Non-intrusive load decomposition method based on EEMD and GRU

A load decomposition, non-intrusive technology, applied in the field of non-intrusive load decomposition based on EEMD and GRU, which can solve the problems of low-power electrical appliances concealment and low electrical decomposition accuracy.

Inactive Publication Date: 2021-07-09
XIANGTAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Non-intrusive load decomposition technology completes the decomposition task by extracting the characteristics of electrical appliances, but most of the existing methods only consider the electrical characteristics of the load, and rarely analyze the time series characteristics and non-electrical characteristics in the data, resulting in the decomposition of electrical appliances in complex states The accuracy is low, and low-power electrical appliances are easily covered by high-power electrical appliances. Therefore, the research on non-intrusive load splitting technology is still facing great challenges

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
  • Non-intrusive load decomposition method based on EEMD and GRU
  • Non-intrusive load decomposition method based on EEMD and GRU
  • Non-intrusive load decomposition method based on EEMD and GRU

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0014] Step 1: Install a monitoring device at the user's total power entrance to obtain the user's power consumption data, process the obtained data, and filter out noise points.

[0015] The present invention denoises through adaptive Gaussian filtering, figure 1 It is a flow chart of adaptive Gaussian filter noise reduction. Gaussian filtering performs convolution operation on the Gaussian function and the original signal to output the filtered signal, expressed as follows:

[0016]

[0017] Its first derivative is:

[0018]

[0019] The result of the original signal after Gaussian filtering is:

[0020] N(t,σ)=f 0 (t)*g'(t,σ) (3)

[0021] Among them, g′(t, σ) is the Gaussian filter, t is the load data, σ is the standard deviation of the Gaussian filter, N(t, σ) is the filtered result, and “*” is the convolution operator.

[0022] Sup...

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 non-intrusive load decomposition method for household loads, and particularly relates to a non-intrusive load decomposition method based on EEMD and GRU. The method mainly comprises the following steps: processing an original power signal by adopting adaptive Gaussian filtering, decomposing the processed power signal into a plurality of modal components by utilizing an EEMD algorithm, and amplifying characteristics contained in the power signal; in order to excavate the time correlation characteristics between the decomposition time point and the plurality of previous time points, building a GRU neural network to process a time sequence signal; finally, inputting test data into the trained GRU network to realize load decomposition, and in order to further improve decomposition precision and speed, optimizing GRU network parameters by using a Tiancattle swarm optimization algorithm. The invention has good load decomposition performance, and can be used as a basis for users to check electricity consumption detailed lists.

Description

technical field [0001] The invention relates to electric energy monitoring in smart grids, in particular to a non-invasive load decomposition method based on EEMD and GRU. Background technique [0002] With the rapid development of smart grid, monitoring technologies such as power information communication technology, advanced measurement system, and power sensor detection technology have gradually been applied. Non-intrusive load monitoring technology is an important step in the advanced measurement system. The smart grid is of great significance. Non-intrusive load monitoring technology collects and calculates the load data of power users, obtains information such as the state parameters and power consumption of each electrical appliance, and analyzes the operating status of each electrical appliance. For users, non-intrusive load monitoring technology can provide users with detailed electricity consumption bills of electrical appliances, obtain basic electricity consumpt...

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): G06K9/00G06N3/04G06N3/08G06Q10/06G06Q50/06
CPCG06N3/086G06Q10/0639G06Q50/06G06N3/044G06F2218/04G06F2218/08
Inventor 熊志刚陈才学彭暄惠
Owner XIANGTAN 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
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