Next Article in Journal
Dynamic Surgical Prioritization: A Machine Learning and XAI-Based Strategy
Previous Article in Journal
Automatic Robotic Ultrasound for 3D Musculoskeletal Reconstruction: A Comprehensive Framework
 
 
Article
Peer-Review Record

Dynamic Controller Design for Maximum Power Point Tracking Control for Solar Energy Systems

Technologies 2025, 13(2), 71; https://doi.org/10.3390/technologies13020071
by M. A. Fkirin, Zeinab M. Gowaly * and Emad A. Elsheikh *
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Technologies 2025, 13(2), 71; https://doi.org/10.3390/technologies13020071
Submission received: 5 January 2025 / Revised: 25 January 2025 / Accepted: 3 February 2025 / Published: 8 February 2025

Round 1

Reviewer 1 Report (Previous Reviewer 2)

Comments and Suggestions for Authors

I recommend the acceptance of the paper as its current version.

Author Response

First Review : is acceptable 

Reviewer 2 Report (Previous Reviewer 1)

Comments and Suggestions for Authors

The authors presented an improved version of the document. Nonetheless, some minor details must be considered. 

- The names of the authors should not be in capital letters according to MDPI format

- The corresponding author should have an institutional e-mail

- The orcids of the authors are missing

- The title of sections 4, 5, 6, and 7 should not be is in sustained uppercase (please see the titles of the other sections)

- Use parenthesis when referring to equations. Example:  Equation (x) ... 

- I guess the expression "merits & demerits" in line 224 and Table 1 is not appropriate try using expressions such as:  strengths and weaknesses /   Benefits and drawbacks  /  strengths and limitations /   ... 

 

Author Response

Comments1: The names of the authors should not be in capital letters according to MDPI format

Response1: Authors' names are rewritten in the revised version according to MDPI format.

Comments 2: The corresponding author should have an institutional e-mail

Response 2: The institutional email for the corresponding authors has been added to the revised version.

Comments 3: The orcids of the authors are missing

Response 3: The Orcid iDs for authors have been added to the revised version.

Comments 4: The title of sections 4, 5, 6, and 7 should not be is in sustained uppercase (please see the titles of the other sections)

Response 4: The titles of all sections have been rewritten in the revised version according to MDPI format.

Comments 5: Use parenthesis when referring to equations. Example:  Equation (x) ...

Response 5: All referred equations have been written as in the suggested example.

Comments 6: I guess the expression "merits & demerits" in line 224 and Table 1 is not appropriate try using expressions such as:  strengths and weaknesses /   Benefits and drawbacks  /  strengths and limitations / 

Response 6: The expression "merits & demerits" has been changed to “strengths and limitations” in the revised version.

 

Reviewer 3 Report (New Reviewer)

Comments and Suggestions for Authors

Paper Title:
Dynamic Controller Design of Maximum Power Point Tracking Control for Solar Energy System

Authors:
M. A. Fkirin, Zeinab M. Gowaly, Emad A. Elsheikh

Affiliations:
Department of Industrial Electronics and Control Engineering, Faculty of Electronic Engineering, Menoufia University, Egypt

1. Summary of the Paper
This paper presents a novel approach to optimizing power extraction in solar energy systems through the development of a dynamic Maximum Power Point Tracking (MPPT) controller. The proposed controller leverages a combination of Long Short-Term Memory (LSTM)-based Artificial Neural Networks (ANN) and Fuzzy Logic Control (FLC) to enhance energy efficiency under variable atmospheric conditions. The study compares the proposed methods with traditional MPPT techniques such as ANN, FLC, and LSTM-PI, evaluating performance metrics such as tracking efficiency, response time, and system stability. Simulation results indicate that the LSTM-optimized controllers outperform conventional approaches, especially in adapting to sudden irradiance and temperature changes.

2. Review Criteria

2.1 Clarity of Aim

  • Evaluation:
    The objective is clearly articulated, aiming to improve MPPT efficiency using a hybrid LSTM-ANN and LSTM-FLC approach.

  • Recommendation:
    The introduction could further highlight the novel contributions of the study compared to existing MPPT techniques.

2.2 Content Structure

  • Evaluation:
    The paper is structured logically, transitioning smoothly from the problem statement to methodology, results, and conclusions.

  • Recommendation:
    Adding brief summaries at the end of each section would enhance readability and reinforce key points.

2.3 Methodology

  • Evaluation:
    The methodology is detailed, covering the design of the MPPT controller and performance evaluation using real-time data.

  • Recommendation:
    Clarify the selection criteria for specific LSTM and fuzzy logic parameters and discuss any computational constraints.

2.4 Verification and Case Studies

  • Evaluation:
    The proposed system is validated through simulation under various environmental conditions.

  • Recommendation:
    Consider including experimental validation in real-world conditions to further support the findings.

2.5 Graphs and Diagrams

  • Evaluation:
    Figures effectively illustrate system performance and comparisons between different MPPT methods.

  • Recommendation:
    Additional schematic diagrams detailing the workflow of the hybrid MPPT approach could improve understanding.

2.6 Results and Discussions

  • Evaluation:
    The results are well-presented, showcasing the advantages of the proposed approach in terms of response time and tracking accuracy.

  • Recommendation:
    Discuss the broader impact of the findings on commercial solar PV applications and potential implementation challenges.

2.7 Conclusions

  • Evaluation:
    Conclusions summarize the contributions effectively and outline the advantages of the proposed system.

  • Recommendation:
    Provide more concrete suggestions for future research directions, such as scalability to larger PV systems.

2.8 Overall Quality

  • Evaluation:
    The paper presents a substantial contribution to the field of solar energy optimization and is well-written with minor language errors.

  • Recommendation:
    Proofread the manuscript to correct grammatical issues and ensure consistent technical terminology.

3. Recommendations for Publication
Based on the evaluation, the paper is recommended for Minor Revisions with the following suggested improvements:

  1. Expand on the unique contributions and novel aspects of the proposed framework in the introduction.

  2. Include a discussion on computational complexity and practical implementation challenges.

  3. Incorporate additional schematic diagrams to visually explain the controller workflow.

  4. Consider experimental validation to support the simulation results.

  5. Proofread the manuscript to eliminate minor grammatical errors and improve clarity.

Comments on the Quality of English Language

Minor grammatical errors and awkward phrasing should be corrected

Author Response

Comments 1 : 2.1 Clarity of Aim

The introduction could further highlight the novel contributions of the study compared to existing MPPT techniques.

Response 1: 

Thank you for your valuable suggestion.

As per the reviewer's comment, the unique contributions and novel aspects of the proposed framework were added in the introduction.

Please see the introduction and contribution parts in the revised version.

Comments 2: 

2.2 Content Structure

Adding brief summaries at the end of each section would enhance readability and reinforce key points.

Response 2: 

Thank you for your valuable suggestion.

As per the reviewer’s comment, a summary of each section has been added.

Please see the summary at the end of each part.

Comments 3: 

2.3 Methodology

Clarify the selection criteria for specific LSTM and fuzzy logic parameters and discuss any computational constraints.

Response 3: 

Thank you for your thoughtful comments.

As per the reviewer's comment, when selecting parameters for LSTM and fuzzy logic models, key considerations include the number of layers and hidden units in LSTM, which affect the model’s ability to capture data patterns without causing overfitting or excessive computational load. The sequence length, learning rate, batch size, and activation functions are also important in model performance. For fuzzy logic, the number and shape of membership functions and the defuzzification process all contribute to the system’s complexity and computational efficiency.

Comments 4:

2.4 Verification and Case Studies

Consider including experimental validation in real-world conditions to further support the findings.

Response 4: 

Thank you for your thoughtful comments.

We appreciate your valuable feedback regarding the need for experimental validation to support the simulation results. We agree that experimental validation is an essential step in demonstrating the practical applicability and robustness of the proposed prediction algorithm.

But, as mentioned in the article in Section 5.1 Input and Target Data Collection, our algorithm is trained and validated based on collected real data. The data were collected from NASA Power, with the data obtained at latitude 23.3374 and longitude 54.3485. The data samples for irradiance and temperature are obtained from March 2023 to March 2024. Since the real data contains all the climate changes during an entire year, this indirectly expresses the extent to which the algorithm can be applied practically.

However, at this stage of our research, we have focused on developing and validating the algorithm using a comprehensive collection of real-world data. While we have not yet applied the algorithm to a practical system for experimental validation, we believe that the rigorous simulation-based evaluation provides a strong foundation for its potential effectiveness.

Comments 5: 

2.5 Graphs and Diagrams 

Additional schematic diagrams detailing the workflow of the hybrid MPPT approach could improve understanding.

Response 5: 

Thank you for your valuable suggestion.

The revised version added more details about the proposed algorithms (ANN structure, fuzzy logic structure, and schematic diagram detailing the workflow of the proposed method).

Please see the following parts: (4.4 LSTM-ANN), (4.5 LSTM-Fuzzy Logic), and (5. Data Processing and Training using LSTM, Figure 12)

Comments 6: 

2.6 Results and Discussions

Discuss the broader impact of the findings on commercial solar PV applications and potential implementation challenges.

Response 6:

Thank you for your valuable suggestion.

As per the Reviewer comment, the findings of this study hold significant potential to enhance the efficiency and reliability of commercial solar PV applications. By introducing advanced MPPT techniques, such as LSTM-ANN and LSTM-FLC, the study demonstrates improved tracking efficiency under varying environmental conditions. This can directly lead to increased energy yields and better system performance in commercial setups, particularly in regions with inconsistent solar irradiance. However, implementing these advanced algorithms in real-world scenarios poses challenges, such as higher computational requirements and the need for robust hardware capable of supporting real-time data processing. Additionally, ensuring seamless integration with existing PV systems and grid infrastructure may require addressing compatibility and reliability concerns, especially in large-scale deployments

Comments 7: 

2.7 Conclusions

Provide more concrete suggestions for future research directions, such as scalability to larger PV systems

Response 7: 

We simplified our investigation by optimizing the PV-side LSTM-based MPPT design. The training procedure is carried out using hardware equipped with an 12th Gen Intel(R) Core (TM) i7-1255U CPU clocked at 1.70 GHz and 16 GB RAM, as well as the MATLAB 2022. However, DL models have intrinsic constraints that require significant computer resources. Training efficiency is also determined by dataset quantity. For real-world deployments, strong GPUs, cloud resources, or specialized hardware may be necessary.

In future research, hybrid approaches combining LSTM with advanced optimization algorithms will be used to optimize the neural network topology and enhance computational efficiency before deploying LSTM-based systems in microgrids and smart grids and evaluating the suggested methodologies in a real-world environment. To implement the LSTM-based MPPT algorithm, we recommend gathering data from a real-time PV systems.

In the revised version, the challenges and future work are added in the conclusion part.

Comments 8: 

2.8 Overall Quality

Proofread the manuscript to correct grammatical issues and ensure consistent technical terminology

Response 8: 

Thank you for your valuable suggestion.

Per the reviewer's comment, the manuscript has been proofread, and the minor grammatical issues have been corrected.

 

 

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.

 

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Please see the attached file. 

Comments for author File: Comments.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

In this work, the authors proposed a dynamic MPPT controller utilizing a combination of Long Short-Term Memory (LSTM)-based Artificial Neural Networks (ANN) and Fuzzy Logic Control (FLC) to optimize power extraction in solar energy systems across diverse irradiance and temperature conditions. The simulation results with real-time data demonstrate that the LSTM-optimized controllers significantly outperform the conventional methods, particularly in adapting to sudden changes in irradiance and temperature. Overall, this paper is well written and organized. I recommend the acceptance of this work after addressing the following issues.

1. In the introduction section, more background information should be added for attracting a wider audience, such as the development of PV technology, including the recently emerging perovskite solar cells and organic solar cells. The related literatures can be referred: ACS Appl. Mater. Interfaces 2023, 15, 7247, ACS Materials Lett. 2024, 6, 2964, Chem. Eng. J. 2023, 471, 144711. The literature review section should be logical, which are suggested to be perfected.

2. The proposed methods are demonstrated better than traditional methods. Why the proposed methods are better, can you summarize the potential reasons?

 

Reviewer 3 Report

Comments and Suggestions for Authors

If Pmpp=213.15W (Table 1) how can the algorithm extract more power from the PV panel? Fig.17 shows several cases above the Pmpp value.

On Fig.18 a transition from 1000 to 500 W/m2 is shown, thought he power is shown only around 107W.

On Fig.19 a transition from 500 to 800 W/m2 is shown. Now the figure only shows the power level at 171W.

Same issue on fig.20, though here is can be seen that the power readings have some traces at higher levels.

How can the Pmpp be 213.15W at 25W/m2? Table 6 shows wrong irradiance values.

Back to TopTop