A neural network wind power prediction method and system

A wind power prediction and neural network technology, applied in the field of neural network wind power prediction, can solve the problems of unstable network learning and memory, disappearance of learning mode information, unstable network memory, etc., so as to improve equipment utilization and reliability, The effect of reducing spare capacity and enhancing generalization performance

Pending Publication Date: 2019-01-18
CHINA ELECTRIC POWER RES INST +3
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When learning new samples during BP neural network training, there is a tendency to forget old samples, that is, the learning and memory of the network are unstable. When a new memory mode is provided to a trained BP network, it will destroy the adjusted network connection weights. , leading to the disappearance of the learning mode information that has been memorized, and the defect of unstable network memory appears

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
  • A neural network wind power prediction method and system
  • A neural network wind power prediction method and system
  • A neural network wind power prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] From figure 1 It can be seen that a neural network wind power prediction method includes:

[0063] S1. Collect numerical weather forecast data at the predicted time;

[0064] S2. Substituting the numerical weather forecast data into a pre-built prediction model to obtain a predicted value of wind power;

[0065] The prediction model is constructed based on principal component analysis and neural network.

[0066] specific,

[0067] The data source of this calculation example is a wind farm in Manchester with a total installed capacity of 120MW. The original data includes wind farm power data measured at intervals of 5 minutes from 2010 to 2011; the numerical weather forecast data for the area where the wind farm is located includes air Density, pressure, temperature, wind speed and direction at 100m height.

[0068] Step 1: Determine the historical output power data of the wind farm and the numerical weather forecast data of this area, including air density, pressure, temperatur...

Embodiment 2

[0109] Based on the same inventive concept, a neural network wind power prediction system proposed by the present invention includes: a data acquisition module and a prediction substitution module;

[0110] The following two modules are further explained. The data collection module is used to collect the numerical weather forecast data at the predicted time;

[0111] The prediction substitution module is used to substitute the numerical weather forecast data into the pre-built prediction model to obtain the predicted value of wind power;

[0112] Wherein, the prediction model is constructed based on principal component analysis method and neural network.

[0113] Furthermore, it also includes the model building module,

[0114] The model building module is used to perform dimensionality reduction processing on the pre-collected historical time numerical weather forecast data according to the principal component analysis method;

[0115] Training the neural network model based on the hist...

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 neural network wind power forecasting method and system includes: collecting numerical weather forecasting data at forecasting time; the wind power prediction value is obtained by substituting the numerical weather forecast data into the prediction model constructed in advance. The prediction model is based on principal component analysis and neural network. The technical scheme of the inventioneffectively improves the prediction accuracy, shows that the method has certain feasibility and advancement in wind power prediction based on numerical weather prediction, and has certain advantagesin processing large sample data.

Description

Technical field [0001] The invention belongs to the technical field of wind power prediction, and specifically relates to a neural network wind power prediction method and system. Background technique [0002] The wind power industry continues to develop rapidly and the installed capacity continues to increase. Because wind energy is volatile and intermittent, fluctuations in generated power will cause voltage, frequency fluctuations and power quality problems. At the same time, there are also control of renewable energy units, power stations, and power station groups, and coordinated control with the grid to connect to the grid for safe and stable operation The problem. [0003] When the penetration rate of wind power is low, the volatility of wind power will not have a significant impact on the grid. With the rapid development of wind power, when the penetration rate of wind power is higher than the limit ratio, wind turbines connected to the grid will pose a serious threat to ...

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): G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06
Inventor 屈小云盛万兴吴鸣刘海涛寇凌峰徐毅虎侯小刚徐斌骆晨
Owner CHINA ELECTRIC POWER RES INST
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