Unlock instant, AI-driven research and patent intelligence for your innovation.

Load identification method based on wavelet transform

A load identification and wavelet transform technology, applied in the field of electric power, can solve the problems of reduced accuracy of load patterns and information loss, and achieve the effect of improving accuracy, reducing lost dimensions, and improving effectiveness

Pending Publication Date: 2021-08-27
HUZHOU ELECTRIC POWER SUPPLY CO OF STATE GRID ZHEJIANG ELECTRIC POWER CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the problem of information loss caused by the unsuitability of the prior art clustering method for curve clustering and the decrease in the accuracy of load pattern extraction, and to provide a load identification method based on wavelet transform, which can meet the needs of different scenarios Response resource matching needs

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
  • Load identification method based on wavelet transform
  • Load identification method based on wavelet transform
  • Load identification method based on wavelet transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] This embodiment provides a load identification method based on wavelet transform, such as figure 1 , including the following steps:

[0051] Step 1: Obtain an n-dimensional daily load curve.

[0052] Step 2. Using multilevel one-dimensional discrete Walsh transform (1D DWT) to reduce the n-dimensional daily load curve X 0 Dimensions, resulting in an approximation signal X αL and detail signal X αH ;

[0053] Use α to represent the series, and use α-level one-dimensional discrete Walsh transform (1D DWT) to reduce the n-dimensional daily load curve X 0 Dimensions, resulting in an approximation signal X αL and detail signal X αH :

[0054] x αL ={x 1,αL ,x 2,αL ,...x N,αL}

[0055] x i,αL =i1 ,a i2 ,...,a in′ >,x i,αH =i1 , d i2 ,...,d in′ >, 1≤i≤N, n'=n / 2 α .

[0056] Step 3. For the approximation signal X αL Perform z-score normalization processing to obtain the processed approximation signal X' αL ;for the approximation signal X αL Perform z-scor...

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

The invention discloses a load identification method based on wavelet transform, which solves the problem that the accuracy of load mode extraction is reduced due to information loss caused by the fact that a clustering method in the prior art is not suitable for curve clustering, and comprises the steps of 1, acquiring an n-dimensional daily load curve; 2, reducing the dimension of the n-dimensional daily load curve X0 by adopting multi-stage one-dimensional discrete Walsh transform, and generating an approximation signal X [alpha] L and a detail signal X [alpha] H; 3, performing z-score standardization processing on the approximation signal X [alpha] L to obtain a processed approximation signal X' [alpha] L, and performing z-score standardization processing on the approximation signal X alpha L; 4, carrying out k-means clustering on the standardized approximation signal X' [alpha] L and the detail signal X [alpha] H, and obtaining clusters A and D; and 5, polymerizing the cluster A and the cluster D. The demand response resource matching requirements in different scenes can be met.

Description

technical field [0001] The invention relates to the field of electric power, in particular to a load identification method based on wavelet transform. Background technique [0002] The action mechanism of demand response on the user side refers to the rules and principles that affect the load characteristics of the entire system by changing the inherent power consumption mode in order to increase the role of the demand side in the operation of the power system, responding to price signals or incentive signals for power users . The load mechanism and load level of different industries often show great differences. In order to meet the business needs of demand response in different scenarios for the differentiated application of demand response resources, it is necessary to study demand response resource matching and pattern recognition in the context of smart grids. method. Smart grid is a modern application system in the field of power energy management. It uses automatic...

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
IPC IPC(8): G06K9/00G06K9/62G06F17/14
CPCG06F17/148G06F2218/12G06F18/23213G06F18/213
Inventor 刘海峰卢峰郑松松王春陈士俊项镭潘康王俊杰费展宏柏卫平盛琦慧沈晓斌
Owner HUZHOU ELECTRIC POWER SUPPLY CO OF STATE GRID ZHEJIANG ELECTRIC POWER CO LTD