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

Deep learning-based traction load ultra-short-term prediction method

A technology of ultra-short-term forecasting and traction load, applied in neural learning methods, forecasting, instruments, etc., can solve the problems of difficulty in establishing a forecasting model and insufficient forecasting accuracy, and achieve the effect of solving the problem of reactive power output coordination and reducing the difficulty of solving

Pending Publication Date: 2021-09-17
XIANGTAN UNIV
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a traction load ultra-short-term forecasting method, which can solve the problems of insufficient forecasting accuracy of traditional forecasting methods and difficulty in establishing forecasting models, and can obtain load forecasting results that meet the actual requirements of the project

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 traction load ultra-short-term prediction method
  • Deep learning-based traction load ultra-short-term prediction method
  • Deep learning-based traction load ultra-short-term prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to make the features and advantages of the present invention more obvious and comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0048] A day-ahead dynamic reactive power optimization method for active distribution network such as figure 1 shown, including:

[0049] Step S101, pre-process the load data, and decompose it into several subsequences by using discrete wavelet decomposition method;

[0050] Step S102, using the temporal convolutional network model to predict medium and low-frequency sequences, and using the support vector regression model to predict high-frequency sequences;

[0051] Step S103, summing up the prediction results of each sequence to obtain the final prediction result;

[0052] The specific implementation method of step S101 is: use the discrete wavelet decomposition method to decompose the traction load data, and the mathematical expression of the specific ...

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

Ultra-short-term prediction of a traction load is a key link in electric energy control of an electrified railway. Aims at the characteristics that the traction load random volatility is high, the jump amplitude value is large, and no-load is frequent, the invention provides a DWT-TCN-SVR combined prediction method which integrates DWT (discrete wavelet transform), TCN (temporal convolutional network) and SVR (support vector regression). The method comprises the following steps: firstly, decomposing a traction load time sequence into low-frequency, intermediate-frequency and high-frequency subsequences by using a wavelet decomposition method, then predicting the low-frequency and intermediate-frequency sequences by using a TCN model, predicting a high-frequency part by using an SVR model, and finally superposing and restoring respective prediction results to obtain a final prediction result.

Description

technical field [0001] The invention relates to the technical field of load forecasting, in particular to an ultra-short-term forecasting method of traction load. Background technique [0002] With the continuous development of electrified railways in my country, the total length of electrified railways has now ranked first in the world, but the rapid development of railways has also brought negative sequence, reactive power, harmonics and other effects. With the development of high-speed and heavy-duty railways, reactive power and harmonics are no longer the main problems, but the problem of negative sequence needs to be further resolved. Realizing the accurate prediction of traction load and grasping its changing trend in different time scales in the future can not only alleviate the negative sequence problem in power quality, but also help improve the reliability of traction power supply system. [0003] Aiming at the problem of traction load forecasting, relevant schola...

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): G06Q10/04G06Q50/30G06N3/04G06N3/08
CPCG06Q10/04G06N3/08G06N3/045G06Q50/40Y04S10/50
Inventor 马茜王豪陈浩
Owner XIANGTAN 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