Photovoltaic output typical scene extraction method combined with spectral clustering algorithm

A technology of spectral clustering algorithm and extraction method, which is applied in the field of typical photovoltaic output scene extraction, can solve the problem that high-dimensional spatial data scenes are difficult to extract typical scenes, etc., to eliminate influence, eliminate long-term planning and operation and short-term scheduling, and meet the requirements of photovoltaic power generation. The effect of reasonable planning body conditions

Pending Publication Date: 2022-04-01
STATE GRID XINJIANG ELECTRIC POWER CO ECONOMIC TECH RES INST
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] For the extraction of typical scenes of photovoltaic output, the existing scene extraction method based on k-means is only suitable for extracting low-dimensional space data scenes, and it is difficult to extract reasonable typical scenes for high-dimensional space data scenes such as light intensity

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 output typical scene extraction method combined with spectral clustering algorithm
  • Photovoltaic output typical scene extraction method combined with spectral clustering algorithm
  • Photovoltaic output typical scene extraction method combined with spectral clustering algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] Taking the actual data of the Hetian area in Xinjiang in 2020 as an example to verify the method for extracting typical scenarios of photovoltaic output in the present invention.

[0069] Step S1: Use the given function formula to calculate the actual photovoltaic output, and convert the light intensity into photovoltaic output power through the photovoltaic output power calculation formula. The light intensity shown in Table 1 is obtained through the PVsyst7.2 software under the NASA database, and the following 12 light intensity data objects are taken as examples to extract the typical scene of photovoltaic output. The designed installed capacity is 5kW, and the area of ​​the 5kW photovoltaic panel is 35.58m 2 .

[0070] Table 1 Intensity of light in Hotan area in 2020 (W / m 2 )

[0071]

[0072]

[0073] Table 2 Photovoltaic output power in Hotan area in 2020 (kW)

[0074]

[0075] Step S2: The data objects numbered 1-12 in Table 2 are the given historical...

Embodiment 2

[0106] Taking the actual data of the Changji region of Xinjiang in 2020 as an example to verify the method for extracting typical scenarios of photovoltaic output in the present invention.

[0107] Step S1: Use the given function formula to calculate the actual photovoltaic output, and convert the light intensity into photovoltaic output power through the photovoltaic output power calculation formula. The light intensity shown in Table 1 is obtained through the PVsyst7.2 software under the NASA database, and the following 12 light intensity data objects are taken as examples to extract the typical scene of photovoltaic output. The designed installed capacity is 5kW, and the area of ​​the 5kW photovoltaic panel is 35.58m 2 .

[0108] Table 7 Illumination intensity in Hotan area in 2020 (W / m 2 )

[0109]

[0110] Table 8 Photovoltaic output power in Hotan area in 2020 (kW)

[0111]

[0112] Step S2: The data objects numbered 1-12 in Table 8 are the given historical data...

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 output typical scene extraction method combined with a spectral clustering algorithm, and relates to the technical field of renewable energy output prediction, a photovoltaic output typical scene is extracted based on the spectral clustering algorithm, clustering analysis can be carried out on data only through a similarity matrix between the data in the calculation process, and the calculation efficiency is improved. The spectral clustering algorithm can realize dimension reduction processing of high-dimensional data, and the result obtained by clustering the high-dimensional data of photovoltaic output is obviously superior to that obtained by a traditional mean value algorithm, so that a typical scene of photovoltaic output can be extracted more efficiently and accurately; the method solves the problem that an existing k-means algorithm is difficult to accurately cluster high-dimensional photovoltaic output data, realizes accurate description of randomness and volatility characteristics of photovoltaic output in a power distribution network, and eliminates the influence of photovoltaic output uncertainty on long-term planning operation and short-term scheduling in a power system. The photovoltaic reasonable planning body condition in the power distribution network is met, and safe, stable and environment-friendly operation and development of a power system are achieved.

Description

technical field [0001] The invention relates to the technical field of renewable energy output forecasting, in particular to a method for extracting typical scenarios of photovoltaic output combined with a spectral clustering algorithm. Background technique [0002] The output of the photovoltaic power generation system is affected by environmental factors such as the intensity of sunlight and temperature, resulting in large fluctuations and intermittency in its output. The foundations of the planning field have important theoretical and practical implications. [0003] For the extraction of typical scenes of photovoltaic output, the existing scene extraction method based on k-means is only suitable for extracting data scenes in low-dimensional space, and it is difficult to extract reasonable typical scenes for high-dimensional space data scenes such as light intensity. Contents of the invention [0004] In order to solve the above-mentioned technical problems, the presen...

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): G06Q10/06G06K9/62G06Q50/06
Inventor 陈伟伟曹茜边家瑜荆世博孙家文王新刚孙立成李忠政钟锐金梦李昌陵于志勇常鹏易庚周连凯安琪翟旭京宋海明张新伟于国康胡志云
Owner STATE GRID XINJIANG ELECTRIC POWER CO ECONOMIC TECH RES INST
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap