Abstract:In the analysis of power equipment location information using the DBSCAN density clustering algorithm, manual parameter tuning is required, leading to significant impacts on clustering results, especially when dealing with varying quantities of analysis objects. This study adopts the silhouette coefficient as the evaluation metric for clustering results and introduces the Particle Swarm Optimization (PSO) algorithm to automatically determine reasonable values for the Eps and MinPts parameters. This adaptation allows the algorithm to better accommodate diverse data characteristics. Through PSO-DBSCAN clustering analysis of power equipment location data, experimental results indicate that the proposed method performs well in terms of clustering effectiveness. The approach successfully addresses the issue of instability in clustering results caused by manually setting parameters, achieving significant progress. This research provides an intelligent and adaptive density clustering analysis method for power system management, overcoming the limitations of traditional manual parameter tuning. It offers a reliable and efficient solution for the analysis of power equipment location information, presenting new perspectives and tools for the management and optimization of power systems.