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

Photovoltaic power prediction method based on ground-based cloud picture image features

A technology of power forecasting and ground-based cloud images, applied in forecasting, image analysis, image enhancement, etc., to achieve simple, high-precision, and easy-to-implement effects

Active Publication Date: 2020-08-25
TIANJIN UNIV
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, there is no report on the accurate prediction of photovoltaic power by using the image features of ground-based cloud images

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
  • Photovoltaic power prediction method based on ground-based cloud picture image features
  • Photovoltaic power prediction method based on ground-based cloud picture image features
  • Photovoltaic power prediction method based on ground-based cloud picture image features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0112] The modeling samples come from the output power of Tianjin University photovoltaic power station in July, August, and September 2019 and the corresponding ground-based cloud images. There are a total of 2979 samples. After the samples are normalized, 80% of them are selected as The training set, and the remaining 20% ​​as the test set. Assuming the learning rate is 0.02, the maximum depth of the tree is 6, and the maximum number of iterations is 1000, the root mean square error of the obtained test set is 0.003472, R 2 The value is 0.933471. The results show that this method can achieve smaller error and higher accuracy in predicting photovoltaic power.

[0113] In the above test set, the comparison results between the actual value and the predicted value of the first 100 pieces of data are as follows: Figure 5 shown. Depend on Figure 5 It can be seen from the results that the predicted value is in good agreement with the actual value, which proves that the featur...

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 photovoltaic power prediction method based on ground-based cloud picture image features. The method comprises the following steps: S1, extracting illumination intensity, a high-frequency component, transmissivity, a zenith distance and cloud factor features based on a ground-based cloud picture; and S2, establishing a GBDT photovoltaic power prediction model, and constructing the GBDT photovoltaic power prediction model by taking image features such as the illumination intensity, the high-frequency components, the transmissivity, the zenith distance and the cloud factors extracted from the foundation cloud atlas as important feature quantities influencing photovoltaic power, thereby realizing accurate prediction of the photovoltaic power. The photovoltaic power prediction result obtained through the method has high precision and certain stability, and the method is simple and easy to implement.

Description

technical field [0001] The invention relates to the field of digital image processing technology and photovoltaic power prediction, in particular to a method for relatively accurate prediction of photovoltaic power by acquiring image features from ground-based cloud images. Background technique [0002] In recent years, renewable energy mainly based on solar energy has attracted more and more attention and application from all over the world. Among them, the most important way to utilize solar energy resources is photovoltaic power generation, and solar irradiance is one of the important factors affecting photovoltaic output power. The solar irradiance is affected by the movement of clouds, showing randomness and volatility, and the photovoltaic output power also has these properties. The ramp-up event caused by the sudden attenuation of photovoltaic output power not only consumes the life of solar cells, but also affects the stable operation of the main grid system. There...

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): G06Q10/04G06Q50/06G06T7/00G06T7/90G06T5/00
CPCG06Q10/04G06Q50/06G06T7/0002G06T7/90G06T2207/10032G06T2207/30192G06T5/73Y04S10/50
Inventor 路志英王泽涵周庆霞李鑫
Owner TIANJIN 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