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

Inverter optimization control method based on reinforcement learning

A technology of reinforcement learning and optimal control, applied in the field of power system, can solve the problem that the inverter frequency and voltage cannot be guaranteed to be stable at the rated value, so as to solve the problem of insufficient accuracy and stability, easy implementation, and reduce frequency and voltage deviation. Effect

Active Publication Date: 2021-07-16
HEFEI UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For these reasons, when the system load changes, the frequency and voltage of the inverter cannot be guaranteed to be stable at the rated value

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 optimization control method based on reinforcement learning
  • Inverter optimization control method based on reinforcement learning
  • Inverter optimization control method based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] In this embodiment, an inverter optimization control method based on reinforcement learning, see Figure 1-Figure 4 , including the following steps:

[0069] Step 1. Construct the mathematical model of the inverter and the reinforcement learning control module such as figure 1 As shown, wherein, the reinforcement learning control module includes a strategy body for policy calculation and an executive body for action execution;

[0070] Step 1.1, modeling of inverter mathematical model:

[0071] Let the input of the inverter mathematical model be Indicates the action determined for the tth time during the nth training of the executive body; let the output state of the inverter mathematical model be And feed back to the executive body and the strategy body, among them, is the AC frequency at the next moment after the tth action when the inverter mathematical model executes the nth training, The AC voltage at the next moment after the t-th action when the n-th tra...

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 optimization control method based on reinforcement learning. The method comprises the following steps: 1, establishing a reinforcement learning control module and an inverter mathematical model; 2, establishing a local reward of reinforcement learning; 3, training a reinforcement learning module for performing inverter optimization control; and 4, performing inverter optimization control by applying the reinforcement learning module. According to the invention, the problem of a system frequency and a voltage deviation generated by the inverter can be overcome so that frequency recovery and voltage regulation can be effectively carried out, and stable operation of the inverter is ensured.

Description

technical field [0001] The invention relates to an inverter optimization control method based on reinforcement learning, which belongs to the field of power systems. Background technique [0002] In recent years, people are in a "mobile" era, mobile office, mobile communication, mobile leisure and entertainment. In the mobile state, people not only need low-voltage DC power supplied by batteries or storage batteries, but also need 220-volt AC power that is indispensable in daily environments, so the demand for inverters is also growing exponentially. On the one hand, people continue to develop new types of inverters; on the other hand, the optimization strategies of various inverters also greatly increase the efficiency and applicability of inverters. However, using traditional inverter control will produce frequency, voltage amplitude deviation and even circulating current during voltage conversion, which has become a major problem affecting the accuracy and stability of i...

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): H02M7/42H02M7/48
CPCH02M7/42H02M7/48
Inventor 孙伟吕秋硕黄磊朱世睿朱梦雨李奇越李帷韬
Owner HEFEI UNIV OF TECH
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