Unsupervised and Supervised Learning Combined Power Load Curve Classification Based on Sequential Trajectory Feature Extraction Algorithm
Advancements in smart grid technology and the extensive applications of electric power big data have made in-depth exploration of the behavioral characteristics of power consumers highly necessary for further development of the electricity market. This paper proposes an effective and interpretable l...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9866777/ |
| _version_ | 1828746453357428736 |
|---|---|
| author | Jing Zhang Yikun Zhang Xiao Xu Xiaofan Fu Yu He |
| author_facet | Jing Zhang Yikun Zhang Xiao Xu Xiaofan Fu Yu He |
| author_sort | Jing Zhang |
| collection | DOAJ |
| description | Advancements in smart grid technology and the extensive applications of electric power big data have made in-depth exploration of the behavioral characteristics of power consumers highly necessary for further development of the electricity market. This paper proposes an effective and interpretable load curve classification method that based on sequential trajectory feature learning and a random forest algorithm. Firstly, the unsupervised K-medoid clustering algorithm is used to obtain and filter precise category labels. Next, the fused lasso generalized eigenvector (FLAG) technique is used to search for interpretable sub-sequences from the labeled data in order to properly account for the sequential trajectory feature of load curves and increase the speed of the computation process. Following that, shapelet transformation is used to extract the sequential trajectory features from original data. Finally, in order to inherit the interpretability of shapelet, the random forest is trained on the sequential trajectory features. The simulated examples based on the real load curves of the specific city in China were investigated in order to assess the performance of the proposed load curve categorization approach. The results of the simulation demonstrate that the proposed approach has considerable advantages in terms of effectiveness, accuracy, and interpretability of load classification. |
| first_indexed | 2024-04-14T04:24:50Z |
| format | Article |
| id | doaj.art-19cd261d3e144bb989dcc74731e7686d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-14T04:24:50Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-19cd261d3e144bb989dcc74731e7686d2022-12-22T02:12:22ZengIEEEIEEE Access2169-35362022-01-0110903129032010.1109/ACCESS.2022.32015529866777Unsupervised and Supervised Learning Combined Power Load Curve Classification Based on Sequential Trajectory Feature Extraction AlgorithmJing Zhang0https://orcid.org/0000-0002-3732-7432Yikun Zhang1https://orcid.org/0000-0001-8790-8254Xiao Xu2Xiaofan Fu3Yu He4School of Electrical Engineering, Guizhou University, Guiyang, ChinaSchool of Electrical Engineering, Xi’an Jiaotong University, Xi’an, ChinaPower Automation Department, China Electric Power Research Institute, Beijing, ChinaSchool of Electrical Engineering, Guizhou University, Guiyang, ChinaSchool of Electrical Engineering, Guizhou University, Guiyang, ChinaAdvancements in smart grid technology and the extensive applications of electric power big data have made in-depth exploration of the behavioral characteristics of power consumers highly necessary for further development of the electricity market. This paper proposes an effective and interpretable load curve classification method that based on sequential trajectory feature learning and a random forest algorithm. Firstly, the unsupervised K-medoid clustering algorithm is used to obtain and filter precise category labels. Next, the fused lasso generalized eigenvector (FLAG) technique is used to search for interpretable sub-sequences from the labeled data in order to properly account for the sequential trajectory feature of load curves and increase the speed of the computation process. Following that, shapelet transformation is used to extract the sequential trajectory features from original data. Finally, in order to inherit the interpretability of shapelet, the random forest is trained on the sequential trajectory features. The simulated examples based on the real load curves of the specific city in China were investigated in order to assess the performance of the proposed load curve categorization approach. The results of the simulation demonstrate that the proposed approach has considerable advantages in terms of effectiveness, accuracy, and interpretability of load classification.https://ieeexplore.ieee.org/document/9866777/Load curve classificationK-mediodsshapeletrandom forestsequential trajectory featuresunsupervised learning |
| spellingShingle | Jing Zhang Yikun Zhang Xiao Xu Xiaofan Fu Yu He Unsupervised and Supervised Learning Combined Power Load Curve Classification Based on Sequential Trajectory Feature Extraction Algorithm IEEE Access Load curve classification K-mediods shapelet random forest sequential trajectory features unsupervised learning |
| title | Unsupervised and Supervised Learning Combined Power Load Curve Classification Based on Sequential Trajectory Feature Extraction Algorithm |
| title_full | Unsupervised and Supervised Learning Combined Power Load Curve Classification Based on Sequential Trajectory Feature Extraction Algorithm |
| title_fullStr | Unsupervised and Supervised Learning Combined Power Load Curve Classification Based on Sequential Trajectory Feature Extraction Algorithm |
| title_full_unstemmed | Unsupervised and Supervised Learning Combined Power Load Curve Classification Based on Sequential Trajectory Feature Extraction Algorithm |
| title_short | Unsupervised and Supervised Learning Combined Power Load Curve Classification Based on Sequential Trajectory Feature Extraction Algorithm |
| title_sort | unsupervised and supervised learning combined power load curve classification based on sequential trajectory feature extraction algorithm |
| topic | Load curve classification K-mediods shapelet random forest sequential trajectory features unsupervised learning |
| url | https://ieeexplore.ieee.org/document/9866777/ |
| work_keys_str_mv | AT jingzhang unsupervisedandsupervisedlearningcombinedpowerloadcurveclassificationbasedonsequentialtrajectoryfeatureextractionalgorithm AT yikunzhang unsupervisedandsupervisedlearningcombinedpowerloadcurveclassificationbasedonsequentialtrajectoryfeatureextractionalgorithm AT xiaoxu unsupervisedandsupervisedlearningcombinedpowerloadcurveclassificationbasedonsequentialtrajectoryfeatureextractionalgorithm AT xiaofanfu unsupervisedandsupervisedlearningcombinedpowerloadcurveclassificationbasedonsequentialtrajectoryfeatureextractionalgorithm AT yuhe unsupervisedandsupervisedlearningcombinedpowerloadcurveclassificationbasedonsequentialtrajectoryfeatureextractionalgorithm |