Enhanced NILM load pattern extraction via variable-length motif discovery

• Published in: International journal of electrical power & energy systems Vol. 152; p. 109207
• Main Authors: Liu, Bo, Zheng, Jinhao, Luan, Wenpeng, Chang, Fenglei, Zhao, Bochao, Liu, Zishuai
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2023
• Subjects: Frequent pattern mining; Iterative learning; Power waveform motif discovery; Unsupervised NILM; Frequent pattern mining; Unsupervised NILM; Power waveform motif discovery; Iterative learning
• ISSN: 0142-0615; 1879-3517
• DOI: 10.1016/j.ijepes.2023.109207

•Variable-length motif discovery is used to detect power waveform motifs (PWMs) for the first time in unsupervised NILM.•An adaptive similarity threshold setting method is proposed for establishing an unsupervised motif discovery method.•Frequent sequence pattern mining is employed to learn the complete power patterns in appliance working cycles.•The proposed method is integrated into the incremental learning framework, which can gradually discover “unknown” appliances.•Comparison results on public and private datasets demonstrate our work performs better on complex appliance identification. Due to the diversity of appliances and users’ power consumption behaviors, it is challenging to accurately extract load signature samples for non-intrusive load monitoring (NILM) in unseen scenarios. To this end, this paper proposes an enhanced NILM load pattern extraction method via variable-length motif discovery. Firstly, the variable-length motif discovery method is used for the first time to discover similar subsequences from the aggregated power time series to extract power waveform signature (PWS) samples for appliances and obtain the power waveform motifs (PWMs). Furthermore, the appliance PWM sequence pattern mining method is proposed to detect complete power consumption patterns of appliance working cycles, and eventually construct the load signature library. Finally, the similarity between the original PWS samples and the templates in the signature library is measured to realize load identification. In practice, the proposed method is intended to integrate into the incremental learning framework, so that the unknown appliances can be identified gradually by continuous iterative learning. The comparison testing results on the public and private datasets demonstrate that the proposed method can effectively discover various PWMs of different appliances, and accurately model their power consumption patterns, thus exhibiting better performance on the unsupervised load identification compared with the existing methods, especially for the complex appliances.