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

Power system frequency situation prediction method based on deep learning

A power system, deep learning technology, applied in a single AC network with different frequencies, etc., can solve problems such as large errors, and achieve the effect of strong system adaptability, good generalization ability, and high precision of deep learning

Inactive Publication Date: 2019-05-21
YUNNAN POWER GRID
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a power system frequency situation prediction method based on deep learning to solve the problem of large error in the existing power system frequency situation prediction 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
  • Power system frequency situation prediction method based on deep learning
  • Power system frequency situation prediction method based on deep learning
  • Power system frequency situation prediction method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be further described below in conjunction with drawings and embodiments.

[0050] When the power system is subjected to active power disturbance, the dynamic change process of the system frequency can be expressed by the following differential equation:

[0051]

[0052]In the formula, Δf(t) is the system frequency deviation, H is the total inertia level of the system, D is the damping coefficient of the load, ΔPL is the active power imbalance caused by the disturbance event, ΔPG i (t) is the active power variation produced by the synchronous generator set participating in the frequency adjustment.

[0053] In order to make the technical solution of the present invention clearer, the deep learning method based on stacked extreme learning machine (SELM) used in the present invention is explained.

[0054] Extreme learning machine (extreme learning machine, ELM) is a single hidden layer feed-forward neural network, see figure 1 , the single...

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 power system frequency situation prediction method based on deep learning. By taking unit regulation power of a unit, an active power disturbance quantity, a unit inertia level, a unit switch state, a rotating reserve level and a damping coefficient as input variables, and taking a frequency extreme value, a maximum frequency change rate and a quasi-steady-state frequencyas output variables, the frequency stability after a disturbance event is comprehensively judged. According to a deep learning method based on a stack extreme learning machine, a nonlinear mapping relation between input and output is built through a deep framework; in the process of layer-by-layer unsupervised training from bottom to top, an automatic encoder algorithm and a regularization coefficient are introduced; and a weight matrix between an input layer and a hidden layer is optimized layer by layer, so that a deep learning network can effectively represent a complex function, and the prediction precision and the generalization ability are improved. The method is used for online prediction of a frequency situation of a power system; and corresponding emergency control measures can beformulated according to prediction conditions, so that the system frequency collapse is prevented.

Description

technical field [0001] The invention relates to the field of power system security, in particular to a deep learning-based power system frequency situation prediction method. Background technique [0002] After the power system is disturbed by active power, high-precision online prediction of the frequency situation of the system is of great significance to ensure the rapid start-up of protection devices such as low-frequency load shedding and high-frequency cut-off, as well as the stability of the grid frequency. According to frequency situation indicators such as extreme frequency, maximum frequency change rate and quasi-steady-state frequency, the transient frequency stability under disturbance accidents can be comprehensively judged. Due to the high-dimensional nonlinear characteristics of the power system, its state space is composed of a large number of differential equations, and it is difficult to obtain an accurate analytical expression of the frequency situation in...

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): H02J3/02
Inventor 肖友强赵荣臻文云峰司大军李玲芳
Owner YUNNAN POWER GRID
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