A Clustering Analysis of Electricity Consumption Behavior

By examining load curves, users can be classified into different categories according to their characteristics. Such results are of great importance to the power industry and socio-economic development. This study therefore analyzes the behavior of user’s electricity consumption through clustering. Specifically, several classic clustering algorithms such as K-means, fuzzy clustering and neural network clustering are described. This is followed by an introduction to a data preprocessing method. Then, selecting an appropriate clustering algorithm as well as an optimal clustering number based on the clustering volatility and clustering accuracy index is discussed. Then, the load curve and the center representative curve are obtained by clustering. In addition, in order to eliminate the discontinuity caused by interval sampling, the moving average method is used to generate a continuous and smooth center load representative curve, and the user’s electricity consumption behavior is further analyzed.

• Publication year

  2022

• Venue

  2022 5th International Conference on Energy, Electrical and Power Engineering (CEEPE)

• Publication date

  2022-04-22

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/CEEPE55110.2022.9783311
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Artificial Immune Network Clustering approach for Anomaly Intrusion Detection

  2012cited by this paper
• Hybrid Personalized Recommender System Using Fast K-medoids Clustering Algorithm

  2011cited by this paper
• Support Vector Clustering of Electrical Load Pattern Data

  2009cited by this paper
• Curve prediction and clustering with mixtures of Gaussian process functional regression models

  2008cited by this paper
• Load profiling and its applications in power market

  2003cited by this paper

• No citing papers are available for this paper.