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

Multi-energy system energy scheduling method based on deep reinforcement learning

A technology of reinforcement learning and energy scheduling, applied in the field of smart grid, can solve problems such as difficulties in energy scheduling management of multi-energy systems

Active Publication Date: 2020-10-23
SHANGHAI JIAO TONG UNIV
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the pure electricity market, these factors bring great difficulties to the energy dispatch management of the multi-energy system

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
  • Multi-energy system energy scheduling method based on deep reinforcement learning
  • Multi-energy system energy scheduling method based on deep reinforcement learning
  • Multi-energy system energy scheduling method based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The following describes several preferred embodiments of the present invention with reference to the accompanying drawings, so as to make the technical content clearer and easier to understand. The present invention can be embodied in many different forms of embodiments, and the protection scope of the present invention is not limited to the embodiments mentioned herein.

[0043] Such as figure 1 As shown, it is a multi-energy trading market structure diagram; the main body is a three-layer structure, the first layer is the retail trading market, the second layer is the internal structure of producers and sellers, and the third layer is the local energy market. Producers and sellers can communicate with the retail energy market and trade in the local energy market.

[0044] A multi-energy market energy management scheme based on deep reinforcement learning proposed by the present invention includes the following steps:

[0045] Step 1: Construct a deep neural network ...

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 multi-energy system energy scheduling method based on deep reinforcement learning, and relates to the field of intelligent power grids. The method comprises the following steps that: step 1, before each transaction is started, a producer and seller selects an effective transaction action according to the energy price of a retail energy market, own energy requirements, energy storage and the historical transaction average price of a local energy market in a current transaction period; 2, the producer and salesman obtains the actual transaction volume in the retail energy market and the local energy market according to the effective transaction action; 3, the producer and salesman calculates the income or overhead of the current transaction period according to the actual transaction volume; 4, the producer and seller updates a transaction strategy according to experience, and enters the next transaction period; and step 5, the above steps are repeated until a stable transaction strategy is obtained. According to the scheme, effective conversion between energy can be achieved, the energy utilization rate is increased, and long-term benefits of producers and marketers are increased.

Description

technical field [0001] The invention relates to the technical field of smart grids, in particular to an energy scheduling method for multi-energy systems based on deep reinforcement learning. Background technique [0002] In recent years, the concept of an energy hub has been proposed. The energy hub realizes the conversion of various energy sources (eg, natural gas, electricity) through different energy carriers to achieve more efficient use of energy. Due to the integration of energy hub and smart grid, a smart multi-energy system is formed. At the same time, the emergence of the role of producers and sellers has naturally led to the emergence of local energy markets. In addition to the retail energy market, it also provides producers and sellers with additional energy trading options. Therefore, the design of multi-energy scheduling strategies is crucial to improving energy utilization in multi-energy systems. [0003] There have been some related works on the multi-ene...

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
IPC IPC(8): G06Q30/02G06Q40/04G06Q50/06G06N3/04G06N3/08
CPCG06Q30/0206G06Q40/04G06Q50/06G06N3/084G06N3/047Y04S10/50
Inventor 朱善迎王子馨于文彬杨博关新平
Owner SHANGHAI JIAO TONG UNIV
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