Research on the Analysis of User Power Consumption Behavior Characteristics based on the Improved K-means Clustering Algorithm

With the rapid economic development and the continuous growth of electricity demand, the power grid is facing severe pressure in power supply guarantee. This study utilizes data mining techniques to analyze user power consumption data and proposes a strategy of using the kmeans algorithm for clustering analysis of user power consumption data. Given that the k-means algorithm is sensitive to noisy data, the DBSCAN algorithm is adopted to optimize the clustering analysis strategy. Moreover, evaluation indicators such as CHI, silhouette coefficient, and DBI are used to conduct a comparative analysis of the clustering results of the traditional k - means algorithm and the k - means algorithm improved by DBSCAN. The results show that the latter exhibits more significant superiority when dealing with user power consumption data. By optimizing the algorithm for clustering analysis of user power consumption behavior characteristics, this research aims to better support personalized services in the power industry and the optimization of power grid dispatching.