Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Data analysis and combination primary function nerve network-based wind power prediction method

A technology of wind power forecasting and neural network, applied in AC network circuits, forecasting, data processing applications, etc., can solve problems such as long forecasting time, low forecasting accuracy, and short forecasting lead time

Inactive Publication Date: 2017-07-18
XINJIANG UNIVERSITY
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, a single forecasting method has its own limitations in forecasting and cannot guarantee stable and excellent forecasting accuracy for any data sample. Therefore, the establishment and application of a comprehensive forecasting model has received more and more attention
At present, most of the existing wind power prediction methods have shortcomings such as short prediction lead time, low prediction accuracy, and long prediction time.

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
  • Data analysis and combination primary function nerve network-based wind power prediction method
  • Data analysis and combination primary function nerve network-based wind power prediction method
  • Data analysis and combination primary function nerve network-based wind power prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The wind power prediction method of the present invention will be further described below in combination with specific examples.

[0075] (1) The 2014 annual output power sample data of a 1.5MW wind farm in Xinjiang is selected, and the time resolution is selected to be 10 minutes. The data on the 5th and 15th of each month are used as training samples, and the data on the 25th are used as forecast data. 5184 data as training and prediction data points, such as figure 2 .

[0076] (2) Parameter setting: Compared with the traditional neural network prediction model, each sub-network of the combined basis function neural network of the present invention avoids the selection of the network structure, and the input of the model depends entirely on the result of the phase space reconstruction; the state The parameters of the transfer algorithm are set as follows: the execution search group size (SE) is set to 80, the number of iterations is 500, the intermittent communicat...

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

A data analysis and combination primary function nerve network-based wind power prediction method is disclosed and relates to the field of wind power prediction. The method comprises the following steps: collected wind power data is subjected to data analyzing operation via variable mode decomposition operation, sample entropy technologies and phase space reconstruction technologies; four groups of subsequences are obtained; primary function nerve networks are built via orthogonal polynomials, and a combined primary function prediction model containing four groups of primary function nerve networks is built; a state transition algorithm is used for optimizing weight and threshold values of the primary function nerve networks, reconstructed subsequences are used as input for the primary function nerve networks, and the optimized prediction model combination primary function nerve networks are used for predicting wind power. Prediction accuracy of the method is markedly higher than that of a BP network and that of an RBF nerve network.

Description

technical field [0001] The invention relates to the technical field of wind power forecasting, and belongs to a wind power forecasting method based on data processing and a combined basis function neural network. Background technique [0002] The World Wind Energy Association announced at the end of 2016 that the world's total installed capacity reached 435 GW, with an overall growth rate of 17.2%. In the past ten years, wind power has become one of the fastest growing clean energy sources. However, the indirectness and randomness of wind force have a great impact on the stability of wind power generation system, which has become a huge challenge to the dispatching operation and safety and stability of the power system. Effective wind power forecasting can reduce power system reserve capacity, reduce system operating costs, and improve system economy and reliability. [0003] Wind power forecasting models mainly include physical forecasting models and statistical forecasti...

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): H02J3/00G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06H02J3/00H02J2203/20
Inventor 王聪张宏立范文慧马萍
Owner XINJIANG UNIVERSITY
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
Eureka Blog
Learn More
PatSnap group products