3. The validation the proposed model has not been presented. This section must be added.
4. No article from 2022 is cited. Please cite few more recent papers.
5. The novel aspect explained by author should be presented in a paragraph form rather than bullets.
6. Data was taken from Dec. 21 to Dec. 24, is there any particular reason for the data selection for this period.
7. Is this model valid for other weather conditions?
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The authors presented an excellent prediction model for integrated energy systems loads. The presented study can be employed to design new advanced energy management strategies that consider the demand management side (DMS). Mentioning it in the introduction can provide more significance.
The paper requires deep proofreading.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Organization of the paper is good.
Author Response
Dear Reviewer:
Thank you for your comments concerning our manuscript entitled “CLSTM-AR Based Multi-dimensional Feature Fusion for Multi-energy Load Forecasting” (ID: 1965333). We tried our best to proofreading to the paper and made some moderate english changes. These changes will not influence the content and framework of the paper. And here we did not list the changes but marked in green in revised paper.
We appreciate for Reviewers’ warm work earnestly, and hope that the correction will meet with approval.
Once again, thank you very much for your comments and suggestions.
Yours sincerely,
Bowen Ren, Cunqiang Huang, Laijun Chen, Shengwei Mei, Juan An, Xingwen Liu and Hengrui Ma
Corresponding author: Name: Hengrui Ma
E-mail: [email protected]
Reviewer 4 Report
After reading the paper carefully, my recommendation is minor revision before acceptance for publication. Some comments below can be helpful.
1. The abstract should be rewritten by including the major findings and the novelty of the results.
I feel like your abstract is too descriptive and not sufficient. More background and rationale should be provided. Main findings and implications can be briefly mentioned.
2. Line 45, Ref. [18] is inappropriate academic writing, please rewrite.
3. In section 2, please describe more detail term “IES”.
4. Please shorten the title of Figure 1, it’s too long currently. The same to Figure 2, Figure 3.
5. Which software did you use to run the forecasting model?
6. Section 4.2, Model Performance Assessment, why you use MAE? How about MAPE?
7. Please add the section of managerial implications of the paper.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The authors have incorporated all the suggestions. The manuscript is recommended for acceptance.
