Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1XW, UK.
Sensors (Basel). 2020 Nov 19;20(22):6628. doi: 10.3390/s20226628.
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.
基于最近使用图拉普拉斯正则化 (GLR) 的无监督非侵入式负载监测 (NILM) 算法，这些算法达到了最新的性能水平，在本文中，我们提出了一种新的无监督方法来设计底层图，以对智能电表测量的时间序列中的相关性进行建模。我们提出了一种可变长度的数据分段方法来提取潜在事件，将与识别出的事件相关的所有测量值分配给每个图节点，采用动态时间规整来定义图的邻接矩阵，并提出了一种稳健的聚类标记方法。我们在四个不同数据集上的模拟结果表明，与竞争方法相比，分类性能提高了 10%。
