A method, system, device and medium for identifying user relationship based on R-square

Through the R-based Taiwan-user relationship identification method, using electricity consumption data to screen suspect users and calculate the voltage R-based party, the problem of long and low accuracy of the existing technology of middle-level Taiwan-user relationship identification is solved, and a fast and accurate Taiwan-based relationship identification is achieved Household relationship identification saves the operation and maintenance and labor costs of the power company.

CN118551332BActive Publication Date: 2024-11-26HANGZHOU ZHICHENG ELECTRONIC TECH CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411026901.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-26
Estimated Expiration
2044-07-30

AI Technical Summary

Technical Problem

The existing Taiwan-account relationship identification method has problems such as long inspection and low accuracy. Especially during the transformation and upgrading of the low-voltage distribution network, manual line inspection efficiency is low, high cost, and frequent errors in user station areas are .

Method used

Using the R-side Taiwan-House Relationship Identification Method, pre-processing of electricity consumption data, screening the suspect users, calculate the three-phase R-side of the user and the current belonging station voltage and the three-phase R-side of the suspect station voltage, and determine the Taiwan-House Relationship Exception, use the R square value to determine whether the user is in the station area correctly.

Benefits of technology

This method can quickly and accurately identify the relationship between Taiwan and households, reduce operation and maintenance costs and labor costs, improve the efficiency of identification of the relationship between low-voltage station users and station areas, and reduce the rate of misjudgment and misjudgment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118551332B_ABST
    Figure CN118551332B_ABST
Patent Text Reader

Abstract

The present application relates to a method, system, device and medium for identifying the relationship between a station and a user based on R-square, wherein the identification method includes screening suspected users based on pre-processed power consumption data; obtaining the load data of the user and the current station area respectively, calculating the three-phase R-square of the user voltage and the voltage of the current station area, taking the maximum value of the three-phase R-square as the first fitting coefficient according to the three-phase R-square of the voltage of the current station area; determining the suspected station area range according to the physical address and logical address of the suspected user, calculating the three-phase R-square of the user and the voltage of the suspected station area, taking the maximum value of the three-phase R-square as the second fitting coefficient according to the three-phase R-square of the voltage of the suspected station area; determining the abnormality of the station-user relationship based on the first fitting coefficient and the second fitting coefficient. The method requires less data and has higher feasibility. It can quickly, effectively and accurately solve the problem of long time consumption and low accuracy of station-user relationship identification inspection, saving the operation and maintenance cost and labor cost of the power company.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of distribution network, and in particular to an R-based station-user relationship identification method, system, device and medium. Background Art

[0002] With the transformation and upgrading of low-voltage distribution networks, the relationship between households and transformers in the substation area changes frequently. The efficiency of manual on-site line inspection is low and the workload is large. The power-off method and voltage-boosting method based on distribution transformers are used to check the relationship between households and transformers. The overall management efficiency is low and the cost is high. In order to solve the problem of wrong connection of user substations, many scholars have done a lot of research on the identification of household-transformer relationships in substation areas. At present, there are mainly identification methods based on Pearson correlation coefficient, current similarity, Kmeans clustering algorithm, etc.

[0003] However, the identification based on methods such as Pearson correlation coefficient, current similarity, and Kmeans clustering algorithm has the problem of long time consumption and low accuracy in the identification and verification of station-user relationships. Summary of the invention

[0004] The embodiment of the present application provides a method for identifying the relationship between a user and a subscriber based on R-square, so as to at least solve the problems in the related art such as the long time consumption and low accuracy of the verification of the relationship between the user and the subscriber.

[0005] The embodiment of the present application provides a method for identifying a user relationship based on R-party, including:

[0006] Screen suspicious users based on pre-processed electricity consumption data;

[0007] Obtain the load data of the user and the current substation respectively, calculate the three-phase R square of the user voltage and the current substation voltage, and take the maximum value of the three-phase R square as the first fitting coefficient according to the three-phase R square of the current substation voltage;

[0008] Determine the suspected area range according to the physical address and logical address of the suspected user, calculate the three-phase R square of the voltage between the user and the suspected area, and take the maximum value of the three-phase R square as the second fitting coefficient according to the three-phase R square of the voltage of the suspected area;

[0009] Based on the first fitting coefficient and the second fitting coefficient, it is determined that the household relationship is abnormal.

[0010] Preferably, before screening suspicious users based on the pre-processed electricity usage data, the method further includes:

[0011] Obtaining electricity consumption data from an electricity consumption information collection system for several days, wherein the electricity consumption data includes user load data and terminal load data; wherein,

[0012] The user load data includes the account number, the electric energy meter asset number, the date, the current, the voltage, the CT and the PT;

[0013] The terminal load data includes the substation number, terminal asset number, date, phase A current, phase B current, phase C current, phase A voltage, phase B voltage, phase C voltage, CT and PT.

[0014] Preferably, the electricity consumption data is preprocessed, wherein the preprocessing includes: removing redundant data; identifying abnormal data; filling missing values; and data integration.

[0015] Preferably, screening suspicious users based on the pre-processed electricity usage data includes:

[0016] Based on the pre-processed power consumption data, the concentrator logical address is used for screening, and users and substations with inconsistent concentrator logical addresses in the same substation area are screened as suspected users;

[0017] Based on the pre-processed electricity consumption data, the users in the same area and whose physical addresses are greater than the preset distance are screened as suspected users.

[0018] Based on the pre-processed electricity consumption data, screening is performed from the direction of one household with multiple meters across different distribution areas, and users with multiple meters and across distribution areas are selected as suspect users;

[0019] Based on the pre-processed electricity consumption data, screening is performed based on the direction of multiple changes in the station-user relationship, and users whose user profiles have changed multiple times are screened as suspected users.

[0020] Preferably, the calculation of the three-phase R square of the user voltage and the current transformer area voltage includes:

[0021] Obtaining a difference between a terminal voltage and a user voltage, and correcting the user voltage according to an average value of the difference to obtain a corrected user voltage;

[0022] Based on the corrected user voltage, calculating the difference between the terminal voltage and the corrected user voltage to obtain an error value;

[0023] Obtaining a total sum of squares according to the terminal voltage and the mean of the terminal voltage, which is used to measure the total variation degree of the original data;

[0024] Based on the error value, a residual sum of squares is obtained to reflect the amount of variation that cannot be explained by the modified model;

[0025] The R-square value is obtained by the ratio of the total sum of squares to the residual sum of squares, and the three-phase R-square value is obtained based on the R-square value.

[0026] Preferably, determining that the household relationship is abnormal based on the first fitting coefficient and the second fitting coefficient includes:

[0027] Determine whether the first fitting coefficient is less than a first threshold, and whether the second fitting coefficient is greater than a second threshold;

[0028] When the first fitting coefficient is smaller than a first threshold value and the second fitting coefficient is larger than a second threshold value, it is determined that the household relationship is abnormal.

[0029] Preferably, the determining that the household relationship is abnormal based on the first fitting coefficient and the second fitting coefficient further includes:

[0030] When the first fitting coefficient is greater than or equal to the first threshold, it is determined that the household relationship is normal; and / or,

[0031] When the second fitting coefficient is less than or equal to the second threshold, it is determined that the household relationship is normal.

[0032] In a second aspect, an embodiment of the present application provides a method for identifying a household relationship based on R-square, wherein the system includes a screening module, a first fitting coefficient module, a second fitting coefficient module and a determination module, wherein:

[0033] The screening module is used to screen suspicious users based on the pre-processed electricity usage data;

[0034] The first fitting coefficient module is used to obtain the user and the current area load data respectively, calculate the three-phase R square of the user voltage and the current area voltage, and take the maximum value of the three-phase R square as the first fitting coefficient according to the three-phase R square of the current area voltage;

[0035] The second fitting coefficient module is used to determine the suspected area range according to the physical address and logical address of the suspected user, calculate the three-phase R square of the voltage between the user and the suspected area, and take the maximum value of the three-phase R square as the second fitting coefficient according to the three-phase R square of the voltage of the suspected area;

[0036] The determination module is used to determine whether the household relationship is abnormal based on the first fitting coefficient and the second fitting coefficient.

[0037] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements a method for identifying user relationships based on R-party as described in the first aspect above.

[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for identifying user relationships based on R-party as described in the first aspect above.

[0039] The R-party-based user relationship identification method, system and medium provided in the embodiments of the present application have at least the following technical effects.

[0040] The present invention is based on the electricity consumption data collected by the electricity consumption collection system, screening suspected users, calculating the R square of the user and the current belonging area voltage, calculating the R square of the user and the suspected area voltage, and outputting the user-to-user conversion to determine the belonging relationship between the low-voltage area user and the area. The method requires less data and has high feasibility. It can quickly, effectively and accurately solve the problem of long time consumption and low accuracy of the identification and verification of the relationship between the station and the household, saving the operation and maintenance costs and labor costs of the power company. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1 A structural block diagram of a method for identifying a user relationship based on R-square according to an exemplary embodiment;

[0043] Figure 2 A schematic diagram of a voltage trend between a user and a current belonging area in a method for identifying a station-user relationship based on R-square according to an exemplary embodiment;

[0044] Figure 3 A schematic diagram of voltage trends of users and suspected migration areas in a method for identifying station-user relationships based on R-squares according to an exemplary embodiment;

[0045] Figure 4 is a block diagram of a system for identifying a user relationship based on R-square according to an exemplary embodiment;

[0046] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0048] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0049] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0050] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantity limitation, and may indicate the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0051] At present, in the identification method based on the Pearson correlation coefficient, by constructing the voltage sequence matrix between the distribution network line and the distribution transformer, the voltage Pearson correlation coefficient is compared one by one in turn, and those outside the threshold range are included in the line-transformer relationship error list. The Pearson correlation coefficient is a statistic that describes the strength and direction of the linear relationship between two variables under the assumption of normal distribution. If the voltage does not conform to the normal distribution or the sequence does not show a linear relationship, the effect of using the Pearson correlation coefficient will be greatly reduced, and the abnormal values ​​of the voltage data also have a great impact on the Pearson correlation coefficient.

[0052] In the household-to-cell relationship recognition method based on current similarity, the single current fragment samples are classified, the proportion of each type of single current fragment samples is counted according to the classification results, and the connection relationship represented by the data group with the highest proportion value is selected as the final recognition result. However, this method is affected by factors such as current anomalies, the particularity of photovoltaic charging pile current, and device failures, and the accuracy of household-to-cell relationship recognition will be reduced.

[0053] In the household-to-substation relationship identification method based on the Kmeans clustering algorithm, the affiliation relationship between each user's electric energy meter and each substation total meter is obtained according to the clustering results. However, Kmeans clustering requires the specification of the number of clusters, and different K values ​​will affect the user's affiliation. In addition, the randomness of the initial cluster center will also affect the final result of the identification of the substation-to-household relationship.

[0054] Identification based on methods such as Pearson correlation coefficient, current similarity, and Kmeans clustering algorithm has the problem of long time consumption and low accuracy in the identification and verification of station-user relationships.

[0055] Based on the above situation, an embodiment of the present application provides a method for identifying user relationships based on R-party.

[0056] In a first aspect, the present application provides a method for identifying a user relationship based on R-party. Figure 1 This is a flowchart of a method for identifying the relationship between a user and a platform based on R-square. Figure 1 As shown, a method for identifying the relationship between a platform and a user based on R-square includes:

[0057] Step S1, data collection;

[0058] The data collected in step S1 includes obtaining the load data of the user, the load data of the terminal and the archive data in the electricity consumption information collection system in the past N days according to the archive data of the user;

[0059] Among them, the user's load data includes the account number, energy meter asset number, date, current, voltage, CT and PT;

[0060] The load data of the terminal includes the substation number, terminal asset number, date, phase A current, phase B current, phase C current, phase A voltage, phase B voltage, phase C voltage, CT and PT.

[0061] The archive data includes basic user information, such as user ID (account number), name, address, contact information, etc. Electricity meter information, such as the meter asset number, type, installation location, reading cycle, maximum range, etc. The user's historical electricity consumption, payment records, complaints or service request history, etc.

[0062] Among them, the user load data is shown in Table 1:

[0063] Table 1: User load data table

[0064] Account Number Energy meter asset number date Current Voltage CT PT 3306023*****2 000100049*****4 20230729000000 0.442 226.1 1 1 3306023*****2 000100049*****4 20230729001500 0.149 227.3 1 1 3306023*****2 000100049*****4 20230729003000 0.148 227.6 1 1 3306023*****2 000100049*****4 20230729004500 0.148 227.4 1 1 3306023*****2 000100049*****4 20230729010000 0.417 228.1 1 1 3306023*****2 000100049*****4 20230729011500 0.148 228.5 1 1 3306023*****2 000100049*****4 20230729013000 0.148 227.2 1 1 3306023*****2 000100049*****4 20230729014500 0.434 228.4 1 1 3306023*****2 000100049*****4 20230729020000 0.147 228.3 1 1 3306023*****2 000100049*****4 20230729021500 0.148 228.1 1 1

[0065] The terminal load data is shown in Table 2:

[0066] Table 2: Terminal load data table

[0067] Area No. Terminal asset number date Phase A current Phase B current Phase C current Phase A voltage Phase B voltage Phase C voltage CT PT 000180***9 001282***8 20230729000000 192 200 184 227 227 227 400 1 000180***9 001282***8 20230729001500 168 228 200 227 227 227 400 1 000180***9 001282***8 20230729003000 152 204 208 226 227 226 400 1 000180***9 001282***8 20230729004500 156 176 180 227 228 227 400 1 000180***9 001282***8 20230729010000 172 160 196 228 228 228 400 1 000180***9 001282***8 20230729011500 160 172 172 228 229 228 400 1 000180***9 001282***8 20230729013000 164 164 148 228 228 228 400 1 000180***9 001282***8 20230729014500 104 172 132 228 229 228 400 1 000180***9 001282***8 20230729020000 120 168 140 229 229 229 400 1 000180***9 001282***8 20230729021500 128 120 140 229 229 229 400 1

[0068] Data collection provides the necessary input for the entire process of identifying household change relationships in the substation area, ensuring the feasibility and effectiveness of subsequent analysis.

[0069] Continue to refer to Figure 1 , after step S1, step S3 is performed, which is as follows:

[0070] Step S3, data preprocessing;

[0071] In the process of power data collection, equipment failure, data transmission failure, human operation errors and other reasons will lead to abnormal power metering data in the power collection system. Data preprocessing is an important step before data analysis.

[0072] The step S3 specifically comprises the following steps:

[0073] Step S301, remove redundant data, and identify the records where the current, voltage, active power, and bottom value are all empty, or the current, voltage, active power, bottom value and other fields are not empty and repeated as duplicates. Since these records are missing due to equipment failure, which will affect the results of data analysis, such records are deleted;

[0074] Step S303, identify abnormal data. Data anomalies will affect the calculated value of R-squared, thus leading to errors in identifying the household relationship. For abnormal data, use the Laida criterion, box plot, isolation forest and other methods to identify abnormal data with significant differences. For these outliers, modify them directly according to the data distribution and actual needs. The correction strategies include using the mode, median, and mean to replace the outliers; replacing the outliers with missing values, and then processing the data according to the missing value filling method; deleting the outliers from the data set to reduce their impact on the model;

[0075] Step S305, fill in missing values. Different missing value filling rules are formulated for different situations such as missing of the entire row of records, missing of a single value of load data, and continuous missing. Use load trend method, exponential smoothing method, and linear interpolation method to predict and fill. The specific method is selected based on the data situation;

[0076] Step S306: Data integration. Since the time dimensions of the terminal and user voltage data may be inconsistent, we need to integrate the terminal and user power data based on time.

[0077] The data preprocessing step improves the quality of power data and provides a solid foundation for subsequent analysis and decision-making. The reliability and effectiveness of the analysis results can be ensured by eliminating redundancy, handling anomalies, filling in gaps and integrating data.

[0078] Continue to refer to Figure 1 , after step S3, step S5 is performed, which is as follows:

[0079] Step S5: screening of suspicious users;

[0080] Before identifying the relationship between users, we need to screen the users first and identify those who are suspected of account changes.

[0081] The step S5 specifically comprises the following steps:

[0082] Step S501: Based on the pre-processed power consumption data, screening is performed based on the concentrator logical address, and users and substations with inconsistent concentrator logical addresses in the same substation area are screened as suspected users;

[0083] Step S503: Screening the pre-processed power consumption data based on the physical address, and screening users in the same area and whose physical addresses are greater than a preset distance as suspected users;

[0084] Step S505: Based on the pre-processed electricity consumption data, screening is performed from the direction of one household with multiple meters across different stations, and users with multiple meters and across different stations are screened as suspected users;

[0085] Step S507: Based on the pre-processed electricity consumption data, screening is performed based on the direction of multiple changes in the station-user relationship, and users whose user profiles have been changed multiple times are screened as suspected users.

[0086] Optionally, before identifying the station-household relationship, we need to screen the users first and screen out users who are suspected of household changes. Users are screened mainly from four perspectives: concentrator logical address, physical address, one household with multiple meters across stations, and multiple changes in station-household relationship. First, the concentrator logical address, based on the principle that the logical addresses of users in the same station area are likely to be consistent, the users and stations with inconsistent concentrator logical addresses in the same station area are obtained as suspected users. Secondly, the physical address, the structured physical address of the user is graded and standardized, and the physical addresses of users in the same station area are observed to see whether they are similar. Users with significant differences in physical addresses in the same station area are screened as suspected users of household changes. Then there is one household with multiple meters across stations. For users with multiple meters and across stations, the station-household relationship of the user may be abnormal, which can be further identified and confirmed. Finally, there are users whose station-household relationship has changed multiple times. Because the user profile has changed multiple times, manual operation errors have occurred, resulting in errors in the station-household relationship. At this time, users whose user profiles have changed multiple times are screened as suspected users.

[0087] Through the above-mentioned suspicious user screening steps, the power company can efficiently identify the user groups that are most likely to have problems, so as to carry out subsequent detailed analysis and confirmation work in a targeted manner. This not only saves a lot of manpower and material resources, but also improves the accuracy and efficiency of household-to-transformer relationship identification, which ultimately contributes to the stable operation of the power system and the provision of high-quality services.

[0088] Continue to refer to Figure 1 , after step S5, step S7 is performed, which is as follows:

[0089] Step S7, calculating the R square of the voltage between the user and the current belonging station area;

[0090] Step S701, obtaining a difference between a terminal voltage and a user voltage, and correcting the user voltage according to an average value of the difference to obtain a corrected user voltage;

[0091] Step S703: Based on the corrected user voltage, calculate the difference between the terminal voltage and the corrected user voltage to obtain an error value;

[0092] Step S705: Obtain a total sum of squares according to the terminal voltage and the mean of the terminal voltage, which is used to measure the total variation degree of the original data;

[0093] Step S707: based on the error value, obtain the residual sum of squares to reflect the variation that cannot be explained by the modified model;

[0094] Step S709: Obtain an R-square value by the ratio of the total sum of squares to the residual sum of squares, and obtain three-phase R-square values ​​based on the R-square value.

[0095] Optionally, R-squared is one of the statistics used to evaluate the goodness of fit of a regression model. It indicates the proportion of the variance of the dependent variable that can be explained by the independent variable. The value of R-squared ranges from 0 to 1. The closer it is to 1, the stronger the model's ability to explain the observed data. In a regression model, R-squared is defined as the ratio of the regression sum of squares (SSR) to the total sum of squares (SST). It can also be expressed as 1 minus the ratio of the residual sum of squares (SSE) to the total sum of squares (SST). The calculation formula is:

[0096]

[0097] R square is calculated based on the voltage data of the user and the substation terminal. Due to line loss, there is a certain voltage drop between the substation terminal voltage and the user voltage. The user voltage needs to be corrected before R square can be calculated. Let the terminal A phase voltage be ter_Av and the user voltage be user_Av. The calculation method is as follows:

[0098] Step 1: Calculate the correction voltage user_Av_move of the user voltage user_Av;

[0099] Voltage difference between user and terminal: Diff = ter_Av - user_Av

[0100] User correction voltage: user_Av_move = user_Av + AVG (Diff)

[0101] Step 2: Calculate the terminal user voltage difference error;

[0102] error = ter_Av - user_Av_move

[0103] Step 3: Calculate the total sum of squares SST;

[0104] Average terminal voltage: avg_ter_Av = Avg (ter_Av)

[0105] Total sum of squares: SST = sum ((ter_Av - avg_ter_Av) * (ter_Av - avg_ter_Av))

[0106] Step 4: Calculate the residual sum of squares SSE;

[0107] SSE = sum(error*error)

[0108] Step 5: Calculate R-square;

[0109] R_square = 1-(SSE / SST), where avg is the average value.

[0110] Example: Based on the above algorithm, user 33063123****4 is selected as an example to illustrate the algorithm calculation process. The current substation number of the user is 000180***7. The voltage data of the user and substation terminals are obtained respectively, and the data is preprocessed to obtain the data after n days of matching. The voltage trend of the user and the current substation is obtained. Figure 2 A schematic diagram of a voltage trend between a user and the current belonging area in a method for identifying a user-to-user relationship based on R-square according to an exemplary embodiment is shown as follows: Figure 2 As shown, Figure 2 In the figure, the user voltage and the terminal A / B / C phase fluctuations are not similar. When the terminal rises, the user voltage will also show a downward trend. Therefore, when the terminal voltage fluctuates, the user's part of the time does not show a synchronous fluctuation trend. It is speculated that the user's station-user relationship is likely to be abnormal, which needs to be further confirmed by R square calculation. Among them, the horizontal axis is time (24-hour system) and the vertical axis is voltage (unit: volt v).

[0111] Since the user is a single-phase meter, the terminal voltage data has three phases A, B, and C, so the R square is calculated for the three phases A / B / C of the terminal based on the user voltage. Taking the calculation of the user and the terminal A phase as an example, the results are shown in Table 3:

[0112] Table 3: Calculation process of phase A voltage between the user and the current substation terminal

[0113] date user_Av ter_Av diff user_Av_move error SST SSE 20230729000000 232.5 239 6.5 242.2149 -3.21489 4.168403 10.33554 20230729001500 231.3 242 10.7 241.0149 0.985106 25.4184 0.970435 20230729003000 230.9 245 14.1 240.6149 4.385106 64.6684 19.22916 20230729004500 231.3 241 9.7 241.0149 -0.01489 16.33507 0.000222 20230729010000 232 243 11 241.7149 1.285106 36.50174 1.651498 20230729011500 229.9 243 13.1 239.6149 3.385106 36.50174 11.45895 20230729013000 229.1 245 15.9 238.8149 6.185106 64.6684 38.25554 20230729014500 229.1 243 13.9 238.8149 4.185106 36.50174 17.51512 20230729020000 229.5 242 12.5 239.2149 2.785106 25.4184 7.756818 20230729021500 229.5 245 15.5 239.2149 5.785106 64.6684 33.46746 20230729023000 229.6 242 12.4 239.3149 2.685106 25.4184 7.209796 20230729024500 229.5 243 13.5 239.2149 3.785106 36.50174 14.32703 20230729030000 229.7 241 11.3 239.4149 1.585106 16.33507 2.512562 20230729031500 229.9 241 11.1 239.6149 1.385106 16.33507 1.91852 20230729033000 229.9 241 11.1 239.6149 1.385106 16.33507 1.91852 20230729034500 229.8 242 12.2 239.5149 2.485106 25.4184 6.175754 20230729040000 229.9 239 9.1 239.6149 -0.61489 4.168403 0.378094 20230729041500 229.9 239 9.1 239.6149 -0.61489 4.168403 0.378094 20230729043000 230.2 239 8.8 239.9149 -0.91489 4.168403 0.83703 20230729044500 230.3 240 9.7 240.0149 -0.01489 9.251736 0.000222 20230729050000 230.3 240 9.7 240.0149 -0.01489 9.251736 0.000222 20230729051500 230 239 9 239.7149 -0.71489 4.168403 0.511073 20230729053000 229.8 241 11.2 239.5149 1.485106 16.33507 2.205541 … … … … … … … …

[0114] The R square (i.e. fitting coefficient) between the user and terminal A is calculated from the results in Table 3:

[0115]

[0116] The R square of the user and the terminal B and C phases is calculated, and the results are 0.55965 and 0.5716. The maximum value of the R square of the user and the terminal three phases 0.5716 is taken as the first fitting coefficient R1 of the user and the current area. R1 < the first threshold α, in this embodiment, the first threshold α is 0.75, and it is inferred that the user does not belong to the area.

[0117] By calculating the R-square value of the voltage between the user and the current substation, the correlation between the user voltage and the substation terminal voltage can be evaluated, thereby determining whether the user is correctly assigned to the current substation. Accurate household-to-substation relationships can reduce electricity fee calculation problems caused by incorrect attribution and avoid disputes between users and power companies.

[0118] Continue to refer to Figure 1 , after step S7, step S9 is performed, which is as follows:

[0119] Step S9, calculating the R square of the voltage between the user and the suspected station (the calculation method is consistent with step S7);

[0120] The step S9 specifically includes the following steps:

[0121] Step S901: Determine the suspected area range according to the physical address and logical address of the suspected user, and calculate the three-phase R square of the voltage between the user and the suspected area;

[0122] Step S903: according to the three-phase R-square of the suspected substation voltage, taking the maximum value of the three-phase R-square as the second fitting coefficient.

[0123] Example: Through the user's logical address, it is found that the logical address also appears in the 000180***9 area, and it is inferred that the area is the suspected migration area. Get the voltage trend diagram of the user and the suspected migration area, Figure 3 A schematic diagram of voltage trends of users and suspected migration areas in a method for identifying the relationship between users and stations based on R-squares according to an exemplary embodiment is shown as follows: Figure 3 As shown, Figure 3 The voltage of the user in the middle almost overlaps with the voltage of the terminal phase C. When the terminal voltage fluctuates, the user also shows a corresponding fluctuation trend, and the fluctuations of the two are highly correlated. It is inferred that the user may belong to this substation, and the fitting coefficient R square is further calculated. Among them, the horizontal axis is time (unit: 24-hour system) and the vertical axis is voltage (unit: volt v).

[0124] The fitting coefficients of the user voltage and the three-phase voltage of the suspected incoming terminal are calculated respectively. Taking the terminal phase A as an example, the calculation process is shown in Table 4.

[0125] Table 4: Calculation process of phase A voltage at the user and suspected migration area terminal

[0126] date user_Av ter_Av diff user_Av_move error SST SSE 20230729000000 232.5 230 -2.5 230.4808511 -0.48085 23.06 0.231218 20230729001500 231.3 230 -1.3 229.2808511 0.719149 23.06 0.517175 20230729003000 230.9 229 -1.9 228.8808511 0.119149 14.45584 0.014196 20230729004500 231.3 229 -2.3 229.2808511 -0.28085 14.45584 0.078877 20230729010000 232 230 -2 229.9808511 0.019149 23.06 0.000367 20230729011500 229.9 228 -1.9 227.8808511 0.119149 7.851671 0.014196 20230729013000 229.1 227 -2.1 227.0808511 -0.08085 3.247504 0.006537 20230729014500 229.1 227 -2.1 227.0808511 -0.08085 3.247504 0.006537 20230729020000 229.5 228 -1.5 227.4808511 0.519149 7.851671 0.269516 20230729021500 229.5 228 -1.5 227.4808511 0.519149 7.851671 0.269516 20230729023000 229.6 228 -1.6 227.5808511 0.419149 7.851671 0.175686 20230729024500 229.5 228 -1.5 227.4808511 0.519149 7.851671 0.269516 20230729030000 229.7 228 -1.7 227.6808511 0.319149 7.851671 0.101856 20230729031500 229.9 228 -1.9 227.8808511 0.119149 7.851671 0.014196 20230729033000 229.9 228 -1.9 227.8808511 0.119149 7.851671 0.014196 20230729034500 229.8 228 -1.8 227.7808511 0.219149 7.851671 0.048026 20230729040000 229.9 228 -1.9 227.8808511 0.119149 7.851671 0.014196 20230729041500 229.9 229 -0.9 227.8808511 1.119149 14.45584 1.252494 20230729043000 230.2 229 -1.2 228.1808511 0.819149 14.45584 0.671005 20230729044500 230.3 229 -1.3 228.2808511 0.719149 14.45584 0.517175 20230729050000 230.3 229 -1.3 228.2808511 0.719149 14.45584 0.517175 20230729051500 230 228 -2 227.9808511 0.019149 7.851671 0.000367 20230729053000 229.8 228 -1.8 227.7808511 0.219149 7.851671 0.048026 … … … … … … … …

[0127] Calculate R square (also known as fitting coefficient) from the results in Table 4:

[0128]

[0129] The R-square of the user and the terminal B and C phases is calculated, and the results are 0.9651 and 0.9672. The maximum value of the R-square of the user and the three-phase area is taken as the second fitting coefficient R2 of the user and the suspected migration area.

[0130] R-square value analysis based on voltage trends can more objectively and quantitatively evaluate the relationship between users and substations, avoid errors that may be caused by subjective judgment, and improve the accuracy of household-transformer relationship identification.

[0131] Continue to refer to Figure 1 , after step S9, step S11 is performed, which is as follows:

[0132] Step S11, output the user-changed user (ie, determine that the station-user relationship is abnormal).

[0133] Determine whether the first fitting coefficient is less than a first threshold, and whether the second fitting coefficient is greater than a second threshold;

[0134] When the first fitting coefficient is smaller than a first threshold value and the second fitting coefficient is larger than a second threshold value, it is determined that the household relationship is abnormal.

[0135] Optionally, if the first fitting coefficient R1 between the user and the current substation is less than the first threshold α, and the second fitting coefficient R2 between the suspected substation and the suspected substation is greater than the second threshold β, where the second threshold β in this embodiment is 0.9, then it is judged that the substation-user relationship is inconsistent, the user's data is integrated, it is determined that the substation-user relationship is abnormal, and the result is output.

[0136] As shown in the examples of step S7 and step S9, by comparison, it is found that the first fitting coefficient R1 of the case user and the current belonging area voltage is 0.5716, while the second fitting coefficient R2 of the suspected area voltage is 0.9672, and the fitting degree is much higher than the original area. The fitting degree of the current belonging area is lower than the first threshold and the fitting degree of the suspected area is higher than the second threshold, so the user is identified as inconsistent with the station-user relationship. Through on-site verification, the user does have a station-user problem and the identification is accurate.

[0137] In addition, compared with the Pearson correlation coefficient method, the R-squared method has a higher recognition sensitivity. Taking user 33063128****5 as an example, the maximum R-squared value between the user and the current station is 0.7347, and the maximum correlation coefficient is 0.7612. The maximum R-squared value between the user and the suspected station is 0.9742, and the maximum correlation coefficient is 0.8361. Through the difference calculation, it can be seen that the R-squared difference value is 0.2395, and the correlation coefficient difference is 0.0749. The R-squared method is more sensitive to measuring the relationship between the station and the user, and can better explain the relationship between the user and the station. As shown in Table 5:

[0138] Table 5: Relationship between users and stations

[0139] Taiwan Area R-square Correlation coefficient The front desk area 0.7347 0.7612 Suspected area 0.9742 0.8361 Difference 0.2395 0.0749

[0140] By setting thresholds and comparing R-square values, users with abnormal station-tenant relationships can be identified more accurately, avoiding misjudgment and missed judgments. By reducing errors in station-tenant relationships, grid overload or underload problems caused by incorrect attribution can be avoided, improving the stability and security of the power system.

[0141] In summary, the purpose of the present invention is to provide a method for identifying the relationship between the user and the transformer in the substation area based on R-square. Based on the power consumption data collected by the power consumption collection system, the relationship between the user in the low-voltage substation area and the substation area is determined by screening suspected users, calculating the R-square between the user and the voltage of the current substation area, calculating the R-square between the user and the voltage of the suspected substation area, and outputting the user of the transformer. The method requires less data and has higher feasibility, saves the operation and maintenance costs and labor costs of the power company, and has the problem of long time consumption and low accuracy in the identification test of the relationship between the user and the transformer area. Compared with the Pearson correlation coefficient method, R-square has no restrictions on data distribution. R-square measures the degree of explanation of the independent variable to the dependent variable, and is not limited to a linear relationship, and it quantifies the proportion of one variable (user voltage) that can be explained by another (substation voltage). The value range of R-square is between 0 and 1. It is very intuitive and easy to understand to use R-square to describe the relationship between the user voltage and the terminal voltage of the substation area.

[0142] With the rapid development of social economy, substations with insufficient power supply capacity often need to be partially or completely transferred and adjusted to solve the problem. If the household transformer files of the power supply system are not updated in time, it will lead to continuous losses. On the other hand, the line loss rate is a very important indicator in the assessment of the power supply quality of the power grid. If the power consumption of individual users in the substation is not correctly recorded in the power collection system, the substation will have high losses or negative losses. The present invention judges the ownership relationship between low-voltage substation users and substations based on the power consumption data collected by the power collection system. The method requires a small amount of data and has high feasibility. It can quickly, effectively and accurately solve the problem of household transformer identification in the substation, save the operation and maintenance costs and labor costs of the power company, and help solve the imbalance of power load in the substation and reduce load imbalance losses.

[0143] In the second aspect, an embodiment of the present application provides a system for identifying user relationships based on R-party. Figure 4 FIG. 1 is a block diagram of a system for identifying user relationships based on R-squares according to an exemplary embodiment. Figure 4 As shown, the system includes a screening module 410, a first fitting coefficient module 420, a second fitting coefficient module 430 and a determination module 440, wherein:

[0144] The screening module 410 is used to screen suspicious users based on the pre-processed electricity usage data;

[0145] The first fitting coefficient module 420 is used to obtain the user and the current area load data respectively, calculate the three-phase R square of the user voltage and the current area voltage, and take the maximum value of the three-phase R square as the first fitting coefficient according to the three-phase R square of the current area voltage;

[0146] The second fitting coefficient module 430 is used to determine the suspected area range according to the physical address and logical address of the suspected user, calculate the three-phase R square of the voltage between the user and the suspected area, and take the maximum value of the three-phase R square as the second fitting coefficient according to the three-phase R square of the voltage of the suspected area;

[0147] The determination module 440 is used to determine whether the household relationship is abnormal based on the first fitting coefficient and the second fitting coefficient.

[0148] In summary, the present application provides a system for identifying the relationship between a station and a household based on R-square. Through the screening module 410, the first fitting coefficient module 420, the second fitting coefficient module 430 and the determination module 440, specifically, by screening suspected users, calculating the R-square of the voltage between the user and the current substation, calculating the R-square of the voltage between the user and the suspected substation, and outputting the household transformer user, the belonging relationship between the low-voltage substation user and the substation is determined. This method requires less data and has higher feasibility. It can quickly, effectively and accurately solve the problem of long time consumption and low accuracy of the identification and verification of the relationship between the station and the household, saving the operation and maintenance costs and labor costs of the power company.

[0149] It should be noted that the R-based household relationship identification system provided in this embodiment is used to implement the above-mentioned implementation mode, and the descriptions that have been made will not be repeated. As used above, the terms "module", "unit", "sub-unit", etc. can implement a combination of software and / or hardware for predetermined functions. Although the device described in the above embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0150] In a third aspect, an embodiment of the present application provides an electronic device, Figure 5 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 5 As shown, the electronic device may include a processor 51 and a memory 52 storing computer program instructions.

[0151] Specifically, the processor 51 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0152] Among them, the memory 52 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 52 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 52 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 52 may be inside or outside the data processing device. In a specific embodiment, the memory 52 is a non-volatile memory. In a specific embodiment, the memory 52 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0153] The memory 52 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 51 .

[0154] The processor 51 reads and executes the computer program instructions stored in the memory 52 to implement any one of the R-based user relationship identification methods in the above embodiments.

[0155] In one embodiment, a user relationship identification device based on R-party may further include a communication interface 53 and a bus 50. Figure 5 As shown, the processor 51, the memory 52, and the communication interface 53 are connected via a bus 50 and communicate with each other.

[0156] The communication interface 53 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication port 53 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0157] The bus 50 includes hardware, software or both, and couples the components of an R-based user relationship identification device to each other. The bus 50 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 50 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 50 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0158] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, an R-party-based user relationship identification method provided in the first aspect is implemented.

[0159] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0160] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to enable the terminal device to execute the steps of an R-based user relationship identification method provided in the first aspect.

[0161] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0162] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for identifying customer relationships based on R-square, characterized in that: include: Screen suspicious users based on pre-processed electricity consumption data; Obtain the load data of the user and the current substation respectively, calculate the three-phase R square of the user voltage and the current substation voltage, and take the maximum value of the three-phase R square as the first fitting coefficient according to the three-phase R square of the current substation voltage; Determine the suspected area range according to the physical address and logical address of the suspected user, calculate the three-phase R square of the voltage between the user and the suspected area, and take the maximum value of the three-phase R square as the second fitting coefficient according to the three-phase R square of the voltage of the suspected area; Based on the first fitting coefficient and the second fitting coefficient, determining that the household relationship is abnormal; Among them, calculating the three-phase R-square of the user voltage and the current transformer area voltage includes: obtaining the difference between the terminal voltage of the current transformer area and the user voltage, correcting the user voltage according to the average value of the difference, and obtaining the corrected user voltage; based on the corrected user voltage, calculating the difference between the terminal voltage of the current transformer area and the corrected user voltage, and obtaining the error value; according to the current transformer area terminal voltage and the mean value of the terminal voltage, obtaining the total sum of squares, which is used to measure the total variation of the original data; based on the error value, obtaining the residual sum of squares, which is used to reflect the variation that cannot be explained by the corrected model; obtaining the R-square value by the ratio of the total sum of squares to the residual sum of squares, and obtaining the three-phase R-square value of the current transformer area voltage based on the R-square value.

2. The method according to claim 1, characterized in that: The determining, based on the first fitting coefficient and the second fitting coefficient, that the household relationship is abnormal includes: Determine whether the first fitting coefficient is less than a first threshold, and whether the second fitting coefficient is greater than a second threshold; When the first fitting coefficient is smaller than a first threshold value and the second fitting coefficient is larger than a second threshold value, it is determined that the household relationship is abnormal.

3. The method according to claim 2, characterized in that The determining, based on the first fitting coefficient and the second fitting coefficient, that the household relationship is abnormal, further includes: When the first fitting coefficient is greater than or equal to the first threshold, it is determined that the household relationship is normal; and / or, When the second fitting coefficient is less than or equal to the second threshold, it is determined that the household relationship is normal.

4. The method according to claim 1, characterized in that: The screening of suspicious users based on the pre-processed electricity consumption data includes: Based on the pre-processed power consumption data, the concentrator logical address is used for screening, and users and substations with inconsistent concentrator logical addresses in the same substation area are screened as suspected users; Based on the pre-processed electricity consumption data, the users in the same area and whose physical addresses are greater than the preset distance are screened as suspected users. Based on the pre-processed electricity consumption data, screening is performed from the direction of one household with multiple meters across different distribution areas, and users with multiple meters and across distribution areas are selected as suspect users; Based on the pre-processed electricity consumption data, screening is performed based on the direction of multiple changes in the station-user relationship, and users whose user profiles have changed multiple times are screened as suspected users.

5. The method according to claim 1, characterized in that Before screening suspected users based on the pre-processed electricity consumption data, the method further includes: Obtaining electricity consumption data from an electricity consumption information collection system for several days, wherein the electricity consumption data includes user load data and terminal load data; wherein, The user load data includes the account number, the electric energy meter asset number, the date, the current, the voltage, the CT and the PT; The terminal load data includes the substation number, terminal asset number, date, phase A current, phase B current, phase C current, phase A voltage, phase B voltage, phase C voltage, CT and PT.

6. The method according to claim 5, characterized in that The electricity consumption data is preprocessed, wherein the preprocessing includes: removing redundant data; identifying abnormal data; filling missing values; and data integration.

7. A system for identifying customer relationships based on R-squares, characterized in that: The system comprises a screening module, a first fitting coefficient module, a second fitting coefficient module and a determination module, wherein: The screening module is used to screen suspicious users based on the pre-processed electricity usage data; The first fitting coefficient module is used to obtain the user and the current area load data respectively, calculate the three-phase R square of the user voltage and the current area voltage, and take the maximum value of the three-phase R square as the first fitting coefficient according to the three-phase R square of the current area voltage; The second fitting coefficient module is used to determine the suspected area range according to the physical address and logical address of the suspected user, calculate the three-phase R square of the voltage between the user and the suspected area, and take the maximum value of the three-phase R square as the second fitting coefficient according to the three-phase R square of the voltage of the suspected area; The determining module is used to determine that the station-household relationship is abnormal based on the first fitting coefficient and the second fitting coefficient; Among them, when calculating the three-phase R-square of the user voltage and the current substation voltage, the first fitting coefficient module is used to obtain the difference between the terminal voltage of the current substation and the user voltage, and correct the user voltage according to the average value of the difference to obtain the corrected user voltage; based on the corrected user voltage, the difference between the terminal voltage of the current substation and the corrected user voltage is calculated to obtain the error value; based on the current substation terminal voltage and the mean of the terminal voltage, the total sum of squares is obtained to measure the total variation of the original data; based on the error value, the residual sum of squares is obtained to reflect the variation that cannot be explained by the corrected model; the R-square value is obtained by the ratio of the total sum of squares to the residual sum of squares, and based on the R-square value, the three-phase R-square value of the current substation voltage is obtained.

8. An electronic device, characterized in that: The method comprises a memory and a processor, a computer program stored in the memory and executable on the processor, and the processor implements the R-square-based user relationship identification method as described in any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the R-squared-based user relationship identification method as described in any one of claims 1 to 6 is implemented.

Citation Information

Patent Citations

  • Low-voltage transformer area topology identification method based on mixed integer programming

    CN112085403A

  • Phase identification method and device for single-phase user, equipment and storage medium

    CN112198375A

  • Power supply network line loss reason determination method and device

    CN114236283A

  • Transformer area user-transformer relation analysis method

    CN115423250A

  • Low-voltage transformer area user relation identification method, medium and computer equipment

    CN116628629A