K-means clustering method based on nearest-neighbor density matrix for customer electricity behavior analysis

• Introducing a novel density measurement utilizing shared nearest neighbors, enhancing the assessment of data point density. • Developing an advanced K-means enhancement technique to dynamically determine cluster quantity and initial cluster center. • Integration of density-based and partition-based clustering methodologies, refining the K-means method's performance. • Achievement of peak performance in clustering outcomes via the proposed K-means modification. • Synergizing with various feature selection strategies for optimal clustering results proves its superior adaptability. User clustering is crucial for tapping the flexibility of the load side and realizing dynamic management of power loads in new power system. K-means method is widely used in clustering analysis due to its simplicity, high efficiency, and scalability, but it needs to specify the number of clusters in advance, and is sensitive to the initial clustering centers. The current initialization method does not take into account the neighborhood distribution of the data points, and the direct use of data that has undergone dimensionality reduction processing leads to inaccurate selection of the initial clustering centers. To address the above problems, a new K-means improvement method that takes into account the initialization problem and the adaptive determination of the number of clusters: K-means clustering method based on nearest-neighbor density matrix is proposed in this paper. The method improves the efficiency of nearest neighbor search by building a K-D tree, and enhances the performance of unsupervised classification by utilizing the adaptive selection strategy of the number of clusters and the initial clustering centers selection algorithm. The proposed method is applied to real datasets, and its effectiveness is assessed by calculating three clustering evaluation metrics of the clustering results in comparison with several existing initialization and clustering methods. The experimental results show that the method proposed in this paper has higher stability and better clustering performance than existing clustering methods.