Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A feature extraction and clustering analysis method for a transient stability result of a power system

A feature extraction and transient stability technology, applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve the problems of slow network convergence, loose connection between different parameters, low normalization degree, etc. The interference performance is good, and the effect of avoiding the weakening of the data clustering effect

Active Publication Date: 2019-04-26
CHINA THREE GORGES UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004]The purpose of the present invention is to solve the problem of low normalization degree existing in existing methods for feature extraction and clustering of power system transient stability results, and between different parameters Technical problems of weak connection and slow network convergence

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A feature extraction and clustering analysis method for a transient stability result of a power system
  • A feature extraction and clustering analysis method for a transient stability result of a power system
  • A feature extraction and clustering analysis method for a transient stability result of a power system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] A method for feature extraction and cluster analysis of power system transient stability results, such as figure 1 shown, including the following steps:

[0061] Step 1: Perform normalized preprocessing on the transiently stable feature data in order to cluster the data. The normalized feature data preprocessing adopts the joint normalization method, and the column vector and the row vector are normalized by the most value method successively. It makes the connection between system data more closely and has better adaptability to system disturbance.

[0062] Data set S = {x 1 ,x 2 ,...x N} is a set containing N sample objects, and each sample object x in S ij ={x i1 ,x i2 ,...,x iτ}(i=1,2,...,N,j=1,2,...,τ) contains τ dimensions, where x ij represents the sample object x i The value of the j-th dimension attribute of , can constitute a (τ×N) sample matrix. The column vector and row vector are normalized successively with the most value method:

[0063] (1) C...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A feature extraction and clustering analysis method for a transient stability result of a power system comprises the following steps: 1) carrying out normalized preprocessing on transient stability feature data to cluster the data; 2) performing feature extraction and abnormal point judgment on the preprocessed data by using an improved clustering algorithm; 3) carrying out effectiveness evaluation on the clustering effect; And 4) analyzing the data features extracted from the transient stability in combination with geographic position information. The objective of the invention is to solve the technical problems of low normalization degree, untight connection between different parameters and slow network convergence in the existing method for extracting and clustering the transient stability result characteristics of the power system. System data features can be effectively and accurately extracted, and help is provided for electric power system planners to identify system responses.

Description

technical field [0001] The invention relates to the field of power system transient stability analysis, in particular to a method for feature extraction and cluster analysis of power system transient stability results. Background technique [0002] Transient stability simulation tools are the key to safe and reliable operation of power systems. In the huge power system in real life, the study of transient stability often produces a large amount of data, which provides an important basis for monitoring and controlling the power system. and identifying possible "anomalies" in the system present significant challenges. Therefore, it is of great significance to develop methods to automatically extract such information from transient stability data. Applying clustering techniques to transient stability data, such as voltage and frequency response signals, addresses the above needs. Identify outliers with uncommon features by extracting common features. At the same time, in vi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/50
CPCG06F30/20
Inventor 刘颂凯毛丹程江洲杨楠王灿杨苗李欣郭攀锋
Owner CHINA THREE GORGES UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products