Ocean wind energy downscaling method based on deep learning neural network

A deep learning and neural network technology, applied in the field of offshore wind energy forecasting, can solve problems such as large downscaling errors, and achieve the effects of strong fault tolerance, improved forecasting accuracy, and high training efficiency

Active Publication Date: 2020-08-04
四川北控清洁能源工程有限公司
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the problem of large downscaling errors in the prior art, the purpose of the present invention is to provide a downscaling method suitable for marine wind energy based on deep learning neural network, so as to reduce the downscaling error

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
  • Ocean wind energy downscaling method based on deep learning neural network
  • Ocean wind energy downscaling method based on deep learning neural network
  • Ocean wind energy downscaling method based on deep learning neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0036] The invention discloses a method for downscaling marine wind energy based on a deep learning neural network, which includes the following steps:

[0037] S1. Collect for a period of time, daily sea surface 100m wind field data in 0.2-0.3° high-resolution reanalysis data, 1-3° sea surface 10m wind field and sea level air pressure field data in 1-3° low-resolution reanalysis data, 1-3 °Daily sea surface 10m wind field and sea level pressure field data from low-resolution global climate model data.

[0038] S2. Perform normalization processing on the data collected in step S1.

[0039] S2.1. Unify the resolution of the 1-3° low-resolution global climate model data to the same resolution as the 1-3° low-resolution reanalysis data through an interpolation expression, the interpolation expression is:

[0040]

[0041] Among them...

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 an ocean wind energy downscaling method based on a deep learning neural network. The method comprises: collecting for a period; performing 0.2-0.3 degree high-resolution reanalysis on day-by-day sea surface 100m wind field data in the data, performing 1-3 degree low-resolution reanalysis on day-by-day sea surface 10m wind field and sea level air pressure field data in the data, and performing 1-3 degree low-resolution global climate mode data on day-by-day sea surface 10m wind field and sea level air pressure field data in the data; carrying out normalization processingon the collected data; training a deep learning neural network model; and applying a deep learning neural network model to obtain 0.2-0.3 degree high-resolution day-by-day sea surface 100m wind fielddata after downscaling of the target area. According to the method, through the deep learning neural network, intrinsic characteristics and essential rules contained in the data are extracted, downscaling errors are reduced, and prediction of ocean wind energy is more accurate.

Description

technical field [0001] The present invention relates to a method for downscaling, in particular, the present invention relates to a method for downscaling ocean wind energy based on a deep learning neural network. The invention belongs to the technical field of marine wind energy prediction. Background technique [0002] my country's ocean wind energy resources are extremely rich, suitable for large-scale development and utilization. Since wind energy resources are a type of climate resources, climate change has a significant impact on wind energy resources. The study found that the surface wind speed in most areas of China showed a decreasing trend in the past few decades, resulting in a 15-17% decrease in the power generation of wind farms in some areas, which brought large economic losses to the invested wind farms. Therefore, it is necessary to scientifically predict the impact of future climate change on marine wind energy, and provide a feasible reference for the inv...

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): G06N3/04G06N3/08G06Q10/04
CPCG06N3/049G06N3/084G06N3/08G06Q10/04G06N3/045Y02A90/10
Inventor 张双益
Owner 四川北控清洁能源工程有限公司
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