Power generator intelligent agent based on depth deterministic strategy gradient algorithm and quotation method

A gradient algorithm, deterministic technology, applied in the field of electric power, which can solve the problem of discontinuous quotation coefficients of generator agents

Pending Publication Date: 2021-04-02
STATE GRID ZHEJIANG ELECTRIC POWER +3
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a power supplier intelligent body and a quotation method based on a deep deterministic strategy gra

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
  • Power generator intelligent agent based on depth deterministic strategy gradient algorithm and quotation method
  • Power generator intelligent agent based on depth deterministic strategy gradient algorithm and quotation method
  • Power generator intelligent agent based on depth deterministic strategy gradient algorithm and quotation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] see figure 1 As shown, this embodiment provides a power supplier agent based on a deep deterministic policy gradient algorithm, including: a deep deterministic policy gradient algorithm network building module, an exploratory quotation action generation module and a deep deterministic policy gradient algorithm training module.

[0052] The deep deterministic policy gradient algorithm network building block is used to establish the deep Actor network composed of Current Actor Network and Target Actor Network, the deep Critic network composed of Current Critic Network and Target Critic Network, and the experience replay library composed of Experience Replay memory. The input state vector is the market clearing price, and the output action is the quotation coefficient of the power supplier, and it is initialized.

[0053] The exploratory quotation action generation module is used to establish a power supplier’s market bidding model for electric energy, and generate a power...

Embodiment 2

[0088] This embodiment also provides a power supplier quotation method based on a deep deterministic strategy gradient algorithm, including:

[0089] (1) Establish a deep deterministic policy gradient algorithm network composed of Current Critic Network, Target Critic Network, Current ActorNetwork, Target Actor Network and Experience Replay memory, and initialize the network parameters;

[0090] (2) Establish a bidding model for power generators in the electric energy market, and select a bidding action based on the established market bidding model based on the results calculated by the CurrentActor Network, submit the power generator's quotation to the ISO for clearing, and report the current status of the power generator agent, Quote coefficients, rewards and new statuses are stored in Experience Replay memory;

[0091] (3) When the data stored in the Experience Replay memory is full, a batch of sample data is randomly selected for training of the deep deterministic policy g...

Embodiment 3

[0128] This embodiment also provides a power supplier quotation system based on a deep deterministic strategy gradient algorithm, which is applied to a power system, and the system includes: a processor and a memory coupled to the processor, and the memory stores a computer program , when the computer program is executed by the processor, the method steps as described in Embodiment 2 are implemented.

[0129] The following uses a 5-machine 5-node test system, such as figure 2 As shown, the simulation analysis of generator behavior in the electricity market is carried out. The 5-node test system contains 5 generators. G1 is connected to node 1, other nodes are connected to node 2, and loads are connected to node 3. The basic information of power generators is shown in Table 1, and the 24-hour load demand is shown in image 3 and Figure 4 shown.

[0130] Table 1

[0131]

[0132] The simulation parameters of the case setting are: the size of the Experience Replay memo...

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 power generator intelligent agent based on a depth deterministic strategy gradient algorithm and a quotation method, and the intelligent agent comprises: a depth deterministic strategy gradient algorithm network construction module which is used for establishing an experience playback library composed of a depth Actor network, a depth Critic network and an Experience Replay memory; and the exploratory quotation action generation module that is used for establishing a market bidding model of the power generator in the electric energy, selecting a quotation action according to a result calculated by the established market bidding model based on Current Actor Network, submitting the quotation of the power generator to ISO for clearing, and storing the current state,the quotation coefficient, the reward and the new state of the intelligent agent of the power generator corresponding to the clearing into Experience Replay memory. According to the invention, the dynamic quotation strategy of the power generator under incomplete information is searched through a deep reinforcement learning method, and the invention is an efficient quotation decision-making tool,and facilitates the more accurate quotation of the power generator in the power market.

Description

technical field [0001] The invention relates to electric power technology, in particular to an intelligent body of a power supplier and a quotation method based on a deep deterministic strategy gradient algorithm. Background technique [0002] With the emergence of the electricity spot market in the domestic market, power generators will gradually participate in the bidding of the electricity market to obtain their own interests. Under the market environment, participants always optimize their bidding strategies in order to obtain higher profits. At present, my country's electricity market is still in its infancy, and power generators are not yet familiar with the market environment, so they need a sound quotation strategy theory as a guide. An efficient quotation decision-making tool can help decision makers and quotation personnel make a successful quotation and obtain high profits. In addition, researching and deducing the quotation behavior of power generators will also...

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): G06Q30/06G06Q30/08G06Q50/06G06N3/04G06N3/08
CPCG06Q30/0611G06Q30/08G06Q50/06G06N3/08G06N3/045
Inventor 朱炳铨肖艳炜李继红项中明孙珂徐立中裘雨音孔飘红黄志华申建强王高琴史新红郑亚先杨争林冯树海王子恒
Owner STATE GRID ZHEJIANG ELECTRIC POWER
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