Research on abnormal power consumption detection method of power big data based on LightGBM model and LSTM model
With the proposal of the dual-carbon economy, smart grids are developing in the direction of energy conservation and emission reduction, and the abnormal power consumption of users has caused serious loss of power resources. Aiming at the problems of low accuracy and slow operation efficiency of tra...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Harbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd.
2025-01-01
|
| Series: | Diance yu yibiao |
| Subjects: | |
| Online Access: | http://www.emijournal.net/dcyyben/ch/reader/create_pdf.aspx?file_no=20220512001&flag=1&journal_id=dcyyben&year_id=2025 |
| _version_ | 1826552830764253184 |
|---|---|
| author | YANG Zhidong DING Jianwu CHEN Guangjiu KANG Xiaojing SHENG Meng |
| author_facet | YANG Zhidong DING Jianwu CHEN Guangjiu KANG Xiaojing SHENG Meng |
| author_sort | YANG Zhidong |
| collection | DOAJ |
| description | With the proposal of the dual-carbon economy, smart grids are developing in the direction of energy conservation and emission reduction, and the abnormal power consumption of users has caused serious loss of power resources. Aiming at the problems of low accuracy and slow operation efficiency of traditional abnormal power consumption detection methods, a lightGBM model combined with an improved long short-term memory network model is proposed for abnormal power consumption detection. Anomaly detection is carried out by combining sampling and lightGBM model, and abnormal electricity consumption category is given by improving long short-term memory network model. The advantages of the proposed method are analyzed through experiments. The results show that, compared with traditional detection methods, the proposed method can detect abnormal users quickly and effectively, with a detection accuracy of 98.64%, meanwhile, the abnormal data is effectively classified, and the comprehensive classification accuracy rate is 96.60%, which provides a certain reference for the development of anomaly detection technology. |
| first_indexed | 2025-03-14T07:15:22Z |
| format | Article |
| id | doaj.art-f8a043a652d04df1b46b5f12ef9645c9 |
| institution | Directory Open Access Journal |
| issn | 1001-1390 |
| language | zho |
| last_indexed | 2025-03-14T07:15:22Z |
| publishDate | 2025-01-01 |
| publisher | Harbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd. |
| record_format | Article |
| series | Diance yu yibiao |
| spelling | doaj.art-f8a043a652d04df1b46b5f12ef9645c92025-03-04T00:59:11ZzhoHarbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd.Diance yu yibiao1001-13902025-01-0162111011510.19753/j.issn1001-1390.2025.01.0131001-1390(2025)01-0110-06Research on abnormal power consumption detection method of power big data based on LightGBM model and LSTM modelYANG Zhidong0DING Jianwu1CHEN Guangjiu2KANG Xiaojing3SHENG Meng4State Grid Beijing Electric Power Company, Beijing 100051, ChinaState Grid Beijing Electric Power Company, Beijing 100051, ChinaState Grid Beijing Electric Power Company, Beijing 100051, ChinaState Grid Beijing Electric Power Company, Beijing 100051, ChinaState Grid Beijing Electric Power Company, Beijing 100051, ChinaWith the proposal of the dual-carbon economy, smart grids are developing in the direction of energy conservation and emission reduction, and the abnormal power consumption of users has caused serious loss of power resources. Aiming at the problems of low accuracy and slow operation efficiency of traditional abnormal power consumption detection methods, a lightGBM model combined with an improved long short-term memory network model is proposed for abnormal power consumption detection. Anomaly detection is carried out by combining sampling and lightGBM model, and abnormal electricity consumption category is given by improving long short-term memory network model. The advantages of the proposed method are analyzed through experiments. The results show that, compared with traditional detection methods, the proposed method can detect abnormal users quickly and effectively, with a detection accuracy of 98.64%, meanwhile, the abnormal data is effectively classified, and the comprehensive classification accuracy rate is 96.60%, which provides a certain reference for the development of anomaly detection technology.http://www.emijournal.net/dcyyben/ch/reader/create_pdf.aspx?file_no=20220512001&flag=1&journal_id=dcyyben&year_id=2025power transformerabnormal power consumptionlightgbm modellstm modeldual-carbon economy |
| spellingShingle | YANG Zhidong DING Jianwu CHEN Guangjiu KANG Xiaojing SHENG Meng Research on abnormal power consumption detection method of power big data based on LightGBM model and LSTM model Diance yu yibiao power transformer abnormal power consumption lightgbm model lstm model dual-carbon economy |
| title | Research on abnormal power consumption detection method of power big data based on LightGBM model and LSTM model |
| title_full | Research on abnormal power consumption detection method of power big data based on LightGBM model and LSTM model |
| title_fullStr | Research on abnormal power consumption detection method of power big data based on LightGBM model and LSTM model |
| title_full_unstemmed | Research on abnormal power consumption detection method of power big data based on LightGBM model and LSTM model |
| title_short | Research on abnormal power consumption detection method of power big data based on LightGBM model and LSTM model |
| title_sort | research on abnormal power consumption detection method of power big data based on lightgbm model and lstm model |
| topic | power transformer abnormal power consumption lightgbm model lstm model dual-carbon economy |
| url | http://www.emijournal.net/dcyyben/ch/reader/create_pdf.aspx?file_no=20220512001&flag=1&journal_id=dcyyben&year_id=2025 |
| work_keys_str_mv | AT yangzhidong researchonabnormalpowerconsumptiondetectionmethodofpowerbigdatabasedonlightgbmmodelandlstmmodel AT dingjianwu researchonabnormalpowerconsumptiondetectionmethodofpowerbigdatabasedonlightgbmmodelandlstmmodel AT chenguangjiu researchonabnormalpowerconsumptiondetectionmethodofpowerbigdatabasedonlightgbmmodelandlstmmodel AT kangxiaojing researchonabnormalpowerconsumptiondetectionmethodofpowerbigdatabasedonlightgbmmodelandlstmmodel AT shengmeng researchonabnormalpowerconsumptiondetectionmethodofpowerbigdatabasedonlightgbmmodelandlstmmodel |