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

A Fast Emergency Control Method Based on Deep Feedforward Neural Network and Numerical Integral Sensitivity

A feed-forward neural network and emergency control technology, which is applied in the direction of AC network circuit, AC network voltage adjustment, power network operating system integration, etc., can solve the problems of large amount of calculation and calculation speed that cannot meet the online calculation requirements of power system

Inactive Publication Date: 2020-07-14
ZHEJIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the shortcomings of the existing emergency control algorithm, which has a large amount of calculation and the calculation speed cannot meet the online calculation requirements of the power system in the calculation of the emergency control strategy of the power system, and provides a method based on deep feedforward neural network and numerical integration sensitivity. Rapid Emergency Control Methods

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 Fast Emergency Control Method Based on Deep Feedforward Neural Network and Numerical Integral Sensitivity
  • A Fast Emergency Control Method Based on Deep Feedforward Neural Network and Numerical Integral Sensitivity
  • A Fast Emergency Control Method Based on Deep Feedforward Neural Network and Numerical Integral Sensitivity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0093] The algorithm proposed by the invention is applied on the IEEE39 system for simulation. Classification neural network training samples are collected according to the following principles: (1) Generator output level and load level are randomly generated between 60% and 120%. (2) The combination of a certain generator output level and load level ensures that the power flow calculation results are reasonable. (3) The fault location setting includes three-phase short-circuit faults at both ends of each line; perform transient stability analysis according to the above conditions to extract transient stability performance indicators and transient stability constraint function values ​​as the input and output values ​​of the neural network for training to generate classification Neural network training sample set. All the transient instability samples in the above classification neural network training sample set form the fitting neural network training sample set.

[0094]T...

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 fast emergency control method based on a depth feedforward neural network and a numerical integral sensitivity. In this method, a two-layer deep feedforward neural network isconstructed, which consists of classification neural network and fitting neural network. Transient stability performance indexes are extracted as input of neural network through short-time numericalintegration. Transient stability evaluation and numerical calculation of transient stability constraint function are carried out through deep feedforward neural network. Combined with numerical integration sensitivity, the gradient and sensitivity of transient stability constraint function with respect to emergency control variables are obtained. Finally, according to the sensitivity of each control variable, the optimal control variable optimization method is used to obtain the final emergency control strategy. The invention converts the numerical integration on the original system into neural network calculation for most of the time, which greatly reduces the calculation amount while retaining the calculation property of the original system transient stability constraint function.

Description

technical field [0001] The invention belongs to power system automation, and relates to an emergency control method of a power system suitable for online computing, in particular to a fast emergency control method based on a deep feedforward neural network and numerical integral sensitivity. Background technique [0002] The continuous expansion of the power grid and the emergence of the power market have made the operating environment of the power system more complex, and the requirements for the safe and stable operation of the power grid are also getting higher and higher. Although there have been quite a lot of research results in the field of stability control systems in our country, there are still many deficiencies. The "offline calculation, real-time matching" method in the stability control has a large amount of calculation, and has poor adaptability to changes in the operation mode and network structure, and is prone to mismatch situations; "online pre-decision mak...

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): H02J3/00H02J3/14
CPCH02J3/00H02J3/14H02J2203/20Y02B70/3225Y04S20/222
Inventor 王建全高一凡肖谭南
Owner ZHEJIANG 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

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