Agglomerative Hierarchical Clustering with Dynamic Time Warping for Household Load Curve Clustering

Abstract

Energy companies often implement various demand response (DR) programs to better match electricity demand and supply by offering the consumers incentives to reduce their demand during critical periods. Classifying clients according to their consumption patterns enables targeting specific groups of consumers for DR. Traditional clustering algorithms use standard distance measurement to find the distance between two points. The results produced by clustering algorithms such as Kmeans, K-medoids, and Gaussian Mixture Models depend on the clustering parameters or initial clusters. In contrast, our methodology uses a shape-based approach that combines Agglomerative Hierarchical Clustering (AHC) with Dynamic Time Warping (DTW) to classify residential households' daily load curves based on their consumption patterns. While DTW seeks the optimal alignment between two load curves, AHC provides a realistic initial clusters center. In this paper, we compare the results with other clustering algorithms such as K-means, K-medoids, and GMM using different distance measures, and we show that AHC using DTW outperformed other clustering algorithms and needed fewer clusters.

Livestock Disease Data Management for E-Surveillance and Disease Mapping Using Cluster Analysis

“…Based on the minimal Davies-Bouldin Index (DBI), the authors found that the average linkage method performed relatively better than the others. Study in [29], applied Agglomerative Hierarchical Clustering with Dynamic Time Warping to classify residential households' daily load curves based on their consumption patterns. The proposed approach used Dynamic Time Warping (DTW) to find the best match between two load curves, whereas Agglomerative Hierarchical Clustering (AHC) was used to get a better starting point for the cluster centers.…”

K-Means and Alternative Clustering Methods in Modern Power Systems

“…Agglomerative Hierarchical Clustering employs a ''bottomup'' methodology, initially treating each data point as an individual cluster and successively merging pairs as we ascend the hierarchy. In power system applications, such as smart grid analytics, this approach can facilitate grouping power consumers with similar energy usage patterns [327], [328], [329], thereby enabling better demand forecasting and load balancing strategies [26].…”