Unsupervised and Supervised Learning Combined Power Load Curve Classification Based on Sequential Trajectory Feature Extraction Algorithm

作     者：Zhang, Jing Zhang, Yikun Xu, Xiao Fu, Xiaofan He, Yu 

作者机构：Guizhou Univ Sch Elect Engn Guiyang 550025 Guizhou Peoples R China Xi An Jiao Tong Univ Sch Elect Engn Xian 710049 Shaanxi Peoples R China China Elect Power Res Inst Power Automat Dept Beijing 100192 Peoples R China 

出 版 物：《IEEE ACCESS》 (IEEE Access)

年 卷 期：2022年第10卷

页      面：90312-90320页

核心收录：

基　　金：Guizhou Province Science and Technology Innovation Talent Project [GCC016-1] Science and Technology Fund of Guizhou Province [Qiankehezhicheng General 365, Grant Qiankehezhicheng General 013, Grant Qiankehezhicheng General 014, Grant Qianjiaoji 043] 

主　　题：Classification algorithms Clustering algorithms Random forests Load modeling Feature extraction Data mining Signal processing algorithms Unsupervised learning Supervised learning Sequential analysis Load curve classification K-mediods shapelet random forest sequential trajectory features unsupervised learning supervised learning 

摘      要：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.