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

Wind power climbing event prediction method based on feature adaptive selection and WDNN

A technology of self-adaptive selection and forecasting methods, applied in forecasting, neural learning methods, computer components, etc., can solve problems such as single influencing factors and low forecasting accuracy

Active Publication Date: 2020-02-07
NORTHEAST DIANLI UNIVERSITY
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the influencing factors of the wind power ramp event considered in the prior art are relatively single, resulting in low prediction accuracy

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
  • Wind power climbing event prediction method based on feature adaptive selection and WDNN
  • Wind power climbing event prediction method based on feature adaptive selection and WDNN
  • Wind power climbing event prediction method based on feature adaptive selection and WDNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0054] Such as figure 1 As shown, the wind power climbing event prediction method based on feature adaptive selection and WDNN of the present invention comprises the following steps:

[0055] Step 1: Extract the time L from the data acquisition and monitoring control system in the wind farm in time series with the sampling period Δt 1 The original data of the active power of the fan and the air temperature in the fan constitute the original data set PT of the fan operation 0 ={(P(t n ) 0 ,T(t n ) 0 )|n=1,2,...,N}; among them, t n is the time corresponding to the nth sampling point, N is the total number of sampling points, t n+1 -t n =Δt,L 1 =(N-1)Δt, P(t n ) 0 for t n Raw data of fan active power at time, T(t n ) 0 for t n Raw data of air temperature at time.

[0056] Step 2: Run the original dataset PT on the turbine 0 Perfor...

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 the technical field of wind power climbing event prediction, and provides a wind power climbing event prediction method based on feature adaptive selection and WDNN. The method comprises the following steps: firstly, collecting and normalizing a fan operation original data set; then constructing a wind power climbing event sample set PTr; secondly, based on a feature adaptive selection method, selecting a related sample set from the sample set PTr, performing wavelet decomposition on signals formed by active power in each related sample, and combining the decomposed signals with temperature and category label data to obtain a decomposed sample set; constructing and training a DNN-based wind power climbing event prediction model by taking variables, except the category labels, in the decomposed sample set as input and taking the category labels as output; and finally, acquiring and processing fan operation original data in real time, and outputting a corresponding category label by utilizing the trained prediction model. According to the invention, the input variable of the wind power climbing event prediction model can be optimized, and the prediction precision is improved.

Description

technical field [0001] The invention relates to the technical field of wind power ramp event prediction, in particular to a wind power ramp event prediction method based on feature adaptive selection and WDNN. Background technique [0002] With the gradual depletion of non-renewable energy sources in the world, renewable energy sources have gradually occupied a dominant position in industry and life. In my country, electric energy, as an indispensable form of energy in life, is also facing tremendous changes, which is mainly reflected in the increasing proportion of wind energy and other new energy generation connected to the grid. According to the information released by China Energy Network, China's wind power generation in 2017 was 305.6 billion kWh, an increase of 26.8% compared with 2016, and the proportion rose from 4.0% to 4.8%. However, with the rapid development of wind power and large-scale grid connection, some problems brought about by wind power have gradually ...

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): G06Q10/04G06Q50/06G06K9/62G06N3/04G06N3/08
CPCG06Q10/04G06Q50/06G06N3/084G06N3/045G06F18/214Y04S10/50Y02E40/70
Inventor 唐振浩孟庆煜曹生现
Owner NORTHEAST DIANLI UNIVERSITY
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