Nontechnical Loss Detection With Duffing–Holmes Self-Synchronization Dynamic Errors and 1D CNN-Based Multilayer Classifier in a Smart Grid
The combined Duffing–Holmes (D–H)–based quantizer and one-dimensional (1D) convolutional neural network (CNN)-based multilayer classifier were applied to perform the nontechnical loss (NTL’s) (electricity fraud) feature quantification, feature extraction,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9831790/ |
| _version_ | 1811215119631253504 |
|---|---|
| author | Chia-Hung Lin Feng-Chang Gu Jian-Xing Wu Chao-Lin Kuo |
| author_facet | Chia-Hung Lin Feng-Chang Gu Jian-Xing Wu Chao-Lin Kuo |
| author_sort | Chia-Hung Lin |
| collection | DOAJ |
| description | The combined Duffing–Holmes (D–H)–based quantizer and one-dimensional (1D) convolutional neural network (CNN)-based multilayer classifier were applied to perform the nontechnical loss (NTL’s) (electricity fraud) feature quantification, feature extraction, and classification tasks to analyze electricity consumption data and to identify either normal or abnormal consumption patterns for NTL detection. The metering data is gathered every 15 minutes and a 3-hour screening window is used to distinguish between the normal conditions and likely NTL events or power outage events. The D–H-based quantizer in the feature quantification layer may quantify the different levels among three events for preliminary screening differences using D–H self-synchronization dynamic errors. In the feature extraction layer, two 1D convolutional-pooling processes are used to extract 1D key feature signals to enhance the distinguished levels for further classification applications. The gray relational analysis (GRA)-based multilayer network is trained as a classifier. In the classification layer, to identify electricity fraud events. The proposed method is verified and validated using simulation data and the electricity fraud attack model. The correlation coefficient and unitary averaged changed intensity index are applied in correlation analysis to discover apparent abnormality between historical consumption and metering consumption patterns within the short-time monitoring. The D-H-based quantizer and 1D CNN-based classifier then work together to accomplish classification tasks on the time-series metering data. The experimental results show that the suggested classifier model demonstrates promising performance and efficiency compared to the traditional multilayer classifier in feature extraction, training, and recall processing, and accurate classification. |
| first_indexed | 2024-04-12T06:15:59Z |
| format | Article |
| id | doaj.art-6b30a59a4efe484ba310be6e973aa95d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T06:15:59Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6b30a59a4efe484ba310be6e973aa95d2022-12-22T03:44:29ZengIEEEIEEE Access2169-35362022-01-0110830028301610.1109/ACCESS.2022.31916859831790Nontechnical Loss Detection With Duffing–Holmes Self-Synchronization Dynamic Errors and 1D CNN-Based Multilayer Classifier in a Smart GridChia-Hung Lin0Feng-Chang Gu1https://orcid.org/0000-0001-5465-3873Jian-Xing Wu2https://orcid.org/0000-0002-9327-7396Chao-Lin Kuo3https://orcid.org/0000-0002-4989-3618Department of Electrical Engineering, National Chin-Yi University of Technology, Taichung, TaiwanDepartment of Electrical Engineering, National Chin-Yi University of Technology, Taichung, TaiwanDepartment of Electrical Engineering, National Chin-Yi University of Technology, Taichung, TaiwanDepartment of Maritime Information and Technology, National Kaohsiung University of Science and Technology, Kaohsiung, TaiwanThe combined Duffing–Holmes (D–H)–based quantizer and one-dimensional (1D) convolutional neural network (CNN)-based multilayer classifier were applied to perform the nontechnical loss (NTL’s) (electricity fraud) feature quantification, feature extraction, and classification tasks to analyze electricity consumption data and to identify either normal or abnormal consumption patterns for NTL detection. The metering data is gathered every 15 minutes and a 3-hour screening window is used to distinguish between the normal conditions and likely NTL events or power outage events. The D–H-based quantizer in the feature quantification layer may quantify the different levels among three events for preliminary screening differences using D–H self-synchronization dynamic errors. In the feature extraction layer, two 1D convolutional-pooling processes are used to extract 1D key feature signals to enhance the distinguished levels for further classification applications. The gray relational analysis (GRA)-based multilayer network is trained as a classifier. In the classification layer, to identify electricity fraud events. The proposed method is verified and validated using simulation data and the electricity fraud attack model. The correlation coefficient and unitary averaged changed intensity index are applied in correlation analysis to discover apparent abnormality between historical consumption and metering consumption patterns within the short-time monitoring. The D-H-based quantizer and 1D CNN-based classifier then work together to accomplish classification tasks on the time-series metering data. The experimental results show that the suggested classifier model demonstrates promising performance and efficiency compared to the traditional multilayer classifier in feature extraction, training, and recall processing, and accurate classification.https://ieeexplore.ieee.org/document/9831790/Nontechnical lossDuffing–Holmes (D-H) based quantizerone-dimension convolutional neural network (CNN)short-time screening windowgray relational analysis (GRA) |
| spellingShingle | Chia-Hung Lin Feng-Chang Gu Jian-Xing Wu Chao-Lin Kuo Nontechnical Loss Detection With Duffing–Holmes Self-Synchronization Dynamic Errors and 1D CNN-Based Multilayer Classifier in a Smart Grid IEEE Access Nontechnical loss Duffing–Holmes (D-H) based quantizer one-dimension convolutional neural network (CNN) short-time screening window gray relational analysis (GRA) |
| title | Nontechnical Loss Detection With Duffing–Holmes Self-Synchronization Dynamic Errors and 1D CNN-Based Multilayer Classifier in a Smart Grid |
| title_full | Nontechnical Loss Detection With Duffing–Holmes Self-Synchronization Dynamic Errors and 1D CNN-Based Multilayer Classifier in a Smart Grid |
| title_fullStr | Nontechnical Loss Detection With Duffing–Holmes Self-Synchronization Dynamic Errors and 1D CNN-Based Multilayer Classifier in a Smart Grid |
| title_full_unstemmed | Nontechnical Loss Detection With Duffing–Holmes Self-Synchronization Dynamic Errors and 1D CNN-Based Multilayer Classifier in a Smart Grid |
| title_short | Nontechnical Loss Detection With Duffing–Holmes Self-Synchronization Dynamic Errors and 1D CNN-Based Multilayer Classifier in a Smart Grid |
| title_sort | nontechnical loss detection with duffing x2013 holmes self synchronization dynamic errors and 1d cnn based multilayer classifier in a smart grid |
| topic | Nontechnical loss Duffing–Holmes (D-H) based quantizer one-dimension convolutional neural network (CNN) short-time screening window gray relational analysis (GRA) |
| url | https://ieeexplore.ieee.org/document/9831790/ |
| work_keys_str_mv | AT chiahunglin nontechnicallossdetectionwithduffingx2013holmesselfsynchronizationdynamicerrorsand1dcnnbasedmultilayerclassifierinasmartgrid AT fengchanggu nontechnicallossdetectionwithduffingx2013holmesselfsynchronizationdynamicerrorsand1dcnnbasedmultilayerclassifierinasmartgrid AT jianxingwu nontechnicallossdetectionwithduffingx2013holmesselfsynchronizationdynamicerrorsand1dcnnbasedmultilayerclassifierinasmartgrid AT chaolinkuo nontechnicallossdetectionwithduffingx2013holmesselfsynchronizationdynamicerrorsand1dcnnbasedmultilayerclassifierinasmartgrid |