Power flow checking method based on graph convolution network acceleration

A technology of convolutional network and power flow checking, applied in biological neural network models, instruments, multi-objective optimization, etc., can solve problems such as the inability to meet the real-time performance of system calculation and the increase of calculation amount.

Active Publication Date: 2021-01-29
ZHEJIANG UNIV +2
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional power flow calculations use numerical calculation methods to iteratively perform calculation tasks, which cannot meet the real-time requirements of system calculations.
In addition, in

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 flow checking method based on graph convolution network acceleration
  • Power flow checking method based on graph convolution network acceleration
  • Power flow checking method based on graph convolution network acceleration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The specific embodiments of the present invention will be further specifically described below through specific embodiments in conjunction with the accompanying drawings.

[0048] The present invention is a power flow checking method based on graph convolutional network acceleration, such as figure 1 shown, including the following steps:

[0049] 1) Collect power system topology data and network parameters, and generate a large number of power system operating states; use traditional power flow calculation methods to determine whether the generated power system operating states exceed the limit, and use whether the limit is exceeded as a label to obtain power system power flow calibration The kernel data set, and then the data set is divided into training data set and test data set; specifically:

[0050] The power system topology data includes the number of power system nodes N and the line connection relationship between each node. The power system network parameter ...

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 flow checking method based on graph convolution network acceleration, and the method comprises the steps: firstly collecting topological data and network parameters ofa power system, generating a large number of operation states of the power system, judging whether the generated operation states of the power system are out of limit or not through a conventional power flow calculation method, and taking whether the operation states of the power system are out of limit or not as a label; obtaining a power flow check data set of the power system; dividing the dataset into a training data set and a test data set; then establishing a graph convolution network model, and training to obtain the graph convolution network model used for accelerating power flow check; and finally, predicting the actual power system operation state data to obtain a power flow out-of-limit judgment result. According to the method, the graph convolution network model is establishedand trained to obtain the classification model capable of judging power flow out-of-limit, so that the calculation speed and efficiency of large-scale power grid power flow check can be improved.

Description

technical field [0001] The invention belongs to the field of static safety checking of power grids, and in particular relates to a power flow checking method based on graph convolution network acceleration. Background technique [0002] As the scale of the large power grid system becomes larger and the component models become more refined, the computational complexity of modern power system analysis becomes higher and the amount of calculation becomes larger; in addition, renewable energy, distributed storage and other new technologies are also becoming more and more complex. These trends have greatly increased the computing power requirements for power system analysis and calculation. Traditional power flow calculations use numerical calculation methods to iteratively perform calculation tasks, which cannot meet the real-time requirements of system calculations. In addition, in power grid power flow calculation, the Newton-Raphson method needs to solve a correction equatio...

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): G06F30/27G06K9/62G06N3/04G06F111/06G06F113/04
CPCG06F30/27G06F2111/06G06F2113/04G06N3/045G06F18/241G06F18/214
Inventor 姜威郭创新徐春雷
Owner ZHEJIANG 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
Try Eureka
PatSnap group products