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

A Charging Spatiotemporal Prediction Method for Hybrid Isomorphic and Heterogeneous Deep Graph Neural Networks

A deep neural network, neural network technology, applied in the field of electric vehicles, can solve the problem that dynamic programming is not suitable for real-time control and so on

Active Publication Date: 2022-04-12
GUANGXI UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The charging spatio-temporal prediction method of hybrid isomorphic and heterogeneous deep graph neural network can be applied to complex road conditions and the distribution of charging piles with a large flow of people
The difference between this method and the traditional space-time prediction method of electric vehicle load based on dynamic traffic flow: (1) the multi-step adaptive dynamic programming can solve the real-time control problem that the traditional dynamic programming is not suitable for complex nonlinear systems; (2) the hybrid The charging space-time prediction method of the isomorphic and heterogeneous deep graph neural network is not only a simple prediction of the charging space-time, but also introduces a graph neural network to improve the accuracy of the method

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
  • A Charging Spatiotemporal Prediction Method for Hybrid Isomorphic and Heterogeneous Deep Graph Neural Networks
  • A Charging Spatiotemporal Prediction Method for Hybrid Isomorphic and Heterogeneous Deep Graph Neural Networks
  • A Charging Spatiotemporal Prediction Method for Hybrid Isomorphic and Heterogeneous Deep Graph Neural Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] A charging space-time prediction method of a mixed isomorphic and heterogeneous depth map neural network proposed by the present invention is described in detail in conjunction with the accompanying drawings as follows:

[0060] figure 1 is a schematic diagram of a hybrid isomorphic and heterogeneous deep graph neural network of the method of the present invention. A homogeneous network refers to a network in which all nodes have the same function in the network, that is, one user exchanges basic functions with the next user. For example, in a fixed telephone network, where each node (phone) performs essentially the same communication function as any other node, and people use phones for the same reasons, telecommunications networks are usually homogeneous (homogeneous) networks.

[0061] A heterogeneous network refers to a network in which nodes are divided into two or more classes by function and utility. For example, on the Honeybook marketplace network, event plan...

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 present invention proposes a charging space-time prediction method for a hybrid isomorphic and heterogeneous depth graph neural network, which includes a deep neural network module, a multi-step adaptive dynamic programming module, a graph neural network module and a hybrid isomorphic and heterogeneous module; depth The neural network module realizes the functions from automatic language translation to image recognition, and models high-complexity data through multi-layer nonlinear transformation; the multi-step adaptive dynamic programming module includes adaptive dynamic programming and adaptive multi-step correction methods for Solve the optimization control problem of large-scale complex nonlinear systems; the graph neural network module constructs the electric vehicle charging space-time prediction model; the hybrid isomorphic and heterogeneous module includes homogeneous networks and heterogeneous networks, and its function is to process similar and different types of information; the method It can effectively solve the problem that the electric vehicle charging load is random and difficult to predict in time and space.

Description

technical field [0001] The invention belongs to the technical field of electric vehicles, and relates to a charging space-time prediction method based on an artificial intelligence method, which is suitable for the distribution of charging piles of electric vehicles. Background technique [0002] Nowadays, problems such as energy shortage, climate warming and environmental pollution are becoming more and more serious. Motor vehicle exhaust pollution is one of the main sources of air pollution. Many countries and regions have formulated a timetable for banning the sale of fuel vehicles. For example, in March 2019, China's Hainan Province issued the "Development Plan for Clean Energy Vehicles in Hainan Province", which was the first in China to propose that the sale of fuel vehicles in the province be banned in 2030. Driven by policies and markets, the scale of electric vehicles and charging demand will usher in a new round of growth, and large-scale charging load access will...

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 Patents(China)
IPC IPC(8): G06Q10/04G06Q50/26G06N3/04
CPCG06Q10/04G06Q50/26G06N3/045
Inventor 殷林飞陈培文马晨骁高放
Owner GUANGXI 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