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

Load characteristic rapid matching method based on AdaBoost model

A technology of load characteristics and matching methods, applied in character and pattern recognition, data processing applications, instruments, etc., can solve problems such as low efficiency of mathematical optimization solutions, difficult to meet, and simple processing scenarios, and achieve good economic benefits and practical value , to achieve a simple, high-accuracy effect

Pending Publication Date: 2021-03-26
ZHEJIANG HUAYUN INFORMATION TECH CO LTD +4
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, mathematical optimization and pattern recognition are two major solutions to load identification and decomposition problems, but the solution efficiency of mathematical optimization is low, and accurate identification requires a complete load feature library, which is often difficult to meet in practice; in pattern recognition, based on Supervised learning load identification algorithms emerge in endlessly, but the types of loads involved are not many, and the processing scenarios are relatively simple. The accuracy of load identification algorithms based on unsupervised learning is low

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
  • Load characteristic rapid matching method based on AdaBoost model
  • Load characteristic rapid matching method based on AdaBoost model
  • Load characteristic rapid matching method based on AdaBoost model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] Such as figure 1 Shown, the present invention comprises the following steps:

[0078] 1) Acquire data, the data includes training data, label data, weak recognizer and number of iterations; the training data is the graphic feature data in the load V-I curve trajectory; the training data and the label data are input into the training data set to form a training data set, wherein the training The dataset is:

[0079] T={(x 1 ,y 1 ),(x 2 ,y 2 ),...,(x n ,y n )} (1)

[0080] In the formula: T is the training data set; x i is the load characteristic; y i It is the label corresponding to the load feature. The label refers to the working state of the equipment. When it is -1, it means it is in a stopped state. When it is 1, it means it is working;

[0081] 2) Initialize the weight distribution of the weak discriminator;

[0082]

[0083] In the formula: D 1 To initialize the weight distribution set of training samples, w i,n is the n-th training weight of the i...

Embodiment 2

[0101] Embodiment two: the same place as the embodiment will not be repeated, the difference is:

[0102] Such as image 3 As shown, the data acquisition of the graphic feature data in the load V-I curve track includes the following steps:

[0103] 101) Acquisition of total electricity load data;

[0104] Use the wave recorder to collect the voltage and current data of a single electrical appliance, and obtain the drawn VI trajectory curve;

[0105] 102) data preprocessing;

[0106] Data preprocessing includes standardization of current and voltage; standardization of current and voltage is achieved by dividing the current and voltage signals by their root mean squares respectively; the standardized current and voltage data are plotted with the voltage as the abscissa axis and the current as the ordinate axis to draw the current Voltage V-I trajectory curve;

[0107] The current and voltage normalized calculation formula is:

[0108]

[0109] v norm(n) =v n / V rms (...

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 load characteristic rapid matching method based on an AdaBoost model, and relates to the field of power load monitoring. At present, mathematical optimization and pattern recognition are two types of solving methods for load recognition and decomposition problems, but the solving efficiency of mathematical optimization is relatively low, and the precision of a load recognition algorithm is relatively low. Therefore, the invention provides a load characteristic rapid matching method based on an AdaBoost model, and the method comprises the steps of taking graphic characteristics in a load VI curve track as an identification sample, defining an identification label for each load, selecting a proper weak recognizer, generating an enhanced strong recognizer, and finally achieving the load identification. By using the AdaBoost recognizer, important training data features can be extracted, the training dimension is reduced, the training speed is increased, and the training precision is improved. According to the method, the load characteristics can be quickly, efficiently and accurately matched, and good economic benefits and practical values are achieved.

Description

technical field [0001] The invention relates to the field of electric load monitoring, in particular to a method for quickly matching load characteristics based on an AdaBoost model. Background technique [0002] With the advancement of ICT technology and the continuous acceleration of intelligent and digital construction of power distribution networks, the development and application of a new generation of power collection systems have new driving forces. Intelligent power consumption and intelligent management of power networks have become The trend of future development. As the most basic link to realize intelligent management of intelligent power consumption under the background of informatization and digital development of power network, the innovation and progress of load identification algorithm has very important value. At present, mathematical optimization and pattern recognition are two types of solutions for load identification and decomposition problems, but the...

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): G06K9/62G06N20/20G06Q50/06
CPCG06N20/20G06Q50/06G06F18/2148G06F18/24
Inventor 陈清泰严华江叶方彬麻吕斌林英鹤姜驰王剑王荣
Owner ZHEJIANG HUAYUN INFORMATION TECH CO LTD
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