Short-term photovoltaic power prediction method based on EWT-KMPMR (empirical wavelet transform and kernel minimax probability machine classification)

A power prediction and photovoltaic technology, applied in prediction, instrument, data processing applications, etc., can solve the problems of mode aliasing, large amount of calculation, and large number of decomposed modes.

Inactive Publication Date: 2017-05-17
ELECTRIC POWER SCI RES INST OF STATE GRID XINJIANG ELECTRIC POWER +3
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a short-term photovoltaic power prediction method based on EWT-KMPMR, which overcomes the above-mentioned deficiencies in the prior art, and can eff...

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 photovoltaic power prediction method based on EWT-KMPMR (empirical wavelet transform and kernel minimax probability machine classification)
  • Short-term photovoltaic power prediction method based on EWT-KMPMR (empirical wavelet transform and kernel minimax probability machine classification)
  • Short-term photovoltaic power prediction method based on EWT-KMPMR (empirical wavelet transform and kernel minimax probability machine classification)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0092] Embodiment 1: as attached figure 1 As shown, the short-term photovoltaic power prediction method based on EWT-KMPMR includes the following steps:

[0093] Step 1: Use the Corrcoef(X,Y) function to filter the daily photovoltaic power history series collected every 15 minutes, and select the series with high correlation with the day to be predicted as training samples. The training samples include sunny day photovoltaic power series and cloudy day day photovoltaic power sequence;

[0094] Step 2: Use the EWT method to decompose the selected sunny-day photovoltaic power sequence and cloudy-day photovoltaic power sequence respectively to obtain the empirical scale component F 0 and the empirical wavelet component F 1 to F N-1 ;

[0095] Step 3: Use the KMPMR method to analyze the empirical scale component F 0 and the empirical wavelet component F 1 to F N-1 Construct the corresponding prediction model, and the output of each component prediction model is the predicti...

Embodiment 2

[0174] Embodiment 2: as table 1, 2 and attached figure 1 , 2 , 3, 4, 5, and 6, taking the short-term photovoltaic power forecast in Aksu area as an example, the short-term photovoltaic power forecast process in Aksu area is as follows:

[0175] Step 1: Use the Corrcoef(X,Y) function to filter the historical data of sunny photovoltaic power data in June 2015 in the Aksu area, and use June 23 as the benchmark to obtain the correlation calculation shown in Table 1 As a result, except for individual sample points on June 7, the variation trend of each similar day is basically consistent with the photovoltaic output, so the data of the first 4 days in Table 1 are selected as the training sample, and the data of June 23 is used as the test sample;

[0176] Step 2: Use the EWT method to decompose the selected sunny-day photovoltaic power sequence for 5 days (57 sample points with an interval of 15 minutes from 07:45 to 21:45 every day, a total of 285 sample points) to obtain the emp...

Embodiment 3

[0182] Embodiment 3: as table 3,4 and appended figure 1 , 7 , 8, 9, 10, and 11, taking the short-term photovoltaic power forecast in Aksu area as an example, the short-term photovoltaic power forecast process in Aksu area is as follows:

[0183] Step 1: Use the Corrcoef(X,Y) function to filter the historical data of cloudy photovoltaic power data in July 2015 in the Aksu area, and use July 31 as the benchmark to obtain the correlation shown in Table 3 As a result of the calculation, the training samples with high correlation with the day to be predicted are selected, so the data of the 26th and 28th are selected as the training samples, that is, the cloudy day photovoltaic power sequence;

[0184] Step 2: Use the EWT method to decompose the selected cloudy photovoltaic power series on the 26th and 28th (57 sample points with an interval of 15 minutes from 07:45 to 21:45 every day, a total of 171 sample points), and get empirical scale component F 0 and the empirical wavelet...

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 new energy source power generation prediction, in particular to a short-term photovoltaic power prediction method based on EWT-KMPMR (empirical wavelet transform and kernel minimax probability machine classification), comprising the steps of I, screening to obtain a training sample highly related to a day to be predicted; II decomposing to obtain empirical dimensional component and experience wavelet component; III, building a corresponding prediction for each component, wherein output of the component prediction models as prediction results for each component; IV, stacking the component prediction results to obtain a predicted value of solar photovoltaic output power to be predicted; by predicting short-term photographic powder with the method, calculating quantity is reduced, modal mixing is avoided, high prediction precision can be acquired, and the method has certain value and great significance to reasonably and economically scheduling electricity of the power grid.

Description

technical field [0001] The invention relates to the technical field of new energy power generation prediction, and relates to a short-term photovoltaic power prediction method based on EWT-KMPMR. Background technique [0002] Photovoltaic power generation has gradually become a renewable clean energy second only to wind power generation. Because it is directly affected by uncontrollable factors such as the alternation of light and day and night and weather changes, it has unavoidable intermittent characteristics. However, with the year-by-year growth of photovoltaic power generation installed capacity, large-scale photovoltaic grid-connection has caused a great impact on the safe and stable operation of the power grid. The ratio of power generation is extremely important. [0003] Short-term photovoltaic power forecasting methods currently mainly include direct forecasting methods based on photovoltaic power and weather information to establish forecasting models, such as u...

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
CPCG06Q10/04G06Q50/06Y02E40/70Y04S10/50
Inventor 李青孙谊媊于永军马天娇王琛郑少鹏钱准立朱鹏王新友祁晓笑陈龙
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