Construction method and device of non-intrusive load identification model and storage medium

An identification model, non-invasive technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as difficult to solve and accurately identify loads, shorten training time, reduce network complexity, and improve training The effect of precision

Pending Publication Date: 2021-07-23
INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER +1
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 provide a non-invasive load identification model construction method for the problem that the traditional non-intrusive load identification method is difficult to solve and accurately identify the load

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
  • Construction method and device of non-intrusive load identification model and storage medium
  • Construction method and device of non-intrusive load identification model and storage medium
  • Construction method and device of non-intrusive load identification model and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Embodiment 1. The construction method of the non-intrusive load identification model, such as figure 1 shown, including the following steps:

[0029] Load signal feature matrix Load signal feature matrix In this embodiment, firstly, according to the characteristics of the collected load signal such as frequency and voltage, the data is subpackaged, and operations such as data standardization are completed, and the collected data is formed into a standardized load signal feature matrix;

[0030] Use singular value decomposition to separate the load of the collected mixed signal, that is, X(t)=UΣV * , where X(t) is the feature matrix of the pre-processing load signal, Σ is the diagonal vector matrix of singular values, U is the vector matrix of left singular values, and V is the vector matrix of right singular values. Set the singular value threshold K=η*sum(Σ), where η is a constant, determined according to the signal characteristics, and sum(Σ) is to sum the diagonal ...

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 construction method and device of a non-intrusive load identification model and a storage medium. The method comprises the following steps: performing singular value decomposition on a load signal feature matrix to obtain a singular value diagonal vector matrix, a left singular value vector matrix and a right singular value vector matrix; singular values higher than a preset singular value threshold are kept in the singular value diagonal vector matrix; left and right singular value vectors corresponding to the updated singular value diagonal vector matrix are selected from the left singular value vector matrix and the right singular value vector matrix, and a new left singular value vector matrix and a new right singular value vector matrix are created. kronecker products corresponding to the new left singular value vector matrix and the new right singular value vector matrix are determined, and a feature matrix is obtained; and the reconstructed load signal feature matrix is input into a convolutional neural network model for training. Signals are preprocessed based on a singular value feature matrix reconstruction method, the latitude of data is reduced, data features are redistributed, the training time is shortened, and network complexity is reduced.

Description

technical field [0001] The invention belongs to the technical field of non-invasive load analysis, and in particular relates to a construction method, device and storage medium of a non-invasive load identification model. Background technique [0002] In the construction of the power Internet of Things, non-intrusive load analysis can provide great convenience. By using this method, power grid managers can accurately and effectively analyze the power consumption behavior of power users, laying a solid foundation for the intelligent management of the power grid. At the same time, non-intrusive load identification is low in implementation cost and less intrusive to users. Through non-intrusive load identification, grid companies can predict various load curves and assist in grid dispatching. Electric users can also use non-intrusive load identification. Identify, grasp the power consumption of factories or households in detail, and improve the intelligence of power consumptio...

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): G06F17/16G06F30/27G06N3/04G06N3/08G06Q50/06
CPCG06F17/16G06F30/27G06N3/08G06Q50/06G06N3/045
Inventor 王传君缪巍巍曾锃朱昊曾文浩李世豪张明轩张震张厦千张瑞滕昌志
Owner INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap