Next Article in Journal
Strategy Based on Two Stages for IR Thermographic Inspections of Photovoltaic Plants
Previous Article in Journal
Mask Branch Network: Weakly Supervised Branch Network with a Template Mask for Classifying Masses in 3D Automated Breast Ultrasound
 
 
Article
Peer-Review Record

Real-Time Short-Term Voltage Stability Assessment Using Combined Temporal Convolutional Neural Network and Long Short-Term Memory Neural Network

Appl. Sci. 2022, 12(13), 6333; https://doi.org/10.3390/app12136333
by Ananta Adhikari, Sumate Naetiladdanon * and Anawach Sangswang
Reviewer 1:
Reviewer 2:
Appl. Sci. 2022, 12(13), 6333; https://doi.org/10.3390/app12136333
Submission received: 20 May 2022 / Revised: 13 June 2022 / Accepted: 17 June 2022 / Published: 22 June 2022
(This article belongs to the Section Electrical, Electronics and Communications Engineering)

Round 1

Reviewer 1 Report

 

Authors describe their method for Authors describe their method for

Authors describe their method for  real-time short-term voltage stability assessment using combined temporal convolutional neural network and long short-term memory neural network. As a result of the application of this method, Authors consider the following assessment of the system state: stable, unstable and stable-with fault-induced delayed voltage recovery phenomenon.

Is the transfer-learning problem considered only for the N-1 contingency case?

The term model is misused in this article.

The term "model" means something other than the term "method" or the term "algorithm".

The discussion of the obtained results should be more extensive.

The authors should arrange the markings of the considered quantities, e.g. n is treated as the number of nodes in the system, and at other times this number is Nb

Formulas (1), (2) should be revised.

Formulas (1), (2) should be revised.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

The current study discusses the models for the assessment of voltage stability. The authors presented a model aiming at the assessment of voltage stability for long/short-run memory neural networks. The past background of the study with research gaps is thoroughly discussed and the research findings are interesting. I am in favor of the paper with a few minor comments to improve the readability of the paper.

1. The abstract is too long. The author must be specific to the research gap and the objectives of the paper.

2. The literature survey must be from 2020 onward to provide a better background for the readers.

3. Double-check the abbreviations.

4. The quality of the figures and their style is confusing it took me time to understand them. please revise them.

5. The limitations of the work must be discussed in the discussion section thoroughly.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

I have no further comments.

Back to TopTop