Unlock instant, AI-driven research and patent intelligence for your innovation.

Anti-normalization interval correction method for improving air speed prediction precision of SVM (Support Vector Machine)

A wind speed prediction and wind speed technology, which is applied in the field of inverse regression interval correction to improve the accuracy of SVM wind speed prediction, can solve the problems of failing to meet the requirements of the power grid, large differences in actual intervals, deviations, etc., and achieve the effect of improving accuracy

Inactive Publication Date: 2013-12-25
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the future real wind speed interval is unknown, when using the wind speed interval of the previous period as the anti-regular interval to carry out the inverse normalization of the forecast wind speed, or directly use the future wind speed interval given by the numerical weather prediction (NWP) as the anti-regular interval. Inverse normalization, after multiple modeling predictions, it was found that the anti-regular interval determined by the above two methods is quite different from the actual interval of the real wind speed in the future prediction period, resulting in the wind speed prediction output by the SVM prediction model after inverse normalization There is a large deviation between the result and the real wind speed, the prediction accuracy is not high, and it cannot meet the requirements of the power grid

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
  • Anti-normalization interval correction method for improving air speed prediction precision of SVM (Support Vector Machine)
  • Anti-normalization interval correction method for improving air speed prediction precision of SVM (Support Vector Machine)

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0035] Such as figure 2 As shown, in this embodiment, m=15, n=4, F=3, k 0 =1, the current time is 8:00 on April 16th, select the wind speed data from 4:15-12:00 on April 13th, the wind speed data from 4:15-12:00 on April 14th and 4 : 15-12:00 wind speed data (acquire wind speed data at 4:15 on April 13th, then obtain wind speed data every 15 minutes until 12:00 on April 13th, and obtain wind speed at 4:15 on April 14th data, then get wind speed data every 15 minutes until 12:00 on April 14th, get wind speed data at 4:15 on April 15th, then get wind speed data every 15 minutes until 12:00 on April 15th), Using the above wind speed data as training samples, the SVM model is established. In this SVM model, the input data is the data obtained from 4:15-8:00 on April 13th, the data obtained from 4:15-8:00 on April 14th, and the data obtained from 4:15-8:00 on April 15th The data obtained at :00; the output data is the data obtained at 8:15-12:00 on April 13, the data obtained a...

no. 2 example

[0044] In this embodiment, the general trend of the wind speed corresponding to the current moment is descending, the wind speed at 8:00 at the current moment is 7m / s, and the trend variation of the wind speed in the next four hours of the numerical weather forecast is -3m / s, then the correction The subsequent inversion interval is [7-3,7], that is, [4,7];

no. 3 example

[0046] In this embodiment, the general trend of the wind speed corresponding to the current moment is flat, the wind speed at 8:00 at the current moment is 7m / s, the wind speed at 7:45 is 8.5m / s, and the wind speed at 7:30 is 6.9m / s. Then the corrected anti-normalization interval is [6.9-1, 8.5+1], that is, [5.9, 9.5].

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 an anti-normalization interval correction method for improving air speed prediction precision of an SVM (Support Vector Machine) and belongs to the field of predication of a wind power. The invention discloses a novel anti-normalization interval correction method to improve the prediction precision of a model. The basic thought of the method comprises the following steps of: firstly, solving tendency variable conditions and tendency variable quantities of an input air speed and a numerical weather prediction (NWP); then, dividing to obtain nine air speed variable conditions according to the tendency variable conditions and the tendency variable quantities; and finally, correcting an anti-normalization interval of the nine air speed conditions according to the tendency variable quantities of the NWP to enable the anti-normalization interval to be closer to a real air speed, so as to improve the predication precision of an SWM model. The anti-normalization interval correction method disclosed by the invention has the beneficial effects of enabling the anti-normalization interval to be close to a virtual air speed interval of a further predication time interval as much as possible, so that the predication precision of the model is improved to the greatest extent.

Description

technical field [0001] The invention belongs to the field of wind power forecasting, in particular to an inverse regression-interval correction method for improving the accuracy of SVM wind speed forecasting. Background technique [0002] Wind energy is a very important and huge resource. It is safe, clean, abundant and unlimited, and can provide an endless and stable supply of energy. The wind power industry is the fastest growing energy industry in the world. A transition based on renewable energy offers the best opportunity. With the emergence of the global energy crisis, countries all over the world have a strong interest in renewable energy. Wind energy is a clean and renewable energy, and wind power generation is the main form of wind energy utilization. With the rapid development of wind power and the continuous increase of installed capacity, large-scale wind power connected to the grid will not only provide clean energy, but also bring severe challenges to the saf...

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 Patents(China)
IPC IPC(8): H02J3/38
CPCY02A30/00
Inventor 杨锡运孙宝君李利霞李金霞刘舒
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)