CN113901679B - Reliability analysis method and device for power system and computer equipment - Google Patents
Reliability analysis method and device for power system and computer equipment Download PDFInfo
- Publication number
- CN113901679B CN113901679B CN202111514373.7A CN202111514373A CN113901679B CN 113901679 B CN113901679 B CN 113901679B CN 202111514373 A CN202111514373 A CN 202111514373A CN 113901679 B CN113901679 B CN 113901679B
- Authority
- CN
- China
- Prior art keywords
- data
- subspaces
- power system
- probability
- data space
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000004590 computer program Methods 0.000 claims abstract description 36
- 238000005070 sampling Methods 0.000 claims abstract description 20
- 238000003860 storage Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 54
- 239000011159 matrix material Substances 0.000 claims description 53
- 239000002245 particle Substances 0.000 claims description 47
- 238000003062 neural network model Methods 0.000 claims description 21
- 238000000354 decomposition reaction Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 description 14
- 238000013528 artificial neural network Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000009467 reduction Effects 0.000 description 10
- 239000013598 vector Substances 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000010076 replication Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000017105 transposition Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present application relates to a reliability analysis method, apparatus, computer device, storage medium and computer program product for an electrical power system, the method comprising: sampling an initial operation data set according to a fault probability density function of a target power system to obtain a first data space; inputting multiple groups of second operation data in the first data space into a power flow equation of the target power system to obtain a second data space; decomposing the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces; and analyzing the reliability of the target power system based on the fault probability of the subspaces. According to the reliability analysis method of the power system, the second data space is decomposed to obtain the multiple subspaces, so that the accuracy of calculating the probability of the small-probability fault event of the data space can be improved, and the reliability analysis of the target power system is more accurate.
Description
Technical Field
The present application relates to the field of big data analysis technologies, and in particular, to a reliability analysis method and apparatus for a power system, a computer device, a storage medium, and a computer program product.
Background
In order to ensure safe and stable operation of the power system, the reliability of the power system needs to be periodically analyzed to evaluate the operation state of the power system, so that measures such as corresponding overhaul and the like can be performed on the power system in time according to the evaluation result of the power system. The method can avoid the deterioration of the fault of the power system, bring inconvenience to production and life of residents and the like and cause unsafe accidents based on timely maintenance and other measures.
At present, the influence on the reliability of the power system mainly comes from noise, a small-probability fault event, operation data and the like of operation data of each node of the power system, and a commonly used analysis method for the reliability of the power system is mainly an MCS reliability analysis method.
Disclosure of Invention
The application provides a reliability analysis method and device for an electric power system, a computer device, a storage medium and a computer program product, which can rapidly perform dimensionality reduction processing on operation data for analyzing the reliability of the electric power system, do not change the characteristics of original data, and further can improve the efficiency of reliability analysis on the electric power system.
In a first aspect, the present application provides a reliability analysis method for an electric power system, including:
sampling an initial operation data set according to a fault probability density function of a target power system to obtain a first data space; the fault probability density function is obtained according to historical operation data of the target power system; the initial operating data set includes a plurality of sets of first operating data of the target power system; the first data space includes a plurality of sets of second operational data of the target power system;
inputting the multiple groups of second operation data into a power flow equation of the target power system to obtain a second data space, wherein the second data space comprises the multiple groups of second operation data and system limit state results corresponding to the multiple groups of second operation data;
decomposing the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces;
the reliability of the target power system is analyzed based on a failure probability of the plurality of subspaces, the failure probability including a probability of a small probability failure event for each of the plurality of subspaces.
In a second aspect, the present application further provides a data processing apparatus, comprising:
the sampling acquisition module is used for sampling the initial operation data set according to a fault probability density function of the target power system to acquire a first data space; the fault probability density function is obtained according to historical operation data of the target power system; the initial operating data set includes a plurality of sets of first operating data of the target power system; the first data space includes a plurality of sets of second operational data of the target power system;
the input obtaining module is used for inputting the multiple groups of second operation data into a power flow equation of the target power system to obtain a second data space, and the second data space comprises the multiple groups of second operation data and system limit state results corresponding to the multiple groups of second operation data;
the decomposition module is used for decomposing the second data space according to the characteristic matrixes of the second data space to obtain a plurality of subspaces;
an analysis module to analyze reliability of the target power system based on a failure probability of the plurality of subspaces, the failure probability including a probability of a small probability failure event for each of the plurality of subspaces.
In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method of any one of the above when executing the computer program:
in a fourth aspect, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of any one of the above.
In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the method of any one of the above.
The application provides a reliability analysis method, a reliability analysis device, a computer device, a storage medium and a computer program product of a power system, wherein the method comprises the following steps: sampling an initial operation data set according to a fault probability density function of a target power system to obtain a first data space; inputting multiple groups of second operation data in the first data space into a power flow equation of the target power system to obtain a second data space; decomposing the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces; and analyzing the reliability of the target power system based on the fault probability of the subspaces. The reliability analysis method of the power system includes the steps that firstly, an initial operation data set is sampled through a fault probability density function of a target power system to achieve first dimension reduction processing of the initial operation data set, and the sampling is obtained through sampling based on the fault probability density function of the target power system, so that the correlation between operation data in an obtained first data space and small-probability fault events of the target power system is strong, further, reliability analysis of the power system depends on calculation of the probability of the small-probability fault events of the data space, the probability of the small-probability fault events is small, namely, a small value is calculated based on a large data space, the probability of the small-probability fault events of the obtained data space is very inaccurate, and therefore the reliability analysis method of the power system based on a characteristic moment of a second data space is obtained in the reliability analysis process of the target power system The array decomposes the second data space to obtain a plurality of subspaces, and decomposes the calculation of the probability of the small-probability fault event of the data space with more data into a plurality of subspaces with less data for calculation respectively, so that the accuracy of calculating the probability of the small-probability fault event of the data space can be improved, and the reliability analysis of the target power system is more accurate.
Drawings
FIG. 1 is a diagram of an exemplary implementation of a reliability analysis method for an electrical power system;
FIG. 2 is a schematic flow chart diagram illustrating a method for reliability analysis of a power system according to one embodiment;
FIG. 3 is a flow chart illustrating the reliability analysis steps of the power system in another embodiment;
FIG. 4 is a schematic flow chart illustrating a method for reliability analysis of an electrical power system according to another embodiment;
FIG. 5 is a block diagram showing the construction of a data processing apparatus according to another embodiment;
fig. 6 is an internal structural view of a computer device in another embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The data processing method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Where a plurality of different terminals 102 communicate with the server 104 over a network, the data storage system may store a variety of operational data of the target power system. The data storage system may be integrated on the server 102, or may be located on the cloud or other network server. The plurality of different terminals 102 transmit the collected different types of data for analyzing the reliability of the target power system to the server 104 through the network, and the server 104 combines the data sent by the plurality of different terminals 102 to form an initial operation data set. Sampling the initial operation data set according to a fault probability density function of the target power system to obtain a first data space, and inputting multiple groups of second operation data in the first data space into a power flow equation of the target power system to obtain a second data space; decomposing the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces; and analyzing the reliability of the target power system based on the fault probability of the subspaces. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
In one embodiment, as shown in fig. 2, a data processing method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
step S202, sampling an initial operation data set according to a fault probability density function of a target power system to obtain a first data space; the fault probability density function is obtained according to historical operation data of the target power system; the initial operating data set includes a plurality of sets of first operating data of the target power system; the first data space includes a plurality of sets of second operational data of the target power system.
The target power system may be a power system for which a user needs to perform reliability analysis. The initial operating data set may include voltage data, current data, reactive power reserve data, etc. since the power system includes a plurality of nodes, the initial operating data set may include voltage data, current data, reactive power reserve data, etc. for each node. Then, a plurality of different types of terminal devices for acquiring the operation data of the power system may be arranged at each node of the target power system, the terminal devices of the devices at each node acquire each item of operation data of the power system, and the acquired operation data is sent to the server in real time through the network, so that the server can perform reliability analysis on the power system conveniently.
The terminal devices of different types can acquire data of corresponding nodes according to preset acquisition time, and the server generates an initial operation data set according to a group of data formed by each node, so that the initial operation data set comprises multiple groups of operation data such as voltage data, current data and reactive power reserve data of multiple nodes of the target power system. After receiving the operation data sent by the terminal, the server may perform preprocessing on the operation data, such as format conversion, data specification, data integration, data cleaning, and the like, to obtain a data set convenient for subsequent processing.
The fault probability density function of the target power system is a function of the likelihood that the output value of a variable describing the operational data of the power system is near a certain value-taking point. The probability that the value of the variable of the operation data of the power system falls within a certain area is the integral of the probability density function in the area. The cumulative distribution function is the integral of the probability density function when the probability density function exists. The fault probability density function of the target power system may be obtained by performing simulation, fitting, and other processes according to historical operating data of the target power system, and stored in the server, and when the server needs to analyze the reliability of the target power system, the fault probability density function of the target power system may be obtained from a corresponding memory address. It should be noted that the fault probability density functions for different power systems are different.
The server may analyze the reliability of the target power system according to an instruction of a user, or may analyze the reliability of the target power system according to a preset analysis time, which is not limited in this application. When the server receives the operation data sent by different terminal devices, the server may obtain the failure probability density function from the corresponding memory address, and sample the initial operation data set based on the failure probability density function to obtain the first data space. The initial operation data set is sampled based on a fault probability density function of the target power system, preliminary dimension reduction processing can be carried out on the initial operation data set, data with strong relevance to a small-probability fault event of the target power system are screened out, and a first data space is formed. The operational data included in the first data space is derived from the initial operational data set, but less data is available in succession to the initial operational data set. And the preliminary dimension reduction processing on the initial operation data set is realized. The data in the initial operating data set is referred to herein as first operating data, and the data in the first data space is referred to as second operating data, where the first operating data includes the second operating data.
Step S204, inputting the multiple sets of second operation data into a power flow equation of the target power system to obtain a second data space, wherein the second data space comprises the multiple sets of second operation data and system limit state results corresponding to the multiple sets of second operation data.
In the process of analyzing the reliability of the target power system, not only the operation data of the power system but also the limit state result of the power system need to be obtained. The server inputs multiple groups of second operation data in the first data space into a power flow equation of the target power system to obtain a system limit state result corresponding to each group of second operation data, and obtains a second data space according to the multiple groups of second operation data and the system limit state result corresponding to the multiple groups of second operation data.
In step S206, the second data space is decomposed according to the plurality of feature matrices of the second data space to obtain a plurality of subspaces.
In order to further perform dimension reduction processing on the initial operation data set, based on a second data space obtained after the initial dimension reduction processing, a plurality of feature matrices of the second data space are calculated according to the second data space, and the second data space is decomposed based on the plurality of feature matrices of the second data space, wherein the decomposition is to perform matrix multiplication on the plurality of feature matrices and the second data space respectively to obtain a plurality of subspaces. The feature matrix is a set of the feature value and the feature vector of the second data space, the feature matrix is equivalent to linearly transforming the second data space, the original characteristic of the second data space is not changed, and the dimension of the feature matrix is lower than that of the second data space, so that the feature matrix and the second data space are subjected to matrix multiplication operation to obtain a plurality of subspaces which are all low-dimensional spaces. Here, it should be noted that the feature matrices are arranged in the order of increasing eigenvalues to decreasing eigenvalues, and therefore, the plurality of correspondingly obtained subspaces are also arranged in the order of arranging the feature matrices.
Step S208, analyzing the reliability of the target power system based on the fault probability of the plurality of subspaces, wherein the fault probability comprises the probability of a small-probability fault event of each subspace in the plurality of subspaces.
And finally, analyzing the reliability of the target power system according to the probability of the small-probability fault events of the plurality of subspaces. Because the subspaces belong to a low-dimensional space, and the probability calculation of the small-probability fault events of the multiple subspaces is simpler and more accurate than that of the small-probability fault events of the initial operation data, the accuracy and efficiency of the reliability analysis of the target power system can be improved.
The application provides a reliability analysis method of a power system, which comprises the following steps: sampling an initial operation data set according to a fault probability density function of a target power system to obtain a first data space; inputting multiple groups of second operation data in the first data space into a power flow equation of the target power system to obtain a second data space; decomposing the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces; and analyzing the reliability of the target power system based on the fault probability of the subspaces. The reliability analysis method of the power system includes the steps that firstly, an initial operation data set is sampled through a fault probability density function of a target power system to achieve first dimension reduction processing of the initial operation data set, and the sampling is obtained through sampling based on the fault probability density function of the target power system, so that the correlation between operation data in an obtained first data space and small-probability fault events of the target power system is strong, further, reliability analysis of the power system depends on calculation of the probability of the small-probability fault events of the data space, the probability of the small-probability fault events is small, namely, a small value is calculated based on a large data space, the probability of the small-probability fault events of the obtained data space is quite inaccurate, and therefore the probability of the small-probability fault events of the obtained data space in the reliability analysis process of the target power system is quite inaccurate through a second data space based on a feature matrix of the second data space The second data space is decomposed to obtain a plurality of subspaces, the calculation of the probability of the small-probability fault event of the data space with more data is decomposed into a plurality of subspaces with less data to be calculated respectively, the accuracy of calculating the probability of the small-probability fault event of the data space can be improved, and the reliability analysis of the target power system is more accurate.
In an embodiment, as shown in fig. 3, fig. 3 is an alternative embodiment of a method for decomposing a second data space to obtain a plurality of subspaces, where the embodiment of the method includes the following steps:
step S302, obtaining a gradient matrix of a second data space based on the plurality of groups of second operation data and the system limit state results corresponding to the plurality of groups of second operation data;
step S304, a plurality of characteristic matrixes of a second data space are calculated according to the gradient matrix;
step S306, carrying out matrix multiplication operation on each feature matrix in the plurality of feature matrices and the second data space to obtain a plurality of subspaces, wherein the plurality of feature matrices are in one-to-one correspondence with the plurality of subspaces.
The decomposition process of the second data space is explained as a whole below:
the second data space may be, for example, { x }i，t（xi) H (i =0, 1, 2, … …, n), i denotes the ith argument. Wherein x isiFor the second run, i represents its serial number, t (x)i) And obtaining system limit state results corresponding to the plurality of groups of second operation data.
Calculating the gradient of the second data space may be by:
wherein,Twhich represents a matrix transposition operation, is performed,
t(x i) Represents t (x)i) In thatxA gradient in direction. The gradient can be obtained by finite element analysis or approximated by a strategy based on the sameThus obtaining the product. The application may be to choose to compute the gradient based on a local linear model in the adjoint strategy:
for each xiCalculating corresponding extreme state results, selecting close to xiIs fitted to the point set by the following linear model to obtain t (x)i) Approximation of
Wherein, beta1~βLAs second operating data x1~xLThe corresponding coefficient is a preset constant,
the index of the last point in the point set is sorted, and
. Then calculating an approximate model
As a replacement for the true gradient.
Then, an n × n order non-central covariance matrix S of the gradient vectors is calculated:
s is approximately
Wherein,
is an approximation of S, is a symmetric semi-positive definite matrix, and is subjected to real eigenvalueAnd (3) decomposition:
wherein
Is a matrix of feature vectors that are combined,
as a matrix of eigenvalues, gamma1~γnRepresenting the characteristic values, wherein the number of the characteristic values is n, and dividing the characteristic values and the characteristic vectors:
wherein
And
in order to obtain a matrix of the eigenvalues after the division,
and
and forming a matrix by the divided feature vectors. Then the subspace may be defined as:
wherein, the superscript T represents the matrix transposition operation, q represents the first subspace, s represents the second subspace, and x is the whole xiIt should be noted that the formed vector is only illustrated here by way of example, and does not mean that the vector can be decomposed into two subspaces, and each subspace corresponds to a feature matrix, which is not described in detail herein.
A plurality of subspaces can also be obtained by using a Single Value Decomposition (SVD) method, which is not described herein.
In an embodiment, the present embodiment is an optional method embodiment for obtaining the failure probabilities of the multiple subspaces, and the method embodiment includes the following steps:
and obtaining the fault probabilities of the multiple subspaces according to the product of the probability of the small-probability fault event of the target subspace and the preset conditional probability, wherein the characteristic value of the characteristic matrix corresponding to the target subspace is minimum.
Wherein, because the failure probability of the computation subspace needs to be computed through the intermediate failure events, the intermediate failure event corresponding to the jth subspace is defined as Rj(j =0, 1, 2, … …, m), m being the number of subspaces. The method of selecting the intermediate fault event is to set a constant PifE (0, 1) as the median failure event probability. Then intermediate failure event RjThe automatic estimation is as follows:
where N is the total number of the second operational data sets, qj-1Is the j-1 st subspace, xiAnd-1 (i =0, 1, 2, … …, n) is the i-1 st second operation data.
In general, the probability P of the occurrence of the first intermediate failure event1Can be estimated by a direct MCS:
wherein x is1(k)（k=1，2，……N1) Is the k-th set of second operating data when xi is i =1,
is an index function; when x is satisfied1 （k）∈R1When the temperature of the water is higher than the set temperature,
The probability P of a small probability fault event is then calculated by the following formulaf
Wherein, PfIs the probability of a small probability of a failure event,
is RjAt Rj-1Probability of occurrence under the occurrence conditions, P (R)m) Intermediate failure event R for the last subspace representationmThe probability of (a) of (b) being,
for intermediate fault event probability PifTo the m-1 power of (1).
In one embodiment, the present embodiment is an alternative embodiment of a method for obtaining a probability of a low probability failure event of a target subspace, the method comprising the steps of:
and inputting the operation data in the target subspace into the target particle swarm wavelet neural network model to obtain the probability of the small-probability fault event of the target subspace.
Optionally, the initial particle swarm wavelet neural network model is trained according to the operating data in the multiple subspaces, and a target particle swarm wavelet neural network model is obtained.
The method comprises the following steps of determining operation data in a plurality of subspaces, and training a particle swarm wavelet neural network model according to the operation data.
The particle swarm wavelet neural network uses wavelet function instead of traditional sigmod function as the nonlinear excitation function of network hidden layer node.
The particle swarm wavelet neural network parameters are used for finding the optimal network parameters by using a particle swarm algorithm, and P (R) is calculated by using a particle swarm wavelet neural network modelm）。
Particle swarm wavelet neural network parameters the particle swarm algorithm is used to find the optimal network parameters. The particle swarm optimization optimizes the whole process of network parameters:
step 1: assuming that K network parameters including a scaling factor, a translation factor and a network weight exist in the neural network, and the population size is 10, randomly initializing each particle speed tau and position sigma in a feasible space and obtaining a historical optimal position of the particle and a global optimal position ybest of the population;
step 2: and updating the speed and the position of each particle according to the historical optimal position and the global optimal position of the particle.
And step 3: and evaluating the fitness function value of the particle, and updating the historical optimal position and the global optimal position of the particle.
And 4, step 4: if the end condition is met, outputting a global optimal result and ending the program, otherwise, turning to the step 2 to continue execution.
Intermediate failure event R of last subspacemProbability of failure P (R)m) The evaluation should be done using an alternative model approach.
In an embodiment, as shown in fig. 4, fig. 4 is an alternative embodiment of a method for determining whether a subspace is available in the embodiment, where the embodiment of the method includes the following steps:
step S402, calculating the error of each subspace in a plurality of subspaces;
step S404, determining whether the plurality of subspaces meet the convergence requirement according to the errors corresponding to the plurality of subspaces;
step S406, if the subspaces meet the convergence requirement, analyzing the reliability of the power system according to the small probability fault event probability of the subspaces;
step S408, if at least one of the plurality of subspaces does not satisfy the convergence requirement, generating an additional condition data space, and updating the first data space according to the additional condition data space.
Is provided with
Is an integer uniformly randomly drawn between 1 and M', where v =1, … …, Nboot. M and M' are both arbitrary constants greater than 1, NbootIs the total number of integers to be extracted. Computing
Is bootstrapped
：
Wherein,
is composed of
The matrix of eigenvalues of (a),
is composed of
The feature vectors of (a) constitute a matrix.
The set of (2) produces an ancillary effect on the eigenvalues that can be used to estimate the bootstrap interval. The deviation of the estimator decreases as M' increases. Similarly, the error of the computation subspace can be estimated by bootstrap replication. The subspace error can be calculated by
And determining the median delta and the quartile deviation epsilon of the errors of the subspace, and using the median delta and the quartile deviation epsilon as robust convergence indexes to evaluate whether the implied low-dimensional structure is reasonable or not. The outcome of this stage depends on the choice of convergence criteria.
To control errors in subspace estimation, use is made of
A defined subspace and
the distance between the defined subspaces quantifies the error. In view of
The dispersion of the error distribution is used as a measure of the well-defined subspace
The median and quartile deviations of (a) serve as robust convergence criteria to evaluate reliability issues. The median δ and the quartile deviation ε satisfy:
wherein A is1And A3The lower quartile and the upper quartile are respectively.
The above flow is illustrated in its entirety as follows: if the target power system comprises six synchronous generators { G1，G2，G3，G4，G5，G6The voltage stability margin is related to the reactive power reserve of each generator, the voltage stability margin is represented by t, and the reactive power reserve of each generator is xiAnd (4) showing. The limiting state function, i.e. the voltage stability margin t, is expressed as t = t (x)i）
Randomly sampling the acquired element data according to the probability density function of the target power system to generate a first data space xi。
Calculating the corresponding extreme state function t (x)i) Obtaining a second data space
And decomposing to obtain a plurality of subspaces, and calculating errors of the subspaces.
General t (x)i) Is a continuous differentiable function, calculates t (x)i) Gradient (2):
for each xiCalculate objective function t = t (x)i) Corresponding value, selected close to xiThe maximum sequence number of the data in the point set is
The following linear model is used to fit the set of points to obtain t (x)i) Approximation of
Then calculating an approximate model
As a replacement for the true gradient.
Then, a 6 × 6 order non-central covariance matrix S of the gradient vectors is calculated:
the obtained data gradient, S is approximately
Due to the fact that
Is a symmetrical semi-positive definite matrix, and the real eigenvalue decomposition is carried out on the matrix:
dividing the characteristic value and the characteristic vector:
then the subspace may be defined as
For v =1, … …, NbootIs provided with
Is an integer uniformly randomly drawn between 1 and M'. The v substitution
The auxiliary program of (2) is calculated as follows:
characteristic value
The set of (2) produces an ancillary effect on the eigenvalues that can be used to estimate the bootstrap interval. The deviation of the estimator decreases as M' increases. Similarly, the error of the computation subspace can be estimated by bootstrap replication. Calculating a subspace error:
and determining the median delta and the quartile deviation epsilon of the errors of the subspace, and using the median delta and the quartile deviation epsilon as robust convergence indexes to evaluate whether the implied low-dimensional structure is reasonable or not.
To control errors in subspace estimation, use is made of
A defined subspace and
the distance between the defined subspaces quantifies the error. In view of
The dispersion of the error distribution is used as a measure of the well-defined subspace
The median and quartile deviations of (a) serve as robust convergence criteria to evaluate reliability issues. The median δ and the quartile deviation ε satisfy:
wherein A is1And A3The lower quartile and the upper quartile are respectively.
Since the probability of failure for computing a subspace needs to be computed by means of intermediate failure events, the intermediate failure event corresponding to each subspace is defined herein as Rj(j =0, 1, 2, … …, m). The method of selecting the intermediate fault event is to set a constant PifE (0, 1) as the median failure event probability. Then intermediate failure event RjThe automatic estimation is as follows:
where N is the total number of second operational data sets,
is the j-1 st subspace, xi-1(i =0, 1, 2, … …, n) is the i-1 st second operating data.
For intermediate fault events R in the above equationjPerforming a recursive operation until a convergence criterion is satisfied:
wherein the convergence index
And
for estimating the quality of the dimensionality reduction result, typically
And
one hundredth toOne in a thousand, in this case
And
. Generating additional condition data using MCMC method
Setting intermediate failure event probability Pif=0.3
From these at RjThe second operational data for the jth level begins. MCMC simulation for generating
Additional condition data. From the ith level and its corresponding response value
Calculate the total NiSecond operation data
。
Then, will
Substituting into the correlation step to obtain error data
And corresponding statistical convergence index
And
。
the above process is repeated recursively until the mth convergence index
And
the convergence criterion is satisfied.
Use of
And obtaining a low-dimensional data set, and then training a particle swarm wavelet neural network model on the dimension reduction data set.
The particle swarm wavelet neural network uses wavelet function instead of traditional sigmod function as the nonlinear excitation function of network hidden layer node.
Particle swarm wavelet neural network parameters the particle swarm algorithm is used to find the optimal network parameters.
The particle swarm wavelet neural network uses wavelet function instead of traditional sigmod function as the nonlinear excitation function of network hidden layer node.
E.g. using basic wavelet functions
Instead of a sigmod function.
Particle swarm wavelet neural network parameters the particle swarm algorithm is used to find the optimal network parameters. The particle swarm optimization optimizes the whole process of network parameters:
step 1: assuming that K network parameters including a scaling factor, a translation factor and a network weight exist in the neural network, and the population size is 10, randomly initializing each particle speed tau and position sigma in a feasible space and obtaining a historical optimal position of the particle and a global optimal position ybest of the population;
step 2: and updating the speed and the position of each particle according to the historical optimal position and the global optimal position of the particle.
And step 3: and evaluating the fitness function value of the particle, and updating the historical optimal position and the global optimal position of the particle.
And 4, step 4: if the end condition is met, outputting a global optimal result and ending the program, otherwise, turning to the step 2 to continue execution.
Last intermediate failure event RmThe failure probability should be evaluated using an alternative model approach.
Finally, the probability P of a small probability fault event is calculated using the following equationf：
Table 1 shows the reliability results for various methods. This method has higher accuracy and efficiency than the other listed methods. As can be seen from Table 1, the error (e) of the failure probability calculated by the proposed methodβ%) was only 0.009%. On the other hand, in this example, the GSA and traditional active subspace approach completely collapse. For the coarse MCS method containing 1500 data, only one data belongs to the fault domain. The results of the subset simulation and the particle swarm wavelet neural network show that the effectiveness and the accuracy of the traditional method are obviously improved by introducing the dimension reduction technology.
TABLE 1 reliability comparison
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a data processing apparatus for implementing the above-mentioned data processing method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the data processing device provided below may refer to the limitations in the above operation and maintenance behavior analysis method, and details are not described here.
In one embodiment, as shown in fig. 5, there is provided a reliability analysis device of a power system, including: a sample acquisition module 502, an input acquisition module 504, a decomposition module 506, and an analysis module 508, wherein:
a sampling obtaining module 502, configured to sample an initial operating data set according to a fault probability density function of a target power system, so as to obtain a first data space; the fault probability density function is obtained according to historical operation data of the target power system; the initial operating data set includes a plurality of sets of first operating data of the target power system; the first data space includes a plurality of sets of second operational data of the target power system;
an input obtaining module 504, configured to input multiple sets of second operation data into a power flow equation of the target power system, and obtain a second data space, where the second data space includes multiple sets of second operation data and system limit state results corresponding to the multiple sets of second operation data;
a decomposition module 506, configured to decompose the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces;
an analysis module 508 for analyzing the reliability of the target power system based on the failure probabilities of the plurality of subspaces, the failure probabilities including a probability of a small probability failure event for each of the plurality of subspaces.
In one embodiment, the decomposition module 506 is specifically configured to obtain a gradient matrix of the second data space based on the plurality of sets of second operating data and the system extreme state results corresponding to the plurality of sets of second operating data; calculating a plurality of feature matrices of the second data space from the gradient matrix; and carrying out matrix multiplication operation on each feature matrix in the feature matrices and the second data space to obtain a plurality of subspaces, wherein the feature matrices are in one-to-one correspondence with the subspaces.
In an embodiment, the analysis module 508 includes an obtaining unit, which is configured to obtain the failure probabilities of the multiple subspaces according to a product of the probability of the small-probability failure event of the target subspace and a preset conditional probability, where a feature value of a feature matrix corresponding to the target subspace is the minimum.
In an embodiment, the obtaining unit is further configured to input the operating data in the target subspace into the target particle swarm wavelet neural network model, so as to obtain the probability of the small-probability fault event of the target subspace.
In an embodiment, the obtaining unit is further configured to train the initial particle swarm wavelet neural network model according to the operating data in the multiple subspaces, so as to obtain the target particle swarm wavelet neural network model.
In one embodiment, the apparatus further comprises a determination module for calculating an error for each of the plurality of subspaces; determining whether the plurality of subspaces meet the convergence requirement according to the errors corresponding to the plurality of subspaces; if the subspaces meet the convergence requirement, analyzing the reliability of the power system according to the small probability fault event probability of the subspaces; and if at least one of the plurality of subspaces does not meet the convergence requirement, generating an additional condition data space, and updating the first data space according to the additional condition data space.
The respective modules in the reliability analysis apparatus of the force system described above may be entirely or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing operation and maintenance data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an operation and maintenance behavior analysis method.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
sampling an initial operation data set according to a fault probability density function of a target power system to obtain a first data space; the fault probability density function is obtained according to historical operation data of the target power system; the initial operating data set includes a plurality of sets of first operating data of the target power system; the first data space includes a plurality of sets of second operational data of the target power system;
inputting the multiple groups of second operation data into a power flow equation of the target power system to obtain a second data space, wherein the second data space comprises the multiple groups of second operation data and system limit state results corresponding to the multiple groups of second operation data;
decomposing the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces;
the reliability of the target power system is analyzed based on a failure probability of the plurality of subspaces, the failure probability including a probability of a small probability failure event for each of the plurality of subspaces.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
obtaining a gradient matrix of a second data space based on the plurality of groups of second operating data and system limit state results corresponding to the plurality of groups of second operating data; calculating a plurality of feature matrices of the second data space from the gradient matrix; and carrying out matrix multiplication operation on each feature matrix in the feature matrices and the second data space to obtain a plurality of subspaces, wherein the feature matrices are in one-to-one correspondence with the subspaces.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and obtaining the fault probabilities of the multiple subspaces according to the product of the probability of the small-probability fault event of the target subspace and the preset conditional probability, wherein the characteristic value of the characteristic matrix corresponding to the target subspace is minimum.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and inputting the operation data in the target subspace into the target particle swarm wavelet neural network model to obtain the probability of the small-probability fault event of the target subspace.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and training the initial particle swarm wavelet neural network model according to the running data in the plurality of subspaces to obtain a target particle swarm wavelet neural network model.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
calculating an error for each of the plurality of subspaces; determining whether the plurality of subspaces meet the convergence requirement according to the errors corresponding to the plurality of subspaces; if the subspaces meet the convergence requirement, analyzing the reliability of the power system according to the small probability fault event probability of the subspaces; and if at least one of the plurality of subspaces does not meet the convergence requirement, generating an additional condition data space, and updating the first data space according to the additional condition data space.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
sampling an initial operation data set according to a fault probability density function of a target power system to obtain a first data space; the fault probability density function is obtained according to historical operation data of the target power system; the initial operating data set includes a plurality of sets of first operating data of the target power system; the first data space includes a plurality of sets of second operational data of the target power system;
inputting the multiple groups of second operation data into a power flow equation of the target power system to obtain a second data space, wherein the second data space comprises the multiple groups of second operation data and system limit state results corresponding to the multiple groups of second operation data;
decomposing the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces;
the reliability of the target power system is analyzed based on a failure probability of the plurality of subspaces, the failure probability including a probability of a small probability failure event for each of the plurality of subspaces.
In one embodiment, the computer program when executed by the processor further performs the steps of:
obtaining a gradient matrix of a second data space based on the plurality of groups of second operating data and system limit state results corresponding to the plurality of groups of second operating data; calculating a plurality of feature matrices of the second data space from the gradient matrix; and carrying out matrix multiplication operation on each feature matrix in the feature matrices and the second data space to obtain a plurality of subspaces, wherein the feature matrices are in one-to-one correspondence with the subspaces.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and obtaining the fault probabilities of the multiple subspaces according to the product of the probability of the small-probability fault event of the target subspace and the preset conditional probability, wherein the characteristic value of the characteristic matrix corresponding to the target subspace is minimum.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and inputting the operation data in the target subspace into the target particle swarm wavelet neural network model to obtain the probability of the small-probability fault event of the target subspace.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and training the initial particle swarm wavelet neural network model according to the running data in the plurality of subspaces to obtain a target particle swarm wavelet neural network model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
calculating an error for each of the plurality of subspaces; determining whether the plurality of subspaces meet the convergence requirement according to the errors corresponding to the plurality of subspaces; if the subspaces meet the convergence requirement, analyzing the reliability of the power system according to the small probability fault event probability of the subspaces; and if at least one of the plurality of subspaces does not meet the convergence requirement, generating an additional condition data space, and updating the first data space according to the additional condition data space.
In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:
sampling an initial operation data set according to a fault probability density function of a target power system to obtain a first data space; the fault probability density function is obtained according to historical operation data of the target power system; the initial operating data set includes a plurality of sets of first operating data of the target power system; the first data space includes a plurality of sets of second operational data of the target power system;
inputting the multiple groups of second operation data into a power flow equation of the target power system to obtain a second data space, wherein the second data space comprises the multiple groups of second operation data and system limit state results corresponding to the multiple groups of second operation data;
decomposing the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces;
the reliability of the target power system is analyzed based on a failure probability of the plurality of subspaces, the failure probability including a probability of a small probability failure event for each of the plurality of subspaces.
In one embodiment, the computer program when executed by the processor further performs the steps of:
obtaining a gradient matrix of a second data space based on the plurality of groups of second operating data and system limit state results corresponding to the plurality of groups of second operating data; calculating a plurality of feature matrices of the second data space from the gradient matrix; and carrying out matrix multiplication operation on each feature matrix in the feature matrices and the second data space to obtain a plurality of subspaces, wherein the feature matrices are in one-to-one correspondence with the subspaces.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and obtaining the fault probabilities of the multiple subspaces according to the product of the probability of the small-probability fault event of the target subspace and the preset conditional probability, wherein the characteristic value of the characteristic matrix corresponding to the target subspace is minimum.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and inputting the operation data in the target subspace into the target particle swarm wavelet neural network model to obtain the probability of the small-probability fault event of the target subspace.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and training the initial particle swarm wavelet neural network model according to the running data in the plurality of subspaces to obtain a target particle swarm wavelet neural network model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
calculating an error for each of the plurality of subspaces; determining whether the plurality of subspaces meet the convergence requirement according to the errors corresponding to the plurality of subspaces; if the subspaces meet the convergence requirement, analyzing the reliability of the power system according to the small probability fault event probability of the subspaces; and if at least one of the plurality of subspaces does not meet the convergence requirement, generating an additional condition data space, and updating the first data space according to the additional condition data space.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A method of reliability analysis of an electrical power system, the method comprising:
sampling an initial operation data set according to a fault probability density function of a target power system to obtain a first data space; the fault probability density function is obtained according to historical operation data of the target power system; the initial set of operating data comprises a plurality of sets of first operating data of the target power system; the first data space includes a plurality of sets of second operational data of the target power system;
inputting the multiple sets of second operation data into a power flow equation of the target power system to obtain a second data space, wherein the second data space comprises the multiple sets of second operation data and system limit state results corresponding to the multiple sets of second operation data;
decomposing the second data space according to a plurality of feature matrices of the second data space to obtain a plurality of subspaces;
analyzing the reliability of the target power system based on a probability of failure of the plurality of subspaces, the probability of failure comprising a probability of a small probability failure event for each of the plurality of subspaces.
2. The method of claim 1, wherein decomposing the second data space according to the plurality of feature matrices of the second data space to obtain a plurality of subspaces comprises:
obtaining a gradient matrix of the second data space based on the plurality of sets of second operating data and system extreme state results corresponding to the plurality of sets of second operating data;
calculating the plurality of feature matrices of the second data space from the gradient matrices;
and performing matrix multiplication operation on each feature matrix in the plurality of feature matrices and the second data space to obtain a plurality of subspaces, wherein the plurality of feature matrices are in one-to-one correspondence with the plurality of subspaces.
3. The method of claim 2, further comprising:
and obtaining the fault probabilities of the plurality of subspaces according to the product of the probability of the small-probability fault event of the target subspace and a preset condition probability, wherein the characteristic value of the characteristic matrix corresponding to the target subspace is minimum.
4. The method of claim 3, further comprising:
and inputting the operation data in the target subspace into a target particle swarm wavelet neural network model to obtain the probability of the small-probability fault event of the target subspace.
5. The method of claim 4, further comprising:
and training an initial particle swarm wavelet neural network model according to the running data in the plurality of subspaces to obtain the target particle swarm wavelet neural network model.
6. The method of claim 1, further comprising:
calculating an error for each of the plurality of subspaces;
determining whether the plurality of subspaces meet convergence requirements according to the errors corresponding to the plurality of subspaces;
if the subspaces meet the convergence requirement, analyzing the reliability of the power system according to the small probability fault event probabilities of the subspaces;
and if at least one of the plurality of subspaces does not meet the convergence requirement, generating an additional condition data space, and updating the first data space according to the additional condition data space.
7. A reliability analysis apparatus of an electric power system, characterized in that the apparatus comprises:
the sampling acquisition module is used for sampling the initial operation data set according to a fault probability density function of the target power system to acquire a first data space; the fault probability density function is obtained according to historical operation data of the target power system; the initial set of operating data comprises a plurality of sets of first operating data of the target power system; the first data space includes a plurality of sets of second operational data of the target power system;
the input obtaining module is used for inputting the multiple groups of second operation data into a power flow equation of the target power system to obtain a second data space, and the second data space comprises the multiple groups of second operation data and system limit state results corresponding to the multiple groups of second operation data;
the decomposition module is used for decomposing the second data space according to the characteristic matrixes of the second data space to obtain a plurality of subspaces;
an analysis module to analyze the reliability of the target power system based on a probability of failure of the plurality of subspaces, the probability of failure comprising a probability of a small probability failure event for each of the plurality of subspaces.
8. The apparatus of claim 7, wherein the decomposition module is specifically configured to obtain a gradient matrix of the second data space based on the plurality of sets of second operating data and system extreme state results corresponding to the plurality of sets of second operating data; calculating the plurality of feature matrices of the second data space from the gradient matrices; and performing matrix multiplication operation on each feature matrix in the plurality of feature matrices and the second data space to obtain a plurality of subspaces, wherein the plurality of feature matrices are in one-to-one correspondence with the plurality of subspaces.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111514373.7A CN113901679B (en) | 2021-12-13 | 2021-12-13 | Reliability analysis method and device for power system and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111514373.7A CN113901679B (en) | 2021-12-13 | 2021-12-13 | Reliability analysis method and device for power system and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113901679A CN113901679A (en) | 2022-01-07 |
| CN113901679B true CN113901679B (en) | 2022-04-26 |
Family
ID=79026304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111514373.7A Active CN113901679B (en) | 2021-12-13 | 2021-12-13 | Reliability analysis method and device for power system and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113901679B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115021335B (en) * | 2022-06-16 | 2024-03-26 | 西安交通大学 | Multi-period robust reliability assessment method considering energy storage and new energy |
| CN116229089B (en) * | 2023-05-10 | 2023-07-14 | 广州市易鸿智能装备有限公司 | Appearance geometric analysis method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102055187A (en) * | 2010-12-10 | 2011-05-11 | 中国电力科学研究院 | Large-scale interconnected power grid spinning reserve risk assessment method based on state space division method |
| CN103955801A (en) * | 2014-05-15 | 2014-07-30 | 华北电力大学 | Electric power system distributed parallel computing management method based on time-space dimension |
| CN108490923A (en) * | 2018-04-28 | 2018-09-04 | 南京航空航天大学 | The design method of small fault detection and positioning for electric traction system |
| CN113591367A (en) * | 2021-06-25 | 2021-11-02 | 中国电力科学研究院有限公司 | Reliability assessment method and system for transient stability intelligent assessment model of power system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160217674A1 (en) * | 2015-01-26 | 2016-07-28 | Trane International Inc. | Remote monitoring of an hvac system for fault detection and diagnostics |
| US20170177016A1 (en) * | 2015-12-21 | 2017-06-22 | Bigwood Technology, Inc. | Smart Power Flow Solvers for Smart Power Grids |
| US11301563B2 (en) * | 2019-03-13 | 2022-04-12 | International Business Machines Corporation | Recurrent neural network based anomaly detection |
-
2021
- 2021-12-13 CN CN202111514373.7A patent/CN113901679B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102055187A (en) * | 2010-12-10 | 2011-05-11 | 中国电力科学研究院 | Large-scale interconnected power grid spinning reserve risk assessment method based on state space division method |
| CN103955801A (en) * | 2014-05-15 | 2014-07-30 | 华北电力大学 | Electric power system distributed parallel computing management method based on time-space dimension |
| CN108490923A (en) * | 2018-04-28 | 2018-09-04 | 南京航空航天大学 | The design method of small fault detection and positioning for electric traction system |
| CN113591367A (en) * | 2021-06-25 | 2021-11-02 | 中国电力科学研究院有限公司 | Reliability assessment method and system for transient stability intelligent assessment model of power system |
Non-Patent Citations (2)
| Title |
|---|
| 电网可靠性评估中相关性变量的非参数R藤Copula模型;赵渊等;《中国电机工程学报》;20191211(第03期);全文 * |
| 系统状态空间分割法在电力系统可靠性评估中的应用;王晓滨等;《电网技术》;20111005(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113901679A (en) | 2022-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113901679B (en) | Reliability analysis method and device for power system and computer equipment | |
| CN110427654B (en) | Landslide prediction model construction method and system based on sensitive state | |
| Zhang et al. | Wind speed prediction research considering wind speed ramp and residual distribution | |
| CN112418482A (en) | Cloud computing energy consumption prediction method based on time series clustering | |
| CN111274532B (en) | Short-term wind power prediction method and device based on CEEMD-LZC and manifold learning | |
| Wang et al. | A data-driven uncertainty quantification method for stochastic economic dispatch | |
| CN113409893B (en) | Molecular feature extraction and performance prediction method based on image convolution | |
| CN116316617B (en) | Multi-station intelligent fusion new energy generation power region prediction method and system | |
| CN115238855A (en) | Completion method of time sequence knowledge graph based on graph neural network and related equipment | |
| CN114676923A (en) | Method and device for predicting generated power, computer equipment and storage medium | |
| CN116702831A (en) | Hybrid short-term wind power prediction method considering massive loss of data | |
| CN115564155A (en) | Distributed wind turbine generator power prediction method and related equipment | |
| CN117578434A (en) | Power distribution network flexibility evaluation method and device considering flexible resource adjustability | |
| CN116682506A (en) | Data processing method, training method, determining method, designing method and device | |
| CN115392594B (en) | Electrical load model training method based on neural network and feature screening | |
| Carbó‐Dorca et al. | Fundamental quantum QSAR (Q2SAR) equation: extensions, nonlinear terms, and generalizations within extended Hilbert–Sobolev spaces | |
| CN116306030A (en) | New energy prediction dynamic scene generation method considering prediction error and fluctuation distribution | |
| CN113705885B (en) | VMD, XGBoost and TCN fused power distribution network voltage prediction method and system | |
| CN114784795A (en) | Wind power prediction method and device, electronic equipment and storage medium | |
| CN115907142A (en) | Short-term electric quantity prediction method and device | |
| Shang et al. | A sequential experimental design for multivariate sensitivity analysis using polynomial chaos expansion | |
| Xinxiang | Collaborative filtering recommendation using matrix factorization: A mapreduce implementation | |
| CN116415510B (en) | Breaker temperature rise prediction method and system based on phase space reconstruction and neural network | |
| Zhang et al. | Second order longitudinal dynamic models with covariates: estimation and forecasting | |
| Daviet | Sequential Monte Carlo for Hierarchical Bayes with Large Datasets |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |