Support-vector-machine-regression-based method for predicting wind speed of wind power plant

A technology of support vector machine and wind speed prediction, which can be used in forecasting, instrumentation, data processing applications, etc., can solve the problems of slow convergence speed and low prediction accuracy, and achieve the effect of improving the convergence speed.

Inactive Publication Date: 2017-03-22
STATE GRID CORP OF CHINA +2
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problems of low forecasting accuracy and slow convergence speed of the existin

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
  • Support-vector-machine-regression-based method for predicting wind speed of wind power plant
  • Support-vector-machine-regression-based method for predicting wind speed of wind power plant
  • Support-vector-machine-regression-based method for predicting wind speed of wind power plant

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0015] Specific implementation mode one: a kind of support vector machine regression based wind farm wind speed prediction method of the present embodiment comprises the following steps:

[0016] Step 1. Select the sample data collected by the wind farm;

[0017] Step 2, determining a sample training set and a test set according to the sample data;

[0018] Step 3, preprocessing the sample data;

[0019] Step 4, select the support vector machine regression (SVM) kernel function, determine the parameters to be optimized in the SVM model, and obtain the best parameters to train the SVM model;

[0020] Step 5: Use the best parameters to train the SVM model to predict the wind speed value in the future.

specific Embodiment approach 2

[0021] Specific embodiment two: the difference between this embodiment and specific embodiment one is: the sample data collected by the wind farm is selected in the step one; the specific process is:

[0022] The sample data collected by the wind farm is to set up wind measuring towers at key points of the wind farm, mainly to study the real-time prediction of the output power of wind turbines in the next 10 minutes, 30 minutes and 1 hour, with a time resolution of 10 minutes; Analyze the performance characteristics of the unit.

[0023] The historical average data of ambient temperature, wind speed and output power of the wind power generation unit with a sampling interval of 10 minutes are selected.

[0024] Other steps and parameters are the same as those in Embodiment 1.

specific Embodiment approach 3

[0025] Specific implementation mode three: the difference between this implementation mode and specific implementation mode one or two is: in said step two, determine the sample training set and the test set according to the sample data; the specific process is:

[0026] The experiment selects the real-time operation data of No. 1 wind turbine unit for 7 days, and expresses it in an N×3 matrix (the 3 columns are ambient temperature, wind speed, and output power), and builds a regression prediction model; considering the above analysis, through simulation experiments, the previous 720 sample data in 5 days are used as the training set of the SVM model, and the power of the wind turbine is defined as:

[0027] P S =1 / 2ρv 3 f p (1)

[0028] where P S is the power value of the wind turbine, the unit is W, ρ is the air density, the unit is kg / m 3 , the v number is the flow velocity, the unit is m / s, f is the area, the unit is m 2 , C p Wind energy utilization coefficient 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

Disclosed in the invention is a support-vector-machine-regression-based method for predicting a wind speed of a wind power plant. The invention relates to a support-vector-machine-regression-based method for predicting a wind speed of a wind power plant, thereby solving problems of low prediction precision and slow convergence speed of the existing wind speed prediction method. The method comprises the following steps: step one, selecting sample data collected by a wind power plant; step two, determining a sample training set and a testing set; step three, carrying out pretreatment on the sample data; step four, selecting a support vector machine (SVM) regression kernel function and determining a to-be-optimized parameter of an SVM model; and step five, training the SVM model by using an optimal parameter and predicting a wind speed value at a future time. The method is applied to the wind power prediction field.

Description

technical field [0001] The invention relates to a wind speed prediction method of a wind farm based on a support vector machine regression. Background technique [0002] The development of wind power is of great significance to improving the energy structure, protecting the ecological environment, ensuring clean energy and achieving sustainable economic development, etc., which has become the consensus of the whole world. However, the current output power of wind turbines is characterized by intermittent, non-linear, fast changing speed, and large fluctuation range. Wind power grid connection has a huge impact on power quality and power system. In order to achieve large-scale utilization of wind power, optimize power grid dispatching, and strengthen wind power market competitiveness, wind farms must carry out wind power forecasting and forecasting, and should have daily and real-time forecasting capabilities. [0003] Therefore, accurate forecasting of wind power output, e...

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): G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06
Inventor 陈洪涛吴刚单小东孟祥辰陈艳孙振胜张海明李伟李军韩显华李冬梅黄树春赵强李一凡韩兆婷
Owner STATE GRID CORP OF CHINA
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