CN113642229A - Sample generation method and device suitable for transient voltage stability evaluation - Google Patents
Sample generation method and device suitable for transient voltage stability evaluation Download PDFInfo
- Publication number
- CN113642229A CN113642229A CN202110771566.4A CN202110771566A CN113642229A CN 113642229 A CN113642229 A CN 113642229A CN 202110771566 A CN202110771566 A CN 202110771566A CN 113642229 A CN113642229 A CN 113642229A
- Authority
- CN
- China
- Prior art keywords
- sample
- stable
- generating
- samples
- generator
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Control Of Eletrric Generators (AREA)
Abstract
The invention provides a sample generation method and a sample generation device suitable for transient voltage stability evaluation, wherein the method comprises the following steps: selecting a sample space dimension and an adjusting range; generating an antagonistic neural network; samples are generated using an antagonistic neural network. The invention can effectively generate samples and cover most of sample space as much as possible. Compared with the traditional method for generating the uniformly distributed samples by manual selection intervention, the method disclosed by the invention is not influenced by the experience of researchers in personal power systems, has good stability, has certain inspiration when the samples are generated, and does not have the problem of dimension disaster when the traditional uniformly distributed method is applied to the generation of the large power grid samples.
Description
Technical Field
The invention relates to the technical field of power grids, in particular to a sample generation method and device suitable for transient voltage stability evaluation.
Background
In recent years, artificial intelligence methods such as deep learning and the like realize leap-type development, and great progress is made in the aspects of feature extraction and classification and judgment. The method has very strong fitting capability on nonlinear systems such as a power grid and the like, and aims at the aspect that an artificial intelligence method is applied to transient voltage stability evaluation, and samples for training an artificial intelligence model have obvious influence on the training effect of machine learning. Most of the sample generation methods at the present stage artificially randomly generate a sample space, the characteristic of stable transient voltage is not considered, and the coverage of the sample space is insufficient.
The artificial intelligence training sample generation method suitable for transient voltage stability evaluation at the present stage mainly has the following defects:
1. different personnel understand the transient voltage stability differently according to themselves, and the generated sample is relatively high in randomness, so that the problem of sample instability can occur.
2. Most of the adopted sample generation methods adopt multi-dimensional equal-interval uniform sampling, and often face the problem of dimension disaster caused by too large sample space.
Therefore, there is a need for improvements to the prior art sample production methods.
Disclosure of Invention
The invention aims to provide a sample generation method and a sample generation device suitable for transient voltage stability evaluation, which can solve the problems of unstable manually generated samples and dimension disaster caused by large sample space in the prior art.
The purpose of the invention is realized by the following technical scheme:
in a first aspect, the present invention provides a sample generation method adapted to transient voltage stability evaluation, including the following steps:
selecting a sample space dimension and an adjusting range;
generating an antagonistic neural network;
samples are generated using an antagonistic neural network.
Further, the anti-neural network includes a stable sample generator and an unstable sample generator.
Further, the generating an antagonistic neural network comprises:
randomly fluctuating the variable of each dimension in the sample space dimension under the influence of noise to generate a random sample space variable;
generating a stable sample for the randomly generated sample space variable by using a stable sample generator, and generating a destabilized sample for the randomly generated sample space variable by using a destabilized sample generator;
judging the stable sample or the unstable sample by using a stable/unstable sample discriminator to generate a correction parameter;
feeding back the correction parameters to the stable sample generator or the unstable sample generator, and correcting the stable sample generator or the unstable sample generator;
samples are generated using an antagonistic neural network.
In a second aspect, the present invention provides a sample generation apparatus adapted for transient voltage stability evaluation, including a selection and adjustment module, a random sample space variable generation module, a parameter setting module, and a sample generation module, wherein:
the selection and adjustment module is used for selecting the spatial dimension of the sample and the upper limit and the lower limit of adjustment of each dimension;
the random sample space variable generation module is used for adding noise influence to the selected space dimension to generate a random sample space variable;
the parameter setting module is used for judging the stable sample or the unstable sample, generating a correction parameter and feeding the correction parameter back to the sample generating module;
and the sample generation module comprises a stable sample generator and an unstable sample generator, and when in correction: inputting a random sample space variable to generate a stable sample or a destabilized sample, and correcting according to a correction parameter; after correction, it is used to generate samples.
In a second aspect, the present invention provides a computer storage medium, in which a computer program is stored, which, when executed, is capable of performing the above-described sample generation method adapted to transient voltage stability assessment.
The sample generation method and the sample generation device suitable for transient voltage stability evaluation can effectively generate samples and cover most of sample spaces as far as possible. Compared with the traditional method for generating the uniformly distributed samples by manual selection intervention, the method disclosed by the invention is not influenced by the experience of researchers in personal power systems, has good stability, has certain inspiration when the samples are generated, and does not have the problem of dimension disaster when the traditional uniformly distributed method is applied to the generation of the large power grid samples.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of the process of generating an anti-neural network according to the present invention;
FIG. 2 is a step diagram of a sample generation method adapted for transient voltage stability assessment according to the present invention;
fig. 3 is a schematic structural diagram of a sample generation apparatus adapted for transient voltage stability evaluation according to the present invention.
Detailed Description
The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure in the specification. It is to be understood that the described embodiments are merely illustrative of some, and not restrictive, of the embodiments of the disclosure. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
The invention discloses a sample generation method suitable for transient voltage stability evaluation, which comprises the following steps of:
and step S1, selecting a sample space dimension and an adjusting range.
According to the problem of transient voltage stability to be researched, selecting a sample space dimension which needs to be dynamically adjusted, such as total active power of a system, total reactive power of the system, bus load needing to be adjusted in a region to be researched and the type of the load on the bus, wherein the total active power of the system and the total reactive power of the system are strongly related to influence the transient voltage stability. The adjustment range is the upper and lower limits of the adjustment for each dimension in the sample space dimension.
And step S2, generating the antagonistic neural network.
Two sets of antagonistic neural networks are formed, one set is used for generating stable samples, the other set is used for generating unstable samples, and the structure of the sample is shown in figure 1. Wherein the sample space is the multi-dimensional sample space selected in step S1, and the variables of each dimension fluctuate randomly under the influence of noise, generating random sample space variables. The stable sample generator and the instability sample generator are two deep neural networks, the stable sample and the instability sample are generated according to input sample space noise, the stable/instability sample discriminator is electromechanical transient simulation software, whether the samples are stable in transient voltage or not can be judged through time domain simulation, and discrimination results are fed back to the stable sample generator or the instability sample generator to modify the neural networks so as to submit the generation accuracy.
Further, generating the antagonistic neural network comprises:
step S201, randomly fluctuating the variables of each dimension in the sample space dimensions under the influence of noise, and generating random sample space variables.
Step S202, generating a stable sample for the randomly generated sample space variable by using a stable sample generator, and generating a destabilized sample for the randomly generated sample space variable by using a destabilized sample generator.
Step S203, a stable sample or an unstable sample is judged by using a stable/unstable sample discriminator to generate a correction parameter.
And step S204, feeding back the correction parameters to the stable sample generator or the unstable sample generator, and correcting the stable sample generator or the unstable sample generator.
And step S3, generating a sample by using the antagonistic neural network.
A specified number of samples are generated using the stable sample generator or the unstable sample generator generated in step S2, based on the number of stable samples and the number of unstable samples set by the user.
The invention also provides a sample generation device suitable for transient voltage stability evaluation, which comprises a selection and adjustment module, a random sample space variable generation module, a parameter setting module and a sample generation module, wherein:
and the selecting and adjusting module is used for selecting the spatial dimension of the sample and the upper limit and the lower limit adjusted by each dimension.
And the random sample space variable generation module adds noise influence to the selected space dimension to generate a random sample space variable.
And the parameter setting module is used for judging the stable sample or the unstable sample, generating a correction parameter and feeding the correction parameter back to the sample generating module.
And the sample generation module comprises a stable sample generator and an unstable sample generator, and when in correction: inputting a random sample space variable to generate a stable sample or a destabilized sample, and correcting according to a correction parameter; after correction, it is used to generate samples.
The present invention also provides a computer storage medium in which a computer program is stored, and the above-described sample generation method adapted to transient voltage stability evaluation can be executed by running the computer program.
In the present invention, unless otherwise expressly stated or limited, the first feature may be "on" the second feature in direct contact with the second feature, or the first and second features may be in indirect contact via an intermediate. "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; may be mechanically coupled, may be electrically coupled or may be in communication with each other; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
The above description is for the purpose of illustrating embodiments of the invention and is not intended to limit the invention, and it will be apparent to those skilled in the art that any modification, equivalent replacement, or improvement made without departing from the spirit and principle of the invention shall fall within the protection scope of the invention.
Claims (5)
1. The sample generation method suitable for transient voltage stability evaluation is characterized by comprising the following steps of:
selecting a sample space dimension and an adjusting range;
generating an antagonistic neural network;
samples are generated using an antagonistic neural network.
2. The method of claim 1, wherein the anti-neural network comprises a stable sample generator and a destabilized sample generator.
3. The method of generating samples adapted for transient voltage stability assessment according to claim 1, wherein said generating a countering neural network comprises:
randomly fluctuating the variable of each dimension in the sample space dimension under the influence of noise to generate a random sample space variable;
generating a stable sample for the randomly generated sample space variable by using a stable sample generator, and generating a destabilized sample for the randomly generated sample space variable by using a destabilized sample generator;
judging the stable sample or the unstable sample by using a stable/unstable sample discriminator to generate a correction parameter;
feeding back the correction parameters to the stable sample generator or the unstable sample generator, and correcting the stable sample generator or the unstable sample generator;
samples are generated using an antagonistic neural network.
4. The sample generation device suitable for transient voltage stability evaluation is characterized by comprising a selection and adjustment module, a random sample space variable generation module, a parameter setting module and a sample generation module, wherein:
the selection and adjustment module is used for selecting the spatial dimension of the sample and the upper limit and the lower limit of adjustment of each dimension;
the random sample space variable generation module is used for adding noise influence to the selected space dimension to generate a random sample space variable;
the parameter setting module is used for judging the stable sample or the unstable sample, generating a correction parameter and feeding the correction parameter back to the sample generating module;
and the sample generation module comprises a stable sample generator and an unstable sample generator, and when in correction: inputting a random sample space variable to generate a stable sample or a destabilized sample, and correcting according to a correction parameter; after correction, it is used to generate samples.
5. A computer storage medium, in which a computer program is stored, wherein the computer program is operable to perform the method of any one of claims 1 to 3 for generating samples adapted to transient voltage stability assessment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110771566.4A CN113642229A (en) | 2021-07-08 | 2021-07-08 | Sample generation method and device suitable for transient voltage stability evaluation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110771566.4A CN113642229A (en) | 2021-07-08 | 2021-07-08 | Sample generation method and device suitable for transient voltage stability evaluation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113642229A true CN113642229A (en) | 2021-11-12 |
Family
ID=78416878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110771566.4A Pending CN113642229A (en) | 2021-07-08 | 2021-07-08 | Sample generation method and device suitable for transient voltage stability evaluation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642229A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110609477A (en) * | 2019-09-27 | 2019-12-24 | 东北大学 | Electric power system transient stability discrimination system and method based on deep learning |
| CN112017070A (en) * | 2020-07-17 | 2020-12-01 | 中国电力科学研究院有限公司 | Method and system for evaluating transient stability of power system based on data enhancement |
| US20200410041A1 (en) * | 2019-06-29 | 2020-12-31 | Wipro Limited | Method and system for data sampling using artificial neural network (ann) model |
-
2021
- 2021-07-08 CN CN202110771566.4A patent/CN113642229A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200410041A1 (en) * | 2019-06-29 | 2020-12-31 | Wipro Limited | Method and system for data sampling using artificial neural network (ann) model |
| CN110609477A (en) * | 2019-09-27 | 2019-12-24 | 东北大学 | Electric power system transient stability discrimination system and method based on deep learning |
| CN112017070A (en) * | 2020-07-17 | 2020-12-01 | 中国电力科学研究院有限公司 | Method and system for evaluating transient stability of power system based on data enhancement |
Non-Patent Citations (1)
| Title |
|---|
| 周艳真等: "基于数据增强和深度残差网络的电力系统暂态稳定预测", 中国电力, vol. 53, no. 1, pages 22 - 31 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102074955B (en) | Method based on knowledge discovery technology for stability assessment and control of electric system | |
| CN107294103B (en) | Section flow control method and device | |
| CN107590564B (en) | Transient stability constraint-based active power output adjustment method for power system | |
| CN106777732B (en) | Fatigue reliability analysis method considering random load and strength degradation | |
| CN109873425B (en) | Power system power flow adjustment method and system based on deep learning and user behavior | |
| CN103825269A (en) | Rapid probabilistic load flow calculation method considering static power frequency characteristics of electric power system | |
| CN109670213A (en) | A kind of wind power plant multimachine equivalent modeling method and device | |
| Kaveh et al. | Ground motion record selection using multi-objective optimization algorithms: A comparative study | |
| Yin et al. | Deep learning based feature reduction for power system transient stability assessment | |
| CN112054519B (en) | Power distribution network low voltage optimization treatment method, system and equipment | |
| CN110649588B (en) | Attack quantitative evaluation method for flexible direct-current transmission control system | |
| CN110969305B (en) | Photovoltaic power station simulation model parameter optimization method and system | |
| CN112564107A (en) | Transient stability assessment method for power system | |
| Wang et al. | Output feedback stabilization based on dynamic surface control for a class of uncertain stochastic nonlinear systems | |
| CN113536623B (en) | Topological optimization design method for robustness of material uncertainty structure | |
| CN104700156B (en) | A kind of wind power forecasting method based on support vector machines selection variables | |
| CN113642229A (en) | Sample generation method and device suitable for transient voltage stability evaluation | |
| CN109904863B (en) | Additional damping controller, hydraulic turbine speed regulator and hydraulic turbine control system | |
| CN110059457B (en) | Body-building method and device | |
| CN116204771A (en) | Power system transient stability key feature selection method, device and product | |
| CN114066214A (en) | Power quality analysis method based on multi-fusion convolutional neural network | |
| CN113794198A (en) | Method, device, terminal and storage medium for suppressing broadband oscillation | |
| Tammam et al. | A multi-objective genetic algorithm based PID controller for load frequency control of power systems | |
| CN108333940B (en) | Method and device for optimizing designated controller parameters | |
| CN113239643A (en) | Dynamic modeling method for automatic power generation control flow field of offshore wind plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |