Building a graph signal processing model using dynamic time warping for load disaggregation

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
8 Downloads (Pure)


Building on recent unsupervised Non-intrusive load monitoring (NILM) algorithms that use graph Laplacian regularization (GLR) and achieve state-of-the-art performance, in this paper, we propose a novel unsupervised approach to design an underlying graph to model the correlation within time-series smart meter measurements. We propose a variable-length data segmentation approach to extract potential events, assign all measurements associated with an identified event to each graph node, employ dynamic time warping to define the adjacency matrix of the graph, and propose a robust cluster labeling approach. Our simulation results on four different datasets show up to 10% improvement in classification performance over competing approaches.

Original languageEnglish
Article number6628
Number of pages16
Issue number22
Publication statusPublished - 19 Nov 2020


  • NILM
  • graph signal processing
  • energy efficiency
  • load disaggregation


Dive into the research topics of 'Building a graph signal processing model using dynamic time warping for load disaggregation'. Together they form a unique fingerprint.

Cite this