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

Distributed wind power prediction method, model training method, equipment and medium

A technology of wind power forecasting and training methods, applied in forecasting, neural learning methods, biological neural network models, etc., can solve problems such as the inability to fully consider unit differences, achieve decentralized wind power forecasting, and improve migration adaptability Effect

Pending Publication Date: 2022-07-15
YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to address the above problems and provide decentralized wind power forecasting methods, model training methods, equipment and media to solve the problem that the differences between units cannot be fully considered in the process of wind power forecasting

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
  • Distributed wind power prediction method, model training method, equipment and medium
  • Distributed wind power prediction method, model training method, equipment and medium
  • Distributed wind power prediction method, model training method, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050]The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0051] like figure 1 shown, figure 1 It is a schematic flowchart of the training method of the distributed wind power prediction model in one embodiment. The steps provided in the training method of the distributed wind power prediction model in this embodiment include:

[0052] Step 102: Obtain historical sample data of the scattered multiple wind turbines.

[0053] In order to facilitate the description of this scheme, the followin...

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 distributed wind power prediction method, a model training method, equipment and a medium, and the method comprises the steps: firstly obtaining the historical sample data of a plurality of dispersed wind turbine generators, and the historical sample data of each wind turbine generator comprises position information, climate characteristics and actual output power; and dimension raising processing is carried out on the climate characteristics of the multiple wind turbine generator sets, multiple generated composite climate characteristics are obtained, and therefore the difference between the wind turbine generator sets is fully considered. According to the method, the position information and the climate characteristics of a plurality of wind turbine generators are clustered and analyzed to form a plurality of clusters, and the position information and the climate characteristics in each cluster are combined to obtain a plurality of climate position codes, so that the spatial positions and the climate characteristics of the units with different spatial positions are linked, and the migration capability of a prediction model is improved. And finally, inputting the plurality of composite climate characteristics and the plurality of climate position codes into a distributed wind power prediction model, and obtaining the output predicted power of each wind turbine generator so as to realize distributed wind power prediction.

Description

technical field [0001] The invention relates to the technical field of wind turbines, in particular to a distributed wind power prediction method, a model training method, equipment and a medium. Background technique [0002] With the continuous expansion of the scale of the wind power industry, the development of concentrated wind power in my country has been greatly restricted, and the problem of wind power consumption has become increasingly prominent. Compared with centralized development of wind power, decentralized wind power has many advantages. The construction of distributed wind farms in the surrounding areas with concentrated loads can relieve grid pressure and reduce the deployment scale of transmission and distribution facilities; and distributed wind farms are arranged at the end of the network where power quality needs to be improved, which can also improve power quality. It can be seen that the development of decentralized wind power that is more friendly to...

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): G06Q10/04G06Q50/06G06N3/08G06N3/04G06K9/62G06F30/27G06F113/06
CPCG06Q10/04G06Q50/06G06F30/27G06N3/08G06F2113/06G06N3/044G06F18/23
Inventor 袁智勇苏适潘姝慧杨家全雷金勇严玉廷李巍张弓帅白浩梁俊宇郭琦杨洋史训涛冯勇
Owner YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST
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