Next Article in Journal
Rationale for the Combined Use of Biological Processes and AOPs in Wastewater Treatment Tasks
Previous Article in Journal
Visioning the Future of Smart Fashion Factories Based on Media Big Data Analysis
Previous Article in Special Issue
Power Efficiency Improvement of a Boost Converter Using a Coupled Inductor with a Fuzzy Logic Controller: Application to a Photovoltaic System
 
 
Review
Peer-Review Record

A State-of-Art-Review on Machine-Learning Based Methods for PV

Appl. Sci. 2021, 11(16), 7550; https://doi.org/10.3390/app11167550
by Giuseppe Marco Tina 1,*, Cristina Ventura 1,*, Sergio Ferlito 2,* and Saverio De Vito 2
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Appl. Sci. 2021, 11(16), 7550; https://doi.org/10.3390/app11167550
Submission received: 12 July 2021 / Revised: 11 August 2021 / Accepted: 12 August 2021 / Published: 17 August 2021

Round 1

Reviewer 1 Report

Interesting and consistent state of art review on machine-learning based methods applied for  PV systems.

The paper topic is in line with the scope of “applied sciences” and can be accepted for publication after minor language corrections, as for example on Line 307: “In [36] i a hybrid model …” .

 

Author Response

The paper has been modified following the suggestions of the reviewer.

Reviewer 2 Report

In my opinion, the paper presents a very complete review of recent works (published since 2018) in which Machine Learning and Deep Learning methods are applied to different fundamental aspects of the operation of solar plants, production prediction, fault or anomaly detection, or optimisation of MPPT mode operation, among others. I think it is a very good compilation work, with good organisation and presentation of the compiled papers in tables, very useful for authors who are working in this field.

I would just like to point out some minor aspects, especially in terms of form, so that authors can take them into account before publishing their work.

It is recommended that the authors read the work and correct some small typos in the text. As examples, line 307. “In [36] i a hybrid model…”, or line 308 “short-term memory (LSTM) networks s proposed…”, line 348 “relies on transferrin”, line 472 “To have and the idea of the power loss coming from faults this can vary from”, line 795 “Tensorflow of Pytorch”.

Separate the headings between different columns in the header of table 2.

Tables 3 and 7. The year column does not appear in bold, but appears in bold in tables 2, 4, 5 or 6.

Line 537. Separate a little the text of the paragraph from the table 4, they are very close. Idem in line 617.

Line 616. Place the beginning of table 6 on the next page, so that it does not remain on one page only the header.

All the parameters that appear in the equations should be explained in the text.

It would be advisable, in order to facilitate the reading of the document, to include a table of acronyms, given that there are numerous acronyms that appear throughout the text of the manuscript.

Author Response

The paper has been modified following the suggestions of the reviewer. Moreover, a table of acronyms has been added to the manuscript.

 

Back to TopTop