Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Non-invasive load decomposition method and system

A load decomposition and non-intrusive technology, applied in the direction of AC network circuits, electrical components, circuit devices, etc., can solve the problem of low accuracy of load characteristics, achieve the effect of improving accuracy and accuracy, and increasing the receptive field

Pending Publication Date: 2019-11-12
CHINA ELECTRIC POWER RES INST +3
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of low accuracy of load features extracted in existing methods, the present invention provides a non-invasive load decomposition method and system

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-invasive load decomposition method and system
  • Non-invasive load decomposition method and system
  • Non-invasive load decomposition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] This embodiment provides a non-intrusive load decomposition method, the method flow chart is as follows figure 1 shown.

[0070] S1: Obtain the total load power sequence of the target user within a period of time.

[0071] The long-term power consumption information of various electrical appliances in more than 600 households and the total power consumption of the entire household are collected, including the historical power consumption data of air conditioners, refrigerators, washing machines, dishwashers, and microwave ovens in the households, which are used for load decomposition tasks. The main reasons for choosing these types of electrical appliances are as follows: (1) The amount of supervised learning experiments on each electrical appliance in each family is huge and unnecessary, while experiments on some common and representative electrical appliances necessary. (2) Some small power consumption appliances contained in the data set are easily disturbed by noi...

Embodiment 2

[0115] This example provides a description of the residual structure used in a non-intrusive load decomposition method.

[0116] (1) Residual structure in the residual network: The residual network draws on the idea of ​​cross-layer connection in high-speed networks. It may be difficult to simply fit an identity map H(x)=x with a forward neural network stacked with one or more hidden layers. However, if the network is designed in the form of H(x)=F(x)+x, the function can be converted into a residual function F(x)=H(x)-x, when F(x)=0, we get The mapping function H(x)=x. The residual network is such a structure that directly transmits the output of the front layer to the back layer by adding an identity map. The residual structure replaces the desired output H(x) with F(x)+x by adding an identity transformation. The two expressions have the same effect on network training, but the optimization difficulty is different. F(x)+x can pass a forward A neural network is implemented ...

Embodiment 3

[0156] This embodiment provides a non-intrusive load splitting system, including:

[0157] Data acquisition module: acquire the total load power sequence of the target user within a period of time;

[0158] Decomposition module: based on the total load power sequence of the user and the set load type, according to the relationship between the pre-trained total power sequence and the power characteristic sequence of each load type, decompose the total load power to obtain the total load power within the time period. The power characteristic sequence of each load type;

[0159] Wherein, the load type is determined by the user's usage of the household appliances;

[0160] The training process in the decomposition module includes: receptive field amplification based on identity mapping and timing.

[0161] The decomposition module includes:

[0162] Multi-user data acquisition sub-module: acquire historical multi-user load total power sequence;

[0163] Use data acquisition su...

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-invasive load decomposition method and system. According to the scheme, the method comprises the steps of acquiring a load total power sequence of a target user within aperiod of time; and based on the load total power sequence of the user and set load types, decomposing load total power to obtain power characteristic sequences of the load types in the time period according to pre-trained relations between the total power sequence and the power characteristic sequences of the load types, wherein the load types are determined by using conditions of household appliances by the user. The training process comprises the steps of performing receptive field amplification based on identity mapping and a time sequence. The non-invasive load is decomposed through the pre-trained relations between the total power sequence and the power characteristic sequences of the load types, so that the correctness and accuracy of a load decomposition result are improved; and inthe training process, the load total power is subjected to a receptive field method according to the time sequence through the identity mapping, so that the problem of gradient disappearance in the load decomposition process is solved, the receptive field is expanded, and the load decomposition result is more authentic.

Description

technical field [0001] The invention relates to the field of electric load decomposition, in particular to a non-invasive load decomposition method and system. Background technique [0002] In recent years, with the development of smart grid, power load decomposition technology has attracted more and more attention from scholars. Load monitoring mainly includes two types: intrusive and non-invasive. Traditional load power monitoring is generally an intrusive method. The data obtained by the intrusive method is accurate and reliable, and the data noise is small, but the implementation is difficult and the user acceptance is low. The emergence of non-intrusive charge load decomposition technology makes up for the shortcomings of intrusive charge load decomposition. It can provide real-time power consumption information for power grids and users, and realize more refined demand-side response to power suppliers and power users to understand their own power consumption. , It is...

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): H02J3/00
CPCH02J3/00
Inventor 王珂夏闵姚建国杨胜春耿建李亚平钱甜甜朱克东汤必强刘建涛郭晓蕊周竞毛文博王刚
Owner CHINA ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com