Multi-Factor Load Classification Method considering Clean Energy Power Generation
The analysis of load characteristics is the basis and premise of load actively participating in power grid regulation. This paper proposes a multi-factor load classification method considering the load of clean energy power generation, the rapidity of load classification, and various subjective and...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi-Wiley
2023-01-01
|
| Series: | International Transactions on Electrical Energy Systems |
| Online Access: | http://dx.doi.org/10.1155/2023/7713397 |
| _version_ | 1797831785884680192 |
|---|---|
| author | Yuxiu Zang Weichun Ge Shunjiang Wang Yan Zhao Tianfeng Chu |
| author_facet | Yuxiu Zang Weichun Ge Shunjiang Wang Yan Zhao Tianfeng Chu |
| author_sort | Yuxiu Zang |
| collection | DOAJ |
| description | The analysis of load characteristics is the basis and premise of load actively participating in power grid regulation. This paper proposes a multi-factor load classification method considering the load of clean energy power generation, the rapidity of load classification, and various subjective and objective factors that may affect the behavior of load consumption. First, it describes the characteristic index of load consumption behavior and analyzes the subjective and objective factors that affect the power grid consumption behavior. The effect of clean energy generation on load side is considered. Based on the load characteristics, the K-means algorithm is used for main clustering. Then, the confidence level of the uncertainty of the actual load adjustable capacity is analyzed by quantifying the load adjustable potential index and the fuzzy C-means clustering method was used for secondary clustering of the adjustable capacity. Finally, DBI and SC indexes are used to evaluate the clustering results, standard values of evaluation indexes are set, and unqualified clustering results are recalculated and corrected. 31 industrial users in a province are selected as research objects, and the load data of the past 365 days are collected to verify the effectiveness and practicability of the proposed method. The classification results show that the classification accuracy is still good when the noise is 30%, and the maximum deviation between the clustering results and the actual load regulation potential is 12%. It can meet the actual engineering error standard. |
| first_indexed | 2024-04-09T13:58:21Z |
| format | Article |
| id | doaj.art-ea5435373aac463e93acb56270f15a9b |
| institution | Directory Open Access Journal |
| issn | 2050-7038 |
| language | English |
| last_indexed | 2024-04-09T13:58:21Z |
| publishDate | 2023-01-01 |
| publisher | Hindawi-Wiley |
| record_format | Article |
| series | International Transactions on Electrical Energy Systems |
| spelling | doaj.art-ea5435373aac463e93acb56270f15a9b2023-05-08T00:25:37ZengHindawi-WileyInternational Transactions on Electrical Energy Systems2050-70382023-01-01202310.1155/2023/7713397Multi-Factor Load Classification Method considering Clean Energy Power GenerationYuxiu Zang0Weichun Ge1Shunjiang Wang2Yan Zhao3Tianfeng Chu4School of Electrical EngineeringSchool of Electrical EngineeringState Grid Liaoning Electric Power Supply Co., Ltd.Shenyang Institute of EngineeringState Grid Liaoning Electric Power Research InstituteThe analysis of load characteristics is the basis and premise of load actively participating in power grid regulation. This paper proposes a multi-factor load classification method considering the load of clean energy power generation, the rapidity of load classification, and various subjective and objective factors that may affect the behavior of load consumption. First, it describes the characteristic index of load consumption behavior and analyzes the subjective and objective factors that affect the power grid consumption behavior. The effect of clean energy generation on load side is considered. Based on the load characteristics, the K-means algorithm is used for main clustering. Then, the confidence level of the uncertainty of the actual load adjustable capacity is analyzed by quantifying the load adjustable potential index and the fuzzy C-means clustering method was used for secondary clustering of the adjustable capacity. Finally, DBI and SC indexes are used to evaluate the clustering results, standard values of evaluation indexes are set, and unqualified clustering results are recalculated and corrected. 31 industrial users in a province are selected as research objects, and the load data of the past 365 days are collected to verify the effectiveness and practicability of the proposed method. The classification results show that the classification accuracy is still good when the noise is 30%, and the maximum deviation between the clustering results and the actual load regulation potential is 12%. It can meet the actual engineering error standard.http://dx.doi.org/10.1155/2023/7713397 |
| spellingShingle | Yuxiu Zang Weichun Ge Shunjiang Wang Yan Zhao Tianfeng Chu Multi-Factor Load Classification Method considering Clean Energy Power Generation International Transactions on Electrical Energy Systems |
| title | Multi-Factor Load Classification Method considering Clean Energy Power Generation |
| title_full | Multi-Factor Load Classification Method considering Clean Energy Power Generation |
| title_fullStr | Multi-Factor Load Classification Method considering Clean Energy Power Generation |
| title_full_unstemmed | Multi-Factor Load Classification Method considering Clean Energy Power Generation |
| title_short | Multi-Factor Load Classification Method considering Clean Energy Power Generation |
| title_sort | multi factor load classification method considering clean energy power generation |
| url | http://dx.doi.org/10.1155/2023/7713397 |
| work_keys_str_mv | AT yuxiuzang multifactorloadclassificationmethodconsideringcleanenergypowergeneration AT weichunge multifactorloadclassificationmethodconsideringcleanenergypowergeneration AT shunjiangwang multifactorloadclassificationmethodconsideringcleanenergypowergeneration AT yanzhao multifactorloadclassificationmethodconsideringcleanenergypowergeneration AT tianfengchu multifactorloadclassificationmethodconsideringcleanenergypowergeneration |