Correcting method of wind power generation system power real-time prediction

A wind power generation system and wind power technology, which are applied in the control of wind turbines, wind energy power generation, wind turbines, etc., can solve the problems of small battery capacity and environmental pollution of batteries, prolong the service life, reduce the battery capacity, and improve the prediction accuracy. Effect

Inactive Publication Date: 2014-01-01
HOHAI UNIV
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Of course, adding a battery energy storage system requires an increase in corresponding investment and maintenance costs. At the same time, waste batteries will also pollute the environment. Therefore, it is very important to choose a reasonable energy storage battery capacity so that it can meet the needs of wind power output smoothing. , power generation according to the prefabricated correction value, and the battery capacity can be relatively small, and the required battery capacity can be fully utilized as much as possible

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
  • Correcting method of wind power generation system power real-time prediction
  • Correcting method of wind power generation system power real-time prediction
  • Correcting method of wind power generation system power real-time prediction

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0043] Such as figure 1 , Figure 9 As shown, the correction method of the real-time power prediction of the wind power generation system includes the following steps.

[0044] Step 1, train the BP neural network with the historical numerical weather forecast data and the historical statistical data of the wind power output by the wind farm, and establish the nonlinear relationship between the weather forecast data and the wind power;

[0045] Step 2. On the sampling time series, predict the wind power according to the numerical weather forecast data, update the BP neural network training sample set and predict the wind power at each sampling time;

[0046] Step 3, according to the predicted wind power P at each sampling time p ’(t) and the actual wind power to get the predicted power error P e ’(t-1), the adaptive correction factor β is obtained from the predicted power error at each sampling moment, and then the expression P p "(t)=P p'(t)-β×P e '(t-1) get the first co...

specific Embodiment 2

[0050] As an optimized embodiment of the specific embodiment one, step 2 is as follows image 3 Specifically, the following steps are shown:

[0051] Step 2-1, collect the weather data of n sample points at the sampling time t as the input of the BP neural network, and predict the output power of the wind farm at the sampling time t+1 of the n sample points, where t and n are natural numbers;

[0052] Step 2-2, add the weather data of n sample points at sampling time t and the predicted wind farm output power of n sample points at sampling time t+1 as new samples to the BP neural network training sample set, and remove the current sampling time the first sample point on the sequence;

[0053] In step 2-3, add 1 to the value of t, enter the next sampling time, and repeat steps 2-1 to 2-2.

specific Embodiment 3

[0054] Specific embodiment three: a hardware method for improving the real-time power prediction accuracy of a wind power generation system based on a wind power prediction algorithm:

[0055] On the basis of specific embodiment 1 or 2, there is step A between step 2 and step 3, selecting the battery capacity of the energy storage system, and improving the accuracy of wind power real-time prediction from the hardware, specifically including the following steps:

[0056] Step A-1, such as Image 6 As shown, the upper and lower limit curves of power prediction are obtained according to the wind power at each sampling time predicted by the BP neural network:

[0057] Step a, the wind power P predicted by the current sampling time p ’(t) and the actual wind power P a (t) Obtain the predicted power absolute error mean value Pe;

[0058] Step b, then correct the wind power at the current sampling time by the absolute average value of the predicted power error to obtain the upper ...

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 a correcting method of wind power generation system power real-time prediction and belongs to the technical field of wind power generation system control. BP neural network prediction errors and training samples are corrected in real time and energy storage batteries are disposed in a wind power plant so as to increase wind power prediction accuracy. Capacity of the energy storage batteries is selected according to the relation of prediction results and errors. By the method, prediction precision is increased, wind power prediction errors are lowered with the energy storage batteries with the capacity low to the greatest extent, battery capacity is lowered, charging and discharging times of the batteries are reduced, service lives of the batteries are prolonged, and investment cost of a wind power generation system is reduced.

Description

technical field [0001] The invention discloses a correction method for real-time power prediction of a wind power generation system, and belongs to the technical field of wind power generation system control. Background technique [0002] In today's world, with the aggravation of environmental pollution and the depletion of traditional energy sources, wind power has become one of the most commercially potential and most dynamic renewable energy sources due to its clean use, low cost, and inexhaustible advantages. The "China Wind Power Development Report 2012" pointed out that by 2030, the cumulative installed capacity may exceed 400GW. At that time, wind power will account for about 8.4% of the country's power generation and about 15% of the power supply structure. Wind power generation has become the best choice for my country's electric power and energy sustainable development strategy, but wind power is a random and intermittent energy source, which leads to large fluctua...

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): F03D7/00
CPCY02E10/723Y02A30/00Y02E10/72
Inventor 潘文霞朱建红张程程全锐
Owner HOHAI UNIV
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