A Combined Forecasting Model Based on a Modified Pelican Optimization Algorithm for Ultra-Short-Term Wind Speed
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThe paper is well structured, well written and I think could have significant merit in a high demanding research topic like the wind speed forecasting. Therefore, I recommend a speed publication as is and I would like to congratulate the authors.
Please refer to the attachment for detailed comments.
Comments for author File: 
Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThis paper proposes a combined forecasting model for ultra-short-term wind speed prediction, utilizing a modified Pelican Optimization Algorithm , Variational Mode Decomposition, and Long Short-Term Memory networks. The model's advantages in terms of prediction accuracy and stability are validated through multiple experiments. The research topic holds practical significance, and the methodology is well-structured, however, some details require further clarification.
1. When introducing the improved Pelican Optimization Algorithm, although the methods of improvement and the results of experimental verification are elaborated in detail, the theoretical performance analysis of the improved algorithm is lacking. For instance, there is no mathematical proof of the convergence of the improved algorithm, and the specific mechanisms by which the algorithm enhancements improve model performance are not explored in theoretically.
2. In the experimental section, most model parameter settings are based on existing research or empirical values. For some key parameters (such as K, alpha, and tau in VMD, as well as hyperparameters in LSTM), the rationale for selecting these specific values is not fully explained.
3. The paper mentions determining the number of modes K using sample entropy but does not specify the threshold or stability criterion. A mathematical definition or example should be included to clarify this point.
4. In Figures 7 and 11, multiple prediction curves overlap, and the color differentiation is insufficient, making it difficult to distinguish between them.
5. The paper notes long computation times but does not provide a quantitative analysis (specific training durations) or suggest optimization directions (such as parallel computing or lightweight models). This information should be supplemented.
6. Some abbreviations (e.g., "WS") are not defined upon first use. The full term (Wind Speed) should be provided for clarity.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsDear Authors,
Thank You for the opportunity of reading this article. First of all I would like to congratulate you for your work.
General statements about the article:
The paper "A Combined Forecasting Model Based on Modified Pelican Optimization Algorithm for Ultra-Short-Term Wind Speed" presents an innovative approach to ultra-short-term wind speed prediction. The authors propose a hybrid forecasting model that integrates the Modified Pelican Optimization Algorithm with Variational Mode Decomposition and Long Short-Term Memory networks to enhance prediction accuracy.
The references in the paper appear to be well-chosen, citing relevant works related to wind speed forecasting and optimization algorithms. The authors referenced some basic research as well as recent achievements, which helps to establish a quality theoretical background. To further improve the quality of references, it would be useful if authors included more recent research (2023, 2024, 2025).
The figures in the paper are clear and well structured. The flowchart of the modified Pelican Optimization Algorithm is logically structured and provides a good understanding of the process. However, some areas for improvement include Ensuring all figures have high resolution, providing better color differentiation in comparison charts, adding figure captions with more descriptive explanations to ensure clarity. The paper presents clear figures, and well-structured tables, contributing to the credibility and clarity of the research. Minor refinements in figure resolution, and table formatting could further enhance the paper’s quality.
This paper makes a valuable contribution to the field of wind speed forecasting by combining advanced optimization techniques with deep learning models. The results indicate that the proposed approach outperforms existing methods in both accuracy and stability. However, additional research on computational efficiency and its adaptability to diverse geographical conditions would further enhance its impact and applicability in renewable energy management.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
