Power system model important parameter group identification method based on trajectory feature clustering

By combining Latin hypercube sampling and time-frequency encoders with UMAP dimensionality reduction and K-Means clustering, the problem of unmodeled parameter coupling relationships in power systems is solved, achieving efficient and accurate parameter identification, which is suitable for rapid fault location and dynamic response simulation correction in power systems.

CN120893318APending Publication Date: 2025-11-04CHINA SOUTHERN POWER GRID COMPANY
0 Cites 1 Cited by

Patent Information

Application Number
CN202511116180.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-08-11
Publication Date
2025-11-04

AI Technical Summary

Technical Problem

Existing methods for identifying critical parameters in power systems rely on time-domain global error indices, which result in the lack of modeling of parameter coupling relationships, difficulty in capturing transient information, and high computational costs, failing to meet the needs of rapid fault location and self-healing scheduling.

Method used

Latin hypercube sampling is used to generate parameter perturbation samples. Differential trajectory features are extracted by time-frequency encoder. Combined with UMAP dimensionality reduction and K-Means clustering, high-sensitivity parameter combinations are selected to achieve high-precision identification of parameter coupling relationships.

Benefits of technology

It significantly reduces the number of simulations and computational burden, quickly filters out the subset of parameters that have the most significant impact on system dynamics, and achieves high-precision, interpretable parameter identification, which is suitable for rapid fault location and dynamic response simulation correction in power systems.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides an electric power system model important parameter group identification method based on trajectory feature clustering, relates to an electric power system simulation technology, and solves the problem that modeling is not performed due to time domain global error index coarse graining and parameter coupling in traditional electric power system important parameter identification. The parameters are used as to-be-identified high-sensitivity parameters; performing time domain difference on each group of simulation tracks and actually measured tracks to obtain difference tracks, and extracting difference track features; the method comprises the following steps: mapping high-dimensional data to a low-dimensional space through a nonlinear dimension reduction method, and executing K-Means clustering on the data in the low-dimensional space to obtain a cluster label of each sample; sensitivity calculation is carried out on all samples in the clusters, and a parameter combination with the highest occurrence frequency and the maximum contribution to dynamic differences in the clusters is screened out to serve as a final dominant parameter set. According to the scheme, the simulation frequency and the calculation burden can be remarkably reduced, and high-precision and interpretable discrimination of important parameters really influencing the system performance is realized.
Need to check novelty before this filing date? Find Prior Art