Review Reports - Forecasting Average Daily and Peak Electrical Load Based on Average Monthly Electricity Consumption Data

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The manuscript presents a method to forecasting average daily electrical loads using average monthly electricity consumption and a generalized coefficient. Several important issues must be addressed to enhance the manuscript.

1. The authors obtain daily load forecasts upon monthly electricity loads. However, monthly electricity load itself requires forecasting to obtain. The authors need to present whether this multiple forecasting procedure can provide reliable forecasting performance. Supporting this with empirical or theoretical justification is necessary.

2. To validate the performance of the proposed method, a comparative experiment with other existing daily load forecasting methods is necessary.

3. The reasons for selecting the three specific regions (Chelyabinsk, Dushanbe, and Khorog) should be stated.

4. Some section titles need to be revised. Moreover, Sections 4 and 5 could be merged, or alternatively, the content of Section 4 should be expanded.

5. Figure Improvements and Caption Consistency
- Figure 1 can be converted into a bar chart for better readability.
- It is better Figures 3 and 4 include a legend, respectively.
- The captions of Figures 3 and 4 are the same.
- Again, Figures 8 to 11 also require legends.

6. A summary of the descriptive statistics of the dataset need to be included. Specifically, the authors should report the number of apartments and individual houses used from each region, as well as the time period covered by the data.

7. The manuscript needs to present a direct comparison between actual and forecast values.

Author Response

Thank you for your valuable comments and recommendations.

Below we respond to the reviewer's comments. All corrections in the text of the article are highlighted in green.

Comments and Suggestions for Authors

The authors obtain daily load forecasts upon monthly electricity loads. However, monthly electricity load itself requires forecasting to obtain. The authors need to present whether this multiple forecasting procedure can provide reliable forecasting performance. Supporting this with empirical or theoretical justification is necessary.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

The results of the comparison of the obtained values of the actual (predicted) electrical load, taking into account the developed generalized coefficient A, are presented on pages 8 and 9 of the corrected version of the article.

To validate the performance of the proposed method, a comparative experiment with other existing daily load forecasting methods is necessary.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

The reasons for selecting the three specific regions (Chelyabinsk, Dushanbe, and Khorog) should be stated.

Thanks for the note. We have the following response to this remark.

Corrections have been made.

Correction made on page 4. Excerpt from corrections (Using the data obtained from the automated system for monitoring and accounting of electricity for 2021-2022, an average monthly graph of electricity consumption with averaging per apartment was constructed for the consumer of the city of Chelyabinsk of the Russian Federation, cities of the Republic of Tajikistan (Dushanbe and Khorog). Fig. 1. The reasons for choosing these cities are that they have a distinctive feature in their location in different territorial and meteorological areas, consumers of the city of Chelyabinsk are provided with hot and warm water supply, while the cities of the Republic of Tajikistan have only a single energy source (electric)……

Some section titles need to be revised. Moreover, Sections 4 and 5 could be merged, or alternatively, the content of Section 4 should be expanded.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

Sections 4 and 5 have been combined. Section 5 has been added. The titles of sections 3 and 4 have been corrected. The new sections are as follows - Materials and Research Methods. Electrical load forecasting. Comparison of actual and forecast values. Conclusion.

Figure Improvements and Caption Consistency

- Figure 1 can be converted into a bar chart for better readability.

- It is better Figures 3 and 4 include a legend, respectively.

- The captions of Figures 3 and 4 are the same.

- Again, Figures 8 to 11 also require legends.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

The recommendations and comments were taken into account in the corrected version of the article. The corrected figures are highlighted in green.

A summary of the descriptive statistics of the dataset need to be included. Specifically, the authors should report the number of apartments and individual houses used from each region, as well as the time period covered by the data.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

Added statistics in the corrected version (Figure 1)

The manuscript needs to present a direct comparison between actual and forecast values.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

Added section 5. Comparison of actual and forecast values

Reviewer 2 Report

Comments and Suggestions for Authors

This work is interesting.

A coefficient Ai related to temperature, which is real archived data, is introduced to predict the power from average monthly electricity consumption. The idea is concise and smart.

I have some suggestions to improve this paper.

Major issue:

For eq.1 and 2, why Ait has a s plus k relationship, while Aie has a s multiplying k relationship?

The predicted power in Fig.8-11 may be compared with measured data to show its predicting ability.

The definitions and physical meaning of specific electric loads (SEL) may be given.

Minor issue:

The meaning of different colors in fig.3,4, 8-11, 12,13 may be given.

Methods published to predict power from monthly electricity consumption may be given in the introduction.

Author Response

Thank you for your valuable comments and recommendations.

Below we respond to the reviewer's comments. All corrections in the text of the article are highlighted in yellow.

Comments and Suggestions for Authors

This work is interesting.

A coefficient Ai related to temperature, which is real archived data, is introduced to predict the power from average monthly electricity consumption. The idea is concise and smart.

I have some suggestions to improve this paper.

Major issue:

For eq.1 and 2, why Ait has a s plus k relationship, while Aie has a s multiplying k relationship?

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

Comments and clarifications on this issue have been added to the text of the article (page 3).

Here is part of an excerpt from the text The denominators of equations (1 and 2) allow us to establish the influence of other energy sources (except electric) on electricity consumption and electric loads. If in the de-nominators of the product, then the significance of the absence of other energy sources (heat and hot water supply and gas supply) ......

The predicted power in Fig.8-11 may be compared with measured data to show its predicting ability.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

In the corrected version of the article we have added a new section 5. Comparison of actual and forecast values. It provides comparisons.

The definitions and physical meaning of specific electric loads (SEL) may be given.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

The definition is given on page 3. Here is part of the excerpt from the text (The term "actual specific power of the electric load" is understood as the ratio of the average monthly (obtained from the data of electricity meters installed at consumers of apartment buildings) or at peak hours (based on the results of measurements at morning and evening peaks at the entrance to apartments) to the number of days and hours in the month or at peak hours...............)

Minor issue:

The meaning of different colors in fig.3,4, 8-11, 12,13 may be given.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

The revised version contains corrections.

Methods published to predict power from monthly electricity consumption may be given in the introduction.

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

1. The first two 1st-round comments have not been adequately answered That is, 1) The authors obtain daily load forecasts upon monthly electricity loads. However, monthly electricity load itself requires forecasting to obtain. The authors need to present whether this multiple forecasting procedure can provide reliable forecasting performance; 2) To validate the performance of the proposed method, a comparative experiment with other existing daily load forecasting methods is necessary.
Both comments are critical for this study and must be addressed.

2. Figures 1 and 2 can be enhanced by adjusting the axis sizes, resolutions, and so on.

3. When comparing actual values and forecasts, it is necessary to use well-known metrics such as MAPE, MAE, and RMSE.

Author Response

Thank you for your valuable comments and recommendations.

Below we respond to the reviewer's comments. All corrections in the text of the article are highlighted in green.

Comments and Suggestions for Authors

The first two 1st-round comments have not been adequately answered That is, 1) The authors obtain daily load forecasts upon monthly electricity loads. However, monthly electricity load itself requires forecasting to obtain. The authors need to present whether this multiple forecasting procedure can provide reliable forecasting performance; 2) To validate the performance of the proposed method, a comparative experiment with other existing daily load forecasting methods is necessary.

Both comments are critical for this study and must be addressed.

Thank you for your comment. We have the following response to this comment.

Corrections have been made.

Corrections are highlighted in green (pages 1-7 and 12, 13).

Figures 1 and 2 can be enhanced by adjusting the axis sizes, resolutions, and so on.

Thank you for your comment. We have the following response to this comment.

In the corrected version the quality of the drawings has been increased

When comparing actual values and forecasts, it is necessary to use well-known metrics such as MAPE, MAE, and RMSE.