Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Graph-based earth surface solar radiance prediction method fusing space-time attention

A technology of solar irradiance and attention, applied in neural learning methods, biological neural network models, design optimization/simulation, etc., can solve problems such as low accuracy of solar irradiance prediction

Pending Publication Date: 2020-10-23
STATE GRID HEBEI ELECTRIC POWER CO LTD +3
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the accuracy of solar irradiance prediction by existing physical methods and statistical methods is not high, and propose a method for predicting surface solar irradiance based on graph-based fusion of space-time attention, thereby improving the prediction of solar irradiance. The accuracy of degree prediction

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
  • Graph-based earth surface solar radiance prediction method fusing space-time attention
  • Graph-based earth surface solar radiance prediction method fusing space-time attention
  • Graph-based earth surface solar radiance prediction method fusing space-time attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] figure 1 A schematic flow chart of a surface solar irradiance prediction method based on a graph-based fusion of space-time attention provided by an embodiment of the present invention; figure 1 with Image 6 As shown, the method includes the following steps:

[0044] Step 1: Select the SWR sub-grid covering the measured sites to construct the graph, and the meteorological grid points and the ground radiation measured sites are used as the nodes of the graph.

[0045] Specifically, use SWR (Short Wave Radiation) products and several ground radiation measurement sites to construct the map. The SWR product is a meteorological grid distributed in space 60N-60S, 80E-160W and with a resolution of 0.05°×0.05° provided by the meteorological satellite Sunflower-8 (such as figure 2 shown). The SWR sub-grid covering the measured sites is selected to construct the graph, and the meteorological grid points and the ground radiation measured sites are both used as the nodes of t...

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 graph-based earth surface solar radiance prediction method fusing space-time attention. The method comprises the following steps: selecting SWR sub-grids covering actual measurement sites to construct a graph, meteorological grid points and ground radiance actual measurement sites as nodes of the graph; representing the graph structure and the time information by using space embedding and time embedding; learning dynamic relationship associativity among nodes in the graph by using an attention mechanism fused with time and space; adding an attention transformation module between an encoder and a decoder, and modeling a historical and future relation through space-time embedding; and adopting the node characteristics of the actual measurement site as the input ofa decoder to predict the solar radiance. According to the method, the spatial-temporal correlation is fully considered, and the radiance can be predicted more accurately.

Description

technical field [0001] The invention relates to surface solar irradiance prediction technology, in particular to a graph-based method for terrestrial solar irradiance prediction with fusion of time and space attention. Background technique [0002] Solar irradiance refers to the radiant energy per unit area and unit time on the solid earth surface after solar radiation is absorbed, scattered and reflected by the atmosphere. Its unit is: Watt / square meter (W / m 2 ). Solar radiation is the most important external energy source and an important factor affecting photovoltaic power generation. Its small changes will also lead to changes in the global energy cycle, water, carbon and nitrogen cycles, and cause huge changes in the earth's environment, climate, and meteorology. Therefore, the prediction of solar irradiance is of great significance. According to the different principles of modeling methods, the models for predicting solar irradiance are basically divided into physic...

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): G06F30/27G06N3/04G06N3/08G06F111/08
CPCG06F30/27G06N3/08G06F2111/08G06N3/047G06N3/045
Inventor 尹瑞王珏张沛时珉王一峰王铁强王晓光刘晓艳姚铁锤王彦棡
Owner STATE GRID HEBEI ELECTRIC POWER CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com