CN111476427A - Low-voltage distribution area topology identification method and identification device - Google Patents
Low-voltage distribution area topology identification method and identification device Download PDFInfo
- Publication number
- CN111476427A CN111476427A CN202010297258.8A CN202010297258A CN111476427A CN 111476427 A CN111476427 A CN 111476427A CN 202010297258 A CN202010297258 A CN 202010297258A CN 111476427 A CN111476427 A CN 111476427A
- Authority
- CN
- China
- Prior art keywords
- low
- matrix
- data matrix
- dimensional
- similarity
- 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 45
- 239000011159 matrix material Substances 0.000 claims abstract description 176
- 230000005611 electricity Effects 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000013507 mapping Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000011478 gradient descent method Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000005259 measurement Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 8
- 238000007726 management method Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 5
- 230000004927 fusion Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000002354 daily effect Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000003442 weekly effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013024 troubleshooting 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/043—Optimisation of two dimensional placement, e.g. cutting of clothes or wood
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of big data analysis, and provides a low-voltage distribution area topology identification method and an identification device, wherein the low-voltage distribution area comprises a plurality of line branches, and the method comprises the following steps: collecting the electricity utilization information data of each line branch at preset time intervals in a preset time period to form an original data matrix; preprocessing the original data matrix to obtain a standardized data matrix; mapping the standardized data matrix to a low-dimensional space with preset dimensions to obtain a low-dimensional data matrix; and drawing the topological structure of the low-voltage transformer area according to the low-dimensional data matrix. The technical scheme provided by the invention can accurately and efficiently automatically identify the topological structure of the low-voltage transformer area, thereby greatly improving the management level of the low-voltage transformer area.
Description
Technical Field
The invention relates to the technical field of big data analysis, in particular to a low-voltage distribution area topology identification method and a low-voltage distribution area topology identification device.
Background
In a new generation of power system, intelligent terminals such as power distribution automation and power utilization information acquisition are increasing day by day, the connection relation and connectivity among the terminals are becoming more and more complicated, and the accurate acquisition of network topology information is beneficial to the lean management of a more and more complicated power distribution network.
The topology of the low-voltage transformer area provides a connection relationship between, for example, feeders, distribution transformers, marketers and users, which is significant for line loss analysis, power outage study and determination, and effective management during power outage of the distribution network. In addition, in order to perform reliable state evaluation on each node in the power distribution network, maintain three-phase load and voltage balance of a distribution transformer and a distribution feeder, and the like, it is necessary to accurately acquire topological information of branches, user variable relations, phase affiliations, and the like of the power distribution network.
The existing topology identification method is generally based on special hardware identification equipment, extra data acquisition needs to be carried out on a distribution network of a distribution area, and the topological structure of the low-voltage distribution area can be obtained by combining modes such as manual analysis and the like. Due to changes in reconfiguration, repair, maintenance and load balancing of the power distribution network, network topology information may change at a certain time, and when a phase jumps, the phase of a user may also be quickly switched, which may cause a topology structure of the power distribution network to change instantly. The existing topology identification method cannot timely capture the instantaneous change, so that the problems of low troubleshooting efficiency, long period and the like of the faults of the line loss abnormal points in the power distribution network are caused, and the requirements of real-time performance and accuracy of topology identification cannot be met. Moreover, the existing topology identification mode needs more manual work, is tedious and time-consuming, and cannot meet the requirement of intelligent topology identification.
Disclosure of Invention
In view of this, the present invention is directed to a low-voltage distribution area topology identification method and an identification apparatus, which can accurately and efficiently automatically identify a topology structure of a low-voltage distribution area, thereby greatly improving a management level of the low-voltage distribution area.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a low-voltage zone topology identification method, the low-voltage zone comprising a plurality of line branches, the method comprising:
collecting the electricity utilization information data of each line branch at preset time intervals in a preset time period to form an original data matrix;
preprocessing the original data matrix to obtain a standardized data matrix;
mapping the standardized data matrix to a low-dimensional space with preset dimensions to obtain a low-dimensional data matrix; the preset dimension is smaller than the dimension of the standardized data matrix;
and drawing the topological structure of the low-voltage transformer area according to the low-dimensional data matrix.
Preferably, the preprocessing the raw data matrix to obtain a normalized data matrix includes:
performing the following operations on each element in the original data matrix to obtain the normalized data matrix: and calculating the difference value of one element and a preset single-phase voltage standard value, and performing absolute value calculation on the difference value.
Preferably, the mapping the normalized data matrix into a low-dimensional space of a preset dimension to obtain a low-dimensional data matrix includes:
calculating the similarity between every two elements in the standardized data matrix to obtain a first similarity matrix;
randomly presetting low-dimensional data in the low-dimensional space with the preset dimension to obtain an initial low-dimensional matrix;
calculating the similarity between every two elements in the initial low-dimensional matrix to obtain a second similarity matrix;
updating the initial low-dimensional matrix by adopting a gradient descent method so as to minimize the difference between the first similarity matrix and the second similarity matrix;
and when the difference between the first similarity matrix and the second similarity matrix is minimized, acquiring a corresponding updated initial low-dimensional matrix, and taking the updated initial low-dimensional matrix as the low-dimensional data matrix.
Preferably, the calculating the similarity between every two elements in the normalized data matrix to obtain a first similarity matrix includes:
calculating the conditional probability between every two elements in the standardized data matrix;
calculating the joint probability between every two elements in the standardized data matrix according to the conditional probability to obtain a first joint probability;
and forming the first similarity matrix according to the first joint probability.
Preferably, the calculating the similarity between every two elements in the initial low-dimensional matrix to obtain a second similarity matrix includes:
calculating the joint probability between every two elements in the initial low-dimensional matrix by adopting a t distribution algorithm to obtain a second joint probability;
and forming the second similarity matrix according to the second joint probability.
Preferably, the difference between the first similarity matrix and the second similarity matrix is calculated using a K L divergence algorithm.
Preferably, the low-dimensional space of the preset dimension is a two-dimensional space.
Another objective of the present invention is to provide a low-voltage distribution area topology identification apparatus, which can accurately and efficiently automatically identify the topology structure of the low-voltage distribution area, so as to greatly improve the management level of the low-voltage distribution area.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a low-voltage zone topology identification apparatus, the low-voltage zone including a plurality of line branches, the apparatus comprising:
the acquisition module is used for simultaneously acquiring the electricity utilization information data of each line branch at preset time intervals in a preset time period to form an original data matrix;
the preprocessing module is used for preprocessing the original data matrix to obtain a standardized data matrix;
the low-dimensional data acquisition module is used for mapping the standardized data matrix to a low-dimensional space with preset dimensions to obtain a low-dimensional data matrix; the preset dimension is smaller than the dimension of the standardized data matrix;
and the topology drawing module is used for drawing the topology structure of the low-voltage transformer area according to the low-dimensional data matrix.
The present invention also provides a computer storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement any one of the above-mentioned low-voltage distribution area topology identification methods.
The invention also provides terminal equipment which comprises a processor, wherein the processor is used for executing any one of the low-voltage distribution area topology identification methods.
According to the low-voltage distribution area topology identification method and the low-voltage distribution area topology identification device, the power utilization information data of each line branch in the low-voltage distribution area are directly collected and processed to obtain the standardized data matrix, the standardized data matrix is mapped to the low-dimensional space, then the high-dimensional standardized data matrix can be represented by the low-dimensional data matrix, and the topological relation among data characteristics can be effectively displayed by the low-dimensional data matrix, so that the topological structure of the low-voltage distribution area can be drawn according to the low-dimensional data matrix. Compared with the prior art, the technical scheme of the invention does not need to additionally install special topology identification equipment or additionally acquire the topology identification data required by the topology identification equipment, and directly adopts the ready electricity utilization information data of each line branch for calculation, thereby saving the equipment cost. Meanwhile, the processed power utilization information data is adopted to draw the topological structure, so that when the power utilization information of a certain line changes, the power utilization information can be reflected in the topological structure in real time, and the real-time performance and the accuracy are achieved. Therefore, the technical scheme provided by the invention can accurately and efficiently automatically identify the topological structure of the low-voltage transformer area, thereby greatly improving the management level of the low-voltage transformer area.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention.
In the drawings:
FIG. 1 is a flow chart of a method of an embodiment of the present invention;
FIG. 2 is a system architecture diagram of a low pressure station area in an embodiment of the present invention;
FIG. 3 is a flowchart of a computing method for mapping a normalized data matrix to a low-dimensional space according to an embodiment of the present invention;
fig. 4 is a diagram showing the structure of an apparatus according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
The system architecture diagram of the low-voltage transformer area in this embodiment is shown in fig. 2, where fig. 2 includes a plurality of line branches, and a metering device is installed at a service switch of each line branch, in this embodiment, M line branches and M corresponding metering devices are assumed, and the metering devices are used to meter power consumption information data, such as active power, reactive power, power factors, voltage, current, power consumption, and the like, of the corresponding line branches. And a total quantity device is installed at the position of a total protection switch of the transformer in the low-voltage transformer area, and is used for summarizing the electricity utilization information data of each line branch and transmitting the summarized electricity utilization information data to the intelligent fusion terminal. This intelligence fuses terminal installation and guarantees the switch position at the transformer always, and intelligence fuses terminal and high in the clouds server wireless connection simultaneously, communicates with high in the clouds server. The topology identification process in this embodiment is specifically executed in the intelligent convergence terminal.
The main idea for solving the problems in the embodiment is that a process of data screening is completed by measuring large data by using a time sequence, namely, data preprocessing is performed, and the data preprocessing is performed to complete a standardization process of acquired original data, meanwhile, on the premise that distance measurement is converted into probability measurement, measurement between data points in a high-dimensional space is completed firstly, measurement between data points in a low-dimensional space is completed secondly, correlation between the two kinds of measurement is established finally, a mapping process of high-dimensional space data to low-dimensional space data is completed, and a data shape is measured by identifying topological features existing in a data set to obtain a low-voltage transformer area network topology, wherein measurement between data points in the high-dimensional space completes calculation of conditional probability between high-dimensional data points, measurement between data points in the low-dimensional space completes calculation of conditional probability between low-dimensional data points, correlation between the two kinds of measurement and calculation of low-dimensional data is established, and the low-dimensional data is calculated, and K L Divergence (Kullk-L eibler) is used to represent difference of two kinds of joint descending probability, and similarity is embedded into a high-dimensional data structure to form the low-dimensional topology.
Based on the system architecture of the low-voltage transformer area and the main idea of solving the problem, a low-voltage transformer area topology identification method provided by the embodiment of the present invention is shown in fig. 1, where the low-voltage transformer area includes a plurality of line branches, and the method includes:
s101, collecting electricity utilization information data of each line branch at preset time intervals in a preset time period to form an original data matrix;
the predetermined time period may be daily, weekly, monthly or yearly, and the predetermined time interval may be set according to actual demand. The step is to acquire the daily, weekly, monthly or yearly electricity consumption information data of all metering equipment in a certain low-voltage distribution area. Taking electricity consumption information data of 96 time points (24 hours, one point is collected every 15 minutes, and the total time is 96 time points) every day as an example, a data set is constructed by screening the electricity consumption information data to obtain an original data matrix.
The intelligent fusion terminal selects voltage data of N (in the embodiment, N is 96) time points each day from the summarized electricity consumption information data, and rejects 0 values and null values to form an M × N matrix, wherein N columns correspond to the voltage data of the N time points in the data set, M rows correspond to the total amount of samples (M metering devices), and the M × N matrix is as shown in formula (1):
s102, preprocessing the original data matrix to obtain a standardized data matrix;
in this embodiment, preprocessing the raw data matrix to obtain a normalized data matrix specifically includes:
performing the following operations on each element in the original data matrix to obtain the normalized data matrix: and calculating the difference value of one element and a preset single-phase voltage standard value, and performing absolute value calculation on the difference value.
In this embodiment, the preset single-phase voltage standard value is 220V, and for convenience of calculation, 220 is subtracted from each element in the M × N matrix, and then an absolute value is taken, so as to obtain a new M × N matrix, i.e. a normalized data matrix, where the normalized data matrix is shown in formula (2):
let x in the calculation processij＝|xij-220|, wherein,
equation (1) is converted to equation (2) by i ═ 1,2, 3.
S103, mapping the standardized data matrix to a low-dimensional space with preset dimensions to obtain a low-dimensional data matrix; the preset dimension is smaller than the dimension of the standardized data matrix;
the method for identifying the topology of the low-voltage distribution area based on the big data measurement analysis is mainly based on the idea of converting the similarity of voltage data points into probability measurement, the Gaussian joint probability is adopted to represent the similarity between high-dimensional data point pairs, the t distribution is adopted to represent the similarity between low-dimensional data point pairs embedded in a high-dimensional data space, the similarity of the low-dimensional data point pairs is made to approach the similarity of the high-dimensional data point pairs as much as possible through a K L divergence and gradient descent method, and finally the low-dimensional data points capable of displaying the high-dimensional data topology are obtained.
For convenience of calculation, designThe number of the measuring devices M is 1, and the N-dimensional voltage data set of a certain day is X { X ═ X1,x2,...xNAnd assuming the dataset is a normalized dataset, i.e., using X ═ X1,x2,...xNRepresents the normalized data matrix obtained in step S102. Meanwhile, a two-dimensional data set Y is preset as { Y ═ Y1,y2This embodiment translates the problem into how to convert X to { X ═ X }1,x2,...xNMapping to Y ═ Y1,y2}. The reason why the high-dimensional space data is mapped to the low-dimensional space is that 96-dimensional data exist in a matrix formed by data of 96 time points acquired every day in the embodiment of the invention, and if the data are not mapped to the low-dimensional space (for example, a two-dimensional space), a two-dimensional topological relation cannot be shown. The dimension of the low-dimensional space is determined according to the requirement of drawing a two-dimensional topological graph. The overall idea to solve this mapping problem is to compute each point pair (x) separately in the high-dimensional space and the low-dimensional spacei，xj) The distance between the two-dimensional data points is measured by a nonlinear gaussian distribution, and the distance between the two-dimensional data points (i.e. the normalized data matrix) is measured by a t-distribution.
Based on the above thought, in this embodiment, mapping the normalized data matrix to a low-dimensional space with a preset dimension to obtain a low-dimensional data matrix, includes the following calculation steps:
(1) calculating the similarity between every two elements in the standardized data matrix to obtain a first similarity matrix;
specifically, calculating the conditional probability between every two elements in the standardized data matrix; calculating the joint probability between every two elements in the standardized data matrix according to the conditional probability to obtain a first joint probability; and forming the first similarity matrix according to the first joint probability. The calculation process is described in detail below with reference to examples:
to calculate the similarity between two elements in a normalized data matrix, first the conditional probability p is calculatedj|iAs shown in formula (3):
wherein p isj|iMeasured as data points xiCentered domain data point xjA distribution of which corresponds to a Gaussian distribution, σ2 iIs the data point xiA gaussian variance at the center. It can be seen that x is awayiThe closer the point, pj|iThe larger the value, and vice versa, the smaller the value. Since only the relationship between pairs of data points is considered, p is set regardless of the relationship of the data points themselves to themselvesi|i0. To obtain σ for each point pair probabilityiIs provided with PiRepresenting all other data points in the data set X relative to XiConditional probability of (2), QiRepresenting all other data points in the data set Y relative to YiAnd defines a degree of misordering PerpAnd implementing smooth measurement on the neighborhood valid data points, as shown in formula (4):
wherein the content of the first and second substances,
in this example, take Perp＝30。
If the data point xiIs an outlier, then | | | xi-xj||2Will be large, xiIf the distance is far from other data points, all x are correspondedjJoint probability p ofijThe values will be small and correspond to the embedded low-dimensional space point yiThe influence of whatever value on the cost function is small, resulting in y being determined from other pointsiThe difficulty is high. Thus, the joint probability p in this embodimentijDetermined by the conditional probability, as shown in equation (5).
Wherein the content of the first and second substances,
m represents the total number of samples, i.e. the number of metering devices described above.
Combining the calculated joint probabilities pijA first similarity matrix is formed.
(2) Randomly presetting low-dimensional data in the low-dimensional space with the preset dimension to obtain an initial low-dimensional matrix;
in this embodiment, let Y be { Y ═ Y in the randomly preset low-dimensional dataset1,y2And taking the matrix as an initial low-dimensional matrix, namely an initial two-dimensional matrix.
(3) Calculating the similarity between every two elements in the initial low-dimensional matrix to obtain a second similarity matrix;
the purpose of calculating the similarity in this embodiment is to make the low-dimensional spatial data more accurately reflect the shape of the high-dimensional spatial data. The high-dimensional voltage data cannot reflect the distance between a certain abnormal node and a transformer in a low-voltage transformer area, and the position of the abnormal node can be reflected after the abnormal node is mapped to a low-dimensional space.
Specifically, a joint probability between every two elements in the initial low-dimensional matrix is calculated by adopting a t-distribution algorithm, and a second joint probability is obtained; and forming the second similarity matrix according to the second joint probability. The calculation process is described in detail below with reference to examples:
for the calculation of the similarity between the point pairs in the low-dimensional space data Y, the joint probability q is calculatedijThe method is realized by adopting t distribution with the degree of freedom of 1, as shown in formula (6):
combining the calculated joint probabilities qijA second similarity matrix is formed.
(4) Updating the initial low-dimensional matrix by adopting a gradient descent method so as to minimize the difference between the first similarity matrix and the second similarity matrix;
(5) and when the difference between the first similarity matrix and the second similarity matrix is minimized, acquiring a corresponding updated initial low-dimensional matrix, and taking the updated initial low-dimensional matrix as the low-dimensional data matrix.
After the first similarity matrix and the second similarity matrix are obtained, in order to better fit the distribution of data in the space X, the first similarity matrix and the second similarity matrix need to be equal to each other as much as possible, so that a low-dimensional space data Y needs to be found, and the conditional probabilities of the data sets in the two spaces are as close as possible.
In this embodiment, the K L divergence algorithm is used to calculate the difference between the first similarity matrix and the second similarity matrix, as shown in equation (7). in order to measure the sum of the probability differences to take the minimum, the gradient descent method is used to minimize the K L distance.
The gradient expression of the component is shown as formula (8):
in order to make the gradient calculation process smoother, two hyper-parameters, i.e. learning rate η and momentum α, are introduced, and the calculation form is shown in formula (9):
wherein, Y(0)By a constant matrix I (0, 10)-4E) Performing initialization, wherein E is AND Y(0)The identity matrix, η equals 10, α (t) equals 0.9, and t represents the number of cycles.
In this embodiment, t is taken to be 5000 times, three groups of Y low-dimensional coordinate data matrices (i.e., the updated initial low-dimensional matrices) are obtained under the conditions that the degree of confusion is 20, 30, and 35, respectively, and one of the three groups is selected as the finally obtained low-dimensional data matrix according to the requirement of field topology identification.
And S104, drawing the topological structure of the low-voltage transformer area according to the low-dimensional data matrix.
In this embodiment, the above steps S101 to S104 are all executed in the intelligent convergence terminal in fig. 2. The intelligent fusion terminal performs platform area topology identification after acquiring the electricity consumption information data transmitted by the total quantity equipment, and the specific topology identification process is as follows:
(1) starting a topology identification program, wherein the topology identification program runs in a data analysis container of the intelligent fusion terminal;
(2) selecting voltage data from the collected power utilization information data to form an original data matrix, and preprocessing the original data matrix to obtain a standardized data matrix;
(3) mapping the standardized data matrix to a low-dimensional space to obtain a low-dimensional data matrix;
(4) sending the low-dimensional data matrix to a cloud end, and drawing a platform area topological structure through the cloud end;
(5) and ending the flow.
The low-voltage transformer area topology obtained by the method can be applied to the aspects of line loss analysis, power failure research and judgment and the like. Taking the case of completing the line loss analysis through the topological relation, firstly, the intelligent fusion terminal acquires the zone topological relation between the transformer and each branch box in the low-voltage zone, then, the mobile terminal acquires the electricity utilization information data of the zone, and finally, the mobile terminal synthesizes the data, calculates and obtains the branch line loss rate of each branch box branch, and realizes the accurate positioning of the abnormal line loss branch of the low-voltage zone.
Correspondingly to the above method embodiment, the present invention further provides a low-voltage distribution area topology identification apparatus, as shown in fig. 4, where the low-voltage distribution area includes a plurality of line branches, and the apparatus includes:
the acquisition module 201 is configured to acquire power consumption information data of each line branch at a predetermined time interval in a predetermined time period, so as to form an original data matrix;
a preprocessing module 202, configured to preprocess the raw data matrix to obtain a standardized data matrix;
a low-dimensional data obtaining module 203, configured to map the standardized data matrix into a low-dimensional space with a preset dimension, so as to obtain a low-dimensional data matrix; the preset dimension is smaller than the dimension of the standardized data matrix;
and a topology drawing module 204, configured to draw a topology structure of the low-voltage transformer area according to the low-dimensional data matrix.
The working principle, the working flow and other contents of the above device related to the specific implementation can be referred to the specific implementation of the low-voltage platform zone topology identification method provided by the present invention, and the same technical contents will not be described in detail here.
The present invention also provides a computer storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the low-voltage distribution area topology identification method according to the embodiment of the present invention.
The invention also provides terminal equipment which comprises a processor, wherein the processor is used for executing the low-voltage distribution area topology identification method.
According to the low-voltage distribution area topology identification method and the low-voltage distribution area topology identification device, the power utilization information data of each line branch in the low-voltage distribution area are directly collected and processed to obtain the standardized data matrix, the standardized data matrix is mapped to the low-dimensional space, then the high-dimensional standardized data matrix can be represented by the low-dimensional data matrix, and the topological relation among data characteristics can be effectively displayed by the low-dimensional data matrix, so that the topological structure of the low-voltage distribution area can be drawn according to the low-dimensional data matrix. Compared with the prior art, the technical scheme of the invention does not need to additionally install special topology identification equipment or additionally acquire the topology identification data required by the topology identification equipment, and directly adopts the ready electricity utilization information data of each line branch for calculation, thereby saving the equipment cost. Meanwhile, the processed power utilization information data is adopted to draw the topological structure, so that when the power utilization information of a certain line changes, the power utilization information can be reflected in the topological structure in real time, and the real-time performance and the accuracy are achieved. Therefore, the technical scheme provided by the invention can accurately and efficiently automatically identify the topological structure of the low-voltage transformer area, thereby greatly improving the management level of the low-voltage transformer area.
Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the details of the above embodiments, and various simple modifications can be made to the technical solutions of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and the simple modifications all belong to the protection scope of the embodiments of the present invention.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, the embodiments of the present invention do not describe every possible combination.
Those skilled in the art will understand that all or part of the steps in the method according to the above embodiments may be implemented by a program, which is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present application. 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.
In addition, any combination of different implementation manners of the embodiments of the present invention can be performed, and the embodiments of the present invention should be considered as disclosed in the embodiments of the present invention as long as the combination does not depart from the idea of the embodiments of the present invention.
Claims (10)
1. A low-voltage zone topology identification method, wherein the low-voltage zone comprises a plurality of line branches, the method comprising:
collecting the electricity utilization information data of each line branch at preset time intervals in a preset time period to form an original data matrix;
preprocessing the original data matrix to obtain a standardized data matrix;
mapping the standardized data matrix to a low-dimensional space with preset dimensions to obtain a low-dimensional data matrix; the preset dimension is smaller than the dimension of the standardized data matrix;
and drawing the topological structure of the low-voltage transformer area according to the low-dimensional data matrix.
2. The method for identifying a topology of a low-voltage transformer area according to claim 1, wherein the preprocessing the raw data matrix to obtain a normalized data matrix comprises:
performing the following operations on each element in the original data matrix to obtain the normalized data matrix: and calculating the difference value of one element and a preset single-phase voltage standard value, and performing absolute value calculation on the difference value.
3. The low-voltage distribution area topology identification method according to claim 1, wherein mapping the normalized data matrix into a low-dimensional space of a preset dimension to obtain a low-dimensional data matrix comprises:
calculating the similarity between every two elements in the standardized data matrix to obtain a first similarity matrix;
randomly presetting low-dimensional data in the low-dimensional space with the preset dimension to obtain an initial low-dimensional matrix;
calculating the similarity between every two elements in the initial low-dimensional matrix to obtain a second similarity matrix;
updating the initial low-dimensional matrix by adopting a gradient descent method so as to minimize the difference between the first similarity matrix and the second similarity matrix;
and when the difference between the first similarity matrix and the second similarity matrix is minimized, acquiring a corresponding updated initial low-dimensional matrix, and taking the updated initial low-dimensional matrix as the low-dimensional data matrix.
4. The method for identifying the topology of the low-voltage transformer area according to claim 3, wherein the calculating the similarity between every two elements in the normalized data matrix to obtain a first similarity matrix comprises:
calculating the conditional probability between every two elements in the standardized data matrix;
calculating the joint probability between every two elements in the standardized data matrix according to the conditional probability to obtain a first joint probability;
and forming the first similarity matrix according to the first joint probability.
5. The method for identifying the topology of the low-voltage transformer area according to claim 3, wherein the calculating the similarity between every two elements in the initial low-dimensional matrix to obtain a second similarity matrix comprises:
calculating the joint probability between every two elements in the initial low-dimensional matrix by adopting a t distribution algorithm to obtain a second joint probability;
and forming the second similarity matrix according to the second joint probability.
6. The low-voltage transformer area topology identification method according to claim 3, characterized in that a K L divergence algorithm is adopted to calculate the difference between the first similarity matrix and the second similarity matrix.
7. The low-voltage transformer area topology identification method according to claim 1, wherein the low-dimensional space of the preset dimension is a two-dimensional space.
8. A low-voltage zone topology identification apparatus, the low-voltage zone comprising a plurality of line branches, the apparatus comprising:
the acquisition module is used for simultaneously acquiring the electricity utilization information data of each line branch at preset time intervals in a preset time period to form an original data matrix;
the preprocessing module is used for preprocessing the original data matrix to obtain a standardized data matrix;
the low-dimensional data acquisition module is used for mapping the standardized data matrix to a low-dimensional space with preset dimensions to obtain a low-dimensional data matrix; the preset dimension is smaller than the dimension of the standardized data matrix;
and the topology drawing module is used for drawing the topology structure of the low-voltage transformer area according to the low-dimensional data matrix.
9. A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the low-voltage station topology identification method of any of claims 1 to 7.
10. A terminal device comprising a processor, wherein the processor is configured to execute the low-voltage station topology identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010297258.8A CN111476427A (en) | 2020-04-15 | 2020-04-15 | Low-voltage distribution area topology identification method and identification device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010297258.8A CN111476427A (en) | 2020-04-15 | 2020-04-15 | Low-voltage distribution area topology identification method and identification device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111476427A true CN111476427A (en) | 2020-07-31 |
Family
ID=71753495
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010297258.8A Pending CN111476427A (en) | 2020-04-15 | 2020-04-15 | Low-voltage distribution area topology identification method and identification device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111476427A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112421614A (en) * | 2020-11-05 | 2021-02-26 | 江苏其厚智能电气设备有限公司 | Power distribution station self-healing control system and method based on local communication and topology identification |
| CN113114497A (en) * | 2021-04-06 | 2021-07-13 | 广西电网有限责任公司电力科学研究院 | Low-voltage distribution area topology automatic identification method |
| CN113809820A (en) * | 2021-07-30 | 2021-12-17 | 北京智芯微电子科技有限公司 | Method, device, system, medium and signal encoding method for identifying platform zone topology |
| CN114050657A (en) * | 2021-11-26 | 2022-02-15 | 北京市腾河智慧能源科技有限公司 | Photovoltaic grid-connected distribution room topology identification method, system, equipment and storage medium |
| CN114330527A (en) * | 2021-12-23 | 2022-04-12 | 国网北京市电力公司 | Building ammeter distribution identification method, system, device and storage medium |
| CN116722658A (en) * | 2023-08-11 | 2023-09-08 | 北京智芯微电子科技有限公司 | Low-voltage area topology identification method and device, storage medium and chip equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109816033A (en) * | 2019-01-31 | 2019-05-28 | 清华四川能源互联网研究院 | A method of the supervised learning based on optimization carries out area user identification zone |
| CN110569316A (en) * | 2019-08-07 | 2019-12-13 | 浙江大学 | low-voltage distribution area user topology identification method based on t-SNE dimension reduction technology and BIRCH clustering |
-
2020
- 2020-04-15 CN CN202010297258.8A patent/CN111476427A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109816033A (en) * | 2019-01-31 | 2019-05-28 | 清华四川能源互联网研究院 | A method of the supervised learning based on optimization carries out area user identification zone |
| CN110569316A (en) * | 2019-08-07 | 2019-12-13 | 浙江大学 | low-voltage distribution area user topology identification method based on t-SNE dimension reduction technology and BIRCH clustering |
Non-Patent Citations (1)
| Title |
|---|
| SATYA JAYADEV PAPPU等: "Identifying Topology of Low Voltage Distribution Networks Based on Smart Meter Data", 《IEEE TRANSACTIONS ON SMART GRID》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112421614A (en) * | 2020-11-05 | 2021-02-26 | 江苏其厚智能电气设备有限公司 | Power distribution station self-healing control system and method based on local communication and topology identification |
| CN113114497A (en) * | 2021-04-06 | 2021-07-13 | 广西电网有限责任公司电力科学研究院 | Low-voltage distribution area topology automatic identification method |
| CN113809820A (en) * | 2021-07-30 | 2021-12-17 | 北京智芯微电子科技有限公司 | Method, device, system, medium and signal encoding method for identifying platform zone topology |
| CN114050657A (en) * | 2021-11-26 | 2022-02-15 | 北京市腾河智慧能源科技有限公司 | Photovoltaic grid-connected distribution room topology identification method, system, equipment and storage medium |
| CN114050657B (en) * | 2021-11-26 | 2023-06-27 | 北京市腾河智慧能源科技有限公司 | Method, system, equipment and storage medium for identifying topology of grid-connected photovoltaic cell |
| CN114330527A (en) * | 2021-12-23 | 2022-04-12 | 国网北京市电力公司 | Building ammeter distribution identification method, system, device and storage medium |
| CN114330527B (en) * | 2021-12-23 | 2023-10-13 | 国网北京市电力公司 | Building ammeter distribution identification method, system, device and storage medium |
| CN116722658A (en) * | 2023-08-11 | 2023-09-08 | 北京智芯微电子科技有限公司 | Low-voltage area topology identification method and device, storage medium and chip equipment |
| CN116722658B (en) * | 2023-08-11 | 2023-12-29 | 北京智芯微电子科技有限公司 | Low-voltage area topology identification method and device, storage medium and chip equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111476427A (en) | Low-voltage distribution area topology identification method and identification device | |
| US9287713B2 (en) | Topology identification in distribution network with limited measurements | |
| Mutanen et al. | Customer classification and load profiling method for distribution systems | |
| Blakely et al. | Spectral clustering for customer phase identification using AMI voltage timeseries | |
| CN113078630B (en) | Low-voltage distribution network topology identification method based on real-time measurement data | |
| CN110705107B (en) | Power distribution network voltage evaluation method, system, equipment and storage medium | |
| CN112688428B (en) | 10-kilovolt power grid synchronous line loss treatment method based on Internet of things technology | |
| CN110019098A (en) | Electrical energy measurement big data analysis system based on Hadoop frame | |
| CN105119282A (en) | On-line calculation system and method for theoretical line loss of power grid | |
| CN112198375B (en) | Phase identification method, device, equipment and storage medium for single-phase user | |
| CN112288303A (en) | Method and device for determining line loss rate | |
| CN111835006B (en) | Low-voltage transformer area topology identification method based on voltage curve and least square | |
| CN111654392A (en) | Low-voltage distribution network topology identification method and system based on mutual information | |
| CN110768256B (en) | Transformer area topology identification method, device and system based on voltage harmonic atlas | |
| EP3449267A1 (en) | A method for identifying the phases of a multi-phase distribution grid | |
| CN118017509A (en) | Large-scale power distribution network parallel optimization method based on digital twin space | |
| CN115186974A (en) | Power distribution network power supply quality comprehensive evaluation method and system based on business middling station | |
| CN113377760A (en) | Method and system for establishing low-voltage resident feature portrait based on electric power data and multivariate data | |
| US20200025810A1 (en) | Low-observability matrix completion | |
| CN116247668A (en) | Power distribution network operation mode identification method based on measurement big data analysis | |
| Domínguez et al. | Analysis of electric power consumption using Self-Organizing Maps. | |
| CN112434019B (en) | Historical electric quantity traceability cleaning method and power system applied to user change relation change | |
| CN115186975A (en) | Power grid line loss management method and system based on service center | |
| Dahale et al. | Phase identification in unobservable distribution systems | |
| CN110707713A (en) | Distribution network reactive voltage space-time distribution characteristic obtaining method based on historical data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200731 |
|
| RJ01 | Rejection of invention patent application after publication |