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

Neural network prediction method for generated output of photovoltaic power station

A power generation and neural network technology, applied in forecasting, instrumentation, data processing applications, etc., to achieve great economic and social benefits, reduce adverse effects, and improve power generation efficiency

Inactive Publication Date: 2013-02-13
JIANGXI JIUJIANG POWER SUPPLY
View PDF3 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a neural network prediction method for photovoltaic power generation power, which solves the problem of online real-time prediction of photovoltaic power generation power, and has the characteristics of fast, accurate, intuitive and simple

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
  • Neural network prediction method for generated output of photovoltaic power station
  • Neural network prediction method for generated output of photovoltaic power station
  • Neural network prediction method for generated output of photovoltaic power station

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Such as figure 1 shown, including steps,

[0026] 1) Establishment of prediction model

[0027] In the power generation prediction model, only the data of the day before the prediction day is used, 12 hours at night are removed, and the power generation per hour is used as an input variable, a total of 12 data, and the average power generation corresponding to each hour is obtained through calculation;

[0028] The output power of the photovoltaic array per unit area is P=nSI (1?0.005(t + 25)), where n is the conversion efficiency; S is the array area; I is the solar radiation intensity; t is the atmospheric temperature;

[0029] 2) Design of prediction model

[0030] The BP neural network is used to design the photovoltaic array power generation prediction model. The BP neural network is a multi-layer forward network with one-way propagation. The output of the input layer node is equal to its input, and wij is the connection between the input layer and the hidden lay...

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 neural network prediction method for the generated output of a photovoltaic power station. According to the invention, a neural network model fitting corresponding function relationships can be established by using a BP (back-propagation) neural network with momentum according to temperatures and illuminations in meteorological history data and generated power history data, and the most similar historical situation can be found according to the weather conditions of the latest two hours, then accordingly, the generated power of the photovoltaic power station in a future period can be predicted. An operation of predicting the output power of a photovoltaic power station helps power grid dispatching departments to comprehensively arrange the coordination of conventional power sources and photovoltaic generated power, timely adjust dispatching plans, and reasonably arrange the running modes of power grids.

Description

technical field [0001] The invention relates to a neural network prediction method for the power generation of a photovoltaic power station, which establishes a neural network model that fits the corresponding functional relationship according to the historical meteorological data and historical power generation data, and predicts a period of time in the future based on the historical meteorological data and the established neural network model Power generation curve of photovoltaic power plant. Background technique [0002] Large-scale photovoltaic grid-connected power generation is an effective way to utilize solar energy, but the photovoltaic power generation system is affected by factors such as light intensity and ambient temperature, and its output power changes with uncertainty, which is not conducive to the grid dispatching department to arrange conventional power and photovoltaic power generation. Coordination of power generation. Therefore, it is necessary to stud...

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): G06Q10/04G06Q50/06
Inventor 张婕苏克明金涛胡世昊
Owner JIANGXI JIUJIANG POWER SUPPLY
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