Microgrid energy storage scheduling method, device and equipment based on deep reinforcement learning

A technology of reinforcement learning and energy storage dispatching, applied in circuit devices, battery circuit devices, energy storage, etc., can solve problems affecting the stability of the power grid

Pending Publication Date: 2021-03-19
台州宏远电力设计院有限公司 +1
View PDF5 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the intermittence and volatility of renewable energy, directly integrating large-scale renewable energy into the grid will affect the stability of the grid.

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 energy storage scheduling method, device and equipment based on deep reinforcement learning
  • Microgrid energy storage scheduling method, device and equipment based on deep reinforcement learning
  • Microgrid energy storage scheduling method, device and equipment based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] Aiming at the characteristics that the microgrid system is faced with the random fluctuation and intermittency of renewable energy, and the load demand is difficult to predict accurately, the embodiment of the present invention provides a microgrid energy storage scheduling method based on deep reinforcement learning. The energy storage system agent passes Interact with the environment to obtain reward feedback to obtain the energy scheduling strategy of the energy storage system, including the following steps:

[0076] Step (1): Establish a corresponding simulation model based on the controlled new energy microgrid, specifically including the following sub-steps:

[0077] (1.1) Establish an energy storage system model: use a dynamic model to represent the energy storage system, P b (t) represents the charging or discharging power of energy storage at each time t, and the state of charge of the energy storage battery is represented by SOC(t), then the SOC dynamic model ...

Embodiment 2

[0127] Energy storage system agent building module: according to the simulation model of the controlled new energy microgrid, the microgrid energy storage scheduling is converted into a Markov decision problem, so as to establish the energy storage system agent;

[0128] Energy storage system agent training module: Train the energy storage system agent according to the forecast data of the microgrid. During the training, after the reward obtained by the energy storage system agent from the environment reaches a stable level, save the network parameters and the training ends;

[0129]Energy storage system scheduling module: use the trained energy storage system agent for the scheduling of the energy storage system in the microgrid. At each energy scheduling time in hours, the energy storage system performs the task according to the real-time power generation and load demand of the microgrid. Charge and discharge control.

Embodiment 3

[0131] An electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the depth-based A Reinforcement Learning Method for Microgrid Energy Storage Scheduling.

[0132] Electronic devices in the embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), and fixed terminals such as desktop computers.

[0133] An electronic device may include processing means (such as a central processing unit) that may perform various appropriate actions and functions in accordance with programs stored in a read-only memory (ROM) or loaded from a storage means into a random-access memory (RAM). deal with. In RAM, various programs and data necessary for the operation of electronic equipment are also stored. The processing means, ROM, and RAM are ...

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 microgrid energy storage scheduling method, device and equipment based on deep reinforcement learning, and the method comprises the steps: firstly building a simulation modelcorresponding to a controlled new energy microgrid according to the controlled new energy microgrid, and converting microgrid energy storage scheduling into a Markov decision problem according to themicrogrid simulation model; then, according to the day-ahead new energy power generation, load and electricity price data of the microgrid, training and establishing an energy storage system intelligent agent; in the training process, after awards obtained by the energy storage system intelligent agent from the environment reach stability, storing network parameters, and ending training; and finally, applying the trained energy storage system intelligent agent to the real-time scheduling of the microgrid energy storage system, and performing charging and discharging control on the energy storage system according to the real-time generating capacity and load demand of the microgrid at each energy scheduling time counted by hour. Renewable energy in the microgrid is fully utilized, impact of the renewable energy on the main power grid is reduced, and minimization of the operation cost of the microgrid is achieved.

Description

technical field [0001] The invention belongs to the technical field of power dispatching engineering, and in particular relates to real-time dispatching of a smart grid energy storage system. Background technique [0002] With the gradual consumption of traditional fossil energy, prominent environmental pollution and the growing demand for energy brought about by the development of human society, energy and environmental issues have attracted more and more attention from all countries in the world. The development and utilization of renewable energy is the solution to environmental pollution and energy crisis. effective means. However, due to the intermittence and volatility of renewable energy, directly connecting large-scale renewable energy to the grid will affect the stability of the grid. In order to make full use of renewable energy, the application of microgrid has been widely valued. Microgrid refers to a small power system composed of various distributed power sou...

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): G06Q50/06G06F30/27H02J3/00H02J3/32H02J7/00G06F113/04
CPCG06Q50/06G06F30/27H02J3/008H02J3/32H02J7/0048G06F2113/04H02J2203/20Y02E70/30
Inventor 高强王昕潘弘林烨叶丽娜杨强杨迷霞
Owner 台州宏远电力设计院有限公司
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