CN106709593A - Electric power system reliability prediction method - Google Patents
Electric power system reliability prediction method Download PDFInfo
- Publication number
- CN106709593A CN106709593A CN201611021845.4A CN201611021845A CN106709593A CN 106709593 A CN106709593 A CN 106709593A CN 201611021845 A CN201611021845 A CN 201611021845A CN 106709593 A CN106709593 A CN 106709593A
- Authority
- CN
- China
- Prior art keywords
- sample
- matrix
- power system
- augmentation
- small sample
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000005516 engineering process Methods 0.000 claims abstract description 24
- 230000003190 augmentative effect Effects 0.000 claims abstract description 15
- 238000005070 sampling Methods 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 35
- 230000003416 augmentation Effects 0.000 claims description 34
- 210000005036 nerve Anatomy 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims 1
- 230000011218 segmentation Effects 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 abstract description 5
- 238000010835 comparative analysis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 230000007812 deficiency Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an electric power system reliability prediction method. A BP-based artificial neural network reliability prediction method is provided and discussed by aiming at the present situation that the fault-environment related samples are rare in an electric power system by comparative analysis of two small sample augmented technologies-the bootstrap small sample augmented technology and the kernel density Latin hypercube sampling augmented technology. The most accurate total fault time indictor prediction result can be given so that the problem of accurate prediction of electric power system operation reliability under the condition of insufficient data samples can be solved.
Description
Technical field
The present invention relates to Power System Intelligent monitoring technology field, more particularly, to Power System Reliability prediction side
Method.
Background technology
At present, conventional electric power system operation reliability Predicting Technique is mostly based on specific reliability model of unit and sets out,
Failure dependency, the method for operation and trend distribution etc. is considered on the basis of factor, by parsing computing or statistical number
The modes such as value simulation are calculated by the The Reliability Indicas of Gereration System of normalized by definition.Refer to clearly to set up input factor and output
The modeling method of target functional relation, above-mentioned existing logic-based reasoning or statistical analysis, generally requires in metastable net
In frame structure or gedanken experiment environment, enough event samples and the environmental characteristic information being closely related are obtained as far as possible, it is this
Electric power of the data demand for contemporary some industries mostly in the fast-developing continuous transformation with environmental factor of grid structure
System is excessively harsh.Such as, the big data power system construction that power grid enterprises are carried out at this stage is just gradually forming a kind of clothes
It is engaged in the data driven type modeling analysis environment of Operation of Electric Systems planning fail-safe analysis.Big data has species how high, number
Amount is huge, and renewal speed is fast and 4V features with a high credibility, is that Power System Reliability is studied in the way of data driven type is high
Dimension complex nonlinear relation provides new approach.
At present, prior art proposes reliability index modeling and the Numerical Predicting Method of data driven type, and these methods are still
So using sufficient information as premise, in practical power systems, due to power system upgrading, redundancy is high and record is lacked
Etc. aspect influence, the more rare situation generally existing of effective fault sample data.
So, it is necessary to solve power train in the case of data sample deficiency under the not perfect enough overall situation of big data environment
The accurate accuracy problem of system reliability prediction.
The content of the invention
The present invention provides a kind of Power System Reliability for overcoming above mentioned problem or solving the above problems at least in part
Forecasting Methodology.
According to an aspect of the present invention, there is provided a kind of Power System Reliability Forecasting Methodology, including：Step 1, utilizes
Bootstrap augmentation technology or cuclear density Latin Hypercube Sampling augmentation technology carry out primary to each influence factor data small sample
Augmentation, obtains primary augmented matrix AE；Step 2, based on primary augmented matrix AECarry out single output nerve network training, by
The predicted value of single each factor of influence of output nerve network inputs of the acquisition, and then obtain the predicted value of reliability index.
The application proposes a kind of Power System Reliability Forecasting Methodology.The application is for failure-ring in current power system
The more rare present situation of border association sample, by two kinds of small sample augmentation technologies of comparative analysis --- bootstrap small samples increase
Wide technology and cuclear density Latin Hypercube Sampling augmentation technology, propose and have inquired into a kind of based on BP artificial neural network reliabilities
Forecasting Methodology.The present invention can provide failure total time index prediction result the most accurate, solve data sample deficiency feelings
Under condition, the problem of Operation of Electric Systems reliability Accurate Prediction.
Brief description of the drawings
Fig. 1 is according to a kind of overall flow schematic diagram of Power System Reliability Forecasting Methodology of the embodiment of the present invention；
Fig. 2 be according to a kind of Power System Reliability Forecasting Methodology of the embodiment of the present invention utilize bootstrap technologies when pair
The schematic diagram of the discrete sample distribution after sample data expansion；
Fig. 3 be according to a kind of Power System Reliability Forecasting Methodology of the embodiment of the present invention utilize bootstrap technologies when pair
The schematic diagram of the Gaussian Kernel Density after sample data expansion；
Fig. 4 is to utilize a kind of Small Sample Database augmentation according to a kind of Power System Reliability Forecasting Methodology of the embodiment of the present invention
The schematic diagram of the Gaussian Kernel Density after expanding sample data during method；
Fig. 5 is to utilize a kind of Small Sample Database augmentation according to a kind of Power System Reliability Forecasting Methodology of the embodiment of the present invention
The schematic diagram of the Gaussian Kernel Density after expanding sample data during method；
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiment of the invention is described in further detail.Hereinafter implement
Example is not limited to the scope of the present invention for illustrating the present invention.
In Fig. 1, in a specific embodiment of the invention, show that a kind of Power System Reliability Forecasting Methodology flow is illustrated
Figure.Generally, including：Step 1, using bootstrap augmentation technology or cuclear density Latin Hypercube Sampling augmentation technology to each
Influence factor data small sample carries out primary augmentation, obtains primary augmented matrix AE；Step 2, is entered based on primary augmented matrix AE
Row list output nerve network training, by the predicted value of the single each factor of influence of output nerve network inputs to the acquisition, enters
And obtain the predicted value of reliability index.
In another specific embodiment of the invention, a kind of Power System Reliability Forecasting Methodology, including：Step 1, utilizes
Bootstrap technologies or be fitted based on cuclear density and consider small sample correlation Latin Hypercube Sampling small sample augmentation skill
Art carries out primary augmentation to each influence factor data small sample, obtains matrix AE∈RN×(M+1)；Step 2, based on matrix AE∈RN ×(M+1)Single output nerve network training is carried out, by the prediction of the single each factor of influence of output nerve network inputs to the acquisition
Value.
In another specific embodiment of the invention, a kind of Power System Reliability Forecasting Methodology, by described in step 2
The predicted value of single each factor of influence of output nerve network inputs of acquisition includes, it is assumed that described single output nerve that training is obtained
Network has an input layer (the 0th layer), M hidden layer and an output layer (M+1 layers), concretely comprises the following steps：Given S(0)
The predicted value of individual influence factor, is designated as vectorial I (0), according to formula (1) and formula (2) with progressive relationship, you can calculate output layer
O(M+1)J () is：
o(k+1)(j)=h(k+1)[n(k+1)(i)] (2)
Wherein, o(0)(j)=I(0)(j),S(k)The k layers of neuron number for being possessed in ground is represented, it is all interior
The symbol for sealing ω and b printed words represents the parameter that neutral net determines by training, for any k layers, h (x)=2/ (1+
exp(-2*x))-1。
In another specific embodiment of the invention, a kind of Power System Reliability Forecasting Methodology.Core is based in the step 1
Density is fitted and considers the Latin Hypercube Sampling small sample augmentation technology of small sample correlation to each influence factor data sample
Originally primary augmentation is carried out, primary augmented matrix A is obtainedEIncluding：Step 11, based on each influence factor data sample, independently
Carry out imparametrization Gaussian Kernel Density estimation；Based on gained Gaussian Kernel Density, Latin Hypercube Sampling is carried out to each variable, by institute
The out of order arrangement of sample is obtained, sample battle array A is obtained；Step 12, tries to achieve A correspondence Spearman coefficient of rank correlation matrixes RA, based on RAEnter
Row Cholesky is decomposed and is obtained inferior triangular flap LRA；A correspondence Van Der Waerden Score matrix Vs are tried to achieve, V correspondences are tried to achieve
Spearman coefficient of rank correlation matrixes RV, based on RVCarry out Cholesky decomposition and obtain inferior triangular flap LRV；Based on the LRA、LRV
Obtain variable grade Description MatrixStep 13, by A according toMiddle arrangement of elements mode is rearranged and obtains augmented sample square
Battle array AE。
In another specific embodiment of the invention, a kind of Power System Reliability Forecasting Methodology.To each in the step 1
Network utilizes Matlab Neural Network Toolbox, is instructed using Levenberg-Marquardt optimization algorithms
Practice.
In another specific embodiment of the invention, a kind of Power System Reliability Forecasting Methodology.Methods described is predicting certain
As a example by the average annual power off time index of Electrical system user, its step is as follows：Referred to year user's power failure hour (TOH) for providing
Based on mark and six most strong the 10 of influence factor (system) primary statistics samples of relevance, see as shown in table 1 below, by it
Used as original small sample storehouse, remaining 3 give over to checking sample to the sample of middle System Number 1~7.
Table 1
It is fitted and considers that the Latin of small sample correlation surpasses using bootstrap small sample augmentation technology, based on cuclear density
The combination of cube sampling small sample augmentation technology or both, carries out 100 times of expansions to small sample storehouse respectively.
The different BP neural network of optional three structures carries out comparative training, hidden layer, nerve that each network is included
First number and transmission function are summarized in table 2 below and table 3.
Table 2
Table 3
Matlab Neural Network Toolbox is utilized to each network, using the most fast Levenberg- of training speed
Marquardt optimization algorithms are trained, and other parameters use software kit default setting.
The effect of different small sample augmentation methods is by after same neural metwork training, verifying the TOH predicted values of Sample Storehouse
Mean square deviation (MSE) between observation is illustrated.Following 12 kinds of situation (S1~BK3) participant observations contrast of setting：
S1：Original small sample+network I；
S2：Original small sample+network II；
S3：Original small sample+network III；
B1：Bootstrap small sample expansion+networks I；
B2：Bootstrap small sample expansion+networks II；
B3：Bootstrap small sample expansion+networks III；
K1：Cuclear density small sample augmentation+network I；
K2：Cuclear density small sample augmentation+network II；
K3：Cuclear density small sample augmentation+network III；
Mean square deviation result such as table 4 below between the predicted value and true value of training sample database itself and the institute of table 5 under every kind of situation
Show.
Table 4
Table 5
In Fig. 2, in another specific embodiment of the invention, show to be utilized in a kind of Power System Reliability Forecasting Methodology
Bootstrap technologies each influence factor data sample is expanded after discrete sample distribution schematic diagram.
In Fig. 3, in another specific embodiment of the invention, show to be utilized in a kind of Power System Reliability Forecasting Methodology
Bootstrap technologies each influence factor data sample is expanded after Gaussian Kernel Density schematic diagram.
In Fig. 4, in another specific embodiment of the invention, show to utilize base in a kind of Power System Reliability Forecasting Methodology
It is fitted in cuclear density and considers the Latin Hypercube Sampling small sample augmentation technology of small sample correlation to each influence factor data
Sample expanded after discrete sample distribution schematic diagram.
In Fig. 5, in another specific embodiment of the invention, show to utilize base in a kind of Power System Reliability Forecasting Methodology
It is fitted in cuclear density and considers the Latin Hypercube Sampling small sample augmentation technology of small sample correlation to each influence factor data
Sample expanded after Gaussian Kernel Density schematic diagram.
In another specific embodiment of the invention, a kind of Small Sample Database augmentation method.On the whole, including：Step 01,
Based on each influence factor data sample, imparametrization Gaussian Kernel Density estimation is independently carried out；Based on gained Gaussian Kernel Density,
Latin Hypercube Sampling is carried out to each variable, by the out of order arrangement of gained sample, sample battle array A is obtained；Step 02, tries to achieve A correspondences
Spearman coefficient of rank correlation matrixes RA, based on RACarry out Cholesky decomposition and obtain inferior triangular flap LRA；A correspondence models are tried to achieve to obtain
Walden rating matrix V, tries to achieve V correspondence Spearman coefficient of rank correlation matrixes RV, based on RVCholesky decomposition is carried out to obtain
Inferior triangular flap LRV；Based on the LRAAnd LRVObtain variable grade Description MatrixStep 03, by A according toMiddle element row
Row mode is rearranged and obtains augmented sample matrix AE。
It is in a kind of Small Sample Database augmentation method and step 01 that gained sample is out of order in another specific embodiment of the invention
Arrangement, obtaining sample battle array A includes：By the out of order arrangement of gained sample, sample battle array A is formed：N × M, wherein N>N0 is represented and is wished to expand
Sample size.
In another specific embodiment of the invention, a kind of Small Sample Database augmentation method tries to achieve A correspondences in the step 02
Model obtains Walden rating matrix V, including：Choose the random disorder Latin hypercube sample composition of obedience standardized normal distribution in A
Column vector, matrix V is constituted using each column vector of gained.
In another specific embodiment of the invention, a kind of Small Sample Database augmentation method, based on described in the step 02
LRAAnd LRVObtain variable grade Description MatrixIncluding：Define new matrixWillIn each element
Sequence, the matrix that all numberings are obtained after the arrangement of element correspondence position are numbered according to the magnitude relationship in its residing rowAsDescriptive grade matrix.
In another specific embodiment of the invention, a kind of Small Sample Database augmentation method, the step 03 also includes：By A
In element with arrange for unit according toThe completely the same mode of numbering of middle correspondence position, rearranges and obtains augmentation sample
This matrix AE。
In another specific embodiment of the invention, a kind of Small Sample Database augmentation method, the step obeys mark in choosing A
The random disorder Latin hypercube sample of quasi normal distribution, constitutes column vector, and constituting matrix V using each column vector of gained includes：
Vj={ Φ-1(i/(N+1))}It is out of order, i ∈ { 1 ..., N }, wherein j=1 ..., M, VjIt is the column vector in matrix V, N is composition
The column vector obeys the random disorder Latin hypercube number of samples of standardized normal distribution.
Finally, the present processes are only preferably embodiment, are not intended to limit the scope of the present invention.It is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements made etc. should be included in protection of the invention
Within the scope of.
Claims (9)
1. a kind of Power System Reliability Forecasting Methodology, it is characterised in that including：
Step 1, using bootstrap augmentation technology or cuclear density Latin Hypercube Sampling augmentation technology to each influence factor data
Small sample carries out primary augmentation, obtains primary augmented matrix AE；
Step 2, based on primary augmented matrix AESingle output nerve network training is carried out, by the single output nerve to the acquisition
The predicted value of each factor of influence of network inputs, and then obtain the predicted value of reliability index.
2. the method for claim 1, it is characterised in that the influence factor data can be：Can turn for feeder line ratio,
The quantity ratio or average annual feeder line capacity-load ratio of dielectric feeder ratio, unit segmental averaging number of users, interconnection ratio, segmentation and feeder line
In at least one.
3. the method for claim 1, it is characterised in that small sample is fitted based on cuclear density and considered in the step 1
The Latin Hypercube Sampling small sample augmentation technology of correlation carries out primary augmentation to each influence factor data small sample, obtains just
Level augmented matrix AEIncluding：
Step 11, based on each influence factor data sample, independently carries out imparametrization Gaussian Kernel Density estimation；Based on gained
Gaussian Kernel Density, Latin Hypercube Sampling is carried out to each influence factor, by the out of order arrangement of gained sample, obtains sample battle array A；
Step 12, tries to achieve A correspondence Spearman coefficient of rank correlation matrixes RA, based on RACarry out Cholesky decomposition and obtain down three
Angle gust LRA；Try to achieve A correspondence models and obtain Walden rating matrix V, try to achieve V correspondence Spearman coefficient of rank correlation matrixes RV, it is based on
RVCarry out Cholesky decomposition and obtain inferior triangular flap LRV；Based on the LRA、LRVObtain variable grade Description Matrix
Step 13, by A according toMiddle arrangement of elements mode is rearranged and obtains augmented sample matrix AE。
4. the method for claim 1, it is characterised in that to each network using Matlab nerves in the step 1
Network tool case, is trained using Levenberg-Marquardt optimization algorithms.
5. the method for claim 1, it is characterised in that by the out of order arrangement of gained sample in the step 11, obtain sample
This gust of A includes：By the out of order arrangement of gained sample, sample battle array A is formed：N × M, wherein N>N0 represents the sample size for wishing to expand.
6. the method for claim 1, it is characterised in that A correspondence models are tried to achieve in the step 12 and obtains Walden scoring square
Battle array V, including：The random disorder Latin hypercube sample group of obedience standardized normal distribution in A is chosen into column vector, it is each using gained
Column vector constitutes matrix V.
7. the method for claim 1, it is characterised in that the L is based in the step 12RAAnd LRVObtain variable grade
Description MatrixIncluding：Define new matrixWillIn each element according to big in its residing row
Small relation is numbered sequence, the matrix that all numberings are obtained after the arrangement of element correspondence positionAsDescriptive grade
Matrix.
8. method as claimed in claim 4, it is characterised in that the step 13 also includes：To arrange it is unit by the element in A
According toThe completely the same mode of numbering of middle correspondence position, rearranges and obtains augmented sample matrix AE。
9. method as claimed in claim 5, it is characterised in that the step obeys the random of standardized normal distribution in choosing A
Out of order Latin hypercube sample, constitutes column vector, and constituting matrix V using each column vector of gained includes：Vj={ Φ-1(i/(N+
1))}It is out of order, i ∈ { 1 ..., N }, wherein j=1 ..., M, VjIt is the column vector in matrix V, N obeys mark to constitute the column vector
The random disorder Latin hypercube number of samples of quasi normal distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611021845.4A CN106709593B (en) | 2016-11-17 | 2016-11-17 | Power system reliability prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611021845.4A CN106709593B (en) | 2016-11-17 | 2016-11-17 | Power system reliability prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106709593A true CN106709593A (en) | 2017-05-24 |
| CN106709593B CN106709593B (en) | 2020-11-06 |
Family
ID=58940994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611021845.4A Active CN106709593B (en) | 2016-11-17 | 2016-11-17 | Power system reliability prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106709593B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107809112A (en) * | 2017-09-28 | 2018-03-16 | 北京航空航天大学 | A kind of detailed distribution method of extra-high voltage GIL equipment dependabilities |
| CN108052953A (en) * | 2017-10-31 | 2018-05-18 | 华北电力大学（保定） | The relevant sample extended method of feature based |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392135A (en) * | 2014-11-28 | 2015-03-04 | 河海大学 | Probabilistic optimal power flow calculation method for alternating-current and direct-current systems of offshore wind power plants subjected to VSC-HVDC (voltage source converter-high voltage direct current) grid connection |
| CN104659782A (en) * | 2015-03-20 | 2015-05-27 | 太原理工大学 | Power system voltage stability risk assessment method capable of considering load fluctuation limit |
| CN106096827A (en) * | 2016-06-02 | 2016-11-09 | 国网山东省电力公司济南供电公司 | The reliability calculation method calculated with minimum tangential load based on mixed sampling and platform |
-
2016
- 2016-11-17 CN CN201611021845.4A patent/CN106709593B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392135A (en) * | 2014-11-28 | 2015-03-04 | 河海大学 | Probabilistic optimal power flow calculation method for alternating-current and direct-current systems of offshore wind power plants subjected to VSC-HVDC (voltage source converter-high voltage direct current) grid connection |
| CN104659782A (en) * | 2015-03-20 | 2015-05-27 | 太原理工大学 | Power system voltage stability risk assessment method capable of considering load fluctuation limit |
| CN106096827A (en) * | 2016-06-02 | 2016-11-09 | 国网山东省电力公司济南供电公司 | The reliability calculation method calculated with minimum tangential load based on mixed sampling and platform |
Non-Patent Citations (5)
| Title |
|---|
| ZHEN SHU ETC: "Latin Hypercube Sampling Techniques for Power Systems Reliability Analysis With Renewable Energy Sources", 《IEEE TRANSACTIONS ON POWER SYSTEMS》 * |
| 张石 等: "基于DPCA-BP神经网络的中长期电力负荷预测方法", 《东北大学学报（自然科学版）》 * |
| 蒋程 等: "基于拉丁超立方采样的含风电电力系统的概率可靠性评估", 《电工技术学报》 * |
| 陈益民: "考虑风电随机性的电力系统无功优化配置研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 黄玮 等: "基于Bootstrap方法的小子样试验评估方法研究", 《机械科学与技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107809112A (en) * | 2017-09-28 | 2018-03-16 | 北京航空航天大学 | A kind of detailed distribution method of extra-high voltage GIL equipment dependabilities |
| CN108052953A (en) * | 2017-10-31 | 2018-05-18 | 华北电力大学（保定） | The relevant sample extended method of feature based |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106709593B (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Du et al. | Achieving 100x acceleration for N-1 contingency screening with uncertain scenarios using deep convolutional neural network | |
| Xin et al. | Cyber-physical modeling and cyber-contingency assessment of hierarchical control systems | |
| Kamwa et al. | Fuzzy partitioning of a real power system for dynamic vulnerability assessment | |
| CN105242544B (en) | Consider the non-linear multiple no-manned plane System Fault Tolerance formation control method of random perturbation | |
| CN108828949A (en) | A kind of optimally in distributed mode collaboration fault tolerant control method based on adaptive Dynamic Programming | |
| DE102012102770B9 (en) | System and method for error isolation and error mitigation based on network modeling | |
| Su et al. | Simulation of a forest-grass ecological network in a typical desert oasis based on multiple scenes | |
| CN104269867B (en) | A kind of node power of disturbance transfer distributing equilibrium degree analytical method | |
| CN106777127A (en) | The automatic generation method and system of the individualized learning process of knowledge based collection of illustrative plates | |
| CN105844060B (en) | It is a kind of can the non-probability decision degree of evaluation structure safety coefficient design method | |
| CN103425874B (en) | A kind of Space Vehicle Health appraisal procedure based on profust reliability theory | |
| CN114779015A (en) | Power distribution network fault diagnosis and positioning method based on super-resolution and graph neural network | |
| CN107038297A (en) | The Step-varied back propagation integration method of global energy internet operation characteristic emulation | |
| CN107632590A (en) | A kind of bottom event sort method based on priority | |
| CN112884163B (en) | Combined service evaluation method and system based on federal machine learning algorithm and cloud feedback | |
| CN105844334B (en) | A kind of temperature interpolation method based on radial base neural net | |
| CN106709593A (en) | Electric power system reliability prediction method | |
| CN105183624B (en) | A kind of emulation back method based on Data Matching | |
| CN103605560B (en) | A kind of relay protection and the cascading failure parallel simulation method of automatic safety device | |
| CN110619148A (en) | Equipment ADC (analog to digital converter) efficiency evaluation method based on interval gray number | |
| CN104992032A (en) | Modification method for holding time in multi-voltage domain design | |
| CN104766247A (en) | Full voltage class power grid reliability calculation method | |
| Chen | Cascaded stalling of induction motors in fault-induced delayed voltage recovery (FIDVR) | |
| CN104300572B (en) | A kind of collocation method of Distributed Generation in Distribution System | |
| Liu et al. | Distribution network topology error identification method based on D-PMU and branch state function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhang Jiangong Inventor after: Hu Qinghui Inventor after: Tian Hongxun Inventor after: Wang Honggang Inventor after: Wan Tao Inventor after: Li Haosong Inventor after: Li Jin Inventor after: Kang Taifeng Inventor after: Li Xin Inventor before: Zhang Jiangong Inventor before: Qing Hui Inventor before: Tian Hongxun Inventor before: Wang Honggang Inventor before: Wan Tao Inventor before: Li Haosong Inventor before: Li Jin Inventor before: Kang Taifeng Inventor before: Li Xin |
|
| CB03 | Change of inventor or designer information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20181219 Address after: 100031 West Chang'an Avenue, Xicheng District, Xicheng District, Beijing Applicant after: State Grid Corporation of China Applicant after: BEIJING NETSTONE ACCENTURE INFORMATION TECHNOLOGY CO., LTD. Applicant after: STATE GRID INFORMATION & TELECOMMUNICATION GROUP CO., LTD. Applicant after: State Grid Shanghai Municipal Electric Power Company Address before: 100031 West Chang'an Avenue, Xicheng District, Xicheng District, Beijing Applicant before: State Grid Corporation of China Applicant before: BEIJING NETSTONE ACCENTURE INFORMATION TECHNOLOGY CO., LTD. Applicant before: STATE GRID INFORMATION & TELECOMMUNICATION GROUP CO., LTD. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |