Classification and Analysis of Users' Electricity Consumption Behavior Using Cluster Analysis Algorithm

Abstract

Understanding and effectively managing electricity consumption behavior is crucial for achieving sustainability goals and ensuring the reliability of power systems. This study employs cluster analysis algorithms to classify and analyze users' electricity consumption behaviors using data collected from smart meters. Through the application of the k-means clustering algorithm on a dataset comprising consumption data from 1000 residential users, distinct consumption behavior patterns are identified. The optimal number of clusters is determined using the elbow method, and clusters are characterized based on average daily consumption levels, peak usage times, and seasonal variations. The findings reveal heterogeneity among consumer segments, highlighting the need for tailored energy management strategies. Insights from this study can inform utilities and policymakers in developing targeted interventions for promoting energy efficiency and sustainability. Further research in this field can explore advanced clustering techniques and additional factors to enhance the accuracy and robustness of clustering results.