CN115545280A - Low-voltage distribution network topology generation method and device - Google Patents
Low-voltage distribution network topology generation method and device Download PDFInfo
- Publication number
- CN115545280A CN115545280A CN202211143570.7A CN202211143570A CN115545280A CN 115545280 A CN115545280 A CN 115545280A CN 202211143570 A CN202211143570 A CN 202211143570A CN 115545280 A CN115545280 A CN 115545280A
- Authority
- CN
- China
- Prior art keywords
- voltage
- data
- dimensional
- low
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 72
- 238000000034 method Methods 0.000 title claims abstract description 64
- 239000011159 matrix material Substances 0.000 claims abstract description 52
- 230000002159 abnormal effect Effects 0.000 claims abstract description 17
- 238000010586 diagram Methods 0.000 claims abstract description 16
- 238000012163 sequencing technique Methods 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 17
- 238000005070 sampling Methods 0.000 claims description 14
- 230000009467 reduction Effects 0.000 claims description 12
- 238000005315 distribution function Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 abstract description 4
- 238000012937 correction Methods 0.000 abstract description 3
- 238000013024 troubleshooting Methods 0.000 abstract description 3
- 238000004088 simulation Methods 0.000 description 11
- 239000000243 solution Substances 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method and a device for generating a low-voltage distribution network topology, wherein the method comprises the following steps: acquiring a time sequence voltage data matrix according to the electrical quantity data, and performing reassignment on the screened abnormal acquisition data; running t-SNE algorithm to obtain low-dimensional voltage characteristic data set Y T (ii) a Operating a DBSCAN algorithm to obtain all cluster sets C and a two-dimensional voltage characteristic cluster map; running an LLE algorithm to obtain a two-dimensional voltage characteristic diagram under the classification of the cluster labels C; calculating and sequencing Euclidean distance relations between cluster centers and summary table clusters in the characteristic diagram, and outputting sequencing results; generating a node adjacency matrix based on the topology identification information obtained by the DBSCAN algorithm and the LLE algorithm; visualizing a node adjacency matrixAnd generating a low-voltage distribution network node connection topological graph. The invention can generate the node topological graph by visualizing the topological information, provides information reference for various advanced applications such as power grid topology error correction and troubleshooting, and can be widely applied to the field of optimized operation and management of the power distribution network.
Description
Technical Field
The invention relates to the field of optimized operation and management of a power distribution network, in particular to a method and a device for generating a low-voltage power distribution network topology.
Background
The distribution network of the low-voltage transformer area is directly connected with thousands of households, and the intelligent level of operation, maintenance and management of the distribution network directly influences the satisfaction degree of customers. The method has the advantages that the topological structure of the low-voltage transformer area is correctly identified, and the method has important significance for a power supply department to calculate the load flow, update the change of the switch state, analyze and judge faults, perform remote cost control, analyze line loss and provide an optimization strategy. However, with the development of economy, the number of low-voltage power supply transformer stations in each city is increased, the connection is disordered more and more, and even a phenomenon that wires are not wired according to regulations exists. With the increasingly wide application of distributed power supplies, controllable loads, electric vehicles and supply and demand response technologies, the safe operation level and economy of a power grid are improved, and meanwhile, the problem that the topology of an urban low-voltage power supply platform area is frequently changed is increasingly highlighted. Therefore, the topological structure recorded by the power supply department mostly has the conditions of data loss, recording errors and the like, and the adoption of the manual topology checking method has high cost and low efficiency. The method for efficiently, accurately and dynamically identifying the power topological structure in the transformer area is explored, a reasonable, accurate and unified low-voltage topological model is established, the management of users in the low-voltage transformer area by a power supply department is facilitated, the requirement on the power supply reliability of a power distribution network is met, and the service quality of customers is improved.
Currently, mainstream topology identification methods can be classified into an offline method and an online method. The off-line method is manually carried out on-site with hardware equipment for testing, sorting and classifying, consumes a large amount of manpower and material resources, and has high cost, low efficiency and accuracy and no automatic updating. The online method performs topology identification on the power distribution network by analyzing the electricity consumption related information, and has the advantages of low cost, high real-time performance and the like, such as an injection signal method, a data tag method and a data analysis method. However, in general, most of the existing network distribution area topology identification methods cannot fully mine the electrical quantity data information acquired by the smart meter in the actual project, and have the characteristics of simple and easy identification and complex structure identification. When a large-scale distribution network topological structure is identified, the accuracy rate still has a further improved space, and a low-voltage distribution network topology identification technology which can be practically applied to engineering is also subject to deep research.
Disclosure of Invention
In order to solve at least one of the technical problems in the prior art to a certain extent, the present invention provides a method and an apparatus for generating a low-voltage distribution network topology.
The technical scheme adopted by the invention is as follows:
a low-voltage distribution network topology generation method comprises the following steps:
acquiring electrical quantity data acquired by user electric meters in a low-voltage distribution area, extracting acquisition information from the electrical quantity data, and generating a time sequence voltage data matrix U according to the acquisition information; the acquisition information comprises an ammeter ID, a voltage amplitude and data acquisition time;
screening abnormal acquisition data from the time sequence voltage data matrix, and performing reassignment on the screened abnormal acquisition data;
assigning initial values to input parameters of the t-SNE algorithm, taking the time sequence voltage data matrix U as an input data set of the t-SNE algorithm, and operating the t-SNE algorithm to obtain a low-dimensional voltage characteristic data set Y T ；
Assigning initial values to input parameters of DBSCAN algorithm, and collecting low-dimensional voltage characteristic data set Y T The method comprises the steps of taking the voltage as an input data set of a DBSCAN algorithm, operating the DBSCAN algorithm, and obtaining all cluster sets C and a two-dimensional voltage characteristic cluster map;
assigning initial values to input parameters of the LLE algorithm, taking the time sequence voltage data matrix U as an input data set of the LLE algorithm, and operating the LLE algorithm to obtain a two-dimensional voltage characteristic diagram under the classification of the cluster labels C;
calculating and sequencing Euclidean distance relations between cluster centers and summary table clusters in the characteristic diagram, and outputting sequencing results to represent relative electrical distance relations between different user branches and the summary table;
generating a node adjacency matrix based on the topology identification information obtained by the DBSCAN algorithm and the LLE algorithm;
and visualizing the node adjacency matrix to generate a low-voltage distribution network node connection topological graph.
Further, the expression of the time sequence voltage data matrix U is:
in the formula, any voltage data U i,tj Expressed as meter i at t j The voltage amplitude measured at the moment; m represents the number of all the users in the region; n represents the number of voltage sampling points of the user collected in a certain period by a meter; any row vector U of time sequence voltage data matrix U i Representing time-series voltage data of the same user meter at all times measured during a sampling period, any column vector U tj And voltage data of different users collected by each ammeter at the same time are represented.
Further, the screened abnormal acquisition data is reassigned in the following way:
in the formula (I), the compound is shown in the specification,
for a certain sampling timing t in the voltage matrix err Abnormal voltage data collected by an ammeter;
and
respectively representing that the sampling time sequence is earlier than the time sequence t and is nearest to the abnormal acquisition data in the same time sequence voltage sequence err And later than the timing t err Normal voltage data.
Further, the input parameters of the t-SNE algorithm include n _ components, property, learning _ rate; wherein n _ components represents a target dimension reduction, perplexity represents a confusion degree, and learning _ rate represents a learning rate;
the t-SNE algorithm operates as follows:
a1, converting Euclidean distances of high-dimensional voltage data points into joint probabilities to express the correlation between the points, wherein the Gaussian distribution function is used for conversion in a high-dimensional space, and the conditional probabilities p are respectively calculated j|i ，p i|j And joint probability distribution p ij ；
A2, adopting normal distribution N (0,10) -4 I) Random initialization of a target low-dimensional dataset Y 0 ＝{y 1 ,y 2 ,...,y n }；
A3, converting the data in the low-dimensional space by using a t distribution function, and calculating the joint probability distribution q of the data in the low-dimensional space ij ；
A4, making probability distribution p ij ＝q ij Optimizing KL divergence between the two probability distributions to establish a target function; iteratively calculating gradient, and performing low-dimensional data set Y according to the calculated gradient t Updating is carried out;
a5, judging whether the iteration times reach n _ iter times or not; if yes, executing the step A6; if not, returning to execute the step A3;
a6, obtaining a low-dimensional characteristic data set with the minimum KL divergence, and representing Y as t-SNE characteristic of a high-dimensional data set T ＝{y 1 ,y 2 ,...,y n And two-dimensional voltage profiles.
Further, the conditional probability p j|i ，p i|j And joint probability distribution p ij The expression of (a) is as follows:
in the formula, x i ，x j ，x k Respectively inputting any 3 high-dimensional vectors in the data set; sigma i And σ j Are respectively represented by x i And x j The variance of a Gaussian function model of a Gaussian distribution center is determined in a binary search mode by inputting a parameter property; n is the number of high-dimensional vectors in the high-dimensional input data set;
joint probability distribution q of data in low dimensional space ij The expression of (c) is as follows:
in the formula, y i ，y j ，y k ，y l Representing initialized or updated target low-dimensional data sets Y, respectively 0 Or Y t Any 4 low-dimensional vectors.
Further, the iterative computation of the gradient is performed, and the target low-dimensional data set Y is subjected to the gradient obtained by the computation t Performing an update comprising:
and (3) iteratively calculating the gradient by adopting a gradient descent method:
in the formula, Y t-1 、Y t-2 Respectively represent Y t And (3) updating the target low-dimensional data sets in the previous two times, wherein eta represents the learning rate, and alpha (t) represents the momentum threshold given by the algorithm.
Further, the input parameters of the DBSCAN algorithm comprise epsilon and MinPts; wherein epsilon is the neighborhood radius of each input specified data sample object, and MinPts is the number of sample objects in the epsilon-neighborhood of the data sample;
the DBSCAN algorithm operates as follows:
b1, from a low-dimensional voltage characteristic data set Y T Optionally selecting a non-category core object as a seed, acquiring all data sample sets with density reachable relation with the core object as a cluster C j (ii) a The core object is defined as an object with the number of sample points in an epsilon-neighborhood being more than or equal to MinPts; density reachable relations are defined as, for a certain sample set, a given string of sample points p 1 ,p 2 ,...,p n ,p＝p 1 ,q＝p n Sample point p satisfying the condition i At p i-1 Within epsilon-neighborhood of (c), and p i-1 Is a core object, then object q is density reachable from object p;
b2, judging whether all the core objects have the categories or not, and if all the core objects have the categories, continuing to execute the step B3; otherwise, returning to execute the step B1;
and B3, marking a few abnormal sample points which are free outside the clusters as noise points, wherein the noise points are not near any core object, and the rest normal sample points are divided into each cluster, so that all cluster sets C and the two-dimensional voltage characteristic cluster map are finally obtained.
Further, the input parameters of the LLE algorithm include d, k and C; wherein d represents a target dimensionality reduction dimension, k represents the nearest neighbor number, and C represents a clustering label;
the LLE algorithm operates as follows:
c1, solving high-dimensional voltage data sample x according to Euclidean distance measurement i K nearest neighbors in the neighborhood
Obtaining high dimensional voltage data samples x i A corresponding local covariance matrix;
c2, obtaining a high-dimensional voltage data sample x i A corresponding weight coefficient vector;
c3, judging whether the conditions are met: solving the local covariance matrix and the weight coefficient vector corresponding to all the high-dimensional voltage data samples; if yes, continuing to execute the step C4; otherwise, returning to the step C1;
c4, according to the weight coefficient vector W i Forming a weight coefficient matrix W, and calculating a matrix M according to the weight coefficient matrix W;
c5, calculating the first d +1 eigenvalues of the matrix M and corresponding eigenvectors thereof, and expanding a matrix Y formed by the 2 nd eigenvector to the d +1 st eigenvector L ＝{y 2 ,y 3 ,...,y d+1 And (5) representing the LLE characteristics of the high-dimensional data set, and simultaneously outputting a two-dimensional voltage characteristic diagram under the classification of the cluster class label C.
Further, the high-dimensional voltage data sample x is obtained by the following method i The corresponding local covariance matrix:
Z i ＝(x i -x j )(x i -x j ) T
in the formula, x j Denotes x i K nearest neighbors in a neighborhood
Any one of the samples in (a);
obtaining high-dimensional voltage data sample x by the following method i Corresponding weight coefficient vector:
in the formula 1 k Expressed as a k-dimensional all-1 vector;
the expression of matrix M is as follows:
M＝(I-W)(I-W) T 。
the other technical scheme adopted by the invention is as follows:
a low voltage distribution network topology generation apparatus comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The invention has the beneficial effects that: the invention uses an improved data dimension reduction clustering method to analyze the voltage space-time characteristics of each load node in the low-voltage network under a long time scale, obtains the possible existing connection relation of each node, and further realizes the identification of node topology information in the low-voltage distribution network. By combining with the graph theory knowledge, the topological information can be visualized to generate a node topological graph, and information reference is provided for various high-level applications such as power grid topology error correction and troubleshooting.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description is made on the drawings of the embodiments of the present invention or the related technical solutions in the prior art, and it should be understood that the drawings in the following description are only for convenience and clarity of describing some embodiments in the technical solutions of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of an exemplary topology of a low voltage distribution substation according to an embodiment of the present invention;
fig. 2 is a simulation topology diagram of a low-voltage distribution network in engineering example 1 according to an embodiment of the present invention;
fig. 3 is a low-voltage distribution network topology prediction graph generated in engineering example 1 according to an embodiment of the present invention;
fig. 4 is a flowchart of a method for generating a topology of a low-voltage distribution network according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided only for convenience of illustration, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
In recent years, with the development and application of more and more intelligent terminal monitoring devices, a low-voltage power distribution network has more visual monitoring interfaces, a large amount of high-density user data information is fed back to a power grid company through an intelligent electric meter, and a data source is provided for automatic identification of a topological structure of a low-voltage power distribution area. The invention provides a low-voltage distribution network topology generation method based on data dimension reduction clustering and graph theory knowledge by utilizing user voltage data acquired by an advanced measurement system (AMI). The method uses an improved data dimension reduction clustering method to analyze the voltage space-time characteristics of each load node in the low-voltage network under a long time scale, and obtains the possible connection relation of each node, thereby realizing the identification of node topology information in the low-voltage distribution network. And then, by combining with the knowledge of graph theory, the topological information can be visualized to generate a node topological graph, and information reference is provided for various high-level applications such as power grid topology error correction and troubleshooting. Meanwhile, the method does not need to consume extra manpower and material resources for equipment installation and maintenance, is more efficient and convenient, and has a higher engineering application prospect. Fig. 1 is a schematic diagram of a typical topology of a low-voltage distribution substation.
As shown in fig. 4, the present embodiment provides a method for generating a topology of a low-voltage distribution network based on data dimension reduction clustering and graph theory knowledge, where the method is suitable for identifying a topology of a low-voltage distribution network, and specifically includes the following steps:
s1, acquiring a complete electric quantity data table acquired by each user electric meter in a low-voltage distribution area from a data acquisition center, extracting three types of key acquisition information (electric meter ID, voltage amplitude and data acquisition time), and generating a time sequence voltage data matrix U shown as the following formula;
in the formula: any voltage data U i,tj Expressed as meter i at t j The voltage amplitude measured at the moment; m represents the number of all the users in the region; n represents the number of voltage sampling points of the user collected by the meter in a certain period. Any row vector U of time sequence voltage data matrix U i Representing time-series voltage data of the same user meter at all times measured during a sampling period, any column vector U tj And voltage data of different users collected by each ammeter at the same time are represented.
S2, screening abnormal collected data (zero voltage data and voltage data with voltage fluctuation larger than 10% of a normal value) from the voltage matrix U, and re-assigning the data by adopting a linear fitting method shown as the following formula so as to avoid influencing the subsequent algorithm identification precision;
in the formula:
for a certain sampling timing t in the voltage matrix err Abnormal voltage data collected by an ammeter;
and
respectively representing distance abnormal acquisition data in same time sequence voltage sequence
Most recent and with sample timing earlier than t err And later than t err Normal voltage data.
S3, assigning initial values to input parameters n _ components, property, learning _ rate and n _ iter of the t-SNE algorithm, taking the voltage matrix U as an input data set of the t-SNE algorithm, and executing the t-SNE algorithm, wherein the specific execution steps comprise steps S4-S9.
Wherein n _ components represents the dimensionality reduction of the target, and is generally set to 2 to be more suitable for the visualization effect of the algorithm and the subsequent compatibility with the clustering algorithm; perplexity represents the degree of confusion, the value of the perplexity represents different convergence and divergence degrees of the dimension reduction data, and the value of the perplexity is generally set as the estimated cluster population size; learning _ rate represents the learning rate, which affects the rate of the cost function to find the optimal solution, and is generally set to 200; n _ iter represents the number of iterations that affect the convergence of the algorithm, which is typically set to 1000.
S4, converting Euclidean distances of high-dimensional voltage data points into joint probabilities to express the correlation between the points, wherein the Gaussian distribution function is used for conversion in a high-dimensional space, and the conditional probabilities p are respectively calculated j|i ，p i|j And joint probability distribution p ij As shown in the following formula;
in the formula: x is the number of i ，x j ，x k Respectively inputting any 3 high-dimensional vectors in the data set; sigma i And σ j Are respectively represented by x i And x j The variance of a Gaussian function model of a Gaussian distribution center is determined in a binary search mode by inputting a parameter property; n is the number of high-dimensional vectors in the high-dimensional input dataset.
S5, using normal distribution N (0,10) -4 I) Random initialization of a target low-dimensional dataset Y 0 ＝{y 1 ,y 2 ,...,y n }；
S6, converting the data in the low-dimensional space by using a t distribution function, and calculating the joint probability distribution q of the data in the low-dimensional space ij As shown in the following formula;
in the formula: y is i ，y j ，y k ，y l Representing initialized or updated target low-dimensional data sets Y, respectively 0 Or Y t Any 4 low-dimensional vectors.
S7, enabling p ij ＝q ij Optimizing KL divergence between two probability distributions, establishing an objective function, and iteratively calculating a gradient by a gradient descent method shown as the following formula
And a target low-dimensional data set Y t Updating is carried out;
in the formula: y is t-1 、Y t-2 Respectively represent Y t And (3) updating the target low-dimensional data sets in the previous two times, wherein eta represents the learning rate, and alpha (t) represents the momentum threshold given by the algorithm.
S8, judging whether the conditions are met: the iteration times reach n _ iter times;
a. if yes, continuing to execute the step S9;
b. if not, returning to the step S6;
s9, obtaining a low-dimensional characteristic data set with the minimum KL divergence as a t-SNE characteristic representation Y of a high-dimensional data set T ＝{y 1 ,y 2 ,...,y n And two-dimensional voltage profiles.
S10, assigning initial values to input parameters epsilon and MinPts of DBSCAN algorithm, and using the low-dimensional voltage characteristic data set Y obtained in S7 T As an input data set of the DBSCAN algorithm, the DBSCAN algorithm is executed, and the specific execution steps comprise steps S11-S13.
Wherein epsilon is the input neighborhood radius specifying each data sample object, minPts is the number of sample objects in the epsilon-neighborhood of a certain data sample, and two parameter values are generally determined by machine parameter tuning.
S11, firstly, from Y T Randomly selecting a non-category core object as a seed, and then finding out all data sample sets with density reachable relation with the core object, namely a cluster C j ；
The core object is defined as an object with the number of sample points in an epsilon-neighborhood being more than or equal to MinPts; density reachability relation is defined as a given string of sample points p for a sample set 1 ,p 2 ,...,p n ,p＝p 1 ,q＝p n Satisfies the conditionsSample point p i At p i-1 Within epsilon-neighborhood of (c), and p i-1 Is a core object, then object q is density reachable from object p.
S12, judging whether the conditions are met: all core objects have a class
a. If yes, continuing to execute the step S13;
b. if not, returning to the step S11;
s13, a few abnormal sample points which are free outside the clusters are marked as noise points, the points are not near any core object, the other normal sample points are divided into each cluster, and finally all cluster sets C and two-dimensional voltage characteristic cluster maps, namely low-voltage platform area classification results and user phase classification results, are obtained and output into a data table in an electric meter ID + classification result format.
And S14, assigning initial values to the input parameters d, k and C of the LLE algorithm, taking the voltage matrix U obtained in the S2 as an input data set of the LLE algorithm, and executing the LLE algorithm, wherein the specific execution steps comprise steps S15-S19.
Wherein d represents a target dimension reduction dimension, and is generally set to 2 to be more suitable for the visualization effect of the algorithm and the subsequent compatibility with the clustering algorithm; k represents the nearest neighbor number, reflects the linear representation sample number of any data, the larger the number is, the more accurate the representation is, and the value is generally set to be the total high-dimensional data sample number of-1; c represents the cluster label obtained in S11.
S15, solving a high-dimensional voltage data sample x according to Euclidean distance measurement i K nearest neighbors in a neighborhood
Then, x is obtained by the following formula i A corresponding local covariance matrix;
Z i ＝(x i -x j )(x i -x j ) T (9)
in the formula: x is the number of j Denotes x i K nearest neighbors in a neighborhood
Any one of the samples in (1).
S16, calculating x by using the following formula i A corresponding weight coefficient vector;
in the formula: 1 k Expressed as a k-dimensional all-1 vector.
S17, judging whether the conditions are met: solving the local covariance matrix and the weight coefficient vector corresponding to all the high-dimensional voltage data samples;
a. if yes, continuing to execute the step S18;
b. if not, returning to the step S15;
s18. The weight coefficient vector W i Forming a weight coefficient matrix W, and calculating a matrix M by using the following formula;
M＝(I-W)(I-W) T (11)
s19, calculating the first d +1 eigenvalues of the matrix M and corresponding eigenvectors thereof, and expanding a matrix Y from the 2 nd eigenvector to the d +1 st eigenvector L ＝{y 2 ,y 3 ,...,y d+1 Representing the LLE characteristics of the high-dimensional data set, and simultaneously outputting a two-dimensional voltage characteristic diagram under the classification of the cluster labels C;
s20, calculating and sequencing Euclidean distance relations between cluster centers and summary table clusters in the characteristic coordinate graph, and outputting sequencing results to represent relative electrical distance relations between different user branches and the summary table;
s21, generating a node adjacency matrix A shown as the following formula based on the topology identification information obtained in S13 and S19 ij ；
And S22, visualizing the node adjacency matrix to generate a low-voltage distribution network node connection topological graph.
The above method is explained in detail below with reference to the drawings and the specific embodiments.
Engineering example 1:
take 2 low voltage distribution network simulation topology data samples as an example, as shown in fig. 2. A topological network represents a low-voltage transformer area, and the node voltage represents the voltage measured by the user intelligent electric meter. The specific topological parameters are as follows: the low-voltage distribution network simulation topology 1 comprises 74 user nodes, the topology 2 comprises 82 user nodes, the voltage data acquisition length of each node is 30 days, the acquisition frequency is 15 min/time, and 2880 voltage acquisition moments are counted. Fig. 2 (a) is a schematic diagram of a simulation topology I, and fig. 2 (b) is a schematic diagram of a simulation topology II.
Because the voltage data similarity between a part of small branch nodes and adjacent large branch nodes in the simulation topology is high, it can be considered that the identification is correct when the small branch is merged into a certain adjacent large branch or a certain node is classified into an adjacent branch, the accuracy rate of the identification result is listed in table 1, and the low-voltage distribution network topology prediction graph is shown in fig. 3. Wherein, fig. 3 (a) is a simulation topology i topology prediction diagram, and fig. 3 (b) is a simulation topology ii topology prediction diagram.
Table 1 analysis and identification accuracy of tSNE-DBSCAN-LLE joint dimensionality reduction clustering method on simulation example
As can be seen from the analysis table 1, for the low-voltage distribution network simulation topology data, that is, under the condition of an ideal data sample, the provided identification method can effectively identify 3 types of topology information under the simulation topology, and generate a low-voltage distribution network prediction topology map according to the identification information, so as to realize the preliminary prediction of the low-voltage distribution area user topology.
Engineering example 2:
take the actual voltage data of users belonging to 3 transformer areas in Guangzhou City of Guangdong province in China as an example, wherein the basic parameters of the 3 actual transformer areas are shown in Table 2. Wherein, the data acquisition length of each intelligent ammeter is 3 days, the data acquisition frequency is 1 min/time, and 4320 moments are counted.
TABLE 2 actual base parameters of the distribution area
Through the field inspection of the corresponding station areas of the engineering embodiment, the accuracy of the recognition results is listed in table 3.
TABLE 3 comparison of accuracy of zone identification and phase identification results
As can be seen from the analysis table 3, the identification method can effectively identify the low-voltage user-low-voltage area affiliation relationship information and the user phase information in the actual low-voltage area for the actual engineering data.
Since the data acquisition capabilities of the smart meters used in each region are different, in order to obtain the application range of the identification method, the embodiment also performs special processing on the input data set, and performs example tests on the user voltage data with different sampling rates under the two conditions that the clock synchronization rate of the smart meter is 100% and the clock synchronization rate is 70%, and the test results are listed in tables 4 and 5 respectively.
TABLE 4 user voltage data test results at different sampling rates under 100% clock synchronization rate
TABLE 5 subscriber voltage data test results at different sampling rates at 70% clock synchronization rate
The test results in tables 4 and 5 show that the identification method can adapt to different data conditions, has certain effectiveness and superiority in solving the problem of identifying the topology information of the low-voltage transformer area, and can provide a reference for the subsequent research in the field of identifying the topology of the low-voltage transformer area.
The present embodiment further provides a low voltage distribution network topology generating device, including:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method of fig. 4.
The low-voltage power distribution network topology generation device provided by the embodiment of the invention can execute the low-voltage power distribution network topology generation method provided by the embodiment of the invention, can execute any combination implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
The embodiment of the application also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and executed by the processor to cause the computer device to perform the method illustrated in fig. 4.
The present embodiment also provides a storage medium, which stores instructions or programs capable of executing the method for generating a topology of a low voltage distribution network according to the method embodiment of the present invention, and when the instructions or the programs are executed, the steps can be implemented in any combination of the method embodiments, and the method has corresponding functions and advantages.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is to be determined from the appended claims along with their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the foregoing description of the specification, reference to the description of "one embodiment/example," "another embodiment/example," or "certain embodiments/examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A low-voltage distribution network topology generation method is characterized by comprising the following steps:
acquiring electrical quantity data acquired by user electric meters in a low-voltage distribution area, extracting acquisition information from the electrical quantity data, and generating a time sequence voltage data matrix U according to the acquisition information; the acquisition information comprises an ammeter ID, a voltage amplitude and data acquisition time;
screening abnormal acquisition data from the time sequence voltage data matrix, and performing reassignment on the screened abnormal acquisition data;
assigning initial values to input parameters of the t-SNE algorithm, taking the time sequence voltage data matrix U as an input data set of the t-SNE algorithm, and operating the t-SNE algorithm to obtain a low-dimensional voltage characteristic data set Y T ；
Assigning initial values to input parameters of DBSCAN algorithm, and collecting low-dimensional voltage characteristic data set Y T The method comprises the steps of using the voltage as an input data set of a DBSCAN algorithm, operating the DBSCAN algorithm, and obtaining all cluster sets C and a two-dimensional voltage characteristic cluster map;
assigning initial values to input parameters of the LLE algorithm, taking the time sequence voltage data matrix U as an input data set of the LLE algorithm, and operating the LLE algorithm to obtain a two-dimensional voltage characteristic diagram under the classification of the cluster labels C;
calculating and sequencing Euclidean distance relations between cluster centers and summary table clusters in the characteristic diagram, and outputting sequencing results to represent relative electrical distance relations between different user branches and the summary table;
generating a node adjacency matrix based on the topology identification information obtained by the DBSCAN algorithm and the LLE algorithm;
and visualizing the node adjacency matrix to generate a low-voltage distribution network node connection topological graph.
2. A method for generating a low voltage distribution network topology according to claim 1, characterized in that said time series voltage data matrix U has the expression:
in the formula, any voltage data U i,tj Expressed as meter i at t j The voltage amplitude measured at the moment; m represents the number of all the users in the region; n represents the number of voltage sampling points of the user collected in a certain period by a meter; any row vector U of time sequence voltage data matrix U i Representing time-series voltage data of the same user meter at all times measured during a sampling period, any column vector U tj And the voltage data of different users collected by each ammeter at the same time are represented.
3. The method according to claim 1, wherein the screened abnormal collected data is reassigned by:
in the formula (I), the compound is shown in the specification,
for a certain sampling timing t in the voltage matrix err Abnormal voltage data collected by an ammeter;
and
respectively representing that the sampling time sequence is earlier than the time sequence t and is nearest to the abnormal acquisition data in the same time sequence voltage sequence err And later than the timing t err Normal voltage data.
4. A method of generating a low voltage distribution network topology according to claim 1, characterized in that input parameters of said t-SNE algorithm comprise n _ components, property, learning _ rate; wherein n _ components represents a target dimension reduction, perplexity represents a confusion degree, and learning _ rate represents a learning rate;
the t-SNE algorithm operates as follows:
a1, converting Euclidean distances of high-dimensional voltage data points into joint probabilities to express the correlation between the points, wherein the Gaussian distribution function is used for conversion in a high-dimensional space, and the conditional probabilities p are respectively calculated j|i ，p i|j And joint probability distribution p ij ；
A2, adopting normal distribution N (0,10) -4 I) Random initialization of a target low-dimensional dataset Y 0 ＝{y 1 ,y 2 ,...,y n }；
A3, converting the data in the low-dimensional space by using a t distribution function, and calculating the joint probability distribution q of the data in the low-dimensional space ij ；
A4, making probability distribution p ij ＝q ij Optimizing KL divergence between the two probability distributions to establish a target function; iteratively calculating gradient, and performing low-dimensional data set Y according to the calculated gradient t Updating is carried out;
a5, judging whether the iteration times reach n _ iter times or not; if yes, executing the step A6; if not, returning to execute the step A3;
a6, obtaining a low-dimensional characteristic data set with the minimum KL divergence, and representing Y as t-SNE characteristic of a high-dimensional data set T ＝{y 1 ,y 2 ,...,y n And two-dimensional voltage profiles.
5. A method for generating a low voltage distribution network topology according to claim 4, characterized in that the conditional probability p j|i ，p i|j And joint probability distribution p ij The expression of (a) is as follows:
in the formula, x i ，x j ，x k Respectively inputting any 3 high-dimensional vectors in the data set; sigma i And σ j Are respectively represented by x i And x j The variance of a Gaussian function model of a Gaussian distribution center is determined in a binary search mode by inputting a parameter property; n is the number of high-dimensional vectors in the high-dimensional input data set;
joint probability distribution q of data in low dimensional space ij The expression of (a) is as follows:
in the formula, y i ，y j ，y k ，y l Representing initialized or updated target low-dimensional data sets Y, respectively 0 Or Y t Any 4 low-dimensional vectors.
6. A method for generating a low voltage distribution network topology according to claim 4, characterized in that said gradients are calculated iteratively, and said target low-dimensional data set Y is subjected to a gradient obtained by calculation t Performing an update comprising:
and (3) iteratively calculating the gradient by adopting a gradient descent method:
in the formula, Y t-1 、Y t-2 Respectively represent Y t And (3) updating the target low-dimensional data sets in the previous two times, wherein eta represents the learning rate, and alpha (t) represents the momentum threshold given by the algorithm.
7. A low voltage power distribution network topology generation method according to claim 1, wherein said DBSCAN algorithm input parameters include s and MinPts; wherein epsilon is the neighborhood radius of each input specified data sample object, and MinPts is the number of sample objects in the epsilon-neighborhood of the data sample;
the DBSCAN algorithm operates as follows:
b1, from a low-dimensional voltage characteristic data set Y T Randomly selecting a non-category core object as a seed to obtain all data sample sets with density reachable relation with the core objectAs a cluster C j (ii) a The core object is defined as an object with the number of sample points in an epsilon-neighborhood being more than or equal to MinPts; density reachable relations are defined as, for a certain sample set, a given string of sample points p 1 ,p 2 ,...,p n ,p＝p 1 ,q＝p n Sample point p satisfying the condition i At p i-1 Within epsilon-neighborhood of (c), and p i-1 Is a core object, then object q is density reachable from object p;
b2, judging whether all the core objects have the categories or not, and if all the core objects have the categories, continuing to execute the step B3; otherwise, returning to execute the step B1;
and B3, marking a few abnormal sample points which are free outside the clusters as noise points, wherein the noise points are not near any core object, and the rest normal sample points are divided into each cluster, so that all cluster sets C and the two-dimensional voltage characteristic cluster map are finally obtained.
8. The method of claim 1, wherein the input parameters of LLE algorithm include d, k and C; wherein d represents a target dimensionality reduction dimension, k represents the nearest neighbor number, and C represents a clustering label;
the LLE algorithm operates as follows:
c1, solving high-dimensional voltage data sample x according to Euclidean distance measurement i K nearest neighbors in a neighborhood
Obtaining high dimensional voltage data samples x i A corresponding local covariance matrix;
c2, obtaining a high-dimensional voltage data sample x i A corresponding weight coefficient vector;
c3, judging whether the conditions are met: solving the local covariance matrix and the weight coefficient vector corresponding to all the high-dimensional voltage data samples; if yes, continuing to execute the step C4; otherwise, returning to the step C1;
c4, according to the weight coefficient vector W i Forming a weight coefficient matrix W based on the weight coefficient matrix WCalculating a matrix M;
c5, calculating the first d +1 eigenvalues of the matrix M and corresponding eigenvectors thereof, and expanding a matrix Y from the 2 nd eigenvector to the d +1 st eigenvector L ＝{y 2 ,y 3 ,...,y d+1 LLE feature representation as a high-dimensional data set, and simultaneously outputting a two-dimensional voltage feature map under the classification of the cluster label C.
9. A method of generating a low voltage distribution network topology according to claim 8, characterized in that high dimensional voltage data samples x are obtained by i The corresponding local covariance matrix:
Z i ＝(x i -x j )(x i -x j ) T
in the formula, x j Denotes x i K nearest neighbors in a neighborhood
Any one of the samples in (a);
obtaining high-dimensional voltage data sample x by the following method i The corresponding weight coefficient vector:
in the formula 1 k Expressed as a k-dimensional all-1 vector;
the expression of matrix M is as follows:
M＝(I-W)(I-W) T 。
10. a low voltage power distribution network topology generation apparatus, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211143570.7A CN115545280A (en) | 2022-09-20 | 2022-09-20 | Low-voltage distribution network topology generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211143570.7A CN115545280A (en) | 2022-09-20 | 2022-09-20 | Low-voltage distribution network topology generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115545280A true CN115545280A (en) | 2022-12-30 |
Family
ID=84728203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211143570.7A Pending CN115545280A (en) | 2022-09-20 | 2022-09-20 | Low-voltage distribution network topology generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115545280A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879037A (en) * | 2023-02-23 | 2023-03-31 | 深圳合众致达科技有限公司 | Student apartment load identification method and system based on intelligent electric meter |
| CN116599055A (en) * | 2023-05-26 | 2023-08-15 | 联桥科技有限公司 | Topology network identification method and system for low-voltage distribution network area |
-
2022
- 2022-09-20 CN CN202211143570.7A patent/CN115545280A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879037A (en) * | 2023-02-23 | 2023-03-31 | 深圳合众致达科技有限公司 | Student apartment load identification method and system based on intelligent electric meter |
| CN116599055A (en) * | 2023-05-26 | 2023-08-15 | 联桥科技有限公司 | Topology network identification method and system for low-voltage distribution network area |
| CN116599055B (en) * | 2023-05-26 | 2023-12-01 | 联桥科技有限公司 | Topology network identification method and system for low-voltage distribution network area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111061821A (en) | Low-voltage distribution network topology verification method and system based on improved k value clustering algorithm | |
| CN115545280A (en) | Low-voltage distribution network topology generation method and device | |
| Giri et al. | An energy estimation framework for event-based methods in non-intrusive load monitoring | |
| US8756181B2 (en) | System and method employing a self-organizing map load feature database to identify electric load types of different electric loads | |
| CN110990461A (en) | Big data analysis model algorithm model selection method and device, electronic equipment and medium | |
| CN108985380B (en) | Point switch fault identification method based on cluster integration | |
| CN110335168B (en) | Method and system for optimizing power utilization information acquisition terminal fault prediction model based on GRU | |
| CN105468677A (en) | Log clustering method based on graph structure | |
| CN111177216A (en) | Association rule generation method and device for behavior characteristics of comprehensive energy consumer | |
| CN110555058A (en) | Power communication equipment state prediction method based on improved decision tree | |
| CN113660225A (en) | Network attack event prediction method, system, device and medium based on time sequence point | |
| CN111551888A (en) | Electric energy meter metering data fault analysis method based on improved AdaBoost algorithm | |
| CN112382354B (en) | Cr12MoV material hardness prediction method and device | |
| Bidoki et al. | Comparison of several clustering methods in the case of electrical load curves classification | |
| CN112163106A (en) | Second-order similarity perception image Hash code extraction model establishing method and application thereof | |
| CN114722947A (en) | Power dispatching monitoring data anomaly detection method based on neighbor search clustering | |
| Han et al. | Non‐intrusive load monitoring by voltage–current trajectory enabled asymmetric deep supervised hashing | |
| Kuang et al. | An Association Rules-Based Method for Outliers Cleaning of Measurement Data in the Distribution Network | |
| CN116247668A (en) | Power distribution network operation mode identification method based on measurement big data analysis | |
| Malik et al. | A Comparative Study on the Performance of Hidden Markov Model in Appliance Modeling | |
| Lv et al. | A new outlier detection method based on machine learning | |
| Tabarsaii et al. | Non intrusive load monitoring using additive time series modeling via finite mixture models aggregation | |
| Kegel | Feature-based time series analytics | |
| Jürgel et al. | Non-Intrusive Load Monitoring in the OpenHAB smart home framework | |
| Oyinlola | Energy prediction in edge environment for smart cities |
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 |