Next Article in Journal
Optimization Design and Analysis of Polymer High Efficiency Mixer in Offshore Oil Field
Previous Article in Journal
Non-Linear Sliding Mode Controller for Photovoltaic Panels with Maximum Power Point Tracking
 
 
Article
Peer-Review Record

Short-Term Wind Power Prediction Based on Improved Grey Wolf Optimization Algorithm for Extreme Learning Machine

Processes 2020, 8(1), 109; https://doi.org/10.3390/pr8010109
by Jiale Ding, Guochu Chen * and Kuo Yuan
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Reviewer 4: Anonymous
Processes 2020, 8(1), 109; https://doi.org/10.3390/pr8010109
Submission received: 27 November 2019 / Revised: 4 January 2020 / Accepted: 13 January 2020 / Published: 15 January 2020
(This article belongs to the Section Process Control and Monitoring)

Round 1

Reviewer 1 Report

Thank you for a nicely written paper, and one that I find very interesting; it is nice to see progress in the conservative area of short-term forecasting. There are a few language errors which could be corrected to make it even better, and some graphs are lacking units and visibility.

A few questions:

For the BAS algorithm, which fitness function is used? It is not quite clear from the paper. The VMD method is a good way to separate noise from usable characteristics, but the number of modes can be hard to select autonomously, and for your simulation case you seem to hand-pick the three bins. Have you any consideration for a method to automate this task? The data available for wind power estimation is often of frequencies 1Hz - 5Hz from turbines, have you considered the lack of high-frequency data for the VMD and how it could impact accuracy? I have a hard time seeing the impact of each individual contribution, e.g. changing to non-linear a, the BAS inclusion, etc. this may be due to the length restriction of the paper but would be a nice to have part.

Otherwise a good paper.

 

Author Response

Dear Reviewer:

Thank you for your comments concerning our manuscript entitled “Short-term Wind Power Prediction Based on Improved Grey Wolf Optimization Algorithm for Extreme Learning Machine” (ID: processes-666838).

Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. Revised portion are marked in red in the paper. The main corrections in the paper and the responds to the reviewer’s comments are as flowing.

Please see the attachment.

Kind Regards

Ding Jiale

Author Response File: Author Response.pdf

Reviewer 2 Report

The manuscript presents the Short-term Wind Power Prediction Based on Improved Grey Wolf Optimization Algorithm for Extreme Learning Machine. The manuscript is well written and discussing one of the interesting topics in the area. However, some minor revision needs for the manuscript before it can be published:

The novelty of the paper not clear, the authors need to add a paragraph in the Introduction Section explaining the paper's novelty comprehensively;  Add sub-section in the Introduction named Contribution, and address the paper contributions in bullet points; Add more details to the proposed method; Add future works in the Conclusion Section. 

Author Response

Dear Reviewer:

Thank you for your comments concerning our manuscript entitled “Short-term Wind Power Prediction Based on Improved Grey Wolf Optimization Algorithm for Extreme Learning Machine” (ID: processes-666838).

Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. Revised portion are marked in red in the paper. The main corrections in the paper and the responds to the reviewer’s comments are as flowing.

Please see the attachment.

Kind Regards

Ding Jiale

Author Response File: Author Response.pdf

Reviewer 3 Report

For wind power forecasting, the input variables are important. The lead-time also affects the results. More importantly, the numerical weather prediction is necessary as the inputs for forecasting. This paper only used historical wind power series to predict future wind power. It is not practical for industry application. The only decision is to reject this paper. 

Author Response

Dear Reviewer:

Thank you for your comments concerning our manuscript entitled “Short-term Wind Power Prediction Based on Improved Grey Wolf Optimization Algorithm for Extreme Learning Machine” (ID: processes-666838).

Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. Revised portion are marked in red in the paper. The main corrections in the paper and the responds to the reviewer’s comments are as flowing.

Please see the attachment.

Kind Regards

Ding Jiale

Author Response File: Author Response.pdf

Reviewer 4 Report

The paper proposes a combined forecasting model based on variational mode decomposition (VMD) and extreme learning machine (ELM) optimized by improved grey wolf optimization GWO algorithm, to be used in short-term prediction of wind power. The optimization results are weighted, being the final predicted value of wind power. The performance of the improved GWO algorithm is compared to the standard particle swarm optimization algorithm and the standard GWO algorithm. The simulation results based on real wind power data prove that the VMD-improved GWO-ELM algorithm has high optimization accuracy than other 3 models.

The paper fits the journal topics, being organized in a logical manner. The state of art covers the latest results in the field. The authors’ own results are not included in the state of art.

A Nomenclature at the beginning of the paper, containing the abbreviations and notations should be useful for paper readability.

There are some grammar errors and typos in the text that should be corrected (prey,which; The above standard GWO may still exist some problems.; In order to further prove the convergence characteristics of the improved  GWO algorithm, compare the optimal value, the worst value, the variance, and the excellent rate of the results of the three algorithms are compared in Table 2.;etc)  

Author Response

Dear Reviewer:

Thank you for your comments concerning our manuscript entitled “Short-term Wind Power Prediction Based on Improved Grey Wolf Optimization Algorithm for Extreme Learning Machine” (ID: processes-666838).

Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. Revised portion are marked in red in the paper. The main corrections in the paper and the responds to the reviewer’s comments are as flowing.

Please see the attachment.

Kind Regards

Ding Jiale

Author Response File: Author Response.pdf

Back to TopTop