Photovoltaic power generation maximum power point tracking control method and device

A technology of maximum power point and photovoltaic power generation, which is applied in photovoltaic power generation, control/regulation systems, and regulation of electrical variables, etc., can solve problems such as dependence, complex system structure, and poor control accuracy, and achieve fast tracking, simple system structure, and difficult The effect of misjudgment

Active Publication Date: 2020-06-23
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional fixed voltage tracking method has simple control and fast tracking speed, but its control accuracy is poor in places where environmental conditions change drastically
Disturbance and observation method, this method has a simple overall structure and a small amount of disturbance parameters,

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 generation maximum power point tracking control method and device
  • Photovoltaic power generation maximum power point tracking control method and device
  • Photovoltaic power generation maximum power point tracking control method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] In this embodiment, aiming at the problems existing in the current photovoltaic power generation maximum power point tracking source, a photovoltaic power generation maximum power point tracking control method is proposed, specifically a photovoltaic power generation maximum power point tracking control method based on Q value reinforcement learning.

[0038] Using the Q value reinforcement learning method in the artificial intelligence method, the reinforcement learning is a model-free, self-learning control method. Based on the characteristics of reinforcement learning and autonomous learning, the control strategy proposed in this embodiment can overcome the shortcomings of traditional methods that require a large amount of accurate prior experience and are prone to misjudgment. The intelligent body continuously interacts with the Q meter to obtain the optimal strategy of the photovoltaic power generation maximum power point tracking control strategy, and track the photov...

Embodiment 2

[0076] Reference Figure 6-7 This embodiment proposes a photovoltaic power generation maximum power point tracking control device. The method of the above embodiment is implemented by this device, and specifically includes a photovoltaic model module 100. The photovoltaic model module 100 includes a photovoltaic power supply, DC / DC direct current Buck converter and resistive load; reinforcement learning module 200, including an agent interacting with the environment, the agent also including a state space model module 201, an action space model module 202, a reward function model module 203, and a Q value algorithm model module 204, respectively used to configure the state space model, the action space model, the reward function model and the Q value algorithm model to realize the intelligent tracking of the maximum power point of photovoltaic power generation.

[0077] More specifically, the maximum power point tracking structure of photovoltaic power generation based on reinforc...

Embodiment 3

[0083] In order to evaluate the effectiveness and accuracy of the control strategy proposed in this embodiment, this embodiment uses simulation to perform simulations under conditions such as fixed environmental conditions (light intensity, temperature) and changes in environmental conditions. The effectiveness and accuracy of the control strategy proposed in this embodiment are verified. In this embodiment, Python is used to design and develop a control method based on improved Q value reinforcement learning to track the maximum power point based on OpenAI Gym, aiming to quickly find the MPP point. In this set of simulations, this embodiment is based on the open circuit voltage V oc 37V, short-circuit current I SC Is 8A respectively in NOT environment (temperature is 25℃ and light amplitude is 1000W / m 2 ) And under STC environment (temperature is 47℃ and light amplitude is 800W / m 2 ) Perform simulation to verify the effectiveness of the control strategy proposed in this embo...

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 generation maximum power point tracking control method and device. The photovoltaic power generation maximum power point tracking control method comprises:conducting intelligent tracking on a photovoltaic power generation maximum power point in a photovoltaic model; continuously interacting with the environment by utilizing feedback signals of an intelligent agent in reinforcement learning, and adjusting and improving intelligent decision behaviors to obtain an optimal tracking strategy; and the intelligent agent deciding an optimal energy storagescheduling strategy, and tracking the photovoltaic power generation maximum power point in a continuously changing environment. The beneficial effects of the method are that the method is universal inalgorithm under the conditions of fixed environment conditions and no priori knowledge, is simple in system structure, is not liable to misjudge, and can accurately track the maximum power point. Under the condition of sudden change of environmental conditions, the maximum power point can be tracked more quickly by the control strategy.

Description

Technical field [0001] The present invention relates to the technical field of photovoltaic power generation maximum power point tracking source, in particular to a photovoltaic power generation maximum power point tracking control method and device based on reinforcement learning. Background technique [0002] In recent years, the industry has been searching for the maximum power point through traditional control theory methods. The traditional fixed voltage tracking method has simple control and fast tracking speed, but its control accuracy is poor in places where environmental conditions change drastically. Disturbance observation method. The overall structure of this method is simple, and the amount of disturbance parameters is small. However, this method requires a more accurate step size, and the method is prone to "misjudgment". The traditional conductance increment method has high tracking accuracy, but this method relies on a microprocessor or a digital signal processor...

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): G05F1/67
CPCG05F1/67Y02E10/56
Inventor 崔承刚钱申晟官乐乐杨宁张传林陈辉
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER
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