Wind power medium-short term prediction method and system based on improved neural network

A neural network, short-term forecasting technology, applied in neural learning methods, biological neural network models, forecasting, etc., can solve problems such as wind power volatility

Pending Publication Date: 2020-04-24
国能陕西新能源发电有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, wind power is volatile and intermittent. As the proportion of grid-connected wind power systems in the grid continues to increase, it poses severe challenges to the safe and stable operation of the power system.

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
  • Wind power medium-short term prediction method and system based on improved neural network
  • Wind power medium-short term prediction method and system based on improved neural network
  • Wind power medium-short term prediction method and system based on improved neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0118] The historical wind power of the entire wind farm and the above characteristic data are collected and organized as training data, and the current data feature vector and actual wind power are collected in real time as subsequent historical data; among them, the characteristic data include: wind farm The real-time characteristic data and the actual wind power corresponding to the real-time characteristic data are collected once at the first preset time interval, such as the first preset If the duration is set to 30 minutes, the data will be collected every 30 minutes.

[0119] Further, as figure 2 As shown, using "unsupervised learning" to cluster wind turbines belongs to a kind of neural network. Each subset is a group, and each group will have a strong association with some potential factors.

[0120] For data set D={x 1 ,x 2 ,...,x m}, containing m unlabeled fan samples, each sample x i =(x i1 ,x i2 ,...,x in ) is an n-dimensional eigenvector, that is, the e...

specific Embodiment 2

[0164] Step 1: Collect the historical wind power and predicted wind power of a wind farm and the characteristic data values ​​affecting wind power: wind direction, air temperature, air pressure, humidity, wind speed, wind turbine height, wind turbine blade diameter, and wind turbine geographical location.

[0165] Step 2: According to the neural network clustering K-means algorithm, iteratively group the wind turbines in the wind farm.

[0166] Step 3: Carry out external and internal measurement of the fan grouping results. If there are external indicators, Jaccard index, FM index, and Rand index can be used. The larger the three index values, the better the clustering effect; the internal index DB index can also be used The Dunn index is used to measure, the smaller the DB, the larger the Dunn, the better the clustering and grouping effect.

[0167] Step 4: According to the historical characteristic data value and the real wind power, use the BP algorithm to establish the win...

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 a wind power medium-short term prediction method and a system based on improved neural network. The method comprises the steps of collecting historical feature data, real-timefeature data and actual wind power of a wind power plant; grouping the fans through loop iteration of a clustering K-means algorithm in a neural network according to the historical feature data; measuring a fan grouping result by adopting a clustering measurement standard; establishing a wind power prediction model for each group of fans according to the historical feature data, the actual wind power and a BP algorithm, and outputting the predicted wind power of each group of fans; summarizing the predicted wind power of each group of fans to obtain full-field predicted wind power; accordingto the clustering algorithm, grouping and grouping modeling are carried out to calculate the wind power, the cost is low, the dependent data size is small, the prediction precision is high, the calculation speed is high, and the reliability and safety of operation of the whole power system are improved.

Description

technical field [0001] The present invention relates to the technical field of generating power forecasting, in particular to a medium and short-term wind power forecasting method and system based on an improved neural network. Background technique [0002] A series of global problems such as global warming and the depletion of conventional fossil energy have aroused people's widespread attention to new energy. Compared with other renewable energy sources, wind power has more mature technology, higher efficiency and rapid development. As of the end of 2014, the cumulative installed capacity of wind power in the world reached 359.7GW. It is estimated that after 2018, with the healthy development of the market, the annual installed capacity of onshore wind power in the world will exceed 55GW. [0003] However, wind power is volatile and intermittent. As the proportion of grid-connected wind power systems in the grid continues to increase, it poses 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
IPC IPC(8): G06Q10/04G06Q10/06G06Q50/06G06N3/04G06N3/08G06K9/62
CPCG06Q10/04G06Q10/06393G06Q50/06G06N3/088G06N3/084G06N3/045G06F18/23213
Inventor 包鼎闫润田陈基伟张有金杨周杰朱得利
Owner 国能陕西新能源发电有限公司
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