CN112531706A - Coherent cluster identification method based on complex invariance and deep neural network - Google Patents

Coherent cluster identification method based on complex invariance and deep neural network Download PDF

Info

Publication number
CN112531706A
CN112531706A CN202011506029.9A CN202011506029A CN112531706A CN 112531706 A CN112531706 A CN 112531706A CN 202011506029 A CN202011506029 A CN 202011506029A CN 112531706 A CN112531706 A CN 112531706A
Authority
CN
China
Prior art keywords
invariance
neural network
complexity
deep neural
centroid
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
Application number
CN202011506029.9A
Other languages
Chinese (zh)
Other versions
CN112531706B (en
Inventor
陈厚合
刘丰瑞
王长江
姜涛
李雪
李国庆
李斌
范维
段方维
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Liaoning Electric Power Co Ltd
Northeast Electric Power University
Original Assignee
Northeast Dianli University
Electric Power Research Institute of State Grid Liaoning Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Northeast Dianli University, Electric Power Research Institute of State Grid Liaoning Electric Power Co Ltd filed Critical Northeast Dianli University
Priority to CN202011506029.9A priority Critical patent/CN112531706B/en
Publication of CN112531706A publication Critical patent/CN112531706A/en
Application granted granted Critical
Publication of CN112531706B publication Critical patent/CN112531706B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
    • H02J3/0012—Contingency detection
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]

Abstract

The invention discloses a coherent cluster identification method based on complex invariance and a deep neural network, which comprises the following steps: mapping the sample to an n-dimensional space, and mining wide-area phasor measurement data characteristics based on the constructed self-encoder deep neural network; calculating complexity invariance distance between unit time sequence data according to the wide-area phasor measurement data characteristics; and determining the similarity between the samples in the n-dimensional space based on the complexity invariance distance, and clustering the unit samples according to the similarity result. The invention effectively solves the problem that some generators with correlation coefficients have the maximum correlation coefficients with the generators in other clusters and simultaneously have the minimum correlation coefficients with other generators in the clusters; the data feature number mined by the multilayer deep neural network constructed by the invention is far more than that mined by other methods, and the key feature loss of data is avoided.

Description

Coherent cluster identification method based on complex invariance and deep neural network
Technical Field
The invention relates to the field of identification of a coherent cluster of a power system, in particular to a coherent cluster identification method based on complex invariance and a deep neural network.
Background
With the continuous enlargement of the interconnection scale of a regional power grid, the continuous increase of large-capacity long-distance alternating-current and direct-current transmission lines, the large-scale grid connection of high-permeability renewable energy sources and the large-scale application of power electronic equipment, the operation mode of a power system is more complicated and changeable, and the uncertainty of system element models and parameters is continuously increased, so that great challenges are brought to the safe and stable operation of the power system. The generator coherence of the power system reflects that generators in the system have the same motion trend in the disturbed dynamic process, and the rapid search and identification of a coherent cluster is the primary task of real-time emergency control of a power grid and active splitting of key branches/sections so as to prevent the power oscillation between long-time areas from inducing system cascading failure and further causing major power failure accidents. The traditional model-based coherent cluster identification method depends on detailed models and accurate parameters of the power system, and the influence of system operation mode change on coherent cluster division results is difficult to consider.
In recent years, with the widespread use of a wide-area synchronous Phasor Measurement Unit (PMU) in engineering, a new opportunity for power system coherent cluster identification based on wide-area measurement information has emerged. The method does not depend on a system model and parameters, and extracts key information capable of representing the coherence among the generators from actual wide area measurement information of the power system by means of a relevant theory of pattern recognition and data mining to divide a coherent cluster. Because the data volume of the wide area measurement information is very large, data mining needs to be carried out on the wide area measurement information, key information is extracted, and the identification efficiency of the coherent unit is improved. Most researchers represent coherent coupling strength among generators by using correlation coefficients, identification and calculation of coherent units are simple and easy to realize based on the optimal projection direction, and rapid identification of coherent groups of a power system is realized by representing key features of data by using a normalized Laplace matrix of a coherent information undirected graph; the graph partitioning method is extremely strong in robustness, and as the graph partitioning method tends to divide the graph into as many sub-graphs as possible, a certain penalty mechanism is added into the algorithm to enable the number of machine sets of each cluster to be relatively balanced.
However, in practical applications, the above method has the following disadvantages:
1. part of generators in the system have larger correlation coefficient values with some generators in a plurality of coherent clusters, and have extremely small correlation coefficient values with other generators in the coherent clusters, so that effective division cannot be carried out;
2. the characteristic number extracted by the normalized Laplacian matrix of the coherent information undirected graph is too low relative to the length of the time sequence, so that the loss of key information of data is caused;
3. in the identification work of the actual coherent cluster of the power system (especially when the local fault of the system is serious), some isolated clusters or clusters with few clusters may exist, and the graph partitioning method can misclassify the clusters and is not easy to analyze subsequent emergency control measures.
Disclosure of Invention
The invention provides a coherent machine group identification method based on complex invariance and a deep neural network, which improves the identification precision and generalization of a coherent machine group of a power system and is described in detail as follows:
a coherent cluster identification method based on complex invariance and deep neural networks, the method comprising:
mapping the sample to an n-dimensional space, and mining wide-area phasor measurement data characteristics based on the constructed self-encoder deep neural network;
calculating complexity invariance distance between unit time sequence data according to the wide-area phasor measurement data characteristics;
and determining the similarity between the samples in the n-dimensional space based on the complexity invariance distance, and clustering the unit samples according to the similarity result.
Wherein the self-encoder deep neural network comprises: an encoder and a decoder, and a control unit,
the encoder includes: the system comprises a 1-dimensional convolutional neural network, a maximum pooling layer and two layers of bidirectional long-term and short-term memory neural networks;
the decoder includes: an upsampling layer and a deconvolution neural network.
Further, the calculating the complexity invariance distance between the unit time sequence data according to the wide-area phasor measurement data characteristics specifically includes:
the complexity invariance distance of the time series Q and C is:
CID(Q,C)＝ED(Q,C)×CF(Q,C)
wherein ED (Q, C) represents Euclidean distance between time series Q and C, and CF (Q, C) represents complexity correlation coefficient between time series Q and C;
Figure BDA0002844674110000021
wherein, the complexity measurement standards of the sequences Q and C are respectively CE (Q) and CE (C);
Figure BDA0002844674110000022
wherein q isiAnd n is the number of sampling points.
The method comprises the following steps of determining similarity among samples in an n-dimensional space based on complexity invariance distance, and clustering unit samples according to a similarity result, wherein the clustering specifically comprises the following steps:
calculating the probability that each sample belongs to a certain class, comparing the probability with the real distribution, calculating KL divergence, reversely changing the initial centroid and the encoder parameters of the clustering layer, and finally selecting the optimal clustering scheme with the minimum KL divergence loss value through grid search;
based on GMM and EM, searching the optimal clustering result by iteratively minimizing KL divergence.
Further, the calculating the probability that each sample belongs to a certain class specifically includes:
Figure BDA0002844674110000031
wherein q isikRepresents the probability that the ith sample belongs to centroid k; phi (z)i|θk) Representing the similarity of the ith sample point and the kth centroid; a iskIs a gaussian distribution coefficient; z is a radical ofiIs an implicit variable of sample i;
Figure BDA0002844674110000032
representing the Gaussian distribution parameter, K being the total number of centroids, μkFor the k-th centroid corresponding to the mean value of the Gaussian distribution, σkThe k-th centroid corresponds to the variance of the gaussian distribution.
Comparing with the real distribution, calculating KL divergence, and reversely changing the initial centroid of the clustering layer and the parameters of the encoder specifically comprise:
the clustering mean of centroid k in the new iteration is:
Figure BDA0002844674110000033
wherein η is the learning rate, and defines the Loss function Loss as the KL divergence between the prediction probability and the true estimation probability:
Figure BDA0002844674110000034
the true estimated probability distribution is:
Figure BDA0002844674110000035
the covariance matrix is:
Figure BDA0002844674110000036
the gaussian distribution coefficient is:
Figure BDA0002844674110000037
wherein p isikThe true probability that the ith sample belongs to the centroid k is shown, N is the total number of the samples, and T is a transposed symbol; sigmakIs a covariance matrix; a iskIs a gaussian distribution coefficient.
Further, the step of finally selecting the optimal clustering scheme with the minimum KL divergence loss value through grid search specifically includes:
and continuously and reversely fine-tuning the parameters and the centroid of the clustering layer of the initial encoder, and jointly adjusting the parameters and the centroid of the clustering layer with the training process of the initial encoder and the initial encoder, wherein when the two loss functions of KL divergence and MSE are minimum, the process is ended.
The technical scheme provided by the invention has the beneficial effects that:
1. the invention maps the samples to the n-dimensional space, determines the similarity among the samples in the n-dimensional space, and clusters the similar samples, wherein the similarity measurement standard defined by the invention is the complexity invariance distance, thereby effectively solving the problem that some generators and generators in other clusters have the maximum correlation coefficient and simultaneously have the minimum correlation coefficient with other generators in the clusters;
2. the data feature number of the multi-layer deep neural network mining constructed by the invention is far more than that of other methods, so that the key feature loss of data is avoided;
3. the cluster layer in the neural network can accurately identify isolated machine sets or machine sets with few number after local faults of the system, and effectively guide the formulation of a subsequent implementation scheme of active splitting.
Drawings
FIG. 1 is a flow chart of a coherent cluster identification method based on complex invariance and deep neural networks;
FIG. 2 is a schematic diagram of a multi-layer neural network;
FIG. 3 is a flow chart of a clustering algorithm;
FIG. 4 is a topological diagram of an example.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in further detail below.
Example 1
In order to accurately identify a coherent cluster of a power system, an embodiment of the present invention provides a coherent cluster identification method based on a complex invariance and a deep neural network, referring to fig. 1 to 3, the method including the following steps:
step 101: mapping the sample to an n-dimensional space, and mining wide-area phasor measurement data characteristics based on the constructed self-encoder deep neural network;
step 102: calculating complexity invariance distance between unit time sequence data according to the wide-area phasor measurement data characteristics;
step 103: and determining the similarity between the samples in the n-dimensional space based on the complexity invariance distance, and clustering the unit samples according to the similarity result.
In summary, the embodiment of the present invention can process the multidimensional timing characteristic operation data of the wide-area phasor measurement, thereby obtaining an accurate and effective coherent cluster division scheme, implementing clustering of unit samples, and completing identification of coherent clusters of the power system.
Example 2
The scheme in embodiment 1 is further described below with reference to specific calculation formulas, fig. 1 to 4, and examples, and is described in detail below:
201: constructing a self-encoder deep neural network;
the Auto-encoder (Auto-encoder) neural network structure constructed by the embodiment of the invention is shown in fig. 2.
After each output, the error is propagated backwards from the encoder, continuously optimizing. The two processes of the Encoder (Encoder) and the decoder (decoder) can be understood as inverse functions of each other, the dimension is continuously reduced in the encoding process, and the dimension is increased in the decoding process. When the self-encoder uses convolution operation to extract features, which is equivalent to that the encoding process is a deep convolutional neural network and multilayer convolution pooling is adopted, the decoding process needs to be performed with deconvolution and deconvolution. Because data collected by the PMU contains noise signals, random noise can be added into time sequence data before input, so that the input of each time is slightly different, then the time sequence data with the noise is subjected to self-coding, and an output value is compared with the time sequence data before the noise is added, so that the trained output has the anti-noise capability.
The encoder portion constructed by the embodiment of the present invention includes: a 1-dimensional Convolutional Neural Network (CNN), a Max-pool Layer (MPL), and two layers of Bidirectional Long Short Term Memory (BilSTM).
Through the superposition of a plurality of filters in the CNN, the edge detection at different angles in space is realized, the CNN can capture various characteristics in the PMU time sequence data of the power plant, and the time sequence data is disassembled into a plurality of characteristics. The mapping parameters of the filter structure are obtained by data learning, and the super parameters such as step length, the number of filters, the dimensionality of the filters and the like are adjusted manually.
The essence of MPL is to maximize the time series data, for example: and setting the MPL super parameter to be 4, wherein the maximum value is taken for every 4 values, and dimension reduction is realized. An intuitive understanding of this goal is to have neural networks only care about the emphasis in one area, the most salient features.
The basis of the BilSTM is a Long Short Term Memory neural network (LSTM), the input of the LSTM is a one-dimensional feature vector formed by the last CNN, timing sequence information is still contained at the moment, then the LSTM can map the timing sequence information with larger dimensionality into a vector with smaller dimensionality, and the mapped parameters are obtained by the neural network through data learning. There are special mechanisms inside the LSTM that make it possible to learn the temporal correlation between points and not treat each data point as independent, so that the resulting feature vector contains both the spatial edge features of the data (provided by CNN) and the temporal features (provided by LSTM).
The BilSTM inputs the input data in the forward direction once and then in the reverse direction once, and finally the output of the BilSTM and the output of the BilSTM are spliced, so that the above information and the following information can be learned, and the finally formed characteristic number is equal to the forward LSTM hidden layer node and the reverse LSTM hidden layer node. The hidden layer information is the language of the neural network, and the number of the nodes can be adjusted manually.
In the encoder part, the embodiment of the invention realizes the compression of power plant time sequence PMU data with tens of thousands of time points into hundreds or even tens of characteristics, and the characteristics are hierarchically described by a plurality of hidden layers inside a neural network. Before the advent of neural networks, feature mining was often required to process time series data, typically using averages, standard deviations, ratios of maxima to minima, or some statistically based F-value, among others. The embodiment of the invention compresses the data of the power plant times time point number into the data of the power plant times characteristic number.
The encoder can directly map each power plant to a euclidean space to calculate CID (complex-Invariant Distance) by obtaining the data of the number of power plants and the characteristic number, and the remaining problem is the determination of mapping parameters. For the above training problem, in order to obtain a structure capable of mapping time series data into feature vectors, the embodiment of the present invention adopts a basic idea of an Auto-encoder: compressing the data, if the compressed data can be basically restored, namely the input layer and the output layer are basically consistent, the compressed data retains most information, and the specific restoration link is realized by adding a decoder.
Referring to fig. 2, a decoder portion constructed in accordance with an embodiment of the present invention includes: an Upsample layer (Upsample) and an inverse CNN.
The CNN disassembles the time series data into several features, which the upsampling layer needs to restore. The upsampling layer of the embodiment of the present invention refers to a simple interpolation method, i.e., each time is repeated several times on the time axis.
Deconvolution is actually a special convolution operation that can be scaled from small samples to large samples. Specifically, 0 is first complemented for the original sequence, then the filter is rotated, and then calculation is performed according to a convolution formula.
After the two layers of upsampling and reverse CNN, the data is restored from the original power plant number characteristic number to the power plant number time point number, and then the difference before and after comparison is measured by Mean-square Error (MSE). Through the training of the decoder, the encoder can learn the mapping parameters, at the moment, the decoder layer is removed, and the rest is a structure capable of mapping the power plant PMU time sequence data into the eigenvector.
Step 202: calculating complexity invariance distance between unit time sequence data according to the wide-area phasor measurement data characteristics;
in clustering of plant time series frequency data, pairs of oscillating plants (which should be of the same class) tend to be further apart than simple euclidean distances of other plants in pairs (which are not necessarily of the same class). Thus, if only simple euclidean distances are used, it is possible to group two different classes of other power plants into the same class, but group a pair of oscillating power plants of the same class into two classes.
The embodiment of the invention defines the distance with the complexity taken into consideration as the similarity measurement standard for mining time series data, namely CID. Complexity invariance, which uses information about the complexity difference between two time series as a correction factor for the existing distance metric, produces a significant improvement in classification accuracy, the simple, parameter-free nature of which makes this improvement not detrimental to the efficiency of algorithms that call distance metrics frequently; modification of the triangle inequality can be used to take advantage of most existing indexing and data mining algorithms. The CIDs for time series Q and C are:
CID(Q,C)＝ED(Q,C)×CF(Q,C) (1)
wherein, ED (Q, C) represents Euclidean distance between time series Q and C, and CF (Q, C) represents complexity correlation coefficient between time series Q and C.
The complexity correlation coefficient CF is equivalent to a complexity ratio, and the more different the complexity, the more different the complexity correlation coefficient, the larger the CID, i.e. the farther the individuals are apart.
Figure BDA0002844674110000071
Wherein, the complexity measurement standards of the sequences Q and C are respectively CE (Q) and CE (C).
In the information theory, there are many methods for measuring the complexity of a time sequence, and the embodiment of the invention provides a method with strong intuition, strong interpretability and no parameter: the more complex a time series is, the longer it should be when it is "straightened out", i.e.:
Figure BDA0002844674110000072
wherein q isiAnd n is the number of sampling points. Since Q and C are both time series and are a string of data, the calculation formula of ce (C) is the same as that of ce (Q), see formula (3), which is not described herein again in the embodiments of the present invention.
Step 203: and determining the similarity between the samples in the n-dimensional space based on the complexity invariance distance, and clustering the unit samples according to the similarity result.
The k-means algorithm is most commonly used in the traditional clustering algorithm, the clustering speed is high, the structure is simple, and the method is widely applied. The idea of k-means is: k centroids are selected, and then the distance from each data point to the centroid is calculated, thereby determining which centroid the data point belongs to. After all calculations, the center point (i.e., the average) of each cluster is selected as the new centroid and the process is repeated. Termination conditions were as follows: the distance the centroid moves at each update is less than a certain threshold or is preset for the number of iterations, i.e., iterations, to be performed. This aggregates the data into k classes.
However, the conventional k-means algorithm needs to determine the number of groups of clusters in advance, which severely limits the application of the k-means algorithm in many scenes. Therefore, in the embodiment of the invention, the samples are not directly classified, but the probability that each sample belongs to a certain class is calculated, and is compared with the real distribution, so that the Kullback-Leibler (KL) divergence is calculated, the initial centroid and the encoder parameters of the clustering layer are reversely changed, and finally, the optimal clustering scheme with the minimum KL divergence loss value is selected through grid search without determining the group number in advance.
Based on Gaussian Mixture Model (GMM) and Expectation-maximization algorithm (EM), the optimal clustering result is searched by iteratively minimizing KL divergence, and the flowchart is shown in fig. 3.
The probability distribution of the prediction in step E in the figure is as follows:
Figure BDA0002844674110000081
wherein q isikRepresents the probability that the ith sample belongs to centroid k; phi (z)i|θk) Representing the similarity of the ith sample point and the kth centroid; a iskIs a gaussian distribution coefficient; z is a radical ofiIs an implicit variable of sample i;
Figure BDA0002844674110000082
representing the Gaussian distribution parameter, K being the total number of centroids, μkFor the k-th centroid corresponding to the mean value of the Gaussian distribution, σkThe k-th centroid corresponds to the variance of the gaussian distribution.
The new iteration parameters calculated in the step M are as follows:
the clustering mean of centroid k in the new iteration is:
Figure BDA0002844674110000083
where η is the learning rate. The embodiment of the invention creatively defines the Loss function Loss as the KL divergence (standard for measuring the difference between two distributions) of the prediction probability and the real estimation probability, namely:
Figure BDA0002844674110000084
the true estimated probability distribution is:
Figure BDA0002844674110000085
the covariance matrix is:
Figure BDA0002844674110000091
the gaussian distribution coefficient is:
Figure BDA0002844674110000092
wherein p isikThe true probability that the ith sample belongs to the centroid k is shown, N is the total number of the samples, and T is a transposed symbol; sigmakIs a covariance matrix; a iskIs a gaussian distribution coefficient.
Because the encoder and the decoder need to continuously optimize parameters, the embodiment of the invention carries out joint adjustment with the training process of the initial decoder and the initial encoder in fig. 2 by continuously and reversely fine-tuning the parameters and the centroid of the initial encoder, and when the two loss functions of KL divergence and MSE are minimum, the process is ended.
Example 3:
the feasibility of the schemes of examples 1 and 2 is verified below with reference to fig. 4, the calculation examples, and tables 1 to 4, as described in detail below:
a typical 16-machine 68 node 5 regional power system was set up for example analysis. With the generator G1 as a reference machine, a three-phase permanent fault is set in a certain ac branch between the nodes 46 to 49, the fault occurrence time is 0.1s, the fault duration time is 0.1s, the fault line cutting time is 0.2s, and the whole simulation time lasts 20 s.
By adopting the algorithm in the embodiment of the invention, the frequency data of the generator is input, if the fault is found in 0.2s, the coherent identification is carried out from 0.2s, and after repeated experiments, the identification result of the coherent cluster is shown in the following table 1.
TABLE 1 coherent cluster after failure of nodes 46 to 49
Figure BDA0002844674110000093
The fault location is changed, three-phase short-circuit faults are set between the nodes 1 to 2, between the nodes 8 to 9 and between the nodes 41 to 42, the previous steps are repeated, and the identification results of the coherent cluster are shown in the following table.
TABLE 2 coherent cluster after 1-2 node failures
Figure BDA0002844674110000101
TABLE 3 coherent cluster after 8-9 nodes failure
Figure BDA0002844674110000102
TABLE 4 coherent cluster after failure of nodes 41 to 42
Figure BDA0002844674110000103
As can be seen from the above table, due to different dominant oscillation modes excited by different faults, the identification results of the coherent clusters may be slightly different, wherein the coherent clusters identified when three-phase short-circuit faults occur between the nodes 8 to 9 and between the nodes 41 to 42 are the same.
The calculation example shows that: the deep neural network constructed based on the self-encoder idea provided by the embodiment of the invention is used for identifying the coherent cluster of the power system by means of wide-area synchronous phasor measurement information of the power system. Adopting CNN, MPL, Bi-LSTM, upsampling and deconvolution to build a deep neural network, regarding an input layer and an output layer as the same layer, and performing data mining and feature extraction; calculating the CID representation unit similarity of the data characteristics by considering the characteristic that the movement trends of the time sequence characteristics of the coherent unit are similar; based on KL divergence, GMM model probability clustering is improved, parameters in a clustering process are automatically set without depending on the number of predetermined clustering groups, so that an optimal coherent cluster division scheme is obtained, isolated units or clusters with few units can be accurately identified after local system faults, and the coherent cluster of the electric power system based on wide-area synchronous phasor measurement information is effectively identified. The method has strong robustness, is completely based on wide-area measurement data to perform coherent clustering, effectively avoids the influence of uncertainty of a power system model and parameters on coherent clustering results, avoids key feature loss of data mining, does not depend on the number of clusters determined in advance, can accurately identify isolated units, and realizes quick and accurate identification of coherent clusters of the power system. The research result has certain reference significance for the safe and stable online monitoring and wide area control of the power system under the background of wide area measurement.
In the embodiment of the present invention, except for the specific description of the model of each device, the model of other devices is not limited, as long as the device can perform the above functions.
Those skilled in the art will appreciate that the drawings are only schematic illustrations of preferred embodiments, and the above-described embodiments of the present invention are merely provided for description and do not represent the merits of the embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (7)

1. A coherent cluster identification method based on complex invariance and a deep neural network is characterized by comprising the following steps:
mapping the sample to an n-dimensional space, and mining wide-area phasor measurement data characteristics based on the constructed self-encoder deep neural network;
calculating complexity invariance distance between unit time sequence data according to the wide-area phasor measurement data characteristics;
and determining the similarity between the samples in the n-dimensional space based on the complexity invariance distance, and clustering the unit samples according to the similarity result.
2. The coherent cluster identification method based on complexity invariance and deep neural network as claimed in claim 1, wherein the self-encoder deep neural network comprises: an encoder and a decoder, and a control unit,
the encoder includes: the system comprises a 1-dimensional convolutional neural network, a maximum pooling layer and two layers of bidirectional long-term and short-term memory neural networks;
the decoder includes: an upsampling layer and a deconvolution neural network.
3. The coherent cluster identification method based on complexity invariance and deep neural network as claimed in claim 1, wherein said calculating complexity invariance distance between unit time series data according to wide-area phasor measurement data features specifically comprises:
the complexity invariance distance of the time series Q and C is:
CID(Q,C)＝ED(Q,C)×CF(Q,C)
wherein ED (Q, C) represents Euclidean distance between time series Q and C, and CF (Q, C) represents complexity correlation coefficient between time series Q and C;
Figure FDA0002844674100000011
wherein, the complexity measurement standards of the sequences Q and C are respectively CE (Q) and CE (C);
Figure FDA0002844674100000012
wherein q isiAnd n is the number of sampling points.
4. The coherent cluster identification method based on complexity invariance and deep neural network as claimed in claim 1, wherein said determining similarity between samples in n-dimensional space based on complexity invariance distance, clustering unit samples according to similarity result specifically comprises:
calculating the probability that each sample belongs to a certain class, comparing the probability with the real distribution, calculating KL divergence, reversely changing the initial centroid and the encoder parameters of the clustering layer, and finally selecting the optimal clustering scheme with the minimum KL divergence loss value through grid search;
based on GMM and EM, searching the optimal clustering result by iteratively minimizing KL divergence.
5. The coherent cluster identification method based on complexity invariance and deep neural network as claimed in claim 4, wherein said calculating the probability that each sample belongs to a certain class specifically comprises:
Figure FDA0002844674100000021
wherein q isikRepresents the probability that the ith sample belongs to centroid k; phi (z)i|θk) Representing the similarity of the ith sample point and the kth centroid; a iskIs a gaussian distribution coefficient; z is a radical ofiIs an implicit variable of sample i;
Figure FDA0002844674100000026
representing the Gaussian distribution parameter, K being the total number of centroids, μkFor the k-th centroid corresponding to the mean value of the Gaussian distribution, σkThe k-th centroid corresponds to the variance of the gaussian distribution.
6. The coherent cluster identification method based on complex invariance and deep neural network according to claim 4, wherein the comparing with the true distribution, calculating KL divergence, and reversely changing the initial centroid of the clustering layer and the encoder parameters specifically comprise:
the clustering mean of centroid k in the new iteration is:
Figure FDA0002844674100000022
wherein η is the learning rate, and defines the Loss function Loss as the KL divergence between the prediction probability and the true estimation probability:
Figure FDA0002844674100000023
the true estimated probability distribution is:
Figure FDA0002844674100000024
the covariance matrix is:
Figure FDA0002844674100000025
the gaussian distribution coefficient is:
Figure FDA0002844674100000031
wherein p isikThe true probability that the ith sample belongs to the centroid k is shown, N is the total number of the samples, and T is a transposed symbol; sigmakIs a covariance matrix; a iskIs a gaussian distribution coefficient.
7. The coherent cluster identification method based on complex invariance and deep neural network according to claim 4, wherein the optimal clustering scheme with the minimum KL divergence loss value finally selected through grid search specifically comprises:
and continuously and reversely fine-tuning the parameters and the centroid of the clustering layer of the initial encoder, and jointly adjusting the parameters and the centroid of the clustering layer with the training process of the initial encoder and the initial encoder, wherein when the two loss functions of KL divergence and MSE are minimum, the process is ended.
CN202011506029.9A 2020-12-18 2020-12-18 Coherent cluster identification method based on complex invariance and deep neural network Active CN112531706B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011506029.9A CN112531706B (en) 2020-12-18 2020-12-18 Coherent cluster identification method based on complex invariance and deep neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011506029.9A CN112531706B (en) 2020-12-18 2020-12-18 Coherent cluster identification method based on complex invariance and deep neural network

Publications (2)

Publication Number Publication Date
CN112531706A true CN112531706A (en) 2021-03-19
CN112531706B CN112531706B (en) 2023-04-18

Family

ID=75001861

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011506029.9A Active CN112531706B (en) 2020-12-18 2020-12-18 Coherent cluster identification method based on complex invariance and deep neural network

Country Status (1)

Country Link
CN (1) CN112531706B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115034337A (en) * 2022-08-10 2022-09-09 江西科骏实业有限公司 Method and device for identifying state of traction motor in rail transit vehicle and medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120123602A1 (en) * 2010-11-17 2012-05-17 Electric Power Research Institute, Inc. Application of phasor measurement units (pmu) for controlled system separation
CN106487026A (en) * 2016-08-25 2017-03-08 天津大学 A kind of Coherent Generator Group method for quickly identifying based on wide area measurement information
CN107590604A (en) * 2017-09-13 2018-01-16 国网福建省电力有限公司 The people having the same aspiration and interest unit grouping method and system of a kind of combination S-transformation and 2DPCA
CN110765700A (en) * 2019-10-21 2020-02-07 国家电网公司华中分部 Ultrahigh voltage transmission line loss prediction method based on quantum ant colony optimization RBF network
CN110943473A (en) * 2019-07-01 2020-03-31 浙江大学 Generator coherence identification method based on wide area measurement system and clustering theory

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120123602A1 (en) * 2010-11-17 2012-05-17 Electric Power Research Institute, Inc. Application of phasor measurement units (pmu) for controlled system separation
CN106487026A (en) * 2016-08-25 2017-03-08 天津大学 A kind of Coherent Generator Group method for quickly identifying based on wide area measurement information
CN107590604A (en) * 2017-09-13 2018-01-16 国网福建省电力有限公司 The people having the same aspiration and interest unit grouping method and system of a kind of combination S-transformation and 2DPCA
CN110943473A (en) * 2019-07-01 2020-03-31 浙江大学 Generator coherence identification method based on wide area measurement system and clustering theory
CN110765700A (en) * 2019-10-21 2020-02-07 国家电网公司华中分部 Ultrahigh voltage transmission line loss prediction method based on quantum ant colony optimization RBF network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘乃龙等: "基于多变量时间序列的接触状态聚类分析", 《电子科技大学学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115034337A (en) * 2022-08-10 2022-09-09 江西科骏实业有限公司 Method and device for identifying state of traction motor in rail transit vehicle and medium
CN115034337B (en) * 2022-08-10 2022-11-01 江西科骏实业有限公司 Method, device and medium for identifying state of traction motor in rail transit vehicle

Also Published As

Publication number Publication date
CN112531706B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
CN112350876A (en) Network flow prediction method based on graph neural network
CN112383052B (en) Power grid fault repairing method and device based on power internet of things
CN112116058A (en) Transformer fault diagnosis method for optimizing multi-granularity cascade forest model based on particle swarm algorithm
CN110726898A (en) Power distribution network fault type identification method
Liu et al. Short-term local prediction of wind speed and wind power based on singular spectrum analysis and locality-sensitive hashing
CN110943453A (en) Power system fault sample generation and model construction method facing transfer learning
CN112531706B (en) Coherent cluster identification method based on complex invariance and deep neural network
CN111965486A (en) Power distribution network fault identification method and system based on intelligent data fusion analysis
CN112289329A (en) High-voltage circuit breaker fault diagnosis method based on GWO-KFCM
CN107590604B (en) Coherent unit grouping method and system combining S transformation and 2DPCA
CN110929989B (en) N-1 safety checking method with uncertainty based on deep learning
Avgoustinakis et al. Audio-based near-duplicate video retrieval with audio similarity learning
CN116089777A (en) Intelligent new energy settlement method and system based on intelligent information matching
CN108805886B (en) Persistent clustering segmentation method for multi-fusion physical signatures
CN112016774A (en) Distribution network running state identification method and system based on data enhancement technology
CN113625108B (en) Flexible direct current power distribution network fault identification method
CN113283043B (en) Scene reduction solving method suitable for high-dimensional large-scale scene
CN112688836A (en) Energy routing equipment online dynamic sensing method based on deep self-coding network
Liu et al. A deep neural network pruning method based on gradient L1-norm
Dabou et al. Supervised learning of overcomplete dictionaries for rapid response-based dynamic stability prediction
Javaheri et al. Joint signal recovery and graph learning from incomplete time-series
CN105671596A (en) Method for determining single anode mathematical model of aluminum electrolysis cell
Romero et al. Outlier detection based on transformations for astronomical time series
CN112241787A (en) Neural network model pruning method and device
Liang et al. A fast manifold learning algorithm for dimensionality reduction

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
TA01 Transfer of patent application right

Effective date of registration: 20210623

Address after: 132012 No. 169, Changchun Road, Jilin, Jilin

Applicant after: NORTHEAST DIANLI University

Applicant after: STATE GRID LIAONING ELECTRIC POWER Research Institute

Applicant after: STATE GRID CORPORATION OF CHINA

Address before: 132012 No. 169, Changchun Road, Jilin, Jilin

Applicant before: NORTHEAST DIANLI University

Applicant before: STATE GRID LIAONING ELECTRIC POWER Research Institute

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant