Short-term power load prediction method based on twin support vector machine

A short-term power load, support vector machine technology, used in forecasting, computer parts, instruments, etc.

Active Publication Date: 2018-11-23
NORTHEASTERN UNIV
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Each method has its own limitations, and currently no metho

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
  • Short-term power load prediction method based on twin support vector machine
  • Short-term power load prediction method based on twin support vector machine
  • Short-term power load prediction method based on twin support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0098] The present invention will be further elaborated below in conjunction with the accompanying drawings of the description.

[0099] The invention provides a short-term power load forecasting method based on twin support vector machines. TWSVM is developed on the basis of SVM. It is a new type of machine learning algorithm, which has faster learning efficiency and stronger promotion ability than SVM. The invention uses TSVR to establish a short-term power load forecasting model, and proposes a DW-TSVR algorithm based on LBSA optimization for the problems of forecasting accuracy and forecasting efficiency of load forecasting.

[0100] Such as figure 1 Shown, a kind of short-term power load forecasting method based on twin support vector machine of the present invention comprises the following steps:

[0101] 1) Make a sample data set according to the format of the model input vector;

[0102] 2) Preprocess the data of the sample data set, which is divided into two catego...

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 relates to a short-term power load prediction method based on a twin support vector machine. The method comprises the following steps of 1) creating a sample data set according to a format of a model input vector; 2) classifying data of the sample data set, wherein one type of the data is used for parameter optimization, and the other type of the data is used for testing; performingnormalization preprocessing on the type of the data for the parameter optimization; 3) optimizing DW-TSVR parameters for the sample data subjected to the normalization preprocessing by using LBSA; and4) by adopting a DW-TSRVR algorithm based on LBSA parameter optimization, and in combination with the other type of the sample data used for testing, performing verification of a DW-TSVR model, and calculating a prediction result of short-term power load. According to the method, Levy flight is introduced into a flight behavior of a BSA algorithm; the LBSA algorithm is provided; the optimizationperformance of the algorithm is obviously improved, and meanwhile, the convergence speed of the algorithm is also improved to a certain extent; and therefore, a Levy flight-based bird flock algorithmprovided in the method has better performance.

Description

technical field [0001] The invention relates to a grid load forecasting technology, in particular to a short-term power load forecasting method based on a twin support vector machine. Background technique [0002] Load forecasting plays an important role in the daily work of power production department and management department. Accurate load forecasting is an important basis for ensuring the smooth operation of the power system. Power systems bring together power plants, transmission and distribution grids, and end users into a complex network. Electricity is a special commodity that is invisible and colorless and cannot be seen with the naked eye. After electricity is produced, it will be transmitted along the transmission and distribution grid to the terminal, and then consumed. This process takes an extremely short amount of time, almost simultaneously, to complete. Due to the particularity of electric energy, large-scale storage of electric energy will outweigh 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): G06Q10/04G06Q50/06G06K9/62
CPCG06Q10/04G06Q50/06G06F18/2411G06F18/214
Inventor 翟莹莹高若涵吕振辽敖志广薛丽芳
Owner NORTHEASTERN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap