Non-intrusive load monitoring based on time-enhanced multidimensional feature visualization
Abstract In the research of non-intrusive load monitoring (NILM), the temporal characteristics of V–I trajectories are often overlooked, and using a single feature for identification may lead to insignificant differences between similar loads. Based on this, this paper proposes a non-intrusive load...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-89191-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862340784750592 |
|---|---|
| author | Tie Chen Yimin Yuan Jiaqi Gao Shinan Guo Pingping Yang |
| author_facet | Tie Chen Yimin Yuan Jiaqi Gao Shinan Guo Pingping Yang |
| author_sort | Tie Chen |
| collection | DOAJ |
| description | Abstract In the research of non-intrusive load monitoring (NILM), the temporal characteristics of V–I trajectories are often overlooked, and using a single feature for identification may lead to insignificant differences between similar loads. Based on this, this paper proposes a non-intrusive load monitoring method based on time-enhanced multidimensional feature visualization. By adding a time axis to the V–I trajectory, it integrates the rate of change in voltage and current, power factor, and third harmonic to form a three-dimensional spatiotemporal color V–I trajectory, addressing the gap in dynamic characteristics. The ECA-ResNet34 network model is used for load identification, avoiding the problems of network degradation and training difficulties caused by the excessive depth of traditional convolutional neural networks (CNN), and achieving efficient monitoring of household loads. The method was validated on the PLAID dataset, achieving an average F1 score of 97.3%. Furthermore, utilizing transfer learning, the model trained and tested on the PLAID dataset was further tested on the WHITED dataset to increase the model’s universality and generalization ability, showing significant effects in identifying loads with similar V–I trajectories and multiple states. |
| format | Article |
| id | doaj-art-cb5b0f0c36d2466ea79def36429893d9 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-cb5b0f0c36d2466ea79def36429893d92025-02-09T12:33:03ZengNature PortfolioScientific Reports2045-23222025-02-0115111810.1038/s41598-025-89191-xNon-intrusive load monitoring based on time-enhanced multidimensional feature visualizationTie Chen0Yimin Yuan1Jiaqi Gao2Shinan Guo3Pingping Yang4Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station, China Three Gorges UniversityHubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station, China Three Gorges UniversityHubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station, China Three Gorges UniversityHubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station, China Three Gorges UniversityHubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station, China Three Gorges UniversityAbstract In the research of non-intrusive load monitoring (NILM), the temporal characteristics of V–I trajectories are often overlooked, and using a single feature for identification may lead to insignificant differences between similar loads. Based on this, this paper proposes a non-intrusive load monitoring method based on time-enhanced multidimensional feature visualization. By adding a time axis to the V–I trajectory, it integrates the rate of change in voltage and current, power factor, and third harmonic to form a three-dimensional spatiotemporal color V–I trajectory, addressing the gap in dynamic characteristics. The ECA-ResNet34 network model is used for load identification, avoiding the problems of network degradation and training difficulties caused by the excessive depth of traditional convolutional neural networks (CNN), and achieving efficient monitoring of household loads. The method was validated on the PLAID dataset, achieving an average F1 score of 97.3%. Furthermore, utilizing transfer learning, the model trained and tested on the PLAID dataset was further tested on the WHITED dataset to increase the model’s universality and generalization ability, showing significant effects in identifying loads with similar V–I trajectories and multiple states.https://doi.org/10.1038/s41598-025-89191-xNon-intrusive load monitoringV-I trajectoryTime-enhancedMultidimensionalColor coding |
| spellingShingle | Tie Chen Yimin Yuan Jiaqi Gao Shinan Guo Pingping Yang Non-intrusive load monitoring based on time-enhanced multidimensional feature visualization Scientific Reports Non-intrusive load monitoring V-I trajectory Time-enhanced Multidimensional Color coding |
| title | Non-intrusive load monitoring based on time-enhanced multidimensional feature visualization |
| title_full | Non-intrusive load monitoring based on time-enhanced multidimensional feature visualization |
| title_fullStr | Non-intrusive load monitoring based on time-enhanced multidimensional feature visualization |
| title_full_unstemmed | Non-intrusive load monitoring based on time-enhanced multidimensional feature visualization |
| title_short | Non-intrusive load monitoring based on time-enhanced multidimensional feature visualization |
| title_sort | non intrusive load monitoring based on time enhanced multidimensional feature visualization |
| topic | Non-intrusive load monitoring V-I trajectory Time-enhanced Multidimensional Color coding |
| url | https://doi.org/10.1038/s41598-025-89191-x |
| work_keys_str_mv | AT tiechen nonintrusiveloadmonitoringbasedontimeenhancedmultidimensionalfeaturevisualization AT yiminyuan nonintrusiveloadmonitoringbasedontimeenhancedmultidimensionalfeaturevisualization AT jiaqigao nonintrusiveloadmonitoringbasedontimeenhancedmultidimensionalfeaturevisualization AT shinanguo nonintrusiveloadmonitoringbasedontimeenhancedmultidimensionalfeaturevisualization AT pingpingyang nonintrusiveloadmonitoringbasedontimeenhancedmultidimensionalfeaturevisualization |