Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Hydrogen-containing energy storage microgrid optimization operation method based on deep reinforcement learning

A technology of optimized operation and enhanced learning, applied in neural learning methods, design optimization/simulation, energy storage, etc., can solve problems such as slow convergence speed, inability to adapt to dynamic changes in source and load, and weak generalization, etc. Optimizing effect, improving micro-grid efficiency, and reducing operating costs

Active Publication Date: 2021-07-09
FUZHOU UNIV
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult for traditional planning algorithms to avoid local optimal solutions for nonlinear and non-convex problems. Heuristic algorithms can solve nonlinear and non-convex problems, but there are problems such as slow convergence speed and weak generalization
Moreover, the above algorithms often rely on the accurate prediction of the uncertainty of renewable energy output and load fluctuations, and cannot adapt to dynamic changes in source loads.

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
  • Hydrogen-containing energy storage microgrid optimization operation method based on deep reinforcement learning
  • Hydrogen-containing energy storage microgrid optimization operation method based on deep reinforcement learning
  • Hydrogen-containing energy storage microgrid optimization operation method based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] In order to make the features and advantages of this patent more obvious and easy to understand, the following special examples are described in detail as follows:

[0069] The hydrogen-containing energy storage microgrid optimization operation method based on the deep deterministic strategy gradient algorithm provided in this embodiment includes the following steps:

[0070] Step S1: Calculate the efficiency and input power of the electrolyzer, obtain the efficiency characteristic data of the electrolyzer, and construct the efficiency characteristic model of the electrolyzer by using the linear interpolation method of the look-up table.

[0071] Step S2: With the goal of minimizing the operating cost of the micro-grid, construct a hydrogen-containing energy storage micro-grid economy including a hydrogen energy storage system consisting of photovoltaic power generation devices, micro gas turbines, electrochemical energy storage, electrolyzers, hydrogen storage tanks, an...

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 provides a hydrogen-containing energy storage microgrid optimization operation method based on deep reinforcement learning, and the method comprises the steps: building an electrolytic cell efficiency characteristic model through a linear interpolation method, combining the electrolytic cell efficiency characteristic model with a gas turbine model, an electrochemical energy storage model, a hydrogen storage tank model, a fuel cell model and the like, and taking the microgrid operation cost as a target, constructing an optimized operation model of the hydrogen-containing energy storage micro-grid. And finally, solving a sequence decision problem of micro-grid optimization operation by adopting a depth deterministic strategy gradient algorithm. According to the method, the efficiency characteristic of the electrolytic cell is considered, the hydrogen energy storage capacity can be fully utilized, the optimization problem is solved according to the deep reinforcement learning principle, the operation cost of the hydrogen-containing energy storage microgrid is reduced, and good generalization is achieved.

Description

technical field [0001] The invention belongs to the technical field of power system optimization operation and scheduling, and in particular relates to a hydrogen-containing energy storage microgrid optimization operation method based on deep reinforcement learning. Background technique [0002] With the goal of "strive to reach the peak of carbon dioxide emissions before 2030 and strive to achieve carbon neutrality before 2060", how to improve the utilization rate of renewable energy and reduce carbon emissions has become a current research hotspot. However, a large amount of renewable energy in the microgrid is intermittent and random, which brings great challenges to the scheduling and operation of the microgrid. [0003] At present, the microgrid economic scheduling problem is usually solved using traditional planning algorithms or heuristic algorithms. However, it is difficult for traditional planning algorithms to avoid local optimal solutions for nonlinear and non-co...

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): G06Q10/06G06N3/04G06N3/08G06F30/20
CPCG06Q10/0637G06Q10/06312G06N3/08G06F30/20G06N3/045Y04S10/50
Inventor 朱振山翁智敏叶成涛陈哲盛郑海林吴诗雨
Owner FUZHOU 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
Eureka Blog
Learn More
PatSnap group products