Learning-Based Approaches for Voltage Regulation and Control in DC Microgrids with CPL

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

In this manuscript, the authors have proposed an approach to controlling DC/DC boost converters that supply constant power loads (CPLs), employing nonlinear distortion observer (NDO) and learning-based composite nonlinear control. The system model is transformed into canonical form, ensuring precise voltage tracking. The NDO methodology is implemented for the evaluation of load power. Then, the artificial neural network (ANN) is trained using data obtained from the NDO and the boost converter. The proposed approach provides the advantage of accurate voltage monitoring while demonstrating strong robustness against external and system uncertainties. On the other hand, the designed procedure can be used to stabilize other DC/DC converters.

 

The literature is well-described, making readers understand a brief studying history of this field. Some pain points in this field and current approaches are introduced.

 

The research methods are well-described, giving readers sufficient to follow the study tools.

 

In summary, the manuscript can be published.

Author Response

Dear teacher, I want to express my sincere gratitude for dedicating your time to review our article and for your valuable efforts. Your positive feedback is truly motivating. Wishing you continued success in your work. Thank you once again.

Reviewer 2 Report

Comments and Suggestions for Authors

In a manuscript titled "Learning-Based Approaches for Voltage Regulation and Control in DC Microgrids with CPL," the authors presented a novel approach to voltage regulation in a DC/DC boost converter involving a combination of a backstepping algorithm (BSC) and artificial neural network (ANN)-based control techniques. The manuscript is interesting as it relates to an area of scientific research related generally to microgrids serving multiple renewable energy sources. 

The literature review in Chapter 1, Introduction, interestingly introduces the reader to the described problem, which the authors tried to solve. I have no comments on the content of Chapter 2. System Modeling and Problem Description, but I do have an editorial comment. Scientific articles usually stick to specific rules, such as, for example, the names of individual chapters. In my opinion, this chapter should be called "Materials and Methods." Besides, what is the point of describing at the end of the Introducton chapter what each of the following chapters (lines 113 to 117) contains? After all, the names of the subsections and chapters make this clear.

Unfortunately, the scientifically weakest part of this manuscript is what should be the most important, i.e., Chapter 4. Simulation Results, Chapter 5. Discussion and Chapter 6. Conclusions.

In Chapter 4. Simulation Results: One expects results from trials of the actual operation of the complete device and not just from the simulation of the method, as presented by the authors. Besides, even in the case of the method simulation, the shape of the peaks and their reason for the differences from other devices are not discussed. For example, the peak at 0.12 s in the Current response graph is particularly interesting. It would have been worthwhile to insert a comment discussing the reasons for this peak shape in this chapter. 

The Discussion chapter needs to be more specific; in particular, it needs references to items in the cited literature on specific regulators and, based on these items from the references, to make a more in-depth discussion. As presented in this chapter, the restrained discussion could be included in a conference paper rather than in a manuscript for a serious scientific journal. Perhaps the research presented produced such trivial results that there is nothing to discuss.

 Chapter 6 Conclusions

Unfortunately, this chapter is only an abstract of the manuscript. It should include what must be here, i.e., the conclusions of the research and its analysis. 

After reading chapters 4 through 6, one gets the impression that the authors have presented commercial information about a new device rather than a scientific article.

Author Response

Dear teacher, I would like to express my sincere gratitude for taking the time to review our article and for your valuable efforts. I wish you continued success in your work. Thanks again.

Author Response File: Author Response.docx

Reviewer 3 Report

Comments and Suggestions for Authors

The paper presents a novel approach to voltage regulation in DC microgrids with constant power loads (CPL) using Learning-Based Nonlinear Control. It combines the backstepping algorithm with artificial neural network-based control techniques to achieve precise voltage tracking, ensuring stability and dynamic response. The approach utilizes the nonlinear distortion observer technique for load power estimation. During the training phase, a neural network is trained using data from the backstepping controller, and it's subsequently used for voltage regulation. The performance of this approach is extensively evaluated through simulations and compared to conventional backstepping and model predictive control (MPC) controllers. The results demonstrate the effectiveness and superiority of the proposed strategy.

My Comments and Suggestions:

1) The paper could provide more technical details about the learning-based control approach, the neural network architecture, and the nonlinear distortion observer technique. 

2) The paper briefly mentions the training phase and utilization of the ANN without elaborating on the process. Providing a step-by-step explanation of the methodology would be helpful.

3) Mention the limitations of the proposed approach, such as any specific scenarios where it might not perform well or requirements for fine-tuning.

4) Discuss potential directions for future research or improvements to the proposed methodology, including its applicability to different converter topologies.

5) The conclusion should be more comprehensive, summarizing the key contributions and practical implications of the proposed approach.

Author Response

Dear teacher, I would like to express my sincere gratitude for taking the time to review our article and for your valuable efforts. I wish you continued success in your work. Thanks again.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

The authors have incorporated many of my suggestions in the revised manuscript.

I have no further comments.

Reviewer 3 Report

Comments and Suggestions for Authors

Accept in present form