A power system distributed adjustable resource node clustering method and system
By using global preprocessing and high-dimensional feature matrix construction, combined with FCM algorithm and fuzzy decision-making, the traditional distribution network clustering method is able to address the shortcomings in characterizing the physical connectivity and uncertain fluctuations between nodes, thus achieving refined aggregation analysis of heterogeneous resources in the distribution network.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NORTH CHINA UNIVERSITY OF TECHNOLOGY
- Filing Date
- 2026-04-02
- Publication Date
- 2026-07-03
AI Technical Summary
Traditional distribution network clustering methods struggle to accurately characterize the physical connectivity and inherent correlations of uncertain fluctuations between nodes, leading to the invalidation of the physical and characteristic meanings of the clustering results and failing to fully tap the aggregation potential between nodes.
A high-dimensional feature matrix is constructed by generating a basic feature matrix and node symbol vectors through global preprocessing. Then, hierarchical clustering with physical adjacency constraints is performed by combining the FCM algorithm and the fuzzy decision algorithm to optimize the upper limit of the number of clusters and ensure the topological connectivity and uncertainty matching of the clustering results.
It achieves the global optimal matching of fluctuation direction and fluctuation amplitude between nodes, solves the "enclave" problem caused by neglecting physical connections in traditional clustering methods, and provides a refined aggregation analysis model for heterogeneous resources in distribution networks.
Smart Images

Figure CN122333010A_ABST