Next Article in Journal
Education- and Income Inequality as Drivers of Violent Property Crime in South Africa: A System Dynamics Model
Previous Article in Journal
Characteristics of Mining-Induced Slope Movement and Ground Behavior under Gully Landforms
 
 
Article
Peer-Review Record

Improving the Efficiency and Sustainability of Intelligent Electricity Inspection: IMFO-ELM Algorithm for Load Forecasting

Sustainability 2022, 14(21), 13942; https://doi.org/10.3390/su142113942
by Xuesong Tian 1, Yuping Zou 1, Xin Wang 1, Minglang Tseng 2,3,4,*, Hua Li 5 and Huijuan Zhang 5
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Sustainability 2022, 14(21), 13942; https://doi.org/10.3390/su142113942
Submission received: 3 September 2022 / Revised: 20 October 2022 / Accepted: 21 October 2022 / Published: 26 October 2022

Round 1

Reviewer 1 Report

 

- The authors should explain their reason for not using a data envelopment analysis approach (popular approach in performance measurement field) to measure efficiency of electricity inspection. For more details, please see the following papers:

Mardani, A., Zavadskas, E. K., Streimikiene, D., Jusoh, A., & Khoshnoudi, M. (2017). A comprehensive review of data envelopment analysis (DEA) approach in energy efficiency. Renewable and Sustainable Energy Reviews, 70, 1298-1322.

 

Zhao, W., Qiu, Y., Lu, W., & Yuan, P. (2022). Input–output efficiency of Chinese power generation enterprises and its improvement direction-based on three-stage DEA model. Sustainability, 14(12), 7421.

Tavassoli, M., Ketabi, S., & Ghandehari, M. (2020). Developing a network DEA model for sustainability analysis of Iran’s electricity distribution network. International Journal of Electrical Power & Energy Systems, 122, 106187.

- Advantages and benefits of the proposed approach should be given in detail. Also, the research gaps and the novelty of this study is not clear.

- The characteristics of current research should be highlighted in the comparative table of literature review from both aspects of theoretical and application.

- Generally, real-world data are tainted by uncertainty. The authors should discuss the proposed approach under data uncertainty.

- The authors should discuss on the limitations of the study.

- The authors should discuss on the generalization of the results of the study.

- The authors should clearly explain and justify the reason for using IMFO-ELM algorithm among the available algorithms in literature.

Author Response

Response to editor and reviewers' comments

 

Manuscript Number: sustainability-1924723
Title: Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting

Dear Editor and Reviewers:

We would like to thank the reviewers for their questions and notable comments that helped us to improve our paper. We applied all valuable comments of reviewers in the revised version. Based on reviewers’ comments, this study clarified some points in more details in the revised paper. The revisions were clearly highlighted in the manuscript.

 

Response to comments for Reviewer 1

Manuscript Number: sustainability-1924723
Title: Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting

Dear Reviewer 1:

Thank you very much for your fruitful comments. Manuscript ID “sustainability-1924723” entitled “Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting” has been carefully revised according to your suggestions. All revised text is highlighted by red color.

 

Comment #1: The authors should explain their reason for not using a data envelopment analysis approach (popular approach in performance measurement field) to measure efficiency of electricity inspection. For more details, please see the following papers:

Mardani, A., Zavadskas, E. K., Streimikiene, D., Jusoh, A., & Khoshnoudi, M. (2017). A comprehensive review of data envelopment analysis (DEA) approach in energy efficiency. Renewable and Sustainable Energy Reviews, 70, 1298-1322.

Zhao, W., Qiu, Y., Lu, W., & Yuan, P. (2022). Input–output efficiency of Chinese power generation enterprises and its improvement direction-based on three-stage DEA model. Sustainability, 14(12), 7421.

Tavassoli, M., Ketabi, S., & Ghandehari, M. (2020). Developing a network DEA model for sustainability analysis of Iran’s electricity distribution network. International Journal of Electrical Power & Energy Systems, 122, 106187.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of the expert, the authors have analyzed and cited the listed literatures in Section 2, and explained the reasons why envelopment analysis approach is not used. The added explanation is as follows:

“In addition, envelopment analysis methods are widely used to measure the efficiency of electric power inspection. For example, Mardani et al. [27] reviewed and summarized different envelopment analysis models used to measure energy efficiency problems. The results show that the envelopment analysis methods are suitable for analyzing energy efficiency problems, and have a good application prospect. Zhao et al. [28] the three-stage envelopment analysis method to measure the input-output efficiency of power generation companies in China. To assess the sustainability of Electricity Distribution Network in Iran, Tavassoli et al. [29] developed the network data envelopment analysis model. As a new statistical analysis method, data envelopment analysis is suitable for studying production systems with multiple inputs, and provides rich and useful information for decision-makers. However, the production function boundary measured by data envelopment analysis is certain, so it is impossible to analyze the influence of random factors and prediction errors. Additionally, the efficiency evaluation of this method is greatly affected by the extreme values, causing this method more sensitive to the selection of input and output indicators.”

 

[27] Mardani, A.; Zavadskas, E.K.; Streimikiene, D.; Jusoh, A.; Khoshnoudi, M. A comprehensive review of data envelopment analysis (DEA) approach in energy efficiency. Renewable and Sustainable Energy Reviews. 2017, 70, 1298-1322.

[28] Zhao, W.; Qiu, Y.; Lu, W.; Yuan, P. Input–output efficiency of Chinese power generation enterprises and its improvement direction-based on three-stage DEA model. Sustainability. 2022, 14(12), 7421.

[29] Tavassoli, M.; Ketabi, S.; Ghandehari, M. Developing a network DEA model for sustainability analysis of Iran’s electricity distribution network. International Journal of Electrical Power & Energy Systems. 2020, 122, 106187.

Please refer to Section 2 for the details of modification.

Comment #2: Advantages and benefits of the proposed approach should be given in detail. Also, the research gaps and the novelty of this study is not clear.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of the expert, the authors have explained the advantages and novelty of the proposed approach in Section 1 as follows:

“Compared with the traditional electricity inspection method, the method proposed in this study has many advantages. By improving the convergence performance of the IMFO algorithm, the load forecasting-based electricity inspection method applies the nonlinear mapping ability of the machine learning model and the superior convergence performance of the artificial intelligence algorithm to improve the efficiency of power inspection. The application of machine learning and artificial intelligence algorithms in the field of electricity inspection has improved the intelligence and automation level of electric power inspection, which is conducive to reducing the operating costs of electric power enterprises. The novelty of this study is as follows:

  1. In view of the current situation that the marketing inspection of power supply enterprises mainly relies on passive methods such as manual inspection and cannot find abnormal users in time, an electricity inspection method based on IMFO-ELM model is proposed.
  2. A novel IMFO algorithm with better optimization ability is proposed, which improves the intelligence level of electricity inspection and promotes the sustainable development of power enterprises.
  3. The proposed electricity inspections method improves the inspection efficiency, which improves the user experience and reduces the operating cost of the enter-prises.”

In addition, the research gaps have been highlighted in Section 2.

For more detailed description, please refer to Section 1 and 2 of the revised version.

Comment #3: The characteristics of current research should be highlighted in the comparative table of literature review from both aspects of theoretical and application.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of the expert, the authors have highlighted the characteristics of current research in literature review from both aspects of theoretical and application as follows:

“As an important part of electric power marketing, electricity inspection has great theoretical and application value for controlling marketing risks, improving the economic benefits of electric power enterprises, and promoting the sustainable development of electric power marketing. The research of electricity inspection method has great theoretical and application value: (1) improving the service quality of electricity inspection; (2) improving the reliability of electric power enterprise management; (3) improving power marketing system; and (4) improving the standardization and efficiency of energy management in electric power enterprises. The development of new energy power generation technique has brought many benefits, but also changed the operation mode of the power grid and increased the difficulty of abnormal load detection. Improving the economy and efficiency of electricity inspection is significance to improve the economic benefits, service quality and management level of electric power enterprises. At the same time, the efficient electricity inspection method can effectively reduce the operating cost of power enterprises, improve the user experience, and promote the sustainable development of enterprises.”

For more detailed description, please refer to Section 2 of the revised version.

Comment #4: Generally, real world data are tainted by uncertainty. The authors should discuss the proposed approach under data uncertainty.

Responses:

Thanks to the expert for your constructive opinions. According to the opinions of the expert, the authors have discussed the proposed approach under data uncertainty in Section 3 and Section 4 as follows:

“Power load is affected by uncertain factors, including known factors and un-known factors. Known factors include power supply units, grid capacity, user conditions, production capacity, etc. Unknown factors include weather conditions, regional economic activities, policy changes, etc. Due to the influence of these uncertainties, the values of historical data and related variables are often inaccurate, resulting in random deviation between the load forecasting results and the actual load values, that is, there is obvious uncertainty in the load forecasting. To deal with the uncertainty of power load forecasting, improving the forecasting accuracy and stability of the model is necessary. Traditional power inspection methods are difficult to deal with the randomness and uncertainty of load. Taking advantage of the periodicity of load changes, a corresponding load monitoring model is established using machine learning methods, and an intelligent optimization algorithm is introduced to optimize the model to improve monitoring accuracy.”

“The test results show that the proposed method can effectively deal with the nonlinearity and uncertainty of power load, which is due to the superior convergence performance of IMFO algorithm to improve the prediction stability of ELM model. The power inspection method based on load forecasting improves the ability to deal with the uncertainty of power load, thereby improving the ability to detect abnormal load, thus improving the efficiency and sustainability of power inspection.”

For more detailed description, please refer to Section 3 and Section 4 of the revised version.

Comment #5: The authors should discuss on the limitations of the study.

Responses:

Thanks to the expert for your constructive opinions. According to the opinions of the experts, the authors have discuss on the limitations of the study in Section 7 as follows:

“Although the abnormal data monitoring method based on load forecasting pro-posed in this study can improve the efficiency and sustainability of electricity inspec-tion to a certain extent, there are still some limitations. First, the ability of the IM-FO-ELM monitoring model to describe the load uncertainty needs to be improve. Sec-ond, the inspection efficiency of abnormal data needs to be improved, so as to promote the intelligent and systematic level of electricity inspection.”

For more detailed description, please refer to Section 7 of the revised version.

Comment #6: The authors should discuss on the generalization of the results of the study.

Responses:

Thanks to the expert for your constructive opinions. According to the opinions of the expert, the authors have discussed the generalization of the results of this study in Section 7 as follows:

The power inspection method based on IMFO-ELM proposed in this study can effectively deal with the uncertainty of power load. The proposed model and results obtained in this study have good generalization value, which is helpful to improve the sustainability of power marketing and the economic benefits of power enterprises. In addition, the IMFO-ELM prediction model has a good generalization ability. It can be used not only in the field of electricity inspection, but also in other fields, such as pat-tern recognition, graphic classification, life prediction, etc.

For more detailed description, please refer to Section 6 of the revised version.

Comment #7: The authors should clearly explain and justify the reason for using IMFO-ELM algorithm among the available algorithms in literature.

Responses:

Thanks to the expert for your constructive opinions. According to the opinions of the expert, the authors have explained and justified the reason for using IMFO-ELM algorithm among the existing algorithms in Section 5.1, as follows:

“Compared with PSO, DE, GA and other existing algorithms, MFO algorithm has stronger ability to find the existence. However, MFO algorithm also has the defect of easily falling into local extreme value, and the problem of poor population diversity. Therefore, to improve the optimization ability, this study improved the MFO algorithm and proposed the IMFO algorithm. The convergence performance test results show that, compared with the existing algorithms, the IMFO algorithm has stronger solving ability and is suitable for optimizing unimodal and multi-modal test functions. In addition, compared with existing machine learning models such as SVM and BPNN, ELM model has strong nonlinear mapping ability and generalization ability, and can better adapt to the uncertainty of power load. However, the mapping ability of ELM is affected by the super parameters. Therefore, this study uses the superior optimization ability of IMFO algorithm to further explore the mapping ability of ELM. Therefore, compared with the existing machine learning models, IMFO-ELM has more advantages.”

For more detailed description, please refer to Section 5.1 of the revised version.

Thank expert again for your contribution to this study. Your comments are very helpful to improve this paper

 

Reviewer 2 Report

The paper presents an abnormal data detection method based on power load forecasting in power networks. The authors used a model based on the improved moth-flame algorithm-optimized extreme learning machine in their analysis.

The manuscript presents a clear structure and presentation of the simulated results seems to be suitable.

However, the authors could improve the presentation of their manuscript.

The practical usefulness of the proposed model should be highlighted with more examples.

The data used for the learning algorithm is quite old: "The data of seven days from July 1 to July 7, 1999 are taken as the experimental data..."

The machine learning method is not described in sufficient detail to allow another researcher to replicate the results. The implementation of the machine learning algorithm in the computing environment should be provided by the authors.

Author Response

Response to editor and reviewers' comments

 

Manuscript Number: sustainability-1924723
Title: Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting

Dear Editor and Reviewers:

We would like to thank the reviewers for their questions and notable comments that helped us to improve our paper. We applied all valuable comments of reviewers in the revised version. Based on reviewers’ comments, this study clarified some points in more details in the revised paper. The revisions were clearly highlighted in the manuscript.

 

 

Response to comments for Reviewer 2

Manuscript Number: sustainability-1924723
Title: Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting

Dear Reviewer 2:

Thank you very much for your fruitful comments. Manuscript ID “sustainability-1924723” entitled “Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting” has been carefully revised according to your suggestions. All revised text is highlighted by red color.

General comment:

The paper presents an abnormal data detection method based on power load forecasting in power networks. The authors used a model based on the improved moth-flame algorithm-optimized extreme learning machine in their analysis. The manuscript presents a clear structure and presentation of the simulated results seems to be suitable. However, the authors could improve the presentation of their manuscript.

Responses:

Thank the expert for your approval of this study and your constructive comments. According to the opinions of expert, the authors has revised this paper and replied the comments one by one.

Comment #1: The practical usefulness of the proposed model should be highlighted with more examples.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of the expert, the authors have furtherly highlighted the practical usefulness of the proposed model, as follows:

In revised Section 2:

“As an important part of electric power marketing, electricity inspection has great theoretical and application value for controlling marketing risks, improving the economic benefits of electric power enterprises, and promoting the sustainable development of electric power marketing. The research of electricity inspection method has great theoretical and application value: (1) improving the service quality of electricity inspection; (2) improving the reliability of electric power enterprise management; (3) improving power marketing system; and (4) improving the standardization and efficiency of energy management in electric power enterprises. The development of new energy power generation technique has brought many benefits, but also changed the operation mode of the power grid and increased the difficulty of abnormal load detection. Improving the economy and efficiency of electricity inspection is significance to improve the economic benefits, service quality and management level of electric power enterprises. At the same time, the efficient electricity inspection method can effectively reduce the operating cost of power enterprises, improve the user experience, and promote the sustainable development of enterprises.”

In revised Section 6:

“Electric power marketing has a significant impact on the development of enterprises, and the effectiveness of marketing determine the overall development level of electric power enterprises. As an important part of electric power marketing, electricity inspection has a significant impact on the development of electric power enterprises. The study of electricity inspection methods has great practical value. To improve the efficiency of electricity inspection and promote the sustainable development of power enterprises, this study proposes a load forecasting-based abnormal load detection method. By analyzing the difference between the inspection results and the actual power consumption of users, the abnormal data points are screened out quickly and efficiently, so the abnormal users are marked to further determine the abnormal cause, which is convenient for the electric power department to investigate improves the user experience. The proposed method enriches the theory of electricity inspection, improves the economy of electricity inspection and the intelligent level of electric power enterprise management, and promotes the sustainable development of electric power marketing business. The practical usefulness and significance of the proposed method is summarized as follows:

(1)The economic losses caused by electricity inspection are reduced by improving the efficiency of electricity inspection.

(2) The efficient electricity inspection method improves the intelligence and informatization level of power enterprise management, and promotes the sustainable development of power marketing business.

(3) The improvement of abnormal load data detection accuracy improves user experience and the service level of power enterprises.”

For more detailed description, please refer to the revised version.

Comment #2: The data used for the learning algorithm is quite old: "The data of seven days from July 1 to July 7, 1999 are taken as the experimental data..."

Responses:

Thanks to the expert for your constructive comments. The power load data used in this paper are mainly used to verify the proposed IMFO-ELM model. According to the opinions of the expert, the authors have revised the description of the power load data and discussed the generalization of the proposed model and the obtained results, as follows:

“The network collected the actual load data of power plants in eastern Slovakia. The data of seven days from 7 months are taken as the experimental data, which was counted every 0.5 hours, and the obtained load curve is shown in Figure 1.”

“The power inspection method based on IMFO-ELM proposed in this study can effectively deal with the uncertainty of power load. The proposed model and results obtained in this study have good generalization value, which is helpful to improve the sustainability of power marketing and the economic benefits of power enterprises. In addition, the IMFO-ELM prediction model has a good generalization ability. It can be used not only in the field of electricity inspection, but also in other fields, such as pattern recognition, graphic classification, life prediction, etc.”

For more detailed description, please refer to Section 3 and Section 6 of the revised version.

Comment #3: The machine learning method is not described in sufficient detail to allow another researcher to replicate the results. The implementation of the machine learning algorithm in the computing environment should be provided by the authors.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of the expert, the authors have described the modeling process of machine learning-based electricity inspection method in detail in Section 4.4 to allow another researcher to replicate the results, and the computing environment is explained in Section 4.3, as follows:

“4.4. Power Load Monitoring Based on IMFO-ELM Model

The electricity inspection method proposed in this paper mainly includes two parts: one is the electric power load forecasting based on IMFO-ELM model, and the other is to judge the abnormal load based on forecasting electric power load. The IMFO algorithm is used to optimize the parameters of ELM model, and the IMFO-ELM model-based load monitoring method is further constructed. The modeling process of machine learning-based electricity inspection method is as follows:

  1. Determine test samples and training samples of the IMFO-ELM model;
  2. Initialize algorithm parameters ;
  3. The IMFO algorithm is used to optimize the parameters of the ELM;
  4. Train the IMFO-ELM model and test the model according to the test sample set;
  5. The monitored load data is denormalized.
  6. Inspect abnormal load based on forecast load.

The modeling process of machine learning-based electricity inspection method is shown in Figure 3.

Figure 3. The modeling process of machine learning-based electricity inspection method

“The computing environment is based on windows10 system, MATLAB R2020a, 8G memory and i5-6500 CPU.”

For more detailed description, please refer to Section 4.3 and Section 4.4 of the revised version.

Thank expert again for your contribution to this study. Your comments are very helpful to improve this paper!

 

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

- The authors have mistakenly used term "Envelopment Analysis" instead of term "Data Envelopment Analysis", which should be corrected in the manuscript.

- The reasons given to justify not using approach Data Envelopment Analysis (DEA) are not acceptable. DEA is a popular and applicable mathematical programming approach in performance measurement field. DEA has been widely applied in various fields and it has become applicable in different fields such as energy, power, water, agriculture, mining, finance, banking, insurance, real estate, transportation, health care, sport, communication, manufacturing, tourism, and education. to handle data uncertainty and ambiguity, the uncertain DEA approaches such as Stochastic DEA, Fuzzy DEA, and Robust DEA can be applied.

 

 

 

- The authors have presented the literature review in the form of text and paragraph, while the characteristics of current research should be highlighted in the comparative table of literature review from both aspects of theoretical and application.

- Some future research directions should be suggested at the end of manuscript.

Author Response

Response to editor and reviewers' comments

 

Manuscript Number: sustainability-1924723R1
Title: Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting

Dear Editor and Reviewers:

We would like to thank the reviewers for their questions and notable comments that helped us to improve our paper. We applied all valuable comments of reviewers in the revised version. Based on reviewers’ comments, this study clarified some points in more details in the revised paper. The revisions were clearly highlighted in the manuscript.

Response to comments for Reviewer 1

Manuscript Number: sustainability-1924723R1
Title: Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting

Dear Reviewer 1:

Thank you very much for your fruitful comments. Manuscript ID “sustainability-1924723R1” entitled “Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting” has been carefully revised according to your suggestions. All revised text is highlighted by red color.

 

Comment #1: The authors have mistakenly used term "Envelopment Analysis" instead of term "Data Envelopment Analysis", which should be corrected in the manuscript.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of the expert, the authors have revised the wrong statement about term "Data Envelopment Analysis" as follows:

“As a new statistical analysis method, data envelopment analysis is suitable for studying production systems with multiple inputs, and provides rich and useful information for decision-makers. Data envelopment analysis method is a quantitative analysis method that uses linear programming to evaluate the relative effectiveness of comparable units of the same type, which is widely used to measure the efficiency of electric power inspection. For example, Mardani et al. [27] reviewed and summarized different data envelopment analysis models used to measure energy efficiency problems. The results show that the data envelopment analysis methods are suitable for analyzing energy efficiency problems, and have a better application prospect. Zhao et al. [28] the three-stage data envelopment analysis method to measure the input output efficiency of power generation companies in China. Tavassoli et al. [29] developed the network data envelopment analysis model to assess the sustainability of Electricity Distribution Network in Iran.”

Please refer to Section 2 for the details of modification.

Comment #2: The reasons given to justify not using approach Data Envelopment Analysis (DEA) are not acceptable. DEA is a popular and applicable mathematical programming approach in performance measurement field. DEA has been widely applied in various fields and it has become applicable in different fields such as energy, power, water, agriculture, mining, finance, banking, insurance, real estate, transportation, health care, sport, communication, manufacturing, tourism, and education. to handle data uncertainty and ambiguity, the uncertain DEA approaches such as Stochastic DEA, Fuzzy DEA, and Robust DEA can be applied.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of experts, the authors have deleted the error statement about the reasons for not using DEA method, and discussed that using Stochastic DEA, Fuzzy DEA, and Robust DEA to deal with power load in Section 7, as follows:

“As a novel and popular mathematical programming approach in performance measurement field, Data Envelopment Analysis is widely used in the field of electric power and type energy with its unique advantages. In future research, Stochastic Data Envelopment Analysis, Fuzzy Data Envelopment Analysis, and Robust Data Envelopment Analysis are considered to deal with the uncertainty of electric load.”

For more detailed description, please refer to Section 7 of the revised version.

Comment #3: The authors have presented the literature review in the form of text and paragraph, while the characteristics of current research should be highlighted in the comparative table of literature review from both aspects of theoretical and application.

 

Responses:

Thanks to the expert for your constructive comments. According to the opinions of the expert, the authors have added the comparative table to analyze the characteristics of current research in Section 2, as follows:

 

Current research methods

Characteristics

Cluster analysis-based data mining techniques

High requirements on the quantity of the data; High the computational cost is

Artificial intelligence algorithms

Strong convergence; Easy to fall into local extreme value

Machine learning

Strong nonlinear mapping ability; Influence of super parameters on prediction stability

Data envelopment analysis

Strong applicability; Wide application range

 

For more detailed description, please refer to Section 2 of the revised version.

Comment #4: Some future research directions should be suggested at the end of manuscript.

Responses:

Thanks to the expert for your constructive opinions. According to the opinions of the expert, the authors have added the future research directions in Section 7 as follows:

“In addition to the research on power inspection methods, the construction of power inspection management system, the improvement of inspection business framework and the expansion of power inspection methods are all the future research directions and objectives.”

For more detailed description, please refer to Section 7 of the revised version.

Thank expert again for your contribution to this study. Your comments are very helpful to improve this paper!

Author Response File: Author Response.pdf

Round 3

Reviewer 1 Report

- The literature review table should be numbered and have a title.

- Relevant references should be mentioned in the literature review table.

- Future research directions should be improved by citing relevant references.

Author Response

Response to editor and reviewers' comments

 

Manuscript Number: sustainability-1924723R2
Title: Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting

Dear Editor and Reviewers:

We would like to thank the reviewers for their questions and notable comments that helped us to improve our paper. We applied all valuable comments of reviewers in the revised version. Based on reviewers’ comments, this study clarified some points in more details in the revised paper. The revisions were clearly highlighted in the manuscript.

Response to comments for Reviewer 1

Manuscript Number: sustainability-1924723R2
Title: Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting

Dear Reviewer 1:

Thank you very much for your fruitful comments. Manuscript ID “sustainability-1924723R2” entitled “Improving the efficiency and sustainability of intelligent electricity inspection: IMFO-ELM algorithm for load forecasting” has been carefully revised according to your suggestions. All revised text is highlighted by red color.

 

Comment #1: The literature review table should be numbered and have a title.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of the expert, the literature review table has been numbered and added a title as follows:

Table 1. The characteristics of the current research

Current research methods

Characteristics

Cluster analysis-based data mining techniques, such as Refs. [11-13]

High requirements on the quantity of the data; High the computational cost is

Machine learning, such as Refs. [14-23]

Strong nonlinear mapping ability; Influence of super parameters on prediction stability

Artificial intelligence algorithms, such as Refs. [24-26]

Strong convergence; Easy to fall into local extreme value

Data envelopment analysis, such as Refs. [27-29]

Strong applicability; Wide application range

Please refer to Section 2 for the details of modification.

Comment #2: Relevant references should be mentioned in the literature review table.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of experts, the relevant references have been cited in the literature review table, as follows:

Table 1. The characteristics of the current research

Current research methods

Characteristics

Cluster analysis-based data mining techniques, such as Refs. [11-13]

High requirements on the quantity of the data; High the computational cost is

Machine learning, such as Refs. [14-23]

Strong nonlinear mapping ability; Influence of super parameters on prediction stability

Artificial intelligence algorithms, such as Refs. [24-26]

Strong convergence; Easy to fall into local extreme value

Data envelopment analysis, such as Refs. [27-29]

Strong applicability; Wide application range

Please refer to Section 2 for the details of modification.

Comment #3: Future research directions should be improved by citing relevant references.

Responses:

Thanks to the expert for your constructive comments. According to the opinions of the expert, the authors have analyzed the future research directions by citing relevant references, as follows:

“In addition to the research on power inspection methods, effective electricity theft inspection, the improvement of inspection business framework and the detection of malicious fraud in electrical energy consumption are all the future research directions and objectives. For example, Kong et al. [45] developed a novel electricity theft inspection method to reduce economic losses for power companies. To improve inspection business framework, Xia et al. [46] devised a suspicion assessment-based inspection algorithm to detect malicious users in smart grid. Santos et al. [47] developed an effective and scalable system to predict fraud and detect the abnormal electricity use.”

  1. Kong, X.Y.; Zhao, X.; Liu, C.; Li, Q.S.; Dong, D.L.; Li, Y. Electricity theft detection in low-voltage stations based on similarity measure and DT-KSVM. International Journal of Electrical Power & Energy Systems. 2021, 125.
  2. Xia, X.F.; Xiao, Y.; Liang, W. SAI: A Suspicion Assessment-Based Inspection Algorithm to Detect Malicious Users in Smart Grid. IEEE Transactions on Information Forensics and Security. 2020, 15, 361-374.
  3. Santos, R.N.; Yamouni, S.; Albiero, B.; Vicente, R.; Silva, J.A.; Souza, T.F.B.; . . . Lei, Z.L. Gradient boosting and Shapley additive explanations for fraud detection in electricity distribution grids. International Transactions on Electrical Energy Systems. 2021, 31(9).

For more detailed description, please refer to Section 6 of the revised version.

Thank expert again for your contribution to this study. Your comments are very helpful to improve this paper!

Author Response File: Author Response.pdf

Back to TopTop