Developing a Deep Neural Network with Fuzzy Wavelets and Integrating an Inline PSO to Predict Energy Consumption Patterns in Urban Buildings
Round 1
Reviewer 1 Report
The authors focus their study on the problem of energy demand estimation within smart grid systems by introducing a deep neural network on fuzzy wavelets in order to predict the energy demand in Iran. The proposed framework is supported by a hybrid training method and a gradient-based algorithm for the proposed deep neural network and fuzzy wavelets component.
The examined research topic is novel and of great interest to the research community given its great applicability in realistic systems.
The provided theoretical analysis is concrete, complete, and correct and the authors have well thought out their main contributions. The authors have provided a detailed set of numerical results in order to show the pure operation and the performance of the proposed framework.
The authors should address the following comments in order to improve the quality of presentation of their manuscript, as well as they are encouraged to consider the following suggestions provided by the reviewer in order to improve the scientific depth of their manuscript.
Initially, in Sections 1 and 2, the authors should present the related work by using more summative language and better categorize the presented literature in order to enable the reader to understand the research gap that the authors tried to address.
Furthermore, there are several distributed solutions that have been introduced in the literature, such as Contract-Theoretic Demand Response Management in Smart Grid Systems, doi: 10.1109/ACCESS.2020.3030195, in order to deal with the problem of energy demand estimation and ultimately with the problem of demand response management. The authors should update the provided related work in order to capture the most recent state of the art.
In Section 3, the authors should include a table summarizing the main notation that is used in the paper, which currently is quite excessive.
In section 4, the authors should include an additional subsection providing the theoretical analysis of the computational complexity of the proposed framework and architecture as well as the information overhead that is imposed to the system.
In section 4, the authors should complement the answer to the previous comment by presenting some indicative numerical results quantifying the computational complexity of the proposed framework.
Finally, the overall manuscript should be checked for typos, syntax, and grammar errors in order to improve the quality of its presentation.
Author Response
Dear Reviewer,
Thank you for your valuable comments. We upload an answer file to address your suggestions.
Best Regards
Lazim Abdullah
Author Response File: Author Response.pdf
Reviewer 2 Report
This reviewer appreciates the authors’ effort for preparing such an informative article and suggests some of the following points to improve the quality of the paper in the revised version:
- Try to limit the acronyms in Title of the paper, Abstract and Conclusion section.
- Try to include the nomenclature of all symbols used in the work at the beginning.
- Redraft the Introduction section with background, challenges, motivations, literature survey, contributions/novelties, and the organization of the paper. Try to highlight major contribution of the works at least in 3-bulleted points prior to the organization of paper. Don’t present the work objective as contribution. Also expand the literature survey with some recent (last 3-years) works such as, doi: 1016/j.apenergy.2014.02.057, 10.3390/en14102735, 10.1016/j.epsr.2019.106073, and so on.
- Try to maintain the work-flow of the article (especially during transitions between sections/ sub-sections) to improve the quality of writing.
- Discuss the problem formulation in more detail. Try to include the flowchart of the proposed method and discuss it with reference to the application in current problem.
- Try to quote all equations at relevant texts with appropriate citations (If adopted from published work).
- Why the author proposed DNFW-PSO for this work? Compare it’s response with some contemporary optimization algorithms to support your claims.
- Try to redraw the result plots with zoomed inset view and include xy-grids for better interpretation.
- Try to include the values of design parameters of the system in appendix.
- Redraft the conclusion section, addressing the result findings appropriately with numerical evidences. Include at least one specific future scope to it.
- Please redraft the entire manuscript with a thorough proofread of the article to rectify some existing typos and grammatical mistakes.
- Format the references in unified style.
Author Response
Dear Reviewers,
Thank you for your valuable comments. We upload an answer file to address your suggestions.
Best Regards
Lazim Abdullah
Author Response File: Author Response.pdf
Reviewer 3 Report
Accept in present form
Author Response
Dear Reviewers,
Thank you for your valuable decision.
Best Regards
Lazim Abdullah
Round 2
Reviewer 1 Report
The comments of the reviewers have been addressed in detail by the authors. The authors have substantially improved the quality of presentation and the structure of the paper. The manuscript can be accepted in its current form.