CN111080105A - Transformer area user-to-user relationship identification method and system based on voltage time sequence data - Google Patents
Transformer area user-to-user relationship identification method and system based on voltage time sequence data Download PDFInfo
- Publication number
- CN111080105A CN111080105A CN201911239321.6A CN201911239321A CN111080105A CN 111080105 A CN111080105 A CN 111080105A CN 201911239321 A CN201911239321 A CN 201911239321A CN 111080105 A CN111080105 A CN 111080105A
- Authority
- CN
- China
- Prior art keywords
- clustering
- observation
- variables
- data
- time sequence
- 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
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000003064 k means clustering Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000007621 cluster analysis Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 35
- 230000009467 reduction Effects 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 18
- 230000002087 whitening effect Effects 0.000 claims description 16
- 230000009466 transformation Effects 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 12
- 238000011946 reduction process Methods 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims 1
- 238000012880 independent component analysis Methods 0.000 abstract description 7
- 230000003068 static effect Effects 0.000 description 9
- 239000013598 vector Substances 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 6
- 230000005611 electricity Effects 0.000 description 4
- 238000000926 separation method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000006854 communication Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000007175 bidirectional communication Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a method and a system for identifying station area subscriber variation relationship based on voltage time sequence data, wherein the method comprises the following steps: collecting and processing voltage time sequence data of a transformer side and each user side of a distribution station area as a plurality of observation variables; the method comprises the steps of performing independent component analysis and feature extraction on a plurality of observation variables by adopting a FastICA technology to obtain a series of mutually independent random variables and mixing matrixes for estimating the plurality of observation variables, performing cluster analysis on data, namely the mixing matrixes after feature extraction, by utilizing a K-means clustering method to obtain clustering results, and determining the corresponding relation of users in a transformer area according to the clustering results.
Description
Technical Field
The invention relates to the technical field of power distribution network management of a power system, in particular to a station area user variable relation identification method and system based on the combination of FastICA algorithm and K-means clustering.
Background
With the rapid development of power grids, the number of power consumers continues to increase, and the scale and structure of low-voltage power distribution networks become larger and more complex. In order to facilitate management, a power company manages the low-voltage distribution network users in a distribution area, and the identification of the relationship among the stations is the basis for realizing marketing refinement, consumption reduction and loss reduction and is also the premise of electricity stealing detection. In order to ensure the accuracy of line loss calculation, the power department needs to frequently check the station area information of users. In a low-voltage transformer area, the circuits of part of old blocks are complex, and due to the reasons of imperfect transformer area information, untimely updating and the like, the user data of the transformer area are often inaccurate or even lost. In addition, the problems that the user incoming line end and the concentrator attribution relation are not accurately recorded and the station-to-user relation is not consistent with the actual condition caused by the change of user wiring or the line reconstruction due to balanced load distribution occur, so that the effective identification of the station-to-user relation is particularly important under the condition of no power failure.
The method for recognizing the relation between users in the foreground is mainly divided into manual recognition and special station area recognition equipment. The manual identification mainly depends on the electric power personnel to find out the affiliation of the user station area to the on-site resident, and along with the increasing of the electricity consumption, the manual identification wastes time and energy and has low efficiency. The special station area identification equipment mainly adopts a pulse current method, wherein the pulse current method is used for sending pulse current signals at the transformer end and receiving the pulse current signals at the identification terminal to complete identification. However, the method cannot perform bidirectional communication, usually requires carrier communication to be used in cooperation with auxiliary communication, and in addition, when a pulse current signal passes through a transformer, an alternating magnetic field cannot be generated, and the pulse current signal cannot pass through the transformer, so that the pulse current signal can only be transmitted in the same phase line range of the same transformer area.
In recent years, with the large-scale installation and popularization of the smart electric meters at the user sides, a power grid can obtain massive operation data such as user voltage, current and the like. In view of the problems in the current research, a method for determining the relationship between the users without installing additional devices and apparatuses and without manual detection is needed.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, an object of the present invention is to provide a station-to-station relationship identification method based on voltage time series data, which can realize intelligent identification of the station-to-station relationship by using only the voltage time series data while ensuring accuracy.
Another objective of the present invention is to provide a station-area correlation identification system based on voltage time series data.
In order to achieve the above object, an embodiment of the present invention provides a station area correlation identification method based on voltage time series data, including the following steps: collecting and processing time sequence voltage data of a transformer side and a user side of a distribution transformer area to obtain a plurality of observation variables; performing dimensionality reduction processing on the plurality of observation variables by adopting a FastICA algorithm to obtain corresponding independent components and corresponding mixed matrixes of the plurality of observation variables; and performing clustering analysis on the mixed matrix by using a K-means clustering method to obtain a clustering result, and determining the corresponding relation of the users in the distribution area according to the clustering result.
According to the station area user variable relation identification method based on the voltage time sequence data, the FastICA algorithm and the K-means method are sequentially used for carrying out data dimension reduction and clustering to realize user variable relation identification, extra equipment and devices do not need to be installed, manual detection is not needed, user voltage time sequence data only need to be collected according to a certain sampling rate, manpower and material resources can be saved to realize user variable relation identification, meanwhile, FastICA independent component analysis converts the voltage time sequence data into static characteristics, the calculated amount in the process of utilizing the voltage time sequence data correlation calculation is reduced, and the efficiency is improved.
In addition, the station area correlation identification method based on the voltage time series data according to the above embodiment of the present invention may further have the following additional technical features:
further, in an embodiment of the present invention, before performing the dimension reduction process of the FastICA algorithm, data preprocessing is performed on the plurality of observation variables, wherein the data preprocessing includes a decentralization and a whitening transformation.
Further, in one embodiment of the present invention, the decentralized process is: calculating an average value of the plurality of observed variables; and subtracting the average value from each sampling point of each observation variable to obtain the decentralized observation variable.
Further, in one embodiment of the present invention, the whitening transformation is to remove the correlation between each observed variable to simplify the extraction process of the independent components.
Further, in an embodiment of the present invention, the performing cluster analysis on the mixing matrix by using K-means clustering includes: selecting k samples from the mixing matrix as initial clustering centers; classifying the k samples into a class to which a clustering center closest to the k samples belongs; recalculating the clustering center; the classification and recalculation processes are iteratively performed until the objective function converges or a maximum number of iterations is reached.
In order to achieve the above object, another embodiment of the present invention provides a station area correlation identification system based on voltage time series data, including: the acquisition module is used for acquiring and processing time sequence voltage data of a transformer side and a user side of a distribution transformer area to obtain a plurality of observation variables; the dimension reduction module is used for carrying out dimension reduction processing on the plurality of observation variables by adopting a FastICA algorithm to obtain corresponding independent components and corresponding mixing matrixes of the plurality of observation variables; and the clustering module is used for carrying out clustering analysis on the mixed matrix by using a K-means clustering method to obtain a clustering result and determining the corresponding relation of the users in the distribution area according to the clustering result.
According to the station area user variable relation identification system based on the voltage time sequence data, the FastICA algorithm and the K-means method are sequentially used for carrying out data dimension reduction and clustering to realize user variable relation identification, extra equipment and devices do not need to be installed, manual detection is not needed, user voltage time sequence data only need to be collected according to a certain sampling rate, manpower and material resources can be saved to realize user variable relation identification, meanwhile, FastICA independent component analysis converts the voltage time sequence data into static characteristics, the calculated amount in the process of utilizing the voltage time sequence data correlation calculation is reduced, and the efficiency is improved.
In addition, the station area correlation identification system based on the voltage time series data according to the above embodiment of the present invention may further have the following additional technical features:
further, in an embodiment of the present invention, before performing the dimension reduction process in the dimension reduction module, data preprocessing is performed on the plurality of observation variables, where the data preprocessing includes decentralization and whitening transformation.
Further, in one embodiment of the present invention, the decentralized process is: calculating an average value of the plurality of observed variables; and subtracting the average value from each sampling point of each observation variable to obtain the decentralized observation variable.
Further, in one embodiment of the present invention, the whitening transformation is to remove the correlation between each observed variable to simplify the extraction process of the independent components.
Further, in an embodiment of the present invention, in the clustering module, performing cluster analysis on the mixing matrix by using a K-means clustering method includes: the selecting unit is used for selecting k samples from the mixed matrix as initial clustering centers; the classification unit is used for classifying the k samples into a class to which a cluster center closest to the k samples belongs; a recalculation unit for recalculating the clustering center; and the iteration unit is used for iteratively executing the classification and recalculation processes until the target function converges or the maximum iteration times is reached.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a station-to-station relationship identification method based on voltage timing data according to an embodiment of the present invention;
fig. 2 is a detailed flowchart of station-to-station relationship change identification according to an embodiment of the present invention;
FIG. 3 is a flow chart of voltage timing observation variable feature extraction according to one embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a station-area correlation identification system based on voltage timing data according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a clustering module in a station-to-station user-variable relationship identification system based on voltage timing data 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 drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The method and system for identifying station area diversity relationship based on voltage time series data according to the embodiments of the present invention are described below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a station area subscriber relationship identification method based on voltage timing data according to an embodiment of the present invention.
As shown in fig. 1, the station area correlation identification method based on voltage time series data includes the following steps:
in step S101, time series voltage data of the transformer side and the user side of the distribution substation are collected and processed to obtain a plurality of observation variables.
Specifically, the method and the device for acquiring the time sequence voltage data of the transformer and the users in the transformer area acquire the time sequence voltage data of the transformer and the users in the transformer area from an acquisition system, and then clear up and clean the time sequence voltage data to obtain a plurality of observation variables;
in step S102, a FastICA algorithm is used to perform dimensionality reduction on the plurality of observed variables to obtain corresponding independent components and corresponding mixing matrices of the plurality of observed variables.
It should be noted that, before the dimension reduction processing of the FastICA algorithm is performed, data preprocessing is performed on a plurality of observation variables, wherein the data preprocessing includes the decentralization and the whitening transformation.
Wherein the decentralized process comprises the following steps: calculating an average value of a plurality of observed variables; and subtracting the average value from each sampling point of each observation variable to obtain the decentralized observation variable.
The specific treatment process is as follows:
for m observation variables with the number of n sampling points, firstly, calculating the average value of the observation variables by using the formula (1), and then subtracting the average value of the observation variables from each sampling point of each observation variable to obtain the decentralized observation variables, wherein the formula (2) is shown.
Wherein, the whitening transformation is to remove the correlation between each observation variable to simplify the extraction process of the independent components.
For example, as shown in FIG. 2, for an observed variable x1(t),x2(t),…,xm(t) performing a whitening transformation, namely:
z(t)=Bx(t) (3)
wherein the content of the first and second substances,is a whitening matrix, E is a covariance matrix E { x (t)TThe unit orthogonal eigenvector of the unit is a matrix of columns; Γ ═ diag (γ)1,γ2,...γm) Is E { x (t)TThe eigenvalues of the are diagonal matrices of diagonal elements, Γ-1/2The diagonal matrix is obtained by taking a square root and then taking the reciprocal of a diagonal element of the gamma.
It should be noted that the objective of the FastICA algorithm is to find a separation matrix WzSo that s (t) is WzZ (t) has the greatest non-Gaussian property, where WzIs the corresponding separation matrix after whitening of the observed variable. Separation matrix W corresponding to observed variable and separation matrix W corresponding to whitened variablezThe following relations exist between the following components:
W=WzB (4)
solving by using FastICA algorithm to obtain WzAnd then obtaining W according to the formula (6), and solving the inverse matrix or the generalized inverse matrix of W to finally obtain a mixed matrix A of the observed variables.
Further, the dimension reduction processing by using the FastICA algorithm comprises the following specific steps:
(1) carrying out whitening transformation on the observation variable X (t) to obtain Z (t) with zero mean and unit variance characteristics;
(2) selecting a random initial weight vector Wz_pSubscript p denotes the pth iteration, let p equal to 1;
(3) the weight vector W is aligned according to equation (5)z_pAdjusting, wherein E (-) is mean value operation, g (-) is nonlinear function;
(4) for weight vector Wz_pPerforming orthogonalization operation;
(5) for weight vector Wz_pCarrying out normalization processing;
Wz_p=Wz_p/||Wz_p|| (7)
(6) if Wz_pIf not, returning to the step (3) to continue iteration;
(7) if p is equal to p +1 and is less than or equal to m, returning to the step (2);
where ICA can be essentially thought of as representing the original observed variable by a linear combination of a set of independent random variables, the expansion is written as follows:
all the observed variables can be linearly represented by random variables, and if the set of random variables is regarded as a set of bases under a high-dimensional space, the row vector a in the mixing matrix AiAnd corresponding to the coordinate of an observation variable in the high-dimensional space, thereby realizing the representation of time series data by using static data. As shown in fig. 3, from the aspect of time series data feature extraction, the set of bases s (t) can be used as the feature of the time series data, and then the row vector aiRepresenting the corresponding characteristic value.
In step S103, performing clustering analysis on the mixed matrix by using a K-means clustering method to obtain a clustering result, and determining a corresponding relationship between users in the distribution area according to the clustering result.
From step S102, the row vector a of the mixing matrix is knowniRepresenting corresponding observation variables, therefore, a static data clustering mode can be used for replacing time sequence data clustering, and K-means clustering is adopted for the obtained mixing matrix.
It is understood that the similarity relationship between the row vectors of the mixing matrix a reflects the similarity relationship between the observed variables x (t) from the relationship between the linear space basis and the coordinates. Therefore, clustering of the observation variables can be realized by clustering the row vectors of A. The dimension of the mixing matrix A is irrelevant to the time t, so that the dimension of time sequence data and the complexity of cluster analysis are greatly reduced.
In the identification of the relation of the subscriber, the category number of the user electricity consumption data needing to be subjected to clustering analysis can be determined in advance and is suitable for adopting a K-means algorithm, so that the embodiment of the invention adopts the ICA-based K-means algorithm to cluster the user electricity consumption time sequence data. Wherein the target function of the K-means is as follows:
in the formula (d)ijIs the Euclidean distance from the sample point to the distance center, k is the number of clusters, niIs the number of samples i, ciIs the cluster center of the ith type sample.
Further, in an embodiment of the present invention, performing cluster analysis on the mixing matrix by using K-means clustering includes:
selecting k samples from the mixed matrix as initial clustering centers;
classifying the k samples into a class to which a clustering center closest to the k samples belongs;
recalculating the clustering center;
the classification and recalculation processes are iteratively performed until the objective function converges or a maximum number of iterations is reached.
That is, the clustering process of K-means is:
(1) selecting k samples as initial clustering centers;
(2) classifying each sample into a class where a cluster center closest to the sample is located;
(3) recalculating the clustering center;
(4) repeating the steps (2) and (3) until the target function converges or the maximum iteration number is reached, obtaining the result of K-means clustering, determining the station area phase information of each class by the determined station area and phase in the class, and determining the station area phase information to which the user belongs in the class, thereby realizing the station area user variable relationship identification.
According to the station area user variation relation identification method based on the voltage time sequence data, provided by the embodiment of the invention, the static characteristics of the time sequence data are extracted by firstly processing the collected user voltage time sequence data and analyzing the FastICA independent components; then, a K-means clustering method of static data is applied to carry out clustering analysis on static characteristics (namely a mixed matrix), so that voltage time sequence data are automatically classified into corresponding categories to realize the identification of the user variable relationship, extra equipment and devices are not required to be installed in the method, manual detection is not required, the voltage time sequence data of a user are only required to be collected according to a certain sampling rate, and the identification of the user variable relationship can be realized by saving manpower and material resources; the FastICA independent component analysis converts the voltage time sequence data into static characteristics, reduces the calculation amount when the voltage time sequence data correlation is used for calculation, and improves the efficiency.
Next, a station-to-station relationship identification system based on voltage timing data according to an embodiment of the present invention will be described with reference to the drawings.
Fig. 4 is a table-area-subscriber relationship identification system based on voltage timing data according to an embodiment of the present invention.
As shown in fig. 4, the station-to-station relationship identification system 10 based on voltage timing data includes: the system comprises an acquisition module 100, a dimension reduction module 200 and a clustering module 300.
The obtaining module 100 is configured to collect and process time sequence voltage data of a transformer side and a user side of a distribution substation to obtain a plurality of observation variables. The dimension reduction module 200 is configured to perform dimension reduction processing on a plurality of observation variables by using a FastICA algorithm, and obtain corresponding independent components and corresponding mixing matrices of the observation variables. The clustering module 300 is configured to perform clustering analysis on the mixed matrix by using a K-means clustering method to obtain a clustering result, and determine a corresponding relationship between users in the distribution area according to the clustering result.
Further, in an embodiment of the present invention, before performing the dimension reduction process in the dimension reduction module, a data preprocessing is performed on the plurality of observation variables, wherein the data preprocessing includes a decentralization and a whitening transformation.
Further, in one embodiment of the present invention, the decentralized process is: calculating an average value of a plurality of observed variables; and subtracting the average value from each sampling point of each observation variable to obtain the decentralized observation variable.
Further, in one embodiment of the present invention, the whitening transformation is to remove the correlation between each observed variable to simplify the extraction process of the independent components.
Further, as shown in fig. 5, in an embodiment of the present invention, in the clustering module 300, performing cluster analysis on the mixing matrix by using a K-means clustering method includes:
a selecting unit 301, configured to select k samples in the mixed matrix as an initial clustering center;
a classifying unit 302, configured to classify the k samples into a class to which a cluster center closest to the k samples belongs;
a recalculation unit 303 for recalculating the clustering center;
an iteration unit 304 for iteratively performing the classification and recalculation processes until the objective function converges or a maximum number of iterations is reached.
According to the station area user variable relation recognition system based on the voltage time sequence data, the FastICA algorithm and the K-means method are sequentially used for carrying out data dimension reduction and clustering to realize user variable relation recognition, extra equipment and devices do not need to be installed, manual detection is not needed, user voltage time sequence data only need to be collected according to a certain sampling rate, manpower and material resources can be saved to realize user variable relation recognition, meanwhile, FastICA independent component analysis converts the voltage time sequence data into static characteristics, the calculated amount in the process of utilizing the voltage time sequence data correlation calculation is reduced, and the efficiency is improved.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean 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, the schematic representations of the terms used above are not necessarily intended to 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. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A transformer area user variation relation identification method based on voltage time sequence data is characterized by comprising the following steps:
collecting and processing time sequence voltage data of a transformer side and a user side of a distribution transformer area to obtain a plurality of observation variables;
performing dimensionality reduction processing on the plurality of observation variables by adopting a FastICA algorithm to obtain corresponding independent components and corresponding mixed matrixes of the plurality of observation variables; and
and performing clustering analysis on the mixed matrix by using a K-means clustering method to obtain a clustering result, and determining the corresponding relation of the users in the distribution area according to the clustering result.
2. The method for identifying station area diversity relationship based on voltage time series data according to claim 1, wherein before performing dimension reduction processing of the FastICA algorithm, data preprocessing is performed on the plurality of observation variables, wherein the data preprocessing includes decentralization and whitening transformation.
3. The method for identifying station area diversity relationship based on voltage time series data according to claim 2, wherein the decentralized process is as follows:
calculating an average value of the plurality of observed variables;
and subtracting the average value from each sampling point of each observation variable to obtain the decentralized observation variable.
4. The method for identifying station-area correlation based on voltage time series data according to claim 2, wherein the whitening transformation is to remove the correlation between each observation variable so as to simplify the extraction process of independent components.
5. The method for identifying station area diversity relationship based on voltage time series data according to claim 1, wherein the performing cluster analysis on the mixing matrix by using K-means clustering comprises:
selecting k samples from the mixing matrix as initial clustering centers;
classifying the k samples into a class to which a clustering center closest to the k samples belongs;
recalculating the clustering center;
the classification and recalculation processes are iteratively performed until the objective function converges or a maximum number of iterations is reached.
6. A transformer area user-dependent relationship identification system based on voltage time sequence data is characterized by comprising:
the acquisition module is used for acquiring and processing time sequence voltage data of a transformer side and a user side of a distribution transformer area to obtain a plurality of observation variables;
the dimension reduction module is used for carrying out dimension reduction processing on the plurality of observation variables by adopting a FastICA algorithm to obtain corresponding independent components and corresponding mixing matrixes of the plurality of observation variables; and
and the clustering module is used for carrying out clustering analysis on the mixed matrix by using a K-means clustering method to obtain a clustering result and determining the corresponding relation of the users in the distribution area according to the clustering result.
7. The system of claim 6, wherein the pre-processing of the plurality of observation variables is performed before performing the dimensionality reduction process in the dimensionality reduction module, wherein the pre-processing of the data comprises a de-centering and a whitening transformation.
8. The system of claim 7, wherein the decentralized process comprises:
calculating an average value of the plurality of observed variables;
and subtracting the average value from each sampling point of each observation variable to obtain the decentralized observation variable.
9. The voltage timing data-based station area correlation identification system according to claim 7, wherein the whitening transformation is to remove correlation between each observed variable to simplify the extraction process of independent components.
10. The system for identifying station area diversity relationship based on voltage time series data according to claim 6, wherein in the clustering module, the mixing matrix is clustered and analyzed by using a K-means clustering method, and the method comprises:
the selecting unit is used for selecting k samples from the mixed matrix as initial clustering centers;
the classification unit is used for classifying the k samples into a class to which a cluster center closest to the k samples belongs;
a recalculation unit for recalculating the clustering center;
and the iteration unit is used for iteratively executing the classification and recalculation processes until the target function converges or the maximum iteration times is reached.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911239321.6A CN111080105A (en) | 2019-12-06 | 2019-12-06 | Transformer area user-to-user relationship identification method and system based on voltage time sequence data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911239321.6A CN111080105A (en) | 2019-12-06 | 2019-12-06 | Transformer area user-to-user relationship identification method and system based on voltage time sequence data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111080105A true CN111080105A (en) | 2020-04-28 |
Family
ID=70313092
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911239321.6A Pending CN111080105A (en) | 2019-12-06 | 2019-12-06 | Transformer area user-to-user relationship identification method and system based on voltage time sequence data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111080105A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111612056A (en) * | 2020-05-16 | 2020-09-01 | 青岛鼎信通讯股份有限公司 | Low-pressure customer variation relation identification method based on fuzzy clustering and zero-crossing offset |
CN111861789A (en) * | 2020-07-14 | 2020-10-30 | 国网湖南省电力有限公司 | Method and system for identifying user variable relationship based on current data integer programming solution |
CN111897888A (en) * | 2020-08-17 | 2020-11-06 | 国网辽宁省电力有限公司沈阳供电公司 | Household variable relation identification method based on Spark framework and coacervation hierarchical clustering algorithm |
CN112000917A (en) * | 2020-10-30 | 2020-11-27 | 杭州电子科技大学 | Low-voltage user meter box identification method integrating known phase difference and address information |
CN112415304A (en) * | 2020-10-30 | 2021-02-26 | 国网天津市电力公司 | Line identification method based on low-voltage transformer area voltage data curve grouping |
CN112631147A (en) * | 2020-12-08 | 2021-04-09 | 国网四川省电力公司经济技术研究院 | Intelligent power grid frequency estimation method and system for impulse noise environment |
CN112819649A (en) * | 2020-12-30 | 2021-05-18 | 国网北京市电力公司 | Method and device for determining station area subscriber change relationship |
CN113344450A (en) * | 2021-07-02 | 2021-09-03 | 广东电网有限责任公司 | Low-voltage station area subscriber identification method, system, terminal equipment and storage medium |
CN115577993A (en) * | 2022-12-09 | 2023-01-06 | 江苏瑞电智芯信息科技有限公司 | Transformer area household change identification method based on time sequence matching |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050091189A1 (en) * | 2003-10-27 | 2005-04-28 | Bin Zhang | Data mining method and system using regression clustering |
CN108734603A (en) * | 2018-05-24 | 2018-11-02 | 河南工业大学 | Big data phase recognition methods based on cluster |
CN109740641A (en) * | 2018-12-18 | 2019-05-10 | 清华四川能源互联网研究院 | A kind of area user identification zone method clustered based on principal component analysis and k-means |
-
2019
- 2019-12-06 CN CN201911239321.6A patent/CN111080105A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050091189A1 (en) * | 2003-10-27 | 2005-04-28 | Bin Zhang | Data mining method and system using regression clustering |
CN108734603A (en) * | 2018-05-24 | 2018-11-02 | 河南工业大学 | Big data phase recognition methods based on cluster |
CN109740641A (en) * | 2018-12-18 | 2019-05-10 | 清华四川能源互联网研究院 | A kind of area user identification zone method clustered based on principal component analysis and k-means |
Non-Patent Citations (1)
Title |
---|
何川 等: "基于改进单通道 FastICA的谐波与间谐波检测" * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111612056A (en) * | 2020-05-16 | 2020-09-01 | 青岛鼎信通讯股份有限公司 | Low-pressure customer variation relation identification method based on fuzzy clustering and zero-crossing offset |
CN111861789A (en) * | 2020-07-14 | 2020-10-30 | 国网湖南省电力有限公司 | Method and system for identifying user variable relationship based on current data integer programming solution |
CN111897888A (en) * | 2020-08-17 | 2020-11-06 | 国网辽宁省电力有限公司沈阳供电公司 | Household variable relation identification method based on Spark framework and coacervation hierarchical clustering algorithm |
CN112415304B (en) * | 2020-10-30 | 2022-08-23 | 国网天津市电力公司 | Line identification method based on low-voltage transformer area voltage data curve grouping |
CN112000917B (en) * | 2020-10-30 | 2021-02-09 | 杭州电子科技大学 | Low-voltage user meter box identification method integrating known phase difference and address information |
CN112415304A (en) * | 2020-10-30 | 2021-02-26 | 国网天津市电力公司 | Line identification method based on low-voltage transformer area voltage data curve grouping |
CN112000917A (en) * | 2020-10-30 | 2020-11-27 | 杭州电子科技大学 | Low-voltage user meter box identification method integrating known phase difference and address information |
CN112631147A (en) * | 2020-12-08 | 2021-04-09 | 国网四川省电力公司经济技术研究院 | Intelligent power grid frequency estimation method and system for impulse noise environment |
CN112631147B (en) * | 2020-12-08 | 2023-05-02 | 国网四川省电力公司经济技术研究院 | Intelligent power grid frequency estimation method and system oriented to impulse noise environment |
CN112819649A (en) * | 2020-12-30 | 2021-05-18 | 国网北京市电力公司 | Method and device for determining station area subscriber change relationship |
CN113344450A (en) * | 2021-07-02 | 2021-09-03 | 广东电网有限责任公司 | Low-voltage station area subscriber identification method, system, terminal equipment and storage medium |
CN113344450B (en) * | 2021-07-02 | 2023-01-20 | 广东电网有限责任公司 | Low-voltage station area subscriber identification method, system, terminal equipment and storage medium |
CN115577993A (en) * | 2022-12-09 | 2023-01-06 | 江苏瑞电智芯信息科技有限公司 | Transformer area household change identification method based on time sequence matching |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111080105A (en) | Transformer area user-to-user relationship identification method and system based on voltage time sequence data | |
CN112699913B (en) | Method and device for diagnosing abnormal relationship of household transformer in transformer area | |
CN109389180A (en) | A power equipment image-recognizing method and inspection robot based on deep learning | |
CN111598166B (en) | Single-phase earth fault classification method and system based on principal component analysis and Softmax function | |
CN108200644B (en) | Passive indoor positioning method based on network visible view | |
CN111126429A (en) | Low-voltage distribution area user access point identification method based on PCA (principal component analysis) degradation and K-Means clustering | |
CN104966161B (en) | A kind of power quality recorder data calculation and analysis methods based on gauss hybrid models | |
CN109975673B (en) | Method for identifying fault arc at direct current side of photovoltaic microgrid | |
CN110569316A (en) | low-voltage distribution area user topology identification method based on t-SNE dimension reduction technology and BIRCH clustering | |
CN112819649A (en) | Method and device for determining station area subscriber change relationship | |
Mian Qaisar et al. | Machine learning with adaptive rate processing for power quality disturbances identification | |
CN108549907B (en) | Data verification method based on multi-source transfer learning | |
CN106950446A (en) | The abnormal quick detection of power network based on PCA and localization method | |
Liao et al. | Recognition of partial discharge patterns | |
CN111861789A (en) | Method and system for identifying user variable relationship based on current data integer programming solution | |
CN113659564B (en) | Low-voltage distribution network topology identification method and system based on voltage fluctuation feature clustering | |
CN113702767B (en) | Island direct-current microgrid fault diagnosis method based on wavelet sliding window energy | |
CN117110798B (en) | Fault detection method and system for intelligent power distribution network | |
CN112508254B (en) | Method for determining investment prediction data of transformer substation engineering project | |
CN112615372A (en) | Voltage interference device-containing zone detection method based on coefficient of variation | |
CN116845971A (en) | Automatic identification method for topological structure of photovoltaic grid-connected low-voltage transformer area | |
CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
CN106845763B (en) | Power grid reliability analysis method and device | |
Wei et al. | Detection of users-transformer relationship in the secondary power distribution system with smart meter data | |
CN114065129A (en) | Line-variable relation detection method and detection system based on spectral clustering method |
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 |