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

Deep convolutional neural network tensor input construction method for electric power system analysis

A technology of power system and neural network, which is applied in the field of tensor input construction of deep convolutional neural network, can solve the problem that the distribution and correlation characteristics of power system input features cannot be considered, and achieve the effect of improving accuracy

Active Publication Date: 2019-06-07
SOUTHWEST JIAOTONG UNIV +1
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some deep learning methods, including multi-layer perceptrons, deep belief networks, etc., have also been applied to power system security analysis. However, the input feature quantities of all the above methods are in the form of vectors, and it is impossible to consider the power system input feature quantities in space. The distribution and correlation properties of

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
  • Deep convolutional neural network tensor input construction method for electric power system analysis
  • Deep convolutional neural network tensor input construction method for electric power system analysis
  • Deep convolutional neural network tensor input construction method for electric power system analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The invention is a deep convolutional neural network tensor input construction method for power system analysis, which can preserve the distance of power system nodes in space, reflect the spatial relevance of power system operation data, and construct a method suitable for deep convolutional neural networks. Multilayer 2D tensor data input to a product neural network. The present invention will be described in further detail below in conjunction with the accompanying drawings and specific implementation methods. The main implementation steps are: use electrical distance to represent the distribution of power system nodes in high-dimensional space, use t-distribution random proximity embedding method to reduce the high-dimensional space distribution of power system nodes to a two-dimensional plane, use multi-layer deep convolutional neural network The input construction method assigns different types of power system operating data to the two-dimensional plane node coord...

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 deep convolutional neural network tensor input construction method for electric power system analysis and evaluation. The deep convolutional neural network tensor input construction method for the electric power system analysis and evaluation comprises the steps that by using a space distribution representing method of electric power system nodes, an electrical distance between the nodes is described through contract impedance between arbitrary nodes of a power grid; and high-dimensional space node distribution represented by the electrical distance is subjected to dimensionality reduction to a two-dimensional plane by using a node space distribution dimensionality reduction method, and meanwhile, a distance relationship between the nodes of original high-dimensional space is kept. The deep convolutional neural network tensor input construction method is used, electric power system operation data is assigned to the nodes in the two-dimensional plane and a two-dimensional tensor characteristic pattern is obtained, and a plurality of two-dimensional tensor characteristic patterns are superimposed to obtain the electric power system operation data with a tensor form. The deep convolutional neural network tensor input construction method for the electric power system analysis and evaluation improves the precision of the electric power system analysis and evaluation.

Description

technical field [0001] The invention belongs to the technical field of power system safety analysis, and relates to a deep convolutional neural network tensor input construction method for power system analysis. Background technique [0002] The modern large power system forms a regional interconnected transmission pattern through high-voltage and ultra-high voltage AC-DC transmission. The interconnection of the power system makes the network structure more complex, the distribution area is wider, the components are more, and the dynamic behavior is more complex. On the other hand, new energy grid-connected with characteristics of randomness, volatility, and intermittency brings great uncertainty to the operation of the power system, increasing the power angle instability, frequency instability, and voltage instability of the system. stable risk. The stability of the power system is the key to the safe operation of the power grid. Once it is damaged, it will cause huge eco...

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): H02J3/00
Inventor 王晓茹林进钿田芳史东宇
Owner SOUTHWEST JIAOTONG 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