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

Non-invasive load monitoring method based on event detection

A technology for event detection and load monitoring, applied in measurement devices, vehicle components, and electric power measurement, etc., can solve the problems of difficult implementation and high economic cost.

Inactive Publication Date: 2020-04-03
ZHEJIANG UNIV OF TECH
View PDF5 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] To sum up, considering that the traditional intrusive load monitoring method is to install data acquisition devices in the user's internal electrical equipment, it has high economic costs, difficult implementation, and involves user privacy and other issues

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 monitoring method based on event detection
  • Non-invasive load monitoring method based on event detection
  • Non-invasive load monitoring method based on event detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0110] The present invention will be further described below in conjunction with the accompanying drawings.

[0111] refer to Figure 1 to Figure 10 , a non-intrusive load monitoring method based on event detection, comprising the following steps:

[0112] S1: Data preprocessing, denoising the original measured power signal in the selected REDD data set, eliminating isolated noise points to reduce false detection of events;

[0113] S2: Use the generalized likelihood ratio detection method for event detection on the processed data, and realize the identification of the time node of the load switch and state change by detecting the active or reactive power sequence of the load;

[0114] S3: Introduce the true positive rate and true positive percentage as metrics to measure the performance of the event monitor to obtain the best event monitor;

[0115] S4: For the detected electrical equipment switching events, extract the steady-state current before and after switching, use t...

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 monitoring method based on event detection. The method comprises the steps of selecting an original measurement power signal in a public REDD data set for denoising processing, carrying out event detection on the processed data by using a generalized likelihood ratio detection method, and identifying a load switch and a state change time node by detecting an active or reactive power sequence of a load; switching a detected electric device into an event, extracting a steady-state current before and after switching, carrying out fast Fourier transformto extract current the harmonic characteristics, combining the active power, establishing a load characteristic library through an affinity propagation clustering algorithm, fitting the actual electric appliance data characteristics and a load characteristic set through a dynamic adaptive discrete particle swarm algorithm, and determining the operation state of the household electric appliance. According to the method, users can conveniently carry out household energy-saving management and make demand response measures for a power grid, the real-time bidirectional interaction of the intelligent power grid is realized, and the asset utilization rate and the energy utilization efficiency are effectively improved.

Description

technical field [0001] The invention relates to a non-invasive load monitoring method based on event detection. Background technique [0002] In recent years, global warming and energy shortage have become the two major problems of today's era. At the same time, social development and power demand continue to grow, and energy conservation has become one of the most important issues. Nowadays, the proportion of electric power in my country as the terminal consumption energy replacing traditional fossil fuels is increasing day by day, and electric energy, as a convenient, widely used, clean and efficient secondary energy source, will continue to grow in the proportion of terminal energy in the future. Therefore, saving energy , it is of great significance to promote the efficient utilization of electric energy. Smart grid is the development direction of the global power grid in the future, which has the characteristics of flexibility, cleanliness, safety, economy and friendlin...

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): G01R21/00G06F17/18
CPCG01R21/002G01R21/003G06F17/18
Inventor 张有兵赵康莉徐铿徐崇博陈竹王力成
Owner ZHEJIANG UNIV OF TECH
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