Clustering of Load Profiles of Residential Customers Using Extreme Points and Demographic Characteristics

• Main Authors: Hyun Cheol Jeong, Minseok Jang, Taegon Kim, Sung-Kwan Joo
• Format: Article
• Language: English
• Published: MDPI AG 2021-01-01
• Series: Electronics
• Subjects: extreme points; demographic characteristics; customer load grouping
• Online Access: https://www.mdpi.com/2079-9292/10/3/290
• ISSN: 2079-9292

In this paper, a systematic method is proposed to cluster the energy consumption patterns of residential customers by utilizing extreme points and demographic characteristics. The extreme points of the energy consumption pattern enable effective clustering of residential customers. Additionally, demographic characteristics can be used to determine an effective extreme point for the clustering algorithm. The K-means-based features selection method is used to classify energy consumption patterns of residential customers into six types. Furthermore, the type of energy consumption pattern can be identified depending on the characteristics of residential customers. The analytical results of this paper show that the extreme points are effective in clustering the energy consumption patterns of residential customers.