CN113449980A - Low-voltage transformer area phase sequence identification method, system, terminal and storage medium - Google Patents

Low-voltage transformer area phase sequence identification method, system, terminal and storage medium Download PDF

Info

Publication number
CN113449980A
CN113449980A CN202110707794.5A CN202110707794A CN113449980A CN 113449980 A CN113449980 A CN 113449980A CN 202110707794 A CN202110707794 A CN 202110707794A CN 113449980 A CN113449980 A CN 113449980A
Authority
CN
China
Prior art keywords
voltage
low
cluster
dimensional
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110707794.5A
Other languages
Chinese (zh)
Other versions
CN113449980B (en
Inventor
招景明
潘峰
杨雨瑶
马键
蔡永智
姜晓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Power Grid Co Ltd
Measurement Center of Guangdong Power Grid Co Ltd
Original Assignee
Guangdong Power Grid Co Ltd
Measurement Center of Guangdong Power Grid Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Power Grid Co Ltd, Measurement Center of Guangdong Power Grid Co Ltd filed Critical Guangdong Power Grid Co Ltd
Priority to CN202110707794.5A priority Critical patent/CN113449980B/en
Publication of CN113449980A publication Critical patent/CN113449980A/en
Application granted granted Critical
Publication of CN113449980B publication Critical patent/CN113449980B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Primary Health Care (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Public Health (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)

Abstract

The invention discloses a method, a system, a terminal and a storage medium for identifying phase sequence of a low-voltage transformer area, wherein the method comprises the following steps: acquiring voltage time sequence data of each phase low-voltage outgoing line and each user intelligent electric meter of the distribution transformer in a preset time period in a target transformer area; performing dimension reduction on the voltage time sequence data according to a multi-dimensional scaling method to obtain a low-dimensional voltage feature set; clustering the low-dimensional voltage feature set according to a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set; and calculating the distance from the corresponding point of each distribution transformer terminal to the center of each cluster according to the low-dimensional voltage characteristic set after clustering, and obtaining the phase sequence attribution relation of the user intelligent electric meter according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster. According to the invention, on the premise that only the user intelligent electric meter is installed in the target area, the phase sequence attribution relation of the user intelligent electric meter can be accurately sorted, additional equipment is not required, and a large amount of manpower and material resource cost can be saved.

Description

Low-voltage transformer area phase sequence identification method, system, terminal and storage medium
Technical Field
The invention relates to the technical field of data processing of intelligent electric meters, in particular to a method, a system, a terminal and a storage medium for identifying phase sequence of a low-voltage transformer area.
Background
With the rapid development of the modernization process of our country, the number of power users is greatly increased, and the power distribution system is improved. In order to improve the reliability of power supply, the intelligent management of power utilization of the power distribution network is of great significance. In a power distribution network, the premise of realizing the intelligent monitoring of distribution of a distribution area is that the topological structure of the distribution area is known, but in the daily power distribution operation and maintenance management work, the loss or inaccuracy of the topological relation information of the low-voltage distribution area often exists, and the improvement of the intelligent level of the operation and maintenance management of the low-voltage distribution area is restricted.
The phase sequence relation of the low-voltage transformer area is used as an important component of the topological relation of the low-voltage transformer area, and the method has an important supporting function for solving the problems of three-phase unbalance, low voltage, heavy overload and the like of the low-voltage transformer area.
At present, the existing phase sequence identification method for the low-voltage transformer area comprises the following steps:
1. manpower prospecting method: the method is characterized in that the method depends on the site of staff of a power company to survey each user by using related equipment, and the phase sequence of each user is determined.
2. And (3) a signal feedback method: and additionally arranging a signal transceiver on a distribution transformer terminal of the transformer area and each user electric meter, injecting characteristic signals into a distribution transformer side of the transformer area, and determining the phase sequence of a user according to the signal feedback condition on the user electric meter.
3. Data fitting method: and fitting the phase sequence of the user by minimizing the error between the actual value and the topological state according to the data such as the voltage, the current and the like of the user ammeter in the gathering area and the terminal of the distribution transformer.
However, the prior art method has the following problems:
1. manpower investigation method: a large amount of manpower and material resources are consumed, the consumed time is long, and the troubleshooting efficiency and the economic benefit are extremely low.
2. And (3) a signal feedback method: the signal transceiver needs to be additionally arranged on the electric meter of each household user, so that the investment is high, the reconstruction workload is large, the operation and maintenance pressure is heavy, the reliability of a signal transceiver circuit is poor, the signal transceiver circuit is easy to interfere, and the signal transceiver circuit is easy to damage under lightning stroke.
3. Data fitting method: during fitting, the line loss and electricity stealing situation of the transformer area cannot be fully considered, and the phase sequence identification accuracy rate can be obviously reduced in the transformer area with high line loss rate or serious electricity stealing.
Disclosure of Invention
The purpose of the invention is: the phase sequence identification method, the phase sequence identification device, the terminal and the storage medium for the low-voltage distribution network can fully utilize mass data information under a digital background, study a machine learning algorithm based on data thinking, solve the problem of phase sequence identification of the low-voltage distribution network from the data driving perspective, accurately card the phase sequence affiliation relation of a user intelligent electric meter on the premise that only the user intelligent electric meter is installed in a target distribution network, do not need additional equipment, and save a large amount of manpower and material cost.
In order to achieve the above object, the present invention provides a phase sequence identification method for a low-voltage transformer area, including:
s1, collecting voltage time sequence data of each phase low-voltage outgoing line and each user intelligent electric meter of the distribution transformer in the target area in a preset time period;
s2, performing dimension reduction on the voltage time sequence data according to a multi-dimensional scaling method to obtain a low-dimensional voltage feature set;
s3, clustering the low-dimensional voltage feature set according to a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set;
and S4, calculating the distance from the corresponding point of each distribution transformer terminal to the center of each cluster according to the low-dimensional voltage feature set after clustering, and obtaining the phase sequence attribution relationship of the user intelligent electric meter according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster.
Furthermore, the number of the collected time sections in the preset time period is greater than or equal to the total number of the user intelligent electric meters in the target distribution area.
Further, the voltage time sequence data is subjected to dimension reduction according to a multidimensional scaling method to obtain a low-dimensional voltage feature set, and the following calculation formula is adopted:
Dij＝||zi-zj||
in the formula, DijIs the Euclidean distance between the ith time and the jth time of the original high-dimensional voltage data, ziRepresenting the mapping of the voltage data at the ith time in a low dimensional space, zjRepresenting a mapping of the voltage data at the jth time in a low dimensional space;
let B be the inner product matrix of the reduced-dimension sample, let B be Zi TZjThen, then
Figure BDA0003131179780000031
Figure BDA0003131179780000032
Centralizing the reduced sample, and then:
Figure BDA0003131179780000033
Figure BDA0003131179780000034
according to Dij＝||zi-zjWill b | |ijBy DijThis means that there are:
Figure BDA0003131179780000035
Figure BDA0003131179780000036
Figure BDA0003131179780000037
in the formula, tr (-) denotes a trace of the matrix;
Figure BDA0003131179780000038
order to
Figure BDA0003131179780000039
Figure BDA0003131179780000041
Figure BDA0003131179780000042
In the formula, m is the number of samples;
from the above, the inner product matrix B can be obtained
Figure BDA0003131179780000043
Carrying out characteristic value decomposition on the obtained product:
B＝VΛVT
Λ＝diag(λ1,λ2,...,λd')
λ1≥λ2≥...≥λd'
Λ＝ΛT
B＝ZTZ＝VΛVT
Figure BDA0003131179780000044
Figure BDA0003131179780000045
in the formula, lambda is a characteristic value of the matrix B, lambda is a diagonal matrix formed by the characteristic values, and v is a characteristic vector matrix of the pertinence;
and d' maximum eigenvalues and eigenvectors before the step are reserved, so that a data matrix characteristic set after dimension reduction can be obtained:
Figure BDA0003131179780000046
further, the clustering processing is performed on the low-dimensional voltage feature set by using a CK-Means semi-supervised clustering algorithm to obtain a low-dimensional voltage feature set after the clustering processing, and the method comprises the following steps:
s31, randomly initializing K clustering centers for the low-dimensional voltage feature set;
s32, each object is allocated to K initial clustering centers based on the distance minimum principle, wherein the distance: the following calculation formula is adopted:
S＝||z-μi(N)||2,i＝1,2,…,K
wherein z is the reduced voltage data, μi(N) is the ith cluster center at the Nth iteration;
s33, judging whether each object z violates the connectionless constraint and fixes, if so, returning the constraint checking function to true, and if not, returning false;
s34, if the constraint check function returns to true, distributing z to the cluster next to it, and returning to step S33 to check the object z again, if the constraint check function returns to false, returning to step S33 and checking the next object; if the same object z continuously violates the constraint for K times, returning to null, which means that no cluster which can legally accommodate the object exists; until all objects are traversed, go to step S35;
s35, calculating the average value of all objects in each cluster, and updating the cluster center of each cluster according to the average value;
s36, repeating the steps S32-S35 until the cluster center is not changed.
Further, based on the distance minimization principle, the following calculation formula is adopted:
S＝||z-μi(N)||2,i＝1,2,…,K
wherein z is the reduced voltage data, μi(N) is the ith cluster center at the Nth iteration.
Further, the average value of all objects in each cluster is calculated, and the cluster center of each cluster is updated according to the average value, and the following calculation formula is adopted:
Figure BDA0003131179780000051
further, the step of calculating a distance from a corresponding point of each distribution transformer terminal to a center of each cluster according to the low-dimensional voltage feature set after the clustering process, and obtaining a phase sequence attribution relationship of the user intelligent electric meter according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster includes:
sequentially calculating the distance between the A, B, C three-phase distribution transformation terminal voltage time sequence and the center of each cluster in the low-dimensional space, determining the cluster closest to the A-phase distribution transformation terminal voltage time sequence as an A cluster, marking users corresponding to all objects as A-phase users, and determining B, C-phase users by analogy, wherein the specific calculation formula is as follows:
S＝||zA-μi||2，i＝1,2,…,K
in the formula, zAAnd changing the terminal voltage time sequence for the A phase after dimension reduction.
The invention also provides a phase sequence identification system of the low-voltage transformer area, which comprises: a data acquisition module, a data dimension reduction module, a data clustering module and a phase sequence identification module, wherein,
the data acquisition module is used for acquiring voltage time sequence data of each phase low-voltage outgoing line and each user intelligent electric meter of the distribution transformer in a preset time period in the target transformer area;
the data dimension reduction module is used for reducing dimensions of the voltage time sequence data according to a multi-dimensional scaling method to obtain a low-dimensional voltage feature set;
the data clustering module is used for clustering the low-dimensional voltage feature set according to a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set;
and the phase sequence identification module is used for calculating the distance from the corresponding point of each distribution transformer terminal to the center of each cluster according to the low-dimensional voltage characteristic set after clustering processing, and obtaining the phase sequence attribution relation of the user intelligent electric meter according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster.
The present invention also provides a computer terminal device, comprising: one or more processors; a memory coupled to the processor for storing one or more programs; when executed by the one or more processors, cause the one or more processors to implement the low-voltage station phase sequence identification method as in any one of the above.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the low-voltage station region phase sequence identification method as described in any of the above.
Compared with the prior art, the method, the system, the terminal and the storage medium for identifying the phase sequence of the low-voltage transformer area have the advantages that:
the method can fully utilize mass data information under a digital background, research a machine learning algorithm based on data thinking, solve the problem of phase sequence identification of the low-voltage distribution network from the data driving perspective, accurately card the phase sequence affiliation of the user intelligent electric meter on the premise that only the user intelligent electric meter is installed in a target station area, do not need additional equipment, and save a large amount of labor and material costs.
Drawings
Fig. 1 is a schematic flow chart of a phase sequence identification method for a low-voltage transformer area according to the present invention;
fig. 2 is a schematic structural diagram of a phase sequence identification system of a low-voltage station area provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
As shown in fig. 1, a method for identifying a phase sequence of a low-voltage station area according to an embodiment of the present invention includes:
s1, collecting voltage time sequence data of each phase low-voltage outgoing line and each user intelligent electric meter of the distribution transformer in the target area in a preset time period;
specifically, voltage time sequence data of each phase low-voltage outgoing line and each user intelligent electric meter of the distribution transformer in a target transformer area in a preset time period are obtained, wherein the number of collected time sections in the preset time period is larger than or equal to the total number of the user intelligent electric meters in the target transformer area.
It should be noted that the time profile may be understood as a state of the system at a certain time (e.g., 19: 48: 50), or at a certain time.
S2, performing dimension reduction on the voltage time sequence data according to a multi-dimensional scaling method to obtain a low-dimensional voltage feature set;
specifically, the voltage time series data is subjected to dimension reduction according to a multidimensional scaling method to obtain a low-dimensional voltage feature set, and the following calculation formula is adopted:
Dij＝||zi-zj||
in the formula, DijIs the Euclidean distance between the ith time and the jth time of the original high-dimensional voltage data, ziRepresenting the mapping of the voltage data at the ith time in a low dimensional space, zjRepresenting a mapping of the voltage data at the jth time in a low dimensional space;
let B be the inner product matrix of the reduced-dimension sample, let B be Zi TZjThen, then
Figure BDA0003131179780000081
Figure BDA0003131179780000082
Centralizing the reduced sample, and then:
Figure BDA0003131179780000091
Figure BDA0003131179780000092
according to Dij＝||zi-zjWill b | |ijBy DijThis means that there are:
Figure BDA0003131179780000093
Figure BDA0003131179780000094
Figure BDA0003131179780000095
in the formula, tr (-) denotes a trace of the matrix;
Figure BDA0003131179780000096
order to
Figure BDA0003131179780000097
Figure BDA0003131179780000098
Figure BDA0003131179780000099
In the formula, m is the number of samples;
from the above, the inner product matrix B can be obtained
Figure BDA00031311797800000910
Carrying out characteristic value decomposition on the obtained product:
B＝VΛVT
Λ＝diag(λ1,λ2,...,λd')
λ1≥λ2≥...≥λd'
Λ＝ΛT
B＝ZTZ＝VΛVT
Figure BDA0003131179780000101
Figure BDA0003131179780000102
in the formula, lambda is a characteristic value of the matrix B, lambda is a diagonal matrix formed by the characteristic values, and v is a characteristic vector matrix of the pertinence;
and d' maximum eigenvalues and eigenvectors before the step are reserved, so that a data matrix characteristic set after dimension reduction can be obtained:
Figure BDA0003131179780000103
s3, clustering the low-dimensional voltage feature set according to a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set;
specifically, the low-dimensional voltage feature set is clustered by using a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set, and the method comprises the following steps:
s31, randomly initializing K clustering centers for the low-dimensional voltage feature set;
s32, each object is allocated to K initial clustering centers based on the distance minimum principle, wherein the distance: the following calculation formula is adopted:
S＝||z-μi(N)||2,i＝1,2,…,K
wherein z is after dimensionality reductionVoltage data of (d), mui(N) is the ith cluster center at the Nth iteration;
s33, judging whether each object z violates the connectionless constraint and fixes, if so, returning the constraint checking function to true, and if not, returning false;
s34, if the constraint check function returns to true, distributing z to the cluster next to it, and returning to step S33 to check the object z again, if the constraint check function returns to false, returning to step S33 and checking the next object; if the same object z continuously violates the constraint for K times, returning to null, which means that no cluster which can legally accommodate the object exists; until all objects are traversed, go to step S35;
s35, calculating the average value of all objects in each cluster, and updating the cluster center of each cluster according to the average value;
s36, repeating the steps S32-S35 until the cluster center is not changed.
And S4, calculating the distance from the corresponding point of each distribution transformer terminal to the center of each cluster according to the low-dimensional voltage feature set after clustering, and obtaining the phase sequence attribution relationship of the user intelligent electric meter according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster.
Specifically, the distances between the A, B, C three-phase distribution transformation terminal voltage timing sequence and the centers of the clusters in the low-dimensional space are sequentially calculated, the cluster closest to the A-phase distribution transformation terminal voltage timing sequence is determined as an A cluster, users corresponding to all objects in the cluster are marked as A-phase users, and so on, B, C-phase users are determined, and a specific calculation formula is as follows:
S＝||zA-μi||2，i＝1,2,…,K
in the formula, zAAnd changing the terminal voltage time sequence for the A phase after dimension reduction.
In one embodiment of the present invention, the number of collected time sections in the preset time period is greater than or equal to the total number of the user smart meters in the target distribution area.
In an embodiment of the present invention, the dimension reduction is performed on the voltage time series data according to a multidimensional scaling method to obtain a low-dimensional voltage feature set, and a calculation formula is adopted as follows:
Dij＝||zi-zj||
in the formula, DijIs the Euclidean distance between the ith time and the jth time of the original high-dimensional voltage data, ziRepresenting the mapping of the voltage data at the ith time in a low dimensional space, zjRepresenting a mapping of the voltage data at the jth time in a low dimensional space;
let B be the inner product matrix of the reduced-dimension sample, let B be Zi TZjThen, then
Figure BDA0003131179780000121
Figure BDA0003131179780000122
Centralizing the reduced sample, and then:
Figure BDA0003131179780000123
Figure BDA0003131179780000124
according to Dij＝||zi-zjWill b | |ijBy DijThis means that there are:
Figure BDA0003131179780000125
Figure BDA0003131179780000126
Figure BDA0003131179780000127
in the formula, tr (-) denotes a trace of the matrix;
Figure BDA0003131179780000128
order to
Figure BDA0003131179780000129
Figure BDA00031311797800001210
Figure BDA00031311797800001211
In the formula, m is the number of samples;
from the above, the inner product matrix B can be obtained
Figure BDA0003131179780000131
Carrying out characteristic value decomposition on the obtained product:
B＝VΛVT
Λ＝diag(λ1,λ2,...,λd')
λ1≥λ2≥...≥λd'
Λ＝ΛT
B＝ZTZ＝VΛVT
Figure BDA0003131179780000132
Figure BDA0003131179780000133
in the formula, lambda is a characteristic value of the matrix B, lambda is a diagonal matrix formed by the characteristic values, and v is a characteristic vector matrix of the pertinence;
and d' maximum eigenvalues and eigenvectors before the step are reserved, so that a data matrix characteristic set after dimension reduction can be obtained:
Figure BDA0003131179780000134
in an embodiment of the present invention, the clustering the low-dimensional voltage feature set by using a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set includes:
s31, randomly initializing K clustering centers for the low-dimensional voltage feature set;
s32, each object is allocated to K initial clustering centers based on the distance minimum principle, wherein the distance: the following calculation formula is adopted:
S＝||z-μi(N)||2,i＝1,2,…,K
wherein z is the reduced voltage data, μi(N) is the ith cluster center at the Nth iteration;
s33, judging whether each object z violates the connectionless constraint and fixes, if so, returning the constraint checking function to true, and if not, returning false;
s34, if the constraint check function returns to true, distributing z to the cluster next to it, and returning to step S33 to check the object z again, if the constraint check function returns to false, returning to step S33 and checking the next object; if the same object z continuously violates the constraint for K times, returning to null, which means that no cluster which can legally accommodate the object exists; until all objects are traversed, go to step S35;
and S35, calculating the average value of all objects in each cluster, and updating the cluster center of each cluster according to the average value.
S36, repeating the steps S32-S35 until the cluster center is not changed.
In an embodiment of the present invention, the following calculation formula is adopted based on the distance minimization principle:
S＝||z-μi(N)||2,i＝1,2,…,K
wherein z is the reduced voltage data, μi(N) is the ith cluster center at the Nth iteration.
In an embodiment of the present invention, the average value of all objects in each cluster is calculated, and the cluster center of each cluster is updated according to the average value, using the following calculation formula:
Figure BDA0003131179780000141
in a certain embodiment of the present invention, the calculating, according to the low-dimensional voltage feature set after the clustering, a distance from a corresponding point of each distribution transformer terminal to a center of each cluster, and obtaining, according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster, a phase sequence attribution relationship of the smart meter of the user, includes:
sequentially calculating the distance between the A, B, C three-phase distribution transformation terminal voltage time sequence and the center of each cluster in the low-dimensional space, determining the cluster closest to the A-phase distribution transformation terminal voltage time sequence as an A cluster, marking users corresponding to all objects as A-phase users, and determining B, C-phase users by analogy, wherein the specific calculation formula is as follows:
S＝||zA-μi||2，i＝1,2,…,K
in the formula, zAAnd changing the terminal voltage time sequence for the A phase after dimension reduction.
For a better understanding of the present invention, the following specific examples may be considered:
the following is an example of the method of the invention, the distribution transformer of the platform area has three outgoing lines in total and is provided with a distribution transformer monitoring and metering terminal, the power supply users account for 109 users in total, wherein 14 users are supplied with power by three phases and are provided with three-phase smart meters, 93 users are supplied with power by single phase and are provided with single-phase smart meters, the smart meters connected to the A phase account for 39 blocks in total, the smart meters connected to the B phase account for 44 blocks in total, and the smart meters connected to the C phase account for 52 blocks in total. Voltage data of each phase low-voltage outgoing line and 288 moments of each intelligent electric meter of the distribution transformer of the transformer area are collected,
and programming and solving by adopting MATLAB software to obtain a phase sequence identification result. The phase sequence identification result obtained by analysis is consistent with the actual phase sequence attribution relationship of the transformer area, and the effectiveness and the feasibility of the method provided by the invention are verified.
Compared with the prior art, the phase sequence identification method for the low-voltage transformer area has the beneficial effects that:
the method can fully utilize mass data information under a digital background, research a machine learning algorithm based on data thinking, solve the problem of phase sequence identification of the low-voltage distribution network from the data driving perspective, accurately card the phase sequence affiliation of the user intelligent electric meter on the premise that only the user intelligent electric meter is installed in a target station area, do not need additional equipment, and save a large amount of labor and material costs.
As shown in fig. 2, the present invention further provides a phase sequence identification system 200 for a low-voltage transformer area, including: a data acquisition module 201, a data dimension reduction module 202, a data clustering module 203 and a phase sequence identification module 204, wherein,
the data acquisition module 201 is used for acquiring voltage time sequence data of each phase low-voltage outgoing line and each user intelligent electric meter of the distribution transformer in a preset time period in the target transformer area;
the data dimension reduction module 202 is configured to perform dimension reduction on the voltage time series data according to a multidimensional scaling method to obtain a low-dimensional voltage feature set;
the data clustering module 203 is configured to perform clustering processing on the low-dimensional voltage feature set according to a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set;
and the phase sequence identification module 204 is configured to calculate a distance from a corresponding point of each distribution transformer terminal to a center of each cluster according to the low-dimensional voltage feature set after the clustering processing, and obtain a phase sequence attribution relationship of the user intelligent electric meter according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster.
The present invention also provides a computer terminal device, comprising: one or more processors; a memory coupled to the processor for storing one or more programs; when executed by the one or more processors, cause the one or more processors to implement the low-voltage station phase sequence identification method as in any one of the above.
It should be noted that the processor may be a Central Processing Unit (CPU), other general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an application-specific programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc., the general-purpose processor may be a microprocessor, or the processor may be any conventional processor, the processor is a control center of the terminal device, and various interfaces and lines are used to connect various parts of the terminal device.
The memory mainly includes a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like, and the data storage area may store related data and the like. In addition, the memory may be a high speed random access memory, may also be a non-volatile memory, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card (FlashCard), and the like, or may also be other volatile solid state memory devices.
It should be noted that the terminal device may include, but is not limited to, a processor and a memory, and those skilled in the art will understand that the terminal device is only an example and does not constitute a limitation of the terminal device, and may include more or less components, or combine some components, or different components.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the low-voltage station region phase sequence identification method as described in any of the above.
It should be noted that the computer program may be divided into one or more modules/units (e.g., computer program), and the one or more modules/units are stored in the memory and executed by the processor to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the terminal device.
The above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and are not intended to limit the scope of the present invention. It should be understood that any modifications, equivalents, improvements and the like, which come within the spirit and principle of the invention, may occur to those skilled in the art and are intended to be included within the scope of the invention.

Claims (10)

1. A phase sequence identification method for a low-voltage transformer area is characterized by comprising the following steps:
s1, collecting voltage time sequence data of each phase low-voltage outgoing line and each user intelligent electric meter of the distribution transformer in the target area in a preset time period;
s2, performing dimension reduction on the voltage time sequence data according to a multi-dimensional scaling method to obtain a low-dimensional voltage feature set;
s3, clustering the low-dimensional voltage feature set according to a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set;
and S4, calculating the distance from the corresponding point of each distribution transformer terminal to the center of each cluster according to the low-dimensional voltage feature set after clustering, and obtaining the phase sequence attribution relationship of the user intelligent electric meter according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster.
2. The low-voltage transformer area phase sequence identification method according to claim 1, wherein the number of collected time sections in the preset time period is greater than or equal to the total number of user smart electric meters in the target transformer area.
3. The low-voltage transformer area phase sequence identification method according to claim 1, wherein the voltage time sequence data is subjected to dimensionality reduction according to a multidimensional scaling method to obtain a low-dimensional voltage feature set, and the following calculation formula is adopted:
Dij＝||zi-zj||
in the formula, DijIs the Euclidean distance between the ith time and the jth time of the original high-dimensional voltage data, ziRepresenting the mapping of the voltage data at the ith time in a low dimensional space, zjRepresenting a mapping of the voltage data at the jth time in a low dimensional space;
let B be the inner product matrix of the reduced-dimension sample, let B be Zi TZjThen, then
Figure FDA0003131179770000021
Figure FDA0003131179770000022
Centralizing the reduced sample, and then:
Figure FDA0003131179770000023
Figure FDA0003131179770000024
according to Dij＝||zi-zjWill b | |ijBy DijThis means that there are:
Figure FDA0003131179770000025
Figure FDA0003131179770000026
Figure FDA0003131179770000027
in the formula, tr (-) denotes a trace of the matrix;
Figure FDA0003131179770000028
order to
Figure FDA0003131179770000029
Figure FDA00031311797700000210
Figure FDA00031311797700000211
In the formula, m is the number of samples;
from the above, the inner product matrix B can be obtained
Figure FDA0003131179770000031
Carrying out characteristic value decomposition on the obtained product:
B＝VΛVT
Λ＝diag(λ1,λ2,...,λd')
λ1≥λ2≥...≥λd'
Λ＝ΛT
B＝ZTZ＝VΛVT
Figure FDA0003131179770000032
Figure FDA0003131179770000033
in the formula, lambda is a characteristic value of the matrix B, lambda is a diagonal matrix formed by the characteristic values, and v is a characteristic vector matrix of the pertinence;
and d' maximum eigenvalues and eigenvectors before the step are reserved, so that a data matrix characteristic set after dimension reduction can be obtained:
Figure FDA0003131179770000034
4. the low-voltage transformer area phase sequence identification method according to claim 1, wherein the clustering processing is performed on the low-dimensional voltage feature set by using a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set, and the method comprises the following steps:
s31, randomly initializing K clustering centers for the low-dimensional voltage feature set;
s32, each object is allocated to K initial clustering centers based on the distance minimum principle, wherein the distance: the following calculation formula is adopted:
S＝||z-μi(N)||2,i＝1,2,…,K
wherein z is the reduced voltage data, μi(N) is the ith cluster center at the Nth iteration;
s33, judging whether each object z violates the connectionless constraint and fixes, if so, returning the constraint checking function to true, and if not, returning false;
s34, if the constraint check function returns to true, distributing z to the cluster next to it, and returning to step S33 to check the object z again, if the constraint check function returns to false, returning to step S33 and checking the next object; if the same object z continuously violates the constraint for K times, returning to null, which means that no cluster which can legally accommodate the object exists; until all objects are traversed, go to step S35;
s35, calculating the average value of all objects in each cluster, and updating the cluster center of each cluster according to the average value;
s36, repeating the steps S32-S35 until the cluster center is not changed.
5. The low-voltage transformer area phase sequence identification method according to claim 4, characterized in that the following calculation formula is adopted based on the distance minimum principle:
S＝||z-μi(N)||2,i＝1,2,…,K
wherein z is the reduced voltage data, μi(N) is the ith cluster center at the Nth iteration.
6. The method for identifying the phase sequence of the low voltage transformer area according to claim 4, wherein the average value of all objects in each cluster is calculated, and the cluster center of each cluster is updated according to the average value, and the following calculation formula is adopted:
Figure FDA0003131179770000041
7. the method for identifying the phase sequence of the low-voltage transformer area according to claim 1, wherein the step of calculating the distance from the corresponding point of each distribution transformer terminal to the center of each cluster according to the low-dimensional voltage feature set after the clustering process, and obtaining the phase sequence attribution relationship of the user intelligent electric meter according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster comprises the steps of:
sequentially calculating the distance between the A, B, C three-phase distribution transformation terminal voltage time sequence and the center of each cluster in the low-dimensional space, determining the cluster closest to the A-phase distribution transformation terminal voltage time sequence as an A cluster, marking users corresponding to all objects as A-phase users, and determining B, C-phase users by analogy, wherein the specific calculation formula is as follows:
S＝||zA-μi||2，i＝1,2,…,K
in the formula, zAAnd changing the terminal voltage time sequence for the A phase after dimension reduction.
8. A low-voltage transformer area phase sequence identification system, comprising: a data acquisition module, a data dimension reduction module, a data clustering module and a phase sequence identification module, wherein,
the data acquisition module is used for acquiring voltage time sequence data of each phase low-voltage outgoing line and each user intelligent electric meter of the distribution transformer in a preset time period in the target transformer area;
the data dimension reduction module is used for reducing dimensions of the voltage time sequence data according to a multi-dimensional scaling method to obtain a low-dimensional voltage feature set;
the data clustering module is used for clustering the low-dimensional voltage feature set according to a CK-Means semi-supervised clustering algorithm to obtain a clustered low-dimensional voltage feature set;
and the phase sequence identification module is used for calculating the distance from the corresponding point of each distribution transformer terminal to the center of each cluster according to the low-dimensional voltage characteristic set after clustering processing, and obtaining the phase sequence attribution relation of the user intelligent electric meter according to the distance from the corresponding point of each distribution transformer terminal to the center of each cluster.
9. A computer terminal device, comprising:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the low-voltage station phase sequence identification method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a low-voltage station phase sequence identification method according to any one of claims 1 to 7.
CN202110707794.5A 2021-06-24 2021-06-24 Low-voltage transformer area phase sequence identification method, system, terminal and storage medium Active CN113449980B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110707794.5A CN113449980B (en) 2021-06-24 2021-06-24 Low-voltage transformer area phase sequence identification method, system, terminal and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110707794.5A CN113449980B (en) 2021-06-24 2021-06-24 Low-voltage transformer area phase sequence identification method, system, terminal and storage medium

Publications (2)

Publication Number Publication Date
CN113449980A true CN113449980A (en) 2021-09-28
CN113449980B CN113449980B (en) 2023-02-24

Family

ID=77812667

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110707794.5A Active CN113449980B (en) 2021-06-24 2021-06-24 Low-voltage transformer area phase sequence identification method, system, terminal and storage medium

Country Status (1)

Country Link
CN (1) CN113449980B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114548226A (en) * 2022-01-21 2022-05-27 国网江苏省电力有限公司常州供电分公司 Method and device for identifying station area user-variable relationship based on K-Means clustering algorithm
CN115310879A (en) * 2022-10-11 2022-11-08 浙江浙石油综合能源销售有限公司 Multi-fueling-station power consumption control method based on semi-supervised clustering algorithm

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190114640A1 (en) * 2017-10-18 2019-04-18 Fis Financial Compliance Solutions, Llc Systems and methods for detecting periodic patterns in large datasets
CN111879983A (en) * 2020-07-31 2020-11-03 广东电网有限责任公司计量中心 Method, device, equipment and medium for identifying relationship between station area household variation and phase sequence
CN112070143A (en) * 2020-09-02 2020-12-11 广东电网有限责任公司广州供电局 Cluster analysis-based station area user variable relation identification method and system
CN112750051A (en) * 2020-12-30 2021-05-04 广东电网有限责任公司计量中心 Random forest algorithm-based phase sequence identification method and device for transformer area and terminal equipment

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190114640A1 (en) * 2017-10-18 2019-04-18 Fis Financial Compliance Solutions, Llc Systems and methods for detecting periodic patterns in large datasets
CN111879983A (en) * 2020-07-31 2020-11-03 广东电网有限责任公司计量中心 Method, device, equipment and medium for identifying relationship between station area household variation and phase sequence
CN112070143A (en) * 2020-09-02 2020-12-11 广东电网有限责任公司广州供电局 Cluster analysis-based station area user variable relation identification method and system
CN112750051A (en) * 2020-12-30 2021-05-04 广东电网有限责任公司计量中心 Random forest algorithm-based phase sequence identification method and device for transformer area and terminal equipment

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114548226A (en) * 2022-01-21 2022-05-27 国网江苏省电力有限公司常州供电分公司 Method and device for identifying station area user-variable relationship based on K-Means clustering algorithm
CN115310879A (en) * 2022-10-11 2022-11-08 浙江浙石油综合能源销售有限公司 Multi-fueling-station power consumption control method based on semi-supervised clustering algorithm
CN115310879B (en) * 2022-10-11 2022-12-16 浙江浙石油综合能源销售有限公司 Multi-fueling-station power consumption control method based on semi-supervised clustering algorithm

Also Published As

Publication number Publication date
CN113449980B (en) 2023-02-24

Similar Documents

Publication Publication Date Title
CN113449980B (en) Low-voltage transformer area phase sequence identification method, system, terminal and storage medium
CN111505433B (en) Low-voltage transformer area indoor variable relation error correction and phase identification method
CN110492480B (en) Power distribution network topology identification method and device, computer equipment and readable storage medium
CN110288039B (en) Electricity stealing detection method based on user electricity load characteristics
CN113933556B (en) Method and device for detecting electricity stealing behavior, computer equipment and storage medium
CN109285087A (en) A kind of platform area topology identification method accelerated based on NB-IoT and GPU
CN103927693A (en) Distribution network line loss management system
CN110244099A (en) Stealing detection method based on user's voltage
CN106874676B (en) State evaluation method for electric energy metering device
CN112615428A (en) Line loss analysis and treatment system and method
CN111091223B (en) Matching short-term load prediction method based on intelligent sensing technology of Internet of things
CN106097137A (en) A kind of anti-electricity-theft monitoring system of differentiation based on power information acquisition system
CN113344450B (en) Low-voltage station area subscriber identification method, system, terminal equipment and storage medium
CN112182499B (en) Low-voltage distribution network topological structure identification method based on time sequence electric quantity data
CN113076618B (en) Power distribution network single line diagram correction method, system, terminal equipment and storage medium
CN110222098A (en) Electric power high amount of traffic abnormality detection based on flow data clustering algorithm
CN113595071A (en) Transformer area user identification and voltage influence evaluation method
CN112215482A (en) Method and device for identifying user variable relationship
CN110991741A (en) Section constraint probability early warning method and system based on deep learning
CN115758188A (en) Non-invasive load identification method, device, equipment and medium
CN114065129A (en) Line-variable relation detection method and detection system based on spectral clustering method
CN112528762B (en) Harmonic source identification method based on data correlation analysis
Hu et al. Transformer-customer relationship identification for low-voltage distribution networks based on joint optimization of voltage silhouette coefficient and power loss coefficient
CN114421453A (en) Power distribution network parameter estimation method and system based on mixed measured values
Abur et al. Optimal meter placement against contingencies

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant