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

Short-term solar radiation prediction method and device based on CNN-LSTM

A solar radiation and site technology, applied in forecasting, neural learning methods, biological neural network models, etc., can solve the problems of high cost, poor short-term forecasting ability, low forecasting accuracy, etc., to improve accuracy, ensure optimal scheduling and safety The effect of stable operation

Active Publication Date: 2020-06-09
HOHAI UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: The purpose of this application is to provide a short-term solar radiation prediction method and device based on CNN-LSTM, using the CNN-LSTM model to predict short-term solar radiation, so as to solve the problem of poor short-term prediction ability, high cost and low prediction accuracy of existing technologies Defects

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
  • Short-term solar radiation prediction method and device based on CNN-LSTM
  • Short-term solar radiation prediction method and device based on CNN-LSTM
  • Short-term solar radiation prediction method and device based on CNN-LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] One aspect of the present invention provides a short-term solar radiation prediction method based on CNN-LSTM, such as figure 1 shown, including:

[0061] S101 takes the target site and adjacent sites as sample sites, and collects meteorological parameters and radiation data of the sample sites;

[0062] S102 forms a two-dimensional matrix based on the meteorological parameters of all sample sites, and reconstructs the spatial characteristics; including the following steps:

[0063] (21) The meteorological parameters of all sample sites at the time to be predicted are calculated according to image 3 The form constitutes a two-dimensional matrix, and each column represents a kind of meteorological parameter of all sites, and each row represents all meteorological parameters of a site; the elements of the two-dimensional matrix are represented by the following formula:

[0064] f i,j (i=1,2,...,S; j=1,2,...,S; j=1,2,...,F)

[0065] Among them, S represents the number...

Embodiment 2

[0087] On the other hand, the present invention also provides a short-term solar radiation prediction device based on CNN-LSTM, such as figure 2 As shown, it includes a data acquisition module 201, a spatial feature reconstruction module 202, a temporal feature reconstruction module 203, and a prediction module 204:

[0088] The data acquisition module 201 is used to use the target site and adjacent sites as sample sites to collect meteorological parameters and radiation data of the sample sites;

[0089] The spatial feature reconstruction module 202 is used to form a two-dimensional matrix based on the meteorological parameters of all sample sites, and reconstructs the spatial features; the spatial feature reconstruction module 202 includes a two-dimensional matrix construction unit and a correlation definition unit; wherein:

[0090] A two-dimensional matrix construction unit is used to form a two-dimensional matrix of meteorological parameters at the time to be predicted a...

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 short-term solar radiation prediction method based on CNN-LSTM, and the method comprises the steps: (1) taking a target site and an adjacent site as sample sites, and collecting the meteorological parameters and radiation data of the sample sites; (2) forming a two-dimensional matrix based on meteorological parameters of all sample stations, and reconstructing spatial features; (3) reconstructing time characteristics based on the historical solar radiation sequences of all the sample stations; and (4) respectively taking the spatial features and the time features as inputs of the CNN part and the LSTM part of the CNN-LSTM hybrid model, and predicting the total solar radiation of the target station. The invention further discloses a short-term solar radiation prediction device based on the CNN-LSTM. The method and the device are based on meteorological parameters and radiation data of a target site and peripheral sites. According to the method, the spatial features and the time features are reconstructed and input into the CNN-LSTM hybrid model to predict the solar radiation of the target station, so that the precision of solar radiation prediction is improved, and the optimal scheduling and safe and stable operation of a power system are guaranteed.

Description

technical field [0001] The invention relates to photovoltaic power generation, in particular to a CNN-LSTM-based short-term solar radiation prediction method and device. Background technique [0002] The current rapid economic development mainly relies on fossil fuels such as petroleum and coal, which has caused serious environmental pollution and greenhouse effect. Therefore, the development and utilization of renewable energy has attracted more and more attention worldwide. Among these energy sources, solar energy is one of the most promising options, especially in photovoltaic power generation. However, solar irradiance is random because it is affected by rapid changes in cloud cover. When large-scale photovoltaic power generation is connected to the grid, this randomness will seriously affect the safe operation of the grid. Therefore, establishing an accurate short-term solar irradiance prediction model is crucial to ensure optimal dispatch and management of power syst...

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): G06Q10/04G06N3/04G06N3/08
CPCG06Q10/04G06N3/049G06N3/08G06N3/045Y04S10/50
Inventor 臧海祥刘玲程礼临卫志农孙国强
Owner HOHAI UNIV
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