Inverter controller based on deep reinforcement learning

A reinforcement learning and inverter technology, which is applied in the direction of converting irreversible DC power input into AC power output, reducing the flickering of the AC network, and converting the output power, can solve the problem that it is difficult to cover the operating state of the inverter and cannot Ensure the stability of the controller and other issues

Active Publication Date: 2021-01-05
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In practice, these controller parameters are often selected through simulation and trial and error, which is difficult to cover all possible operating states of the inverter, and it is also impossible to guarantee that the designed controller can maintain stability in a complex operating environment.

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
  • Inverter controller based on deep reinforcement learning
  • Inverter controller based on deep reinforcement learning
  • Inverter controller based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0064]Such asfigure 1 As shown, the main circuit topology and control block diagram of the inverter controller of the present invention include power circuit, current and voltage measurement unit, controller, drive circuit and other modules. Combine belowfigure 1 , Specifically introduce the structure and function of each part:

[0065]1) Power circuit part: This part of the circuit includes the inverter DC side, three-phase full-bridge inverter circuit, LC filter and closing switch KM, etc., which are mainly used for the transmission of electric energy.figure 1 Middle, rfAnd LfIt is the equivalent inductance and resistance of the L part of the inductor in the inverter LC filter. Usually, this resistance is so small compared to the inductance that it can be ignored. CfIs the capacitor C in the inverter LC filter. r and L are the equivalent resistance and inductance of the transmission line from the inverter to the connected grid. UdcIt is the DC side power supply voltage, such as a bat...

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 an inverter controller based on deep reinforcement learning. The inverter controller comprises a dq conversion module, an output active, reactive and terminal voltage effectivevalue calculation module, a modulation wave signal amplitude calculation module, a simulation rotor motion equation module, a deep reinforcement learning control module, and a dq inverse transformation and PWM modulation module, wherein the inverter controller simulates a synchronous generator rotor motion equation, and adjusts the virtual moment of inertia through the deep reinforcement learningcontrol module so as to obtain a good power system low-frequency oscillation suppression effect.

Description

Technical field[0001]The invention relates to the technical field of power electronic inverters, in particular to an inverter controller based on deep reinforcement learning.Background technique[0002]In view of the pressure of energy and environmental protection, more and more renewable energy sources are connected to the grid through power electronic power generation equipment. As a kind of electric energy conversion equipment that can convert direct current to alternating current, inverters are widely used in wind power, energy storage, photovoltaic and other fields. The earliest inverter control strategy adopted a two-layer control structure, that is, the inner layer is a current loop, and the outer layer is a power loop or a voltage loop. However, the response speed of this control strategy is fast, which is not conducive to the stability of the frequency of the power system, and it cannot adaptively adjust the output power of the inverter according to the voltage and frequency ...

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): H02M7/48H02M7/5387H02M7/493H02M1/08H02M1/084H02M1/088H02J3/38H02J3/00
CPCH02M7/48H02M7/53871H02M7/493H02M1/084H02M1/08H02M1/088H02J3/381H02J3/002H02J2203/10H02J2203/20
Inventor 张昌华张坤徐子豪
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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