Microgrid Distributed Online Scheduling Method and System Based on Hierarchical Reinforcement Learning

A technology of reinforcement learning and scheduling methods, applied in flexible AC transmission systems, electrical components, circuit devices, etc., can solve the problem of not considering the global constraints of the cooperative relationship, to reduce the sample size and computational complexity, reduce the learning dimension, Guaranteed feasibility

Active Publication Date: 2022-04-08
SHANDONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The prior art proposes multi-agent reinforcement learning algorithms for fully cooperative tasks, but where each agent must achieve its own complete goal, and does not consider satisfying the global constraints of the cooperative relationship

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
  • Microgrid Distributed Online Scheduling Method and System Based on Hierarchical Reinforcement Learning
  • Microgrid Distributed Online Scheduling Method and System Based on Hierarchical Reinforcement Learning
  • Microgrid Distributed Online Scheduling Method and System Based on Hierarchical Reinforcement Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] According to an embodiment of the present invention, a distributed online scheduling method for a microgrid based on hierarchical reinforcement learning is disclosed, which specifically includes the following steps:

[0052] (1) Obtain real-time electricity price information, total transaction power of each microgrid, power output of dispatchable units in each microgrid, output power of battery energy storage system, and charge / discharge efficiency data;

[0053] (2) Aiming at the lowest overall operating cost of all microgrids, an objective function for multi-microgrid online scheduling is established;

[0054] Specifically, the economic goal of managing multiple microgrids is to reduce the overall operating cost by coordinating all microgrids. The objective function consists of three parts: electricity transaction settlement Dispatchable unit power generation cost Total cost of charging / discharging battery energy storage system

[0055]

[0056] in, and ...

Embodiment 2

[0105] According to an embodiment of the present invention, a distributed online scheduling system for microgrids based on hierarchical reinforcement learning is disclosed, including:

[0106] The data acquisition module is used to obtain real-time electricity price information, the total transaction power of each microgrid, the power output of dispatchable units in each microgrid, the output power of the battery energy storage system, and the charging / discharging efficiency data;

[0107] The objective function building block is used to establish the objective function of multi-microgrid online scheduling with the goal of the lowest overall operating cost of all microgrids;

[0108] The objective function conversion module is used to convert the local constraints of the objective function of the multi-microgrid online scheduling into rules by embedding the knowledge of the set domain, and establish a knowledge-guided and data-driven multi-microgrid online scheduling model;

...

Embodiment 3

[0112] According to an embodiment of the present invention, an embodiment of a terminal device is disclosed, which includes a processor and a memory, the processor is used to implement instructions; the memory is used to store multiple instructions, and the instructions are suitable for being loaded and executed by the processor The distributed online scheduling method of microgrid based on hierarchical reinforcement learning described in the first embodiment.

[0113] In other embodiments, a computer-readable storage medium is disclosed, in which a plurality of instructions are stored, and the instructions are suitable for being loaded by the processor of the terminal device and executing the hierarchical reinforcement learning-based method described in Embodiment 1. Distributed online scheduling method for microgrid.

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 distributed online scheduling method and system for a microgrid based on layered reinforcement learning, including: obtaining real-time electricity price information, the total transaction power of each microgrid, and the power output of dispatchable units in each microgrid , the output power of the battery energy storage system and the charging / discharging efficiency data; aiming at the lowest overall operating cost of all microgrids, establish the objective function of multi-microgrid online scheduling; The local constraints of the objective function are converted into rules, and a knowledge-guided and data-driven multi-microgrid online scheduling model is established; a hierarchical reinforcement learning method for microgrid migration is designed, and the knowledge-guided and data-driven multi-microgrid online scheduling model is developed. Solve to get the optimal scheduling strategy that can make the overall operating cost of all microgrids the lowest. The invention improves the learning efficiency, reduces the long-term operation cost of the system and improves the operation stability of the system by embedding operation knowledge.

Description

technical field [0001] The invention relates to the technical field of distributed online dispatching of microgrids, in particular to a method and system for distributed online dispatching of microgrids based on layered reinforcement learning. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With people's growing concern about climate change and the decline in the cost of wind and solar power generation, the power system is accelerating the transition from an energy model that relies heavily on fossil fuels to a model that mixes a large amount of renewable energy. However, the forecast deviation of renewable energy in the system makes the power system with high proportion of renewable energy put forward higher requirements for rolling correction and self-adaptation. [0004] Microgrids provide a common interface for different types of dist...

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 Patents(China)
IPC IPC(8): H02J3/00H02J3/46H02J3/32
CPCH02J3/00H02J3/466H02J3/32H02J2203/10H02J2203/20Y02E40/10
Inventor 吕天光李竞郝然艾芊孙树敏李勇
Owner SHANDONG UNIV
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