Short-term wind power prediction method based on EWT-ESN

A wind power forecasting and wind power technology, applied in forecasting, instrumentation, data processing applications, etc., can solve the problems of forecasting point error and low forecasting accuracy

Inactive Publication Date: 2017-06-13
ELECTRIC POWER SCI RES INST OF STATE GRID XINJIANG ELECTRIC POWER +3
View PDF3 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a short-term wind power prediction method based on EWT-ESN, which overcomes the shortcomings of the above-mentioned prior art, and can effectively solve the problem of low prediction accuracy and severe wind power changes in the existing wind power output power prediction method. Problems prone to errors in prediction points

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 wind power prediction method based on EWT-ESN
  • Short-term wind power prediction method based on EWT-ESN
  • Short-term wind power prediction method based on EWT-ESN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] Embodiment 1: as attached figure 1 , 2 , 3, and 4, the short-term wind power forecasting method based on EWT-ESN includes the following steps:

[0073] In the first step, the original wind power with strong nonlinearity and non-stationarity is decomposed using the EWT algorithm to obtain N modal components, where F 0 Denotes the empirical scale component, F 1 to F N Indicates the empirical wavelet component; that is, the calculation of the EWT decomposes the original signal f(t) into N+1 intrinsic mode functions f k (t), a f k (t) is defined as a group of amplitude modulation and frequency modulation signals, that is, AM-FM signals, and the expression formula is as follows:

[0074]

[0075] In the second step, combine the decomposition components F 0 to F N According to the characteristics of the time series, the ESN prediction model of each component is established, and the formula is as follows:

[0076]

[0077] Among them, η represents the number of p...

Embodiment 2

[0138] Embodiment 2: as attached Figure 5 , 6 , 7, 8 and table 1, shown in table 2, according to the actually measured wind power data between December 1, 2010 to the 27th of Canada's Alberta wind farm, the sampling interval of the original data set is 10min, in the present invention Take 30min as the sampling interval to obtain the experimental data set, take the first 80% of the data as training samples, and the remaining 20% ​​of the data as testing samples.

[0139] The original data set is decomposed by EMD and EWT methods, and the decomposition results are shown in the attached Figure 5 And attached Figure 6 As shown, it can be seen that there is a big difference between the decomposition results of EWT and EMD. First, EWT decomposes to obtain 6 modal components, while EMD decomposes to obtain 8 modal components. number, which saves the calculation scale of combined forecasting; secondly, the IMF components obtained by EMD decomposition show the law of changing fro...

Embodiment 3

[0143] Embodiment 3: as attached Figure 9 , 10 , 11, 12, and Tables 3 and 4, according to the measured wind power data from September 23 to September 30 of the China Energy Conservation Wind Farm in Urumqi, Xinjiang, the sampling interval of the data set is 15 minutes. Get the data of the first 7 days as the training data set, and the data set of the 30th day (96 sample points) is used as the test data set to verify the prediction effect of the present invention.

[0144] According to attached Figure 9 And attached Figure 10 Shown, adopt EMD and EWT method to decompose the decomposition result figure that 8 days of raw data obtain, with embodiment 2, there is very big difference in the decomposition result of EWT and EMD, and EWT decomposition has obtained 5 modal components, and EMD decomposes to obtain 8 modal components; secondly, the amplitude of the component F0 decomposed by EWT accounts for a large proportion of the original original component x, and its change is...

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 field of wind power output power prediction technology, in particular to a short-term wind power prediction method based on EWT-ESN. The method comprises the steps that first, EWT is adopted to disintegrate original wind power with strong nonlinearity and non-stationarity to obtain N AM-FM components, wherein F0 refers to an experience dimension component, and F1 refers to an experience wavelet component; second, an ESN prediction model for all the components is established in combination with characteristics of all the disintegrated components from F0 to FN; third, prediction results of all the components are superposed to obtain a final prediction result; and fourth, prediction result analysis is performed according to error evaluation indexes. According to the method, first, the EWT algorithm is utilized to disintegrate an original sequence of the non-stationary wind power into the AM-FM components with compact support Fourier spectrum characteristics, then ESN is utilized to perform prediction on all the AM-FM components, and superposition is performed to obtain the final prediction result. Through the method, wind power prediction precision can be effectively improved.

Description

technical field [0001] The invention relates to the technical field of wind power output power forecasting, and relates to a short-term wind power forecasting method based on EWT-ESN. Background technique [0002] At present, the rapid development of wind power generation technology has gradually increased the proportion of wind power installed capacity in the regional power system. However, the wind power output power is extremely unstable due to the intermittent and fluctuating effects of wind power. Large-scale wind power grid-connected to the power system dispatch Therefore, accurate and reliable wind power output prediction is of great significance. [0003] The randomness and intermittent characteristics of wind energy lead to wind power output power as a nonlinear time series with strong fluctuations. At present, many computational intelligent forecasting methods, including neural networks and SVM, can describe the input and output power from the historical time serie...

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): G06Q50/06G06Q10/04
CPCG06Q10/04G06Q50/06
Inventor 李青于永军李德存王琛马天娇郑少鹏刘国营李明王新友祁晓笑陈龙
Owner ELECTRIC POWER SCI RES INST OF STATE GRID XINJIANG ELECTRIC POWER
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