CN113837458B - Distribution network data edge calculation model of distribution network equipment and defect elimination auxiliary method and system - Google Patents

Distribution network data edge calculation model of distribution network equipment and defect elimination auxiliary method and system Download PDF

Info

Publication number
CN113837458B
CN113837458B CN202111082952.9A CN202111082952A CN113837458B CN 113837458 B CN113837458 B CN 113837458B CN 202111082952 A CN202111082952 A CN 202111082952A CN 113837458 B CN113837458 B CN 113837458B
Authority
CN
China
Prior art keywords
cluster
data
distribution network
center
updated
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.)
Active
Application number
CN202111082952.9A
Other languages
Chinese (zh)
Other versions
CN113837458A (en
Inventor
肖惠
慈白山
袁帅
胡超
彭立
于鹏
邹欢
张坚
李强
李海涛
刘云祥
欧阳耀军
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.)
Nanchang Honggutan Power Supply Branch State Grid Jiangxi Electric Power Co ltd
Nanchang Power Supply Branch State Grid Jiangxi Province Electric Power Co ltd
State Grid Corp of China SGCC
Original Assignee
Nanchang Honggutan Power Supply Branch State Grid Jiangxi Electric Power Co ltd
Nanchang Power Supply Branch State Grid Jiangxi Province Electric Power Co ltd
State Grid Corp of China SGCC
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 Nanchang Honggutan Power Supply Branch State Grid Jiangxi Electric Power Co ltd, Nanchang Power Supply Branch State Grid Jiangxi Province Electric Power Co ltd, State Grid Corp of China SGCC filed Critical Nanchang Honggutan Power Supply Branch State Grid Jiangxi Electric Power Co ltd
Publication of CN113837458A publication Critical patent/CN113837458A/en
Application granted granted Critical
Publication of CN113837458B publication Critical patent/CN113837458B/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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • 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
    • 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
    • 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
    • G06Q10/20—Administration of product repair or maintenance
    • 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
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y10/00—Economic sectors
    • G16Y10/35—Utilities, e.g. electricity, gas or water
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/20—Information sensed or collected by the things relating to the thing itself
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/30—Information sensed or collected by the things relating to resources, e.g. consumed power
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/10—Detection; Monitoring
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/20—Analytics; Diagnosis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/40—Maintenance of things
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/50—Safety; Security of things, users, data or systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/60—Positioning; Navigation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Computing Systems (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • General Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Toxicology (AREA)
  • Artificial Intelligence (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Accounting & Taxation (AREA)
  • Probability & Statistics with Applications (AREA)
  • General Engineering & Computer Science (AREA)
  • Water Supply & Treatment (AREA)
  • Environmental & Geological Engineering (AREA)
  • Biomedical Technology (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Security & Cryptography (AREA)

Abstract

The invention discloses a distribution network data edge calculation model of distribution network equipment, which comprises the steps of (1) collecting state data of the distribution network equipment to obtain a data set; (2) determining a cluster number K value; (3) determining cluster radius-Euclidean distance; (4) updating the cluster center and the iteration output. The invention also discloses a method and a system for assisting in eliminating the defect of the distribution network data edge calculation model of the distribution network equipment. The device is embedded and installed on the power distribution network equipment, so that the information rapid increase can be relieved, the pressure of background data processing is relieved, the background data processing time is shortened, and the data processing rate of a power distribution network system is improved. The system stores related information such as a secondary wiring diagram of power distribution network equipment, reduces the loss rate of the information, improves the defect eliminating efficiency and accuracy of operation and maintenance team personnel, and does not delay defect eliminating time due to different power distribution network equipment types and different wiring modes.

Description

Distribution network data edge calculation model of distribution network equipment and defect elimination auxiliary method and system
Technical Field
The invention belongs to the technical field of power defect elimination assistance, in particular relates to a distribution network data edge calculation model of distribution network equipment, and further relates to a defect elimination assistance method and system based on the model.
Background
With the continuous development and progress of society, the power demands of industry, commerce and residents are rapidly increased, the power grid construction is also rapidly developed, the power grid load rate is continuously increased, and the number of distribution network equipment which is rapidly increased brings higher and higher requirements to the fine operation and maintenance work of the distribution network. On one hand, the rapid increase of the information uploaded by the distribution network equipment causes the increase of information transmission delay, time and bandwidth, and seriously affects the data processing rate of the distribution network system; on the other hand, due to the large task quantity of eliminating the shortage and the high quality index of high-quality service, the low data processing rate of the distribution network system can lead to the prolonged working time and high psychological pressure of first-line team personnel. Under normal conditions, the drawings of the primary and secondary electrical wiring diagrams of the distribution network equipment are placed in the cabinet body before the distribution network equipment is put into operation, but the loss probability is increased along with the increase of operation and maintenance defect eliminating times. And because the distribution network equipment is various in types and different in types, the primary and secondary electric wiring of different types has a little difference, and great challenges are brought to accurate and rapid defect elimination of operation and maintenance team personnel.
Disclosure of Invention
The invention mainly solves the technical problems of providing a distribution network data edge calculation model of distribution network equipment, realizing the transparency of the geographical information of a ring main unit, the data refinement and paperless management of a defect-free electrical drawing, and further solving the problem of delay time when the conventional distribution network equipment is subjected to defect elimination.
The invention solves the technical problems through the following technical proposal,
the distribution network data edge calculation model of the distribution network equipment comprises the steps of,
(1) Collecting state data of distribution network equipment to obtain a data set
X n ＝{(x 1 ,y 1 ,...,z 1 ),(x 2 ,y 2 ,...,z 2 ),…,(x n ,y n ,...,z n )}；
(2) Cluster number K value determination
Setting a coefficient a as a convergence condition parameter of a clustering number K value, wherein 0< a <1;
(2.1) random on data set X n Selecting an m point as the 1 st clustering center
Figure GDA0004162259340000011
Figure GDA0004162259340000012
1 st cluster center representing m-point as starting point, wherein +.>
Figure GDA0004162259340000013
Representing m points as 1 st cluster centers in data set X n The value of (2) is the value of the starting point m;
(2.2) in dataset X n Selecting the 1 st cluster center
Figure GDA0004162259340000021
The furthest point is taken as the 2 nd clustering center
Figure GDA0004162259340000022
The point selected as the clustering center is selected by the clustering center after the point is not entered any more;
(2.3) in dataset X n In the method, the distance between each point except the cluster center and all the cluster centers is calculated, and the distance formula is as follows:
Figure GDA0004162259340000023
i is more than or equal to 1 and less than or equal to n, i is a data set X except a clustering center n Is a dot in (2);
j is more than or equal to 1 and less than or equal to k, wherein k is the number of the selected cluster centers;
(2.4) obtaining the minimum distance from all the cluster centers for each point except the cluster center
Figure GDA0004162259340000024
Figure GDA0004162259340000025
I is more than or equal to 1 and less than or equal to n, i is a data set X except a clustering center n Is a dot in (2);
(2.5) determining the minimum distance
Figure GDA0004162259340000026
Whether or not it satisfies:
Figure GDA0004162259340000027
a is the coefficient set in the step (2), 0< a <1;
if it is
Figure GDA0004162259340000028
The point i is a cluster-like of the cluster center closest to the point i;
if it is
Figure GDA0004162259340000029
Then point i is selected as the k+1th cluster center;
(2.6) repeating the steps (2.3) - (2.5) to select the Kth clustering center
Figure GDA00041622593400000210
Determining the value of the cluster number K and removing the data set X outside the cluster center n Dividing the points in the cluster into cluster centers closest to the cluster centers to form class clusters of the cluster centers;
(3) Cluster radius-euclidean distance
The similarity index of the clusters is represented by Euclidean distance, and the cluster radius is selected as the maximum value of the distance from all points in the clusters to the cluster center;
through the step (2), K cluster centers are obtained in total, namely K clusters are obtained,
then the j-th cluster center
Figure GDA0004162259340000031
The radius of (2) is:
Figure GDA0004162259340000032
i is a cluster of class in the j-th cluster, and m is more than or equal to 1 and less than or equal to n;
wherein the point (x i ,y i ,...,z i ) Values belonging to class clusters in the j-th cluster;
obtaining the cluster radius of K cluster centers altogether;
(4) Updating cluster centers and iterative outputs
(4.1) computing a clustering objective function
The clustering objective function is set as
Figure GDA0004162259340000033
Obtaining a clustering objective function divided by K clustering centers;
(4.2) taking the average value of the class clusters in the same cluster as a first updating cluster center, calculating to obtain K first updating cluster centers, and calculating a corresponding first updating cluster objective function;
(4.3) if the first updated cluster objective function and the first updated cluster center change from either the cluster objective function or the cluster center, recalculating the dataset X n The distance between each element and K first updated clustering centersIs used for the distance of (a),
the distance formula is:
Figure GDA0004162259340000034
i is more than or equal to 1 and less than or equal to n, i is a data set X n All points in (a);
j is more than or equal to 1 and less than or equal to K, wherein K is the number of clusters, namely a K value;
obtaining a data set X n The minimum distance of each point in (a) from all first updated cluster centers
Figure GDA0004162259340000035
Figure GDA0004162259340000036
I is more than or equal to 1 and less than or equal to n, i is a data set X n All points in (a);
minimum distance
Figure GDA0004162259340000037
The corresponding element is marked as +.>
Figure GDA0004162259340000038
Updating class clusters of the cluster center for the first time;
obtaining K cluster elements of the first updating cluster again;
(4.4) obtaining the cluster radius of K first updated cluster centers according to the step (3);
(4.5) according to the step (4.2), taking the average value of the class clusters in the same cluster as a second updating cluster center, calculating to obtain K second updating cluster centers, and calculating a corresponding second updating cluster objective function;
(4.6) according to step (4.4), if the second updated clustering objective function and the second updated clustering center are changed from any one of the first updated clustering objective function and the first updated clustering center, recalculating the data set X n The distance between each element and K second updated cluster centers to obtain a data set X n The minimum distance of each point in (a) from all second updated cluster centers
Figure GDA0004162259340000041
Minimum distance
Figure GDA0004162259340000042
The corresponding element is marked as +.>
Figure GDA0004162259340000043
Updating class clusters of the cluster center for the corresponding second time;
obtaining K cluster elements of the second updating clusters again;
and (4.7) repeating the steps (4.4) - (4.6) until the s-th updated clustering objective function and the s-th updated clustering center are unchanged from any one of the s-1-th updated clustering objective function and the s-1-th updated clustering center, indicating data convergence, and outputting the s-th updated clustering center.
The s-th updated clustering center is output as representative data, so that the data volume of background processing can be reduced.
The invention also discloses a distribution network data edge calculation model defect elimination auxiliary system of the distribution network equipment, which comprises a distribution network equipment acquisition module and a distribution network communication module, and is characterized in that,
the distribution network equipment acquisition module comprises a data acquisition unit, a position acquisition unit and a data alarm unit,
the data acquisition unit acquires state data of the distribution network equipment;
the position acquisition unit acquires geographic position information data of distribution network equipment;
the data alarm unit compares the state data and/or the geographic position information data with preset data, and when the state data and/or the geographic position information data exceed the preset data range, the data alarm unit sends alarm data, sends the alarm data to the distribution network communication module, and sends the alarm data to the back-end distribution network system server through the distribution network communication module;
the distribution network communication module comprises a data supervision unit, a data processing unit and a data transmission unit,
the data supervision unit supervises the state data of the distribution network equipment in real time, supervises whether the distribution network equipment operates normally, and if the equipment operates abnormally, sends supervision signals to a back-end distribution network system server for recording;
the data processing unit is used for preprocessing the state data through the power distribution network data edge calculation model to obtain preprocessed state data, uploading the preprocessed state data to a rear-end power distribution network system server, reducing the information data quantity transmitted to the power distribution network system by the data transmission unit, and reducing the pressure of the power distribution network system for calculating the processed state data;
the data transmission unit is used for transmitting the preprocessed data processed by the data processing unit to the rear-end power distribution network system server through optical fibers or wireless.
In order to obtain a better technical effect, the state data comprise real-time voltage, real-time current, a voltage transformer, a current transformer, switch opening and closing, relay protection switching and temperature;
in order to obtain better technical effects, the distribution network equipment acquisition module further comprises a data storage unit, wherein the data storage unit stores historical data of the data acquisition unit and the position acquisition unit and equipment information data of the distribution network equipment, and the historical data can be automatically cleaned in a selective period;
in order to obtain a better technical effect, the equipment information data comprise equipment delivery time, equipment manufacturer, equipment instruction book and stored equipment information;
in order to obtain better technical effects, the distribution network communication module further comprises a security guarantee unit, wherein the security guarantee unit is an encryption module containing an encryption algorithm, and is used for carrying out encryption protection on various running state data of distribution network equipment so as to ensure that the data is not easy to hijack and crack in the transmission process.
The invention also discloses a defect elimination auxiliary method of the defect elimination auxiliary system of the distribution network data edge calculation model of the distribution network equipment, which comprises the steps of,
(1) Displaying fault information and pre-judged specific information on a web page and a mobile phone terminal by using a prediction result of a system server of the back-end power distribution network, and automatically sending a fault short message to maintainers and operation maintenance staff responsible for the geographical information according to the geographical information of the fault by the system;
(2) The maintainer and the operation and maintenance team responsible person receive the equipment fault short message and log in the mobile phone terminal to check the detailed fault message;
(3) The operation and maintenance team personnel judges whether the fault message needs to go out to eliminate the defect according to the detailed fault message;
(4) If the fault is not urgent, normal operation of the equipment is not hindered, and the equipment is not suitable for live working, the fault message can be loaded into a historical fault message, and later operation and maintenance staff can go out in batches in a unified way according to the historical fault message to eliminate the defect;
(5) If the fault needs to be solved, the operation and maintenance team personnel navigate to the position of the fault equipment according to the equipment positioning data acquired by the position acquisition unit of the power distribution equipment acquisition module;
(6) In the process of eliminating the operation and maintenance of the equipment, the wiring diagram and the schematic diagram of the equipment are slightly different due to various kinds of distribution network equipment, so that challenges are brought to the fine operation and maintenance elimination. And the operation and maintenance team personnel search related information such as a secondary wiring diagram and the like of the fault equipment through the mobile phone terminal of the system, and then perform accurate defect elimination on the fault equipment.
The device is embedded and installed on the power distribution network equipment, so that the information rapid increase can be relieved, the pressure of background data processing is relieved, the background data processing time is shortened, and the data processing rate of a power distribution network system is improved. The system stores related information such as a secondary wiring diagram of power distribution network equipment, reduces the loss rate of the information, improves the defect eliminating efficiency and accuracy of operation and maintenance team personnel, and does not delay defect eliminating time due to different power distribution network equipment types and different wiring modes.
Drawings
FIG. 1 is a schematic diagram of an embodiment of the present invention;
FIG. 2 is a flow chart illustrating the process of eliminating defects according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to the drawings and examples.
Example 1
The distribution network data edge calculation model of the distribution network equipment comprises the steps of,
(1) Collecting state data of distribution network equipment to obtain a data set
X n ＝{(x 1 ,y 1 ,...,z 1 ),(x 2 ,y 2 ,...,z 2 ),…,(x n ,y n ,...,z n )}；
(2) Cluster number K value determination
Setting a coefficient a as a convergence condition parameter of a clustering number K value, wherein 0< a <1;
(2.1) random on data set X n Selecting an m point as the 1 st clustering center
Figure GDA0004162259340000061
Figure GDA0004162259340000062
1 st cluster center representing m-point as starting point, wherein +.>
Figure GDA0004162259340000063
Representing m points as 1 st cluster centers in data set X n The value of (2) is the value of the starting point m;
(2.2) in dataset X n Selecting the 1 st cluster center
Figure GDA0004162259340000064
The furthest point is taken as the 2 nd clustering center
Figure GDA0004162259340000065
Clustering after points selected as cluster centers no longer enterSelecting a center;
(2.3) in dataset X n In the method, the distance from each point except the cluster center to each cluster center is calculated, and the distance formula is as follows:
Figure GDA0004162259340000071
i is more than or equal to 1 and less than or equal to n, i is a data set X except a clustering center n Is a dot in (2);
j is more than or equal to 1 and less than or equal to k, wherein k is the number of the selected cluster centers;
(2.4) obtaining the minimum distance from all the cluster centers for each point except the cluster center
Figure GDA0004162259340000072
Figure GDA0004162259340000073
I is more than or equal to 1 and less than or equal to n, i is a data set X except a clustering center n Is a dot in (2);
(2.5) determining the minimum distance
Figure GDA0004162259340000074
Whether or not it satisfies:
Figure GDA0004162259340000075
a is the coefficient set in the step (2), 0< a <1;
if it is
Figure GDA0004162259340000076
The point i is a cluster-like of the cluster center closest to the point i;
if it is
Figure GDA0004162259340000077
Then point i is selected as the k+1th cluster center;
(2.6) repeating the steps (2.3) - (2.5) to select the Kth clustering center
Figure GDA0004162259340000078
Determining the value of the cluster number K and removing the data set X outside the cluster center n Dividing the points in the cluster into cluster centers closest to the cluster centers to form class clusters of the cluster centers;
(3) Cluster radius-euclidean distance
The similarity index of the clusters is represented by Euclidean distance, and the cluster radius is selected as the maximum value of the distance from all points in the clusters to the cluster center;
through the step (2), K cluster centers are obtained in total, namely K clusters are obtained,
then the j-th cluster center
Figure GDA0004162259340000079
The radius of (2) is:
Figure GDA00041622593400000710
i is a cluster of class in the j-th cluster, and m is more than or equal to 1 and less than or equal to n;
wherein the dot is
Figure GDA0004162259340000081
For the j-th cluster center->
Figure GDA0004162259340000082
The value of (x) i ,y i ,...,z i ) Values belonging to cluster-like elements in the j-th cluster;
obtaining the cluster radius of K cluster centers altogether;
(4) Updating cluster centers and iterative outputs
(4.1) computing a clustering objective function
The clustering objective function is set as
Figure GDA0004162259340000083
Obtaining a cluster objective function divided by K cluster centers, wherein +.>
Figure GDA0004162259340000084
For the j-th cluster center->
Figure GDA0004162259340000085
Is a value of (2);
(4.2) taking the average value of cluster-like elements in the same cluster as a first updating cluster center, calculating to obtain K first updating cluster centers, and calculating a corresponding first updating cluster objective function;
(4.3) if the first updated cluster objective function and the first updated cluster center change from either the cluster objective function or the cluster center, recalculating the dataset X n The distance between each element in the plurality of elements and K of the first updated cluster centers,
the distance formula is:
Figure GDA0004162259340000086
i is more than or equal to 1 and less than or equal to n, i is a data set X n All points in (a);
j is more than or equal to 1 and less than or equal to K, wherein K is the number of clusters, namely a K value;
obtaining a data set X n The minimum distance of each point in (a) from all first updated cluster centers
Figure GDA0004162259340000087
Figure GDA0004162259340000088
I is more than or equal to 1 and less than or equal to n, i is a data set X n All points in (a);
minimum distance
Figure GDA0004162259340000089
The corresponding element is marked as +.>
Figure GDA00041622593400000810
Updating class clusters of the cluster center for the first time;
obtaining K cluster elements of the first updating cluster again;
(4.4) obtaining the cluster radius of K first updated cluster centers according to the method in the step (3);
(4.5) according to the method in the step (4.2), taking the average value of the class clusters in the same cluster as a second updating cluster center, calculating to obtain K second updating cluster centers, and calculating a corresponding second updating cluster objective function;
(4.6) according to the method of step (4.4), if the second updated clustering objective function and the second updated clustering center are changed from any of the first updated clustering objective function and the first updated clustering center, recalculating the data set X n The distance between each element and K second updated cluster centers to obtain a data set X n The minimum distance of each point in (a) from all second updated cluster centers
Figure GDA0004162259340000091
Minimum distance
Figure GDA0004162259340000092
The corresponding element is marked as +.>
Figure GDA0004162259340000093
Updating class clusters of the cluster center for the corresponding second time;
obtaining K cluster elements of the second updating clusters again;
and (4.7) repeating the steps (4.4) - (4.6) until the s-th updated clustering objective function and the s-1-th updated clustering center are unchanged, so that data convergence is indicated, the s-th updated clustering center is output, the output s-th updated clustering center is used as representative data, and the data volume of background processing can be reduced.
Example 2
The distribution network data edge calculation model of the distribution network equipment comprises the steps of,
(1) In order to simply illustrate the implementation process, the embodiment selects and collects the real-time current (A) and real-time voltage (kV) parameters of the distribution network equipment to obtain a data set X n ＝{X 1 (5.1,4.98)，X 2 (5,5.07)，X 3 (0.11,0)，X 4 (0.01,0.01)，X 5 (6.13,5.77)，X 6 (6.3,5.77)，X 7 (6.29,5.79)}；
In the actual working process, according to the complexity of the power grid and the actual running condition of a power supply company, the selectable state data comprise real-time voltage, real-time current, a voltage transformer, a current transformer, switch opening and closing, relay protection switching and temperature; the real-time voltage selects a current value (unit A) when data are extracted; the voltage value (unit kV) when the data is extracted is selected by the real-time voltage; primary and secondary current values (unit a) of the voltage transformer; the primary voltage value and the secondary voltage value (unit kV) of the current transformer are respectively selected from the states of a switch and a relay when data are extracted by switching on and switching off of the switch and relay protection switching on and switching off, wherein the switching on and the relay protection switching on are 1, and the switching off and the relay protection switching off are 0; temperature value (unit ℃) when the data are extracted is selected by temperature;
(2) Class number K value determination
Setting a coefficient a=0.2, wherein the coefficient a is a convergence condition parameter of a cluster number K value;
(2.1) random on data set X n Selecting an m point as the 1 st clustering center
Figure GDA0004162259340000101
In this embodiment, the 2 nd point X is selected 2 (5,5.07) as the 1 st cluster center->
Figure GDA0004162259340000102
I.e. < ->
Figure GDA0004162259340000103
Is (5,5.07);
(2.2) in dataset X n Selecting the 1 st cluster center
Figure GDA0004162259340000104
The furthest point is taken as the 2 nd clustering center
Figure GDA0004162259340000105
Found by calculation, 4 th point X 4 (0.01 ) as cluster center 2 +.>
Figure GDA0004162259340000106
I.e. < ->
Figure GDA0004162259340000107
Is (0.01 ); the point selected as the clustering center is selected by the clustering center after the point is not entered any more;
(2.3) in dataset X n In (3) calculating each point except the cluster center to each cluster center
Figure GDA0004162259340000108
The distance formula is:
Figure GDA0004162259340000109
i is more than or equal to 1 and less than or equal to n, i is a data set X except a clustering center n Is a dot in (2);
j is more than or equal to 1 and less than or equal to k, wherein k is the number of the selected cluster centers;
(2.4) obtaining the minimum distance from all the cluster centers for each point except the cluster center
Figure GDA00041622593400001010
Figure GDA00041622593400001011
X 1 To the point of
Figure GDA00041622593400001012
The distances of (2) are respectively as follows:
Figure GDA00041622593400001013
Figure GDA00041622593400001014
Figure GDA00041622593400001015
/>
(2.5) determining the minimum distance
Figure GDA00041622593400001016
Whether or not it satisfies:
Figure GDA00041622593400001017
a is the coefficient set in the step (2), 0< a <1;
in the present embodiment
Figure GDA00041622593400001018
The distance between them is->
Figure GDA00041622593400001019
Discovery for data set X n Point 1X in (a) 1 The condition is not satisfied:
Figure GDA0004162259340000111
x obtained by calculation in step (2.4) 1 To each cluster center
Figure GDA0004162259340000112
Distance of->
Figure GDA0004162259340000113
Figure GDA0004162259340000114
Discovery dataset X n Point 1X in (a) 1 To->
Figure GDA0004162259340000115
Closest to, i.e. X 1 To->
Figure GDA0004162259340000116
The element of the 1 st cluster of the cluster center;
(2.6) due to dataset X n Point 2X in (a) 2 Is selected as cluster 1 center, thus skipping data set X n Point 2X in (a) 2 Direct calculation of data set X n Point X of 3 in (2) 3 ，
Calculating the data set X according to steps (2.3) - (2.5) n Point X of 3 in (2) 3 To each cluster center
Figure GDA0004162259340000117
Figure GDA0004162259340000118
The distances of (2) are respectively as follows:
Figure GDA0004162259340000119
Figure GDA00041622593400001110
Figure GDA00041622593400001111
discovery for data set X n 3 rd point in (3)X 3 The condition is not satisfied:
Figure GDA00041622593400001112
from X obtained by calculation 3 To each cluster center
Figure GDA00041622593400001113
Distance of->
Figure GDA00041622593400001114
Discovery dataset X n Point X of 3 in (2) 3 To->
Figure GDA00041622593400001115
Closest to, i.e. X 3 To->
Figure GDA00041622593400001116
The element of the 2 nd cluster of the cluster center;
(2.7) due to dataset X n Point X of 4 in (2) 4 Is selected as cluster center 2, thus skipping data set X n Point X of 4 in (2) 4 Direct calculation of data set X n Point X of 5 in (2) 5 ，
Calculating the data set X according to steps (2.3) - (2.5) n Point X of 5 in (2) 5 To each cluster center
Figure GDA00041622593400001117
Figure GDA00041622593400001118
The distances of (2) are respectively as follows:
Figure GDA00041622593400001119
Figure GDA0004162259340000121
Figure GDA0004162259340000122
discovery for data set X n Point X of 5 in (2) 5 The condition is not satisfied:
Figure GDA0004162259340000123
from X obtained by calculation 5 To each cluster center
Figure GDA0004162259340000124
Distance of->
Figure GDA0004162259340000125
Discovery dataset X n Point X of 5 in (2) 5 To->
Figure GDA0004162259340000126
Closest to, i.e. X 5 To->
Figure GDA0004162259340000127
The element of the 1 st cluster of the cluster center;
(2.8) computing data set X n Point X of (6) 6 ，
Calculating the data set X according to steps (2.3) - (2.5) n Point X of (6) 6 To each cluster center
Figure GDA0004162259340000128
Figure GDA0004162259340000129
The distances of (2) are respectively as follows:
Figure GDA00041622593400001210
Figure GDA00041622593400001211
ρ 6 ＝min{ρ 61 ,ρ 62 }＝1.4765；
discovery for data set X n Point X of (6) 6 The conditions are satisfied:
Figure GDA00041622593400001212
thus, data set X n Point X of (6) 6 Is selected as the third cluster center
Figure GDA00041622593400001213
(2.9) computing data set X n Point 7X in (a) 7 ，
Calculating the data set X according to steps (2.3) - (2.5) n Point 7X in (a) 7 To each cluster center
Figure GDA00041622593400001214
Figure GDA00041622593400001215
The distances of (2) are respectively as follows:
Figure GDA00041622593400001216
Figure GDA00041622593400001217
Figure GDA00041622593400001218
Figure GDA0004162259340000131
discovery for data set X n Point 7X in (a) 7 The condition is not satisfied:
Figure GDA0004162259340000132
from X obtained by calculation 5 To each cluster center
Figure GDA0004162259340000133
Distance of->
Figure GDA0004162259340000134
Figure GDA0004162259340000135
Discovery dataset X n Point 7X in (a) 7 To->
Figure GDA0004162259340000136
Recently, X is 7 To->
Figure GDA0004162259340000137
The element of the 3 rd cluster which is the cluster center;
thus, for this embodiment, the cluster number k=3, there are 3 cluster centers:
Figure GDA0004162259340000138
Figure GDA0004162259340000139
the list is as follows:
Figure GDA00041622593400001310
/>
(3) Cluster radius-euclidean distance
The similarity index of the clusters is represented by Euclidean distance, and the cluster radius is selected as the maximum value of the distance from all points in the clusters to the cluster center;
through step 2), there are k=3 cluster centers in total, i.e. k=3 clusters,
then the j-th cluster center
Figure GDA00041622593400001311
The radius of (2) is:
Figure GDA00041622593400001312
i is a cluster-like element in the j-th cluster, and m is more than or equal to 1 and less than or equal to n=7;
wherein the point (x i ,y i ) Values belonging to cluster-like elements in the j-th cluster;
according to
Figure GDA00041622593400001313
Calculation yields k=3 cluster radii:
Figure GDA00041622593400001314
Figure GDA00041622593400001315
Figure GDA0004162259340000141
Figure GDA0004162259340000142
(4) Updating cluster center and iterative output
(4.1) computing a clustering objective function
S m ＝|X 1 -M 1 | 2 +|X 1 -M 2 | 2 +|X 1 -M 3 | 2 +…+|X 7 -M 1 | 2 +|X 7 -M 2 | 2 +|X 7 -M 3 | 2 ，
Obtaining S m ＝572.2357；
(4.2) taking the mean value of cluster-like elements in the same cluster as a first updating cluster center, calculating to obtain K first updating cluster centers, calculating a corresponding first updating cluster objective function, and re-calculating the cluster radius as follows:
first update of 1 st cluster center
Figure GDA0004162259340000143
Figure GDA0004162259340000144
Figure GDA0004162259340000145
First update of the 2 nd cluster center
Figure GDA0004162259340000146
Figure GDA0004162259340000147
/>
Figure GDA0004162259340000148
First update 3 rd cluster center
Figure GDA0004162259340000149
Figure GDA00041622593400001410
Figure GDA00041622593400001411
Then according to the method of step (3), calculating corresponding three first updated cluster radii through three first updated cluster centers respectively, and the results are as follows:
Figure GDA0004162259340000151
calculating a first updated clustering objective function according to the step (4.1): s= 579.4782;
(4.3) since the first updated cluster objective function and the first updated cluster center are changed from either the cluster objective function and the cluster center, the data set X needs to be recalculated in steps (2.3) - (2.6) n The distance from each element to the first updated cluster center is used for determining the cluster element in the cluster center; the cluster center is updated for the second time according to the average value of the cluster-like elements in the same cluster,
data set X n The distance result from each element to the first updated clustering center is shown in the figure:
Figure GDA0004162259340000152
according to step (2), based on data set X n The minimum distance from each element in the cluster to the first updated cluster center is used for determining the cluster element in the cluster center, and the average value of the cluster elements in the same cluster is used as the calculated second updated cluster radius, and the specific result is as follows:
Figure GDA0004162259340000153
calculating a clustering objective function: s= 567.9279
(4.4) since the second updated cluster objective function and the second updated cluster center are both changed compared to the first updated cluster objective function and the first updated cluster centerTherefore, it is necessary to recalculate the data set X in steps (2.3) - (2.6) n The distance between each element and the cluster center is updated for the second time, and a cluster of the cluster center is determined; the cluster center is updated for the third time according to the average value of the cluster-like elements in the same cluster,
the calculation result according to the step (4.3) is as follows:
Figure GDA0004162259340000161
calculating a clustering objective function: s= 567.9279
The calculation finds that the clustering objective function and the clustering center of the step (4.3) and the step (4.4) are not changed, which indicates that the data is converged and the clustering center M = { (5.05,5.025), (0.06,0.005), (6.24,5.7767) }.
The 3 rd updating cluster center is output as representative data, so that the data volume of background processing can be reduced. Compared with the conventional method, the conventional method requires outputting the data set X n And the invention only needs to output representative 3 data, thereby greatly reducing the data volume of background processing.
Example 3
The auxiliary system for eliminating the defects of the distribution network data edge calculation model of the distribution network equipment comprises a distribution network equipment acquisition module and a distribution network communication module,
the distribution network equipment acquisition module comprises a data acquisition unit, a position acquisition unit, a data storage unit and a data alarm unit,
the data acquisition unit acquires state data of the distribution network equipment;
the state data comprise real-time voltage, real-time current, a voltage transformer, a current transformer, switch opening and closing, relay protection switching and temperature;
the position acquisition unit acquires geographic position information data of distribution network equipment;
the data alarm unit compares the state data and/or the geographic position information data with preset data, and when the state data and/or the geographic position information data exceed the preset data range, the data alarm unit sends alarm data, sends the alarm data to the distribution network communication module, and sends the alarm data to the back-end distribution network system server through the distribution network communication module;
the data storage unit stores historical data of the data acquisition unit and the position acquisition unit and equipment information data of the distribution network equipment, and the historical data can be automatically cleaned in a selective period;
in order to obtain a better technical effect, the equipment information data comprise equipment delivery time, equipment manufacturer, equipment specifications and stored equipment information;
the distribution network communication module comprises a data supervision unit, a data processing unit, a data transmission unit and a safety guarantee unit,
the data supervision unit supervises the state data of the distribution network equipment in real time, supervises whether the distribution network equipment operates normally, and if the equipment operates abnormally, sends supervision signals to a back-end distribution network system server for recording;
the data processing unit performs preprocessing on the state data through the power distribution network data edge calculation model described in embodiment 1 or embodiment 2 to obtain preprocessed state data, uploads the preprocessed state data to a rear-end power distribution network system server, reduces the amount of information data transmitted to the power distribution network system by the data transmission unit, and reduces the pressure of the power distribution network system for calculating the processed state data;
the data transmission unit is used for transmitting the preprocessed data processed by the data processing unit to the rear-end power distribution network system server through optical fibers or wireless.
The security unit is an encryption module containing an encryption algorithm, and is used for carrying out encryption protection on various running state data of the distribution network equipment, so that the data is not easy to hijack and crack in the transmission process.
Example 4
The auxiliary method for eliminating the auxiliary system of the auxiliary system for eliminating the defects of the distribution network data edge calculation model of the distribution network equipment comprises the steps of,
(1) Displaying fault information and pre-judged specific information on a web page and a mobile phone terminal by using a prediction result of a system server of the back-end power distribution network, and automatically sending a fault short message to maintainers and operation maintenance staff responsible for the geographical information according to the geographical information of the fault by the system;
(2) The maintainer and the operation and maintenance team responsible person receive the equipment fault short message and log in the mobile phone terminal to check the detailed fault message;
(3) The operation and maintenance team personnel judges whether the fault message needs to go out to eliminate the defect according to the detailed fault message;
(4) If the fault is not urgent, normal operation of the equipment is not hindered, and the equipment is not suitable for live working, the fault message can be loaded into a historical fault message, and later operation and maintenance staff can go out in batches in a unified way according to the historical fault message to eliminate the defect;
(5) If the fault needs to be solved, the operation and maintenance team personnel navigate to the position of the fault equipment according to the equipment positioning data acquired by the position acquisition unit of the power distribution equipment acquisition module;
(6) In the operation and maintenance defect elimination process of equipment, the wiring diagram and the schematic diagram of the equipment are slightly different due to various kinds of distribution network equipment, so that challenges are brought to the fine operation and maintenance defect elimination, and operation and maintenance team personnel search related information such as a first wiring diagram and a second wiring diagram of the fault equipment through a mobile phone terminal of a system and then accurately eliminate the fault equipment.
The device is embedded and installed on the power distribution network equipment, so that the information rapid increase pressure can be greatly relieved, the background data processing pressure is relieved, the background data processing time is shortened, and the data processing rate of the power distribution network system is improved. The system stores related information such as the primary wiring diagram and the secondary wiring diagram of the power distribution network equipment, reduces the loss rate of the information, improves the efficiency and the accuracy of eliminating the defects of operation and maintenance team personnel, and does not delay the time for eliminating the defects due to the differences of different power distribution network equipment types, wiring modes and the like.

Claims (7)

1. The distribution network data edge calculation model of the distribution network equipment comprises the steps of,
(1) Collecting state data of distribution network equipment to obtain a data set X n ＝{(x 1 ,y 1 ,...,z 1 ),(x 2 ,y 2 ,...,z 2 ),…,(x n ,y n ,...,z n )}；
(2) Cluster number K value determination
Setting a coefficient a as a convergence condition parameter of a clustering number K value, wherein 0< a <1;
(2.1) random on data set X n Selecting an m point as the 1 st clustering center
Figure QLYQS_1
Figure QLYQS_2
1 st cluster center representing m-point as starting point, wherein +.>
Figure QLYQS_3
Representing m points as 1 st cluster centers in data set X n The value of (2) is the value of the starting point m;
(2.2) in dataset X n Selecting the 1 st cluster center
Figure QLYQS_4
The furthest point is taken as the 2 nd clustering center
Figure QLYQS_5
The point selected as the clustering center is selected by the clustering center after the point is not entered any more;
(2.3) in dataset X n In the method, the distance between each point except the cluster center and all the cluster centers is calculated, and the distance formula is as follows:
Figure QLYQS_6
i is more than or equal to 1 and less than or equal to n, i is a data set X except a clustering center n Is a dot in (2);
j is more than or equal to 1 and less than or equal to k, wherein k is the number of the selected cluster centers;
(2.4) obtaining the minimum distance from all the cluster centers for each point except the cluster center
Figure QLYQS_7
Figure QLYQS_8
I is more than or equal to 1 and less than or equal to n, i is a data set X except a clustering center n Is a dot in (2);
(2.5) determining the minimum distance
Figure QLYQS_9
Whether or not it satisfies:
Figure QLYQS_10
a is the coefficient set in the step (2), 0< a <1;
if it is
Figure QLYQS_11
The point i is a cluster-like of the cluster center closest to the point i;
if it is
Figure QLYQS_12
Then point i is selected as the k+1th cluster center;
(2.6) repeating the steps (2.3) - (2.5) to select the Kth clustering center
Figure QLYQS_13
Determining the value of the cluster number K and removing the data set X outside the cluster center n Dividing the points in the cluster into cluster centers closest to the cluster centers to form class clusters of the cluster centers;
(3) Cluster radius-euclidean distance
The similarity index of the clusters is represented by Euclidean distance, and the cluster radius is selected as the maximum value of the distance from all points in the clusters to the cluster center;
through the step (2), K cluster centers are obtained in total, namely K clusters are obtained,
then the j-th cluster center
Figure QLYQS_14
The radius of (2) is:
Figure QLYQS_15
i is a cluster of class in the j-th cluster, and m is more than or equal to 1 and less than or equal to n;
wherein the point (x i ,y i ,...,z i ) Values belonging to class clusters in the j-th cluster;
obtaining the cluster radius of K cluster centers altogether;
(4) Updating cluster centers and iterative outputs
(4.1) computing a clustering objective function
The clustering objective function is set as
Figure QLYQS_16
Obtaining a clustering objective function divided by K clustering centers;
(4.2) taking the average value of the class clusters in the same cluster as a first updating cluster center, calculating to obtain K first updating cluster centers, and calculating a corresponding first updating cluster objective function;
(4.3) if the first updated cluster objective function and the first updated cluster center change from either the cluster objective function or the cluster center, recalculating the dataset X n The distance between each element in the plurality of elements and K of the first updated cluster centers,
the distance formula is:
Figure QLYQS_17
i is more than or equal to 1 and less than or equal to n, i is a data set X n All points in (a);
j is more than or equal to 1 and less than or equal to K, wherein K is the number of clusters, namely a K value;
obtaining a data set X n The minimum distance of each point in (a) from all first updated cluster centers
Figure QLYQS_18
Figure QLYQS_19
I is more than or equal to 1 and less than or equal to n, i is a data set X n All points in (a);
minimum distance
Figure QLYQS_20
The corresponding element is marked as +.>
Figure QLYQS_21
Updating class clusters of the cluster center for the first time;
obtaining K cluster elements of the first updating cluster again;
(4.4) obtaining the cluster radius of K first updated cluster centers according to the step (3);
(4.5) according to the step (4.2), taking the average value of the class clusters in the same cluster as a second updating cluster center, calculating to obtain K second updating cluster centers, and calculating a corresponding second updating cluster objective function;
(4.6) according to step (4.4), if the second updated clustering objective function and the second updated clustering center are changed from any one of the first updated clustering objective function and the first updated clustering center, recalculating the data set X n The distance between each element and K second updated cluster centers to obtain a data set X n The minimum distance of each point in (a) from all second updated cluster centers
Figure QLYQS_22
Minimum distance
Figure QLYQS_23
The corresponding element is marked as +.>
Figure QLYQS_24
Updating class clusters of the cluster center for the corresponding second time;
obtaining K cluster elements of the second updating clusters again;
and (4.7) repeating the steps (4.4) - (4.6) until the s-th updated clustering objective function and the s-th updated clustering center are unchanged from any one of the s-1-th updated clustering objective function and the s-1-th updated clustering center, indicating data convergence, and outputting the s-th updated clustering center.
2. A defect elimination auxiliary system based on the model of claim 1, comprising a distribution network equipment acquisition module and a distribution network communication module, characterized in that,
the distribution network equipment acquisition module comprises a data acquisition unit, a position acquisition unit and a data alarm unit, wherein the data acquisition unit acquires state data of the distribution network equipment;
the position acquisition unit acquires geographic position information data of distribution network equipment;
the data alarm unit compares the state data and/or the geographic position information data with preset data, and when the state data and/or the geographic position information data exceed the preset data range, the data alarm unit sends alarm data, sends the alarm data to the distribution network communication module, and sends the alarm data to the back-end distribution network system server through the distribution network communication module;
the distribution network communication module comprises a data supervision unit, a data processing unit and a data transmission unit,
the data supervision unit supervises the state data of the distribution network equipment in real time, supervises whether the distribution network equipment operates normally, and if the equipment operates abnormally, sends supervision signals to a back-end distribution network system server for recording;
the data processing unit is used for preprocessing the state data through the power distribution network data edge calculation model to obtain preprocessed state data, uploading the preprocessed state data to a rear-end power distribution network system server, reducing the information data quantity transmitted to the power distribution network system by the data transmission unit, and reducing the pressure of the power distribution network system for calculating the processed state data;
the data transmission unit is used for transmitting the preprocessed data processed by the data processing unit to the rear-end power distribution network system server through optical fibers or wireless.
3. The model-based defect elimination auxiliary system according to claim 2, wherein the state data comprises real-time voltage, real-time current, voltage transformer, current transformer, switch on/off, relay protection switching, and temperature.
4. The model-based defect elimination auxiliary system according to claim 2, wherein the distribution network equipment acquisition module further comprises a data storage unit, wherein the data storage unit stores historical data of the data acquisition unit and the position acquisition unit, and equipment information data of the distribution network equipment, and the historical data can be automatically cleaned in a selective period.
5. The model based defect elimination assistance system of claim 4, wherein said device information data comprises device factory time, device manufacturer, device specification, stored device information.
6. The model-based defect elimination auxiliary system according to claim 2, wherein the distribution network communication module further comprises a security guarantee unit, wherein the security guarantee unit is an encryption module containing an encryption algorithm, and is used for carrying out encryption protection on various running state data of distribution network equipment so as to ensure that the data is not easy to hijack and crack in the transmission process.
7. A defect elimination assisting method of a defect elimination assisting system according to any one of claims 2 to 6, characterized in that,
(1) Displaying fault information and pre-judged specific information on a web page and a mobile phone terminal by using a prediction result of a system server of the back-end power distribution network, and automatically sending a fault short message to maintainers and operation maintenance staff responsible for the geographical information according to the geographical information of the fault by the system;
(2) The maintainer and the operation and maintenance team responsible person receive the equipment fault short message and log in the mobile phone terminal to check the detailed fault message;
(3) The operation and maintenance team personnel judges whether the fault message needs to go out to eliminate the defect according to the detailed fault message;
(4) If the fault is not urgent, normal operation of the equipment is not hindered, and the equipment is not suitable for live working, the fault message can be loaded into a historical fault message, and later operation and maintenance staff can go out in batches in a unified way according to the historical fault message to eliminate the defect;
(5) If the fault needs to be solved, the operation and maintenance team personnel navigate to the position of the fault equipment according to the equipment positioning data acquired by the position acquisition unit of the power distribution equipment acquisition module;
(6) And the operation and maintenance team personnel search the related information of the secondary wiring diagram of the fault equipment through the mobile phone terminal of the system, and then perform accurate defect elimination on the fault equipment.
CN202111082952.9A 2020-12-29 2021-09-15 Distribution network data edge calculation model of distribution network equipment and defect elimination auxiliary method and system Active CN113837458B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2020115898639 2020-12-29
CN202011589863 2020-12-29

Publications (2)

Publication Number Publication Date
CN113837458A CN113837458A (en) 2021-12-24
CN113837458B true CN113837458B (en) 2023-05-16

Family

ID=78959595

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111082952.9A Active CN113837458B (en) 2020-12-29 2021-09-15 Distribution network data edge calculation model of distribution network equipment and defect elimination auxiliary method and system

Country Status (1)

Country Link
CN (1) CN113837458B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106710164A (en) * 2017-03-06 2017-05-24 国电南瑞科技股份有限公司 Power distribution network fault early warning method aiming at multiple factors
CN111564906A (en) * 2020-06-16 2020-08-21 国网湖北省电力有限公司黄石供电公司 Method for efficiently processing automation defects of urban network distribution network

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104899229A (en) * 2014-03-07 2015-09-09 上海市玻森数据科技有限公司 Swarm intelligence based behavior clustering system
JP6334454B2 (en) * 2015-04-23 2018-05-30 日本電信電話株式会社 Clustering apparatus, method, and program
CN106022614A (en) * 2016-05-22 2016-10-12 广州供电局有限公司 Data mining method of neural network based on nearest neighbor clustering
CN109145957B (en) * 2018-07-26 2023-09-12 国网浙江省电力有限公司温州供电公司 Method and device for identifying and processing abnormal indexes of power distribution network based on big data

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106710164A (en) * 2017-03-06 2017-05-24 国电南瑞科技股份有限公司 Power distribution network fault early warning method aiming at multiple factors
CN111564906A (en) * 2020-06-16 2020-08-21 国网湖北省电力有限公司黄石供电公司 Method for efficiently processing automation defects of urban network distribution network

Also Published As

Publication number Publication date
CN113837458A (en) 2021-12-24

Similar Documents

Publication Publication Date Title
CN109146093B (en) Power equipment field investigation method based on learning
CN111639921B (en) Intelligent equipment fault judgment and auxiliary disposal method based on expert system
CN106204330A (en) A kind of power distribution network intelligent diagnosis system
CN110707817B (en) Intelligent power grid monitoring control system and method based on geographic information technology
CN112713658A (en) Intelligent control method and system for monitoring defects of power grid equipment
CN107862392B (en) Equipment account management and control method based on power distribution network intelligent operation and maintenance management and control platform
CN110363326B (en) Power grid 110kV line short-term load curve prediction method
CN116805212B (en) Risk data processing method and system suitable for power grid main equipment
CN106817708A (en) One kind patrols and examines cluster construction method and device
CN115272027A (en) Low-carbon emission data monitoring system for double-carbon management
CN113409162A (en) Centralized control station equipment monitoring system and control method based on intelligent event processing
CN116914939A (en) Big data-based energy storage management system, method and energy storage power station system
CN113837458B (en) Distribution network data edge calculation model of distribution network equipment and defect elimination auxiliary method and system
CN115186964A (en) Power distribution network line risk prediction system and method considering subjective evaluation data
CN111709597B (en) Power grid production domain operation monitoring system
CN113435612A (en) Intelligent first-aid repair order dispatching method and device based on big data support
CN114741447B (en) Distributed energy station data processing method and device
CN116094174A (en) Knowledge graph-based power grid operation and maintenance monitoring method, system, equipment and medium
CN112101422B (en) Typical case self-learning method for power system fault case
CN115603459A (en) Digital twin technology-based power distribution network key station monitoring method and system
CN112862249B (en) Lean management method and system for intelligent power distribution equipment
CN117638928B (en) Intelligent power distribution network management system based on cloud computing
CN116298675B (en) Intelligent algorithm-based power distribution network line loss anomaly detection method and system
CN117792279B (en) Distributed photovoltaic monitoring system based on neural network
CN116231868B (en) Hydropower safety monitoring system based on Internet of things

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