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

Photovoltaic array online modeling method based on reinforcement learning

A technology of reinforcement learning and photovoltaic array, applied in the field of solar photovoltaic power generation, can solve the problems of difficulty in guaranteeing model accuracy, inability to consider the reduction of photovoltaic system model accuracy, and long time consumption, etc., to achieve real-time fault detection or diagnosis, and improve operation and maintenance efficiency.

Active Publication Date: 2020-05-19
HOHAI UNIV CHANGZHOU
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] As the installed capacity of photovoltaic power plants at home and abroad has increased year by year in recent years, the mathematical modeling of photovoltaic systems, especially photovoltaic arrays, has attracted increasing attention. At present, the mathematical models of photovoltaic arrays mainly use single-diode or double-diode models based on equivalent physical models, and the model parameters Susceptible to environmental influences, conventional model parameter extraction methods are difficult to guarantee model accuracy under different environmental conditions, and cannot consider the reduction of model accuracy caused by photovoltaic system performance degradation, so the current model parameter extraction methods still have limitations; For the photovoltaic array current-voltage (I-V) curve, the meta-heuristic optimization algorithm is used to extract the model parameters. This method has high accuracy but can only guarantee the model accuracy under the current environmental conditions, and the parameter extraction process needs repeated iterative calculations, which is time-consuming and difficult. Guarantee the real-time performance of photovoltaic array online modeling

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 array online modeling method based on reinforcement learning
  • Photovoltaic array online modeling method based on reinforcement learning
  • Photovoltaic array online modeling method based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0025] Taking the Q-learning algorithm as an example, first establish a reinforcement learning model executor 101 with parameter a, parameter R s The reinforcement learning model executor 102, parameter R sh The reinforcement learning model executor 103 of the parameter dG and the reinforcement learning model executor 104 of the parameter dG, the initial output of each actuator is the parameters a and R solved under standard conditions s , R sh value, denoted as a ref , R s_ref , R sh_ref , the initial value of the parameter dG is set to 0, the reinforcement learning model executor 101 of the parameter a, the parameter R s The reinforcement learning model executor 102, parameter R sh The behaviors of the reinforcement learning model executor 103 and parameter dG of the reinforcement learning model executor 104 are set to three types, respectively:

[0026]

[0027]

[0028]

[0029]

[0030] where a k , R s,k , R sh,k 、dG k Output parameter value for the ...

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 array online modeling method based on reinforcement learning. A system for implementing the method comprises a reinforcement learning model actuator (101) of a parameter a, a reinforcement learning model actuator (102) of a parameter Rs, a reinforcement learning model actuator (103) of a parameter Rsh, a reinforcement learning model actuator (104) of a parameter dG, a single-diode model (105), an error calculation module (106), an estimation I-V curve and actual measurement I-V curve characteristic state extraction module (107), a return value calculationmodule (108), a power converter (201) with an I-V curve scanning function, an irradiance sensor (202) and a photovoltaic module temperature sensor (203). Online model parameter extraction and photovoltaic array I-V characteristic curve real-time calculation are realized through the reinforcement learning model actuator, and meanwhile, the model calculation precision and calculation speed are ensured.

Description

technical field [0001] The invention relates to the field of solar photovoltaic power generation, in particular to an online modeling method for photovoltaic arrays. Background technique [0002] As the installed capacity of photovoltaic power plants at home and abroad has increased year by year in recent years, the mathematical modeling of photovoltaic systems, especially photovoltaic arrays, has attracted increasing attention. At present, the mathematical models of photovoltaic arrays mainly use single-diode or double-diode models based on equivalent physical models, and the model parameters Susceptible to environmental influences, conventional model parameter extraction methods are difficult to guarantee model accuracy under different environmental conditions, and cannot consider the reduction of model accuracy caused by photovoltaic system performance degradation, so the current model parameter extraction methods still have limitations; For the photovoltaic array current...

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): G06F30/27G06N20/00
CPCG06N20/00Y02E60/00
Inventor 张经炜丁坤陈曦晖
Owner HOHAI UNIV CHANGZHOU
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