Non-intrusive load identification method based on VMD-LSTM
Non-intrusive load monitoring (NILM) technology is only based on the current and voltage information of the main entrance of home power supply to obtain the electrical information of indoor electrical equipment. Improving the accuracy of load identification is of great significance to optimize the e...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
National Computer System Engineering Research Institute of China
2023-02-01
|
| Series: | Dianzi Jishu Yingyong |
| Subjects: | |
| Online Access: | http://www.chinaaet.com/article/3000159730 |
| _version_ | 1797448185731350528 |
|---|---|
| author | Wang Yi Yi Huan Li Songnong Feng Ling Liu Qilie Song Runan |
| author_facet | Wang Yi Yi Huan Li Songnong Feng Ling Liu Qilie Song Runan |
| author_sort | Wang Yi |
| collection | DOAJ |
| description | Non-intrusive load monitoring (NILM) technology is only based on the current and voltage information of the main entrance of home power supply to obtain the electrical information of indoor electrical equipment. Improving the accuracy of load identification is of great significance to optimize the energy structure, improve the efficiency of power utilization and reduce energy consumption. Firstly, the normalized current signal is decomposed by using variational mode decomposition (VMD), and then the correlation coefficients between each component and the original current signal are calculated. The two components with the largest correlation coefficients are selected as the load characteristics and input into the trained LSTM neural network for identification. The test results of an example show that the recognition rate of this method is up to 99% on public data set PLAID and 96.6% on laboratory data set, which proves the effectiveness of this method. |
| first_indexed | 2024-03-09T14:06:48Z |
| format | Article |
| id | doaj.art-571d6694f9624c6cb3eaaa51dc69ea67 |
| institution | Directory Open Access Journal |
| issn | 0258-7998 |
| language | zho |
| last_indexed | 2024-03-09T14:06:48Z |
| publishDate | 2023-02-01 |
| publisher | National Computer System Engineering Research Institute of China |
| record_format | Article |
| series | Dianzi Jishu Yingyong |
| spelling | doaj.art-571d6694f9624c6cb3eaaa51dc69ea672023-11-30T03:40:55ZzhoNational Computer System Engineering Research Institute of ChinaDianzi Jishu Yingyong0258-79982023-02-0149212713210.16157/j.issn.0258-7998.2230243000159730Non-intrusive load identification method based on VMD-LSTMWang Yi0Yi Huan1Li Songnong2Feng Ling3Liu Qilie4Song Runan5Communication and Information Engineering College， Chongqing University of Posts and Telecommunications， Chongqing 400067， ChinaCommunication and Information Engineering College， Chongqing University of Posts and Telecommunications， Chongqing 400067， ChinaChongqing Electric Power Research Institute， Chongqing 400014， ChinaPostdoctoral Workstation of the Chongqing Electric Power Corporation， Chongqing 400014， ChinaCommunication and Information Engineering College， Chongqing University of Posts and Telecommunications， Chongqing 400067， ChinaChina Electric Power Research Institute，Beijing100192，ChinaNon-intrusive load monitoring (NILM) technology is only based on the current and voltage information of the main entrance of home power supply to obtain the electrical information of indoor electrical equipment. Improving the accuracy of load identification is of great significance to optimize the energy structure, improve the efficiency of power utilization and reduce energy consumption. Firstly, the normalized current signal is decomposed by using variational mode decomposition (VMD), and then the correlation coefficients between each component and the original current signal are calculated. The two components with the largest correlation coefficients are selected as the load characteristics and input into the trained LSTM neural network for identification. The test results of an example show that the recognition rate of this method is up to 99% on public data set PLAID and 96.6% on laboratory data set, which proves the effectiveness of this method.http://www.chinaaet.com/article/3000159730variational mode decompositionsmart gridlstmcorrelation coefficient |
| spellingShingle | Wang Yi Yi Huan Li Songnong Feng Ling Liu Qilie Song Runan Non-intrusive load identification method based on VMD-LSTM Dianzi Jishu Yingyong variational mode decomposition smart grid lstm correlation coefficient |
| title | Non-intrusive load identification method based on VMD-LSTM |
| title_full | Non-intrusive load identification method based on VMD-LSTM |
| title_fullStr | Non-intrusive load identification method based on VMD-LSTM |
| title_full_unstemmed | Non-intrusive load identification method based on VMD-LSTM |
| title_short | Non-intrusive load identification method based on VMD-LSTM |
| title_sort | non intrusive load identification method based on vmd lstm |
| topic | variational mode decomposition smart grid lstm correlation coefficient |
| url | http://www.chinaaet.com/article/3000159730 |
| work_keys_str_mv | AT wangyi nonintrusiveloadidentificationmethodbasedonvmdlstm AT yihuan nonintrusiveloadidentificationmethodbasedonvmdlstm AT lisongnong nonintrusiveloadidentificationmethodbasedonvmdlstm AT fengling nonintrusiveloadidentificationmethodbasedonvmdlstm AT liuqilie nonintrusiveloadidentificationmethodbasedonvmdlstm AT songrunan nonintrusiveloadidentificationmethodbasedonvmdlstm |