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

Deep learning-based load modeling and online correction method

A technology of load modeling and deep learning, applied in character and pattern recognition, data processing applications, instruments, etc., can solve problems such as high dependence on fault data and modeling algorithms that cannot be applied online

Active Publication Date: 2019-12-20
TIANJIN UNIV +1
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: based on the basic theory of load modeling and online correction of load model parameters based on WAMS measurement data, a method of power load modeling and online correction that can be applied in the case of complex power systems is provided, which overcomes the The shortcomings of the traditional modeling method, which are highly dependent on fault data and the modeling algorithm cannot be applied online, provide load model preparation for power grid operators to perform simulation calculation and analysis

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
  • Deep learning-based load modeling and online correction method
  • Deep learning-based load modeling and online correction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] A load modeling and online correction method based on deep learning, comprising the following steps:

[0021] Step 1. Obtain the historical data samples of the load nodes to be identified, cluster the data samples according to the simulation calculation input variables, select the samples closest to the cluster center in each category as typical samples, and calculate the relationship between each sample in the same category and Variation in a typical sample;

[0022] The acquired node historical data includes active power P, reactive power Q, node voltage U and bus frequency f of load nodes. Among them, P and Q are the input quantities of the simulation calculation, U and f are the output quantities of the simulation calculation. When clustering, the continuously changing P and Q waveform curves within 15 minutes were used as samples for clustering, and the clustering method used the Mini Batch K-Means algorithm. The specific steps of the algorithm can be found in re...

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 deep learning-based load modeling and online correction method, which includes: (1) clustering historical sample data and calculating a variable quantity; (2) constructing anoffline simulation sample and calculating a simulation output variable quantity; (3) calculating an association rule between input and output variable quantities and a load model parametric variationby using a deep learning network; and (4) acquiring online data and online correcting the model. Based on a conventional power system load model research, the method, by using the idea of offline learning and online application and based on the deep learning, solves the construction and online correction of a complex power system load model in the context of a smart grid. The method provides a feasible solution for the construction and online correction of the power system load model, further improves the accuracy and the calculation accuracy of power system simulation model under a complex condition, and provides new research ideas for subsequent power system load modeling research.

Description

technical field [0001] The present invention relates to a load modeling and online correction method based on deep learning, in particular to a load modeling and online correction method based on deep learning. Background technique [0002] As one of the important components in the power system, the load has a great influence on the analysis and simulation calculation of the static, dynamic and transient characteristics and stability of the power system. However, the widely used load models are still relatively oversimplified and rough, such as static load models such as constant impedance and power. The excessive roughness of the load model has become a key factor restricting the accuracy of power system analysis and simulation calculations. It is of great practical significance to establish a dynamic load model that is realistic and can accurately reflect the important characteristics of the actual situation. [0003] With the continuous development of the power system, t...

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): H02J3/00G06K9/62G06Q50/06
CPCH02J3/00G06Q50/06G06F18/23213Y04S10/22Y02E60/00
Inventor 曾沅贾凡秦超孙冰刘博
Owner TIANJIN UNIV
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