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

Non-invasive power load monitoring and decomposition method and system based on ensemble learning

A power load, non-intrusive technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as poor detection effect and single feature, and achieve high test accuracy, improved continuity, and strong reliability Effect

Inactive Publication Date: 2019-01-04
SHANDONG NORMAL UNIV
View PDF4 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, most studies use basic algorithms such as K-nearest neighbors, neural networks, and support vector machines to detect a single load state. The features used are relatively single, and they can only detect some common specific electrical appliances. Poor detection of complex situations

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 power load monitoring and decomposition method and system based on ensemble learning
  • Non-invasive power load monitoring and decomposition method and system based on ensemble learning
  • Non-invasive power load monitoring and decomposition method and system based on ensemble learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0119] In order to verify the reliability of the model, we conducted research and analysis on 5 types of electrical equipment, namely Oakes fans, Midea microwave ovens, Joyoung kettles, ThinkPad notebooks, and incandescent lamps. 5 The power vectors of these 32 situations are used as the input of the neural network, and the number of neurons in the input layer of the neural network is designed to be 32, and the input matrix P is composed of input variables L =[P L (1) ,...,P L (32) ].

[0120] The three-layer neural network can basically approach the nonlinear load decomposition model, so the multi-layer neural network designed in this paper is three layers. Usually, a neural network consists of an input layer, a hidden layer and an output layer, such as Figure 6 shown.

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 power load monitoring and decomposition method and system based on ensemble learning. The method comprises the following steps: acquiring voltage and current data at the power load inlet; the characteristics of active power, current harmonics, power factor angle and current harmonics distortion rate at the power load entrance being calculated, and the sampleset is constructed; the sample set being randomly divided into training set and prediction set, and the ensemble learner being trained by a training set; when the ensemble training is completed, the prediction set being used to test the categories of samples in the sample set. The method and system has high test accuracy, strong reliability and more stable effect.

Description

technical field [0001] The invention belongs to the field of power data mining, and in particular relates to a non-intrusive power load monitoring and decomposition method and system based on integrated learning. Background technique [0002] Load monitoring is of great significance to the reliability of the power system, and the application of sub-item measurement technology can realize a scientific and quantitative power management mode. There are two typical implementation schemes for load electricity detail monitoring: intrusive and non-intrusive. Among them, the non-intrusive power load monitoring and decomposition technology does not need to enter the load, only by measuring and analyzing the voltage, current and power at the entrance of the power load, the real-time power consumption ratio of different electrical equipment inside the load can be obtained , so as to realize the power load decomposition. The method is simple, economical, reliable, and easy to promote ...

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): G06K9/62
CPCG06F18/23213G06F18/24
Inventor 王红王露潼宋永强王倩刘海燕于晓梅胡斌
Owner SHANDONG NORMAL UNIV
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com