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

Wind power prediction method and system based on image generation

A wind power prediction and image generation technology, applied in the field of wind power, can solve problems such as restricting development, insufficient historical data, and easy to be affected by external factors, and achieve high reliability

Pending Publication Date: 2021-08-24
NINGBO POLYTECHNIC
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the wind power climbing event is a small probability event. In a short period of time, historical data are insufficient, and the use of long-term data for statistics is easily affected by external factors, which restricts the development of this type of method.

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 prediction method and system based on image generation
  • Wind power prediction method and system based on image generation
  • Wind power prediction method and system based on image generation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Wind power ramp refers to the rapid change of power in a short period of time under the influence of extreme weather in the wind farm. It seriously threatens the stable operation and construction energy quality of the power grid. Such as image 3 As shown, the ramp events are divided into two categories: up ramp and down ramp according to the direction of power change. When weather such as hurricanes and showers occurs, the output power of the wind farm increases rapidly, which is an upslope event. When the wind turbine stops running on land, the output power of the wind farm drops rapidly, which is a downhill event. This paper conducts qualitative and quantitative analysis on ramping events, summarizes commonly used forecasting and evaluation indicators, and lays a theoretical foundation for the research of wind power ramping power prediction method based on GAN. Such as figure 1 As shown, the present invention proposes a wind power prediction method based on image...

Embodiment 2

[0069] In order to better understand the technical content of the present invention, this embodiment illustrates the present invention in the form of a system structure, such as figure 2 As shown, a wind power prediction system based on image generation, including:

[0070] The feature extraction module is used to normalize the historical wind power climbing image group, and extract the normalized image feature set according to the climbing characteristics;

[0071] Generate a confrontation network, which is used to generate a simulated wind power ramp image according to the combination of any image feature in the image feature set and the combination of the historical wind power ramp image;

[0072] Generate a confrontation network, which is also used to conduct discriminative training on historical wind power ramp images and simulated wind power ramp images under the total loss constraint, and obtain wind power ramp training image groups through the wind power ramp training...

Embodiment 3

[0077] In order to verify the effectiveness of the proposed wind power ramp-up power prediction model based on the generative confrontation network, this embodiment takes a specific verification experiment as an example, through the method described in the present invention, on a wind power data set in a certain area in Northwest China verify. Preprocess the historical climbing data to remove redundant information.

[0078] The data samples of slope climbing events in wind farms in recent years are selected for experiments. In order to ensure the number of climbing sample data and obtain a reasonable wind power prediction data set, the input data set of the model is Figure 4 The steps of are divided into the following parts: the sample wind power climbing data set is fed to the generative adversarial network, and the generator generates new climbing images. The original image and the generated image are used together as the input sample set (including 10% historical trainin...

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 wind power prediction method and system based on image generation, and relates to the field of wind power. The method specifically comprises the steps: carrying out normalization processing according to a historical wind power climbing image group, and extracting a normalized image feature set according to climbing features; generating simulated wind power climbing images through a generative adversarial network according to the combination of any image feature in the image feature set and the combination of historical wind power climbing images; performing discriminant training on the historical wind power climbing images and the simulated wind power climbing images under the constraint of total loss through the generative adversarial network, and obtaining a wind power climbing training image group; and substituting the historical wind power climbing images and the wind power climbing training images into a convolutional neural network model, and obtaining wind power prediction data by using a preset power prediction algorithm. According to the method, by judging the simulated wind power climbing images and the historical wind power climbing images, it is guaranteed that the obtained wind power climbing training image group better conforms to real wind power climbing data, and the reliability is higher.

Description

technical field [0001] The invention relates to the field of wind power, in particular to a wind power prediction method and system based on image generation. Background technique [0002] As an important boost to the development of human society, energy has brought serious environmental pollution problems to the earth while bringing rich material life and enjoyment. The use of traditional fossil energy will produce greenhouse gases such as carbon dioxide and sulfur oxides and toxic heavy metal particles such as mercury. Fossil energy is also facing the threat of resource depletion. Therefore, renewable clean energy has become the focus of research at home and abroad. Wind energy has the characteristics of large reserves, wide distribution, low pollution, and mature technology, and is widely favored by power systems. However, it is affected by wind speed, has natural randomness and intermittent nature, is unstable and difficult to control. Especially the ramp-up event of...

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): G06Q10/04G06Q50/06G06F30/27G06F113/06G06F119/02
CPCG06Q10/04G06Q50/06G06F30/27G06F2113/06G06F2119/02
Inventor 黄棋悦卢雄涛杜书语罗攀登江玮澄黄浩天王鑫伟张昊
Owner NINGBO POLYTECHNIC
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com