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

5G energy internet virtual power plant economic dispatching method based on edge intelligence

An energy Internet and virtual power plant technology, which is applied in the field of 5G energy Internet virtual power plant economic dispatch based on edge intelligence to achieve the effects of reducing costs, reducing consumption and reducing demand

Active Publication Date: 2020-04-24
STATE GRID HEILONGJIANG ELECTRIC POWER COMPANY +1
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem of how to integrate new energy sources to reduce the cost of the power system and reduce the consumption of communication, and proposes an economic scheduling method for 5G energy Internet virtual power plants based on edge intelligence

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
  • 5G energy internet virtual power plant economic dispatching method based on edge intelligence
  • 5G energy internet virtual power plant economic dispatching method based on edge intelligence
  • 5G energy internet virtual power plant economic dispatching method based on edge intelligence

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0026] Specific implementation mode 1: An edge intelligence-based 5G energy Internet virtual power plant economic scheduling method described in this implementation mode, the method includes the following steps:

[0027] Step 1. Construct an Actor-Critic architecture including actor target network, actor estimation network, critic target network and critic estimation network;

[0028] Step 2. Input the state s of the virtual power plant into the actor estimation network;

[0029] Step 3: Use deterministic policy gradient to select the action a corresponding to the state s, and then use the state s and action a to calculate the reward function R and the next state s′, and obtain an experience fragment (s, a, R, s′ ), and store the obtained experience fragments (s, a, R, s′) into the experience pool;

[0030] Step 4. Input the state s' into the actor estimation network;

[0031] Step 5. Repeat the process of step 3 and step 4 until the termination state is reached to complete ...

specific Embodiment approach 2

[0055] Specific implementation mode two: the difference between this implementation mode and specific implementation mode one is:

[0056] The actor target network is a deep neural network composed of 3 hidden layers fully connected with 10 neural units per layer, and the structure of the actor estimation network is the same as that of the actor target network;

[0057] The critic target network is a deep neural network composed of 5 hidden layers fully connected with 20 neurons in each layer, and the structure of the critic estimation network is the same as that of the critic target network.

specific Embodiment approach 3

[0058] Specific embodiment three: the difference between this embodiment and specific embodiment one is: the neuron activation functions of the hidden layer of the actor target network, actor estimation network, critic target network, and critic estimation network are all relu functions, and the neuron activation functions of the output layer The activation functions are all linear activation functions.

[0059] The weight is initialized to mean 0, the covariance matrix is ​​1, the PC used in the experiment is 4-core CPU Inter(R)core i7-5770, 8GB of RAM and GPU is RTX 1060, 5G RAM machine, python is 1.36.0 Version.

[0060] For the Critic estimation network, its loss function is the mean square error of Q estimation and Q reality, namely:

[0061]

[0062] For the actor estimation network, its loss function is different from that of DPG, because it is a deep deterministic strategy. Then the defined loss gradient is:

[0063]

[0064] Actor estimation network loss func...

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 5G energy internet virtual power plant economic dispatching method based on edge intelligence, and belongs to the technical field of virtual power plant cost optimization. According to the invention, the problems of how to integrate new energy to reduce the cost of the power system and reduce the consumption of communication are solved. According to the invention, machinelearning and edge calculation are combined, and an edge intelligent structure is provided for solving the problem of economic dispatch in the energy internet vpp. Compared with traditional edge computing, the structure inherits original characteristics, the burden of cloud computing is reduced, and the computing capacity of edge computing is improved. By splitting the model and deploying part ofthe model at the terminal, real-time control can be conveniently carried out, and the cost of the power system is reduced. Due to mutual transmission between the split model and the corresponding model, only part of information and gradient information are effectively transmitted, communication consumption is reduced, and the requirement for the communication environment is reduced. The method canbe applied to economic dispatching of the virtual power plant.

Description

technical field [0001] The invention belongs to the technical field of cost optimization of virtual power plants, and in particular relates to an economic scheduling method for 5G energy Internet virtual power plants based on edge intelligence. Background technique [0002] In recent years, with the integration of a large number of distributed energy systems in the power system, how to effectively access and control distributed energy sources has become a mainstream issue. The distributed energy system is mainly composed of two distributed energy sources, including distributed new energy systems, such as photovoltaic power generation, wind power generation, etc., and distributed traditional energy systems, such as gas turbine power generation and diesel generators. Among them, the control of distributed new energy systems is challenging. This is due to the unstable and unsustainable characteristics of distributed new energy. Moreover, a large number of distributed new ener...

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): G06Q10/06G06Q50/06H04W24/02H04W24/06
CPCG06Q10/06312G06Q50/06H04W24/02H04W24/06Y02D30/70Y04S10/50Y02E40/70
Inventor 彭宇关心孙迪房大伟
Owner STATE GRID HEILONGJIANG ELECTRIC POWER COMPANY
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