Temporal feature adaptive non-intrusive load monitoring via unsupervised probability density evolution
Toward the smart power and energy consumption, non-intrusive load monitoring is emerging as the promising technical assistance of intelligent energy user. The load behaviors of individual power users are distinct, that is potential to enhance the monitoring performance if effectively addressed. In t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-11-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484721006570 |
| _version_ | 1831690167744724992 |
|---|---|
| author | Yu Liu Tiancheng E. Song Xiaolong Sun Shan Gao Xueliang Huang |
| author_facet | Yu Liu Tiancheng E. Song Xiaolong Sun Shan Gao Xueliang Huang |
| author_sort | Yu Liu |
| collection | DOAJ |
| description | Toward the smart power and energy consumption, non-intrusive load monitoring is emerging as the promising technical assistance of intelligent energy user. The load behaviors of individual power users are distinct, that is potential to enhance the monitoring performance if effectively addressed. In this paper, the customized temporal behaviors are thoroughly investigated and utilized for load disaggregation from the view of time characteristics. At the first stage, the temporal features of appliance usage are formularized via customized time of use probability, and the model is adaptive for the specific user habit via unsupervised probability density evolution method. Then, a generic two-stage load disaggregation framework is proposed, where the primary stage is formulized by dictionary learning and for basic load disaggregation, and the secondary stage is integrated with probabilistic temporal weights and for optimal disaggregation decision. Lastly, the sparse coding principle and risk analysis theory are employed for the robust problem solution. By comprehensive verifications on low voltage networks simulator, it is demonstrated that the proposed approach is effective in temporal load feature modeling, and thereby achieving the higher accuracy and flexibility for the non-intrusive load monitoring problem. |
| first_indexed | 2024-12-20T11:04:19Z |
| format | Article |
| id | doaj.art-456d7cc932dd4a348efc563edad40b5c |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-12-20T11:04:19Z |
| publishDate | 2021-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-456d7cc932dd4a348efc563edad40b5c2022-12-21T19:42:55ZengElsevierEnergy Reports2352-48472021-11-017209217Temporal feature adaptive non-intrusive load monitoring via unsupervised probability density evolutionYu Liu0Tiancheng E. Song1Xiaolong Sun2Shan Gao3Xueliang Huang4School of Electrical Engineering, Southeast University, 2 Sipailou, Xuanwu Dist., Nanjing 210018, China; Jiangsu Provincial Key Laboratory of Smart Grid Technology and Equipment, Nanjing 210018, China; Corresponding author at: School of Electrical Engineering, Southeast University, 2 Sipailou, Xuanwu Dist., Nanjing 210018, China.School of Electrical Engineering, Southeast University, 2 Sipailou, Xuanwu Dist., Nanjing 210018, ChinaGuodian Nanjing Automation Co., Ltd., 39 Shuige Road, Jiangning Development Zone, Nanjing 211153, ChinaSchool of Electrical Engineering, Southeast University, 2 Sipailou, Xuanwu Dist., Nanjing 210018, China; Jiangsu Provincial Key Laboratory of Smart Grid Technology and Equipment, Nanjing 210018, ChinaSchool of Electrical Engineering, Southeast University, 2 Sipailou, Xuanwu Dist., Nanjing 210018, China; Jiangsu Provincial Key Laboratory of Smart Grid Technology and Equipment, Nanjing 210018, ChinaToward the smart power and energy consumption, non-intrusive load monitoring is emerging as the promising technical assistance of intelligent energy user. The load behaviors of individual power users are distinct, that is potential to enhance the monitoring performance if effectively addressed. In this paper, the customized temporal behaviors are thoroughly investigated and utilized for load disaggregation from the view of time characteristics. At the first stage, the temporal features of appliance usage are formularized via customized time of use probability, and the model is adaptive for the specific user habit via unsupervised probability density evolution method. Then, a generic two-stage load disaggregation framework is proposed, where the primary stage is formulized by dictionary learning and for basic load disaggregation, and the secondary stage is integrated with probabilistic temporal weights and for optimal disaggregation decision. Lastly, the sparse coding principle and risk analysis theory are employed for the robust problem solution. By comprehensive verifications on low voltage networks simulator, it is demonstrated that the proposed approach is effective in temporal load feature modeling, and thereby achieving the higher accuracy and flexibility for the non-intrusive load monitoring problem.http://www.sciencedirect.com/science/article/pii/S2352484721006570Dictionary learningEnergy consumption disaggregationRisk analysisTime of use probabilityUnsupervised learning |
| spellingShingle | Yu Liu Tiancheng E. Song Xiaolong Sun Shan Gao Xueliang Huang Temporal feature adaptive non-intrusive load monitoring via unsupervised probability density evolution Energy Reports Dictionary learning Energy consumption disaggregation Risk analysis Time of use probability Unsupervised learning |
| title | Temporal feature adaptive non-intrusive load monitoring via unsupervised probability density evolution |
| title_full | Temporal feature adaptive non-intrusive load monitoring via unsupervised probability density evolution |
| title_fullStr | Temporal feature adaptive non-intrusive load monitoring via unsupervised probability density evolution |
| title_full_unstemmed | Temporal feature adaptive non-intrusive load monitoring via unsupervised probability density evolution |
| title_short | Temporal feature adaptive non-intrusive load monitoring via unsupervised probability density evolution |
| title_sort | temporal feature adaptive non intrusive load monitoring via unsupervised probability density evolution |
| topic | Dictionary learning Energy consumption disaggregation Risk analysis Time of use probability Unsupervised learning |
| url | http://www.sciencedirect.com/science/article/pii/S2352484721006570 |
| work_keys_str_mv | AT yuliu temporalfeatureadaptivenonintrusiveloadmonitoringviaunsupervisedprobabilitydensityevolution AT tianchengesong temporalfeatureadaptivenonintrusiveloadmonitoringviaunsupervisedprobabilitydensityevolution AT xiaolongsun temporalfeatureadaptivenonintrusiveloadmonitoringviaunsupervisedprobabilitydensityevolution AT shangao temporalfeatureadaptivenonintrusiveloadmonitoringviaunsupervisedprobabilitydensityevolution AT xuelianghuang temporalfeatureadaptivenonintrusiveloadmonitoringviaunsupervisedprobabilitydensityevolution |