Charging pile user account-change relation abnormity identification method
A data-driven method for identifying abnormal household-to-transformer relationships in low-voltage networks by analyzing line loss and power consumption data improves accuracy and efficiency in fault location and management.
Patent Information
- Application Number
- CN202411100994.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-12-10
AI Technical Summary
The traditional method for identifying household-to-transformer relationships in low-voltage distribution networks is inefficient and inaccurate due to the hidden nature of charging piles, leading to errors in line loss calculation and fault location, and incorrect relationships cause difficulties in charging and fault repair.
A data-driven method involving data preprocessing and analysis to identify abnormal relationships by calculating correlations and complementarity between line loss rates and power consumption data, screening out users with suspected errors for on-site investigation.
Accurately and efficiently identifies users with abnormal household-to-transformer relationships, improving line loss management and fault location efficiency in low-voltage distribution networks.
Smart Images
Figure CN119109017A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of abnormal line loss monitoring, and in particular to a method for identifying abnormal relationship between charging pile users. Background Art
[0002] In the low-voltage distribution network, the transformer area generally refers to the power supply area of a transformer and the power supply users to which it belongs. The household-to-transformer relationship refers to the affiliation between the transformer in the transformer area and the power user. In recent years, with the development of electric vehicles and the growth of users, the number of charging piles in the power system has also increased rapidly. Charging piles need to be registered and metered separately when connected to the power grid. Since charging piles are generally built in underground parking spaces and the power supply line paths are hidden in the ceiling or cable ducts, it is very easy to cause errors in the household-to-transformer relationship, which in turn affects the inaccurate calculation of line losses and negative losses in the transformer area. In addition, incorrect household-to-transformer relationships can also lead to problems such as difficulty in charging and difficulty in locating line fault repairs. The traditional governance method relies on the transformer area manager to conduct on-site inspections. Due to the large number of users in a transformer area and the messy and hidden lines, the household-to-transformer relationship inspection is inefficient and ineffective. Summary of the invention
[0003] In view of this, the purpose of the present invention is to provide a method for identifying abnormal household change relationships among charging pile users, which can overcome the defects in the prior art. For situations such as incorrect household change relationships among charging piles, data analysis methods can be used to preliminarily screen out users with suspected household change errors, thereby helping to improve the efficiency of on-site inspections of such problems by substation managers.
[0004] To achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a method for identifying abnormal relationship between charging pile users, including the use of a data preprocessing module and a data analysis module, including the following steps;
[0005] Step A: The data preprocessing module cleans the acquired area line loss data and charging pile user daily power consumption data to obtain valid data for subsequent data analysis;
[0006] Step B: The data analysis module calculates the correlation between the line loss rate of the substation area and the daily power consumption of the charging pile users, and preliminarily screens out the user data suspected of having abnormal household-to-household relationship;
[0007] Step C: The data analysis module calculates the complementarity between the daily power consumption of charging pile users and the power consumption of the distribution area to improve the accuracy of model recognition; and obtains the final investigation list of suspected abnormal household-to-household relationship.
[0008] In a preferred embodiment: Step A comprises the following steps;
[0009] Step A1: Obtain the line loss data of the area in the past month and the daily power consumption data of all charging pile users in the area from the power consumption information collection system; the line loss data includes the power loss and line loss rate, where the power loss = power supply - power sales, and the line loss rate = power loss / power supply;
[0010] Step A2: Data cleaning; Incorrect relationship between charging pile users and users will cause the line loss rate of the current area to be reduced during charging, and the line loss of the actual area to be increased. The greater the power consumption, the greater the impact on the line loss rate of the area; if the power consumption information collection system fails to collect daily line loss data, it may cause abnormal values of the line loss on that day. The daily line loss data of the area with a collection success rate of less than 100% and the daily power data of the charging pile users under the area will be eliminated; in addition, the user data with a daily power consumption of all 0 or all null values will be regarded as users who have not used electricity and have no analysis value, and this part of the data will be eliminated.
[0011] In a preferred embodiment: Step B comprises the following steps;
[0012] Step B1: Assume that the daily power consumption of charging pile users is negatively correlated with the line loss rate of the substation. The power supply of the substation remains unchanged. When the power is used, the user's power sales collected by the metering device increases, so the power consumption of the substation decreases, resulting in a decrease in the line loss rate of the substation. On the contrary, when the power is not used, the line loss rate of the substation is normal;
[0013] Step B2: By calculating the correlation between the daily power consumption of charging pile users and the line loss rate of the substation area, the user data with suspected errors in the household-to-substation relationship can be preliminarily screened out. The stronger the negative correlation, the greater the possibility that the user has an abnormal household-to-substation relationship;
[0014] Let X n :{X1,X2,...,X n} is the daily line loss rate data of the station area in that month, Y n :{Y1,Y2,...,Y n} is the daily power consumption data of the charging pile user in the current month, and n is the number of days of data taken; then formula (1) is as follows:
[0015]
[0016] Among them, ρ XY is the Pearson correlation coefficient, E(X) and E(Y) are the means of X and Y respectively, σ x ,σ y are the standard deviations of X and Y respectively; when -1<ρ XY When <0, X and Y are negatively correlated, ρ XY The smaller the negative correlation, the stronger the negative correlation. XY For charging pile users with a household change relationship of <-0.7 and suspected errors, the next step of data analysis will be carried out.
[0017] In a preferred embodiment: Step C comprises the following steps;
[0018] Step C1: Assume that there is a complementary relationship between the daily power consumption of the charging pile user and the power consumption of the substation, that is, when the electricity is used, the user's power sales collected by the metering device increases, and the power consumption of the current substation decreases. When the electricity is not used, the user's daily power consumption is normal, the power consumption of the substation does not fluctuate, and the sum of the user's daily power consumption and the power consumption of the substation tends to a stable value; on the contrary, there is no complementary relationship between the daily power consumption of the charging pile user and the power consumption of the substation with a normal household-to-substation relationship;
[0019] Step C2: = Based on the user data with suspected abnormal household-to-substation relationship initially screened out by using correlation in step B, further screen out user data with a higher possibility of household-to-substation relationship error by comparing the sum of the user's daily power consumption and the corresponding area power loss in two periods when the user's daily power consumption tends to 0 and the daily power consumption is normal; the daily power consumption tends to 0 means that the daily power consumption is between 0 and 1; the daily power consumption is normal means that the daily power consumption is greater than 1;
[0020] Let A p :{A a ,A b ,...,A p} is the daily power consumption of the user during the period when the daily power consumption tends to 0, B p :{B a ,B b ,...,B p} is the corresponding area power consumption, A q :{A r ,A s ,...,A q} is the daily power consumption of the user in the normal daily power cycle, B q :{B r ,B s ,...,B q} is the corresponding area power consumption, where p+q=n, n is the number of days of data taken;
[0021]
[0022] Among them, δ AB is the complementarity, which represents the difference between the mean of the sum of the daily power consumption of users and the power consumption of the corresponding area in two periods. AB When the value is less than 5, it is considered that there is a complementary relationship between the daily power consumption of the user and the power consumption of the substation area, that is, the user may have a wrong household-to-household relationship;
[0023] Step C3: Obtain the user investigation list of suspected errors in household change relations output by the model for subsequent on-site investigation.
[0024] Compared with the prior art, the present invention has the following beneficial effects: the present invention combines and analyzes the line loss data of the substation area and the daily power consumption data of the charging pile users through a data analysis method, and screens out a list of charging pile users with suspected errors in the household-to-transformer relationship in two stages for subsequent on-site investigation, which is more accurate and efficient than the traditional method of relying on the on-site household investigation by the substation manager. The management of abnormal household-to-transformer relationship is of great significance to the lean management of low-voltage distribution networks. The method proposed in the present invention can accurately locate the abnormal household-to-transformer relationship, and solve the problems of false statistical line loss in the substation area and interference in the line loss control in the substation area. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 It is a schematic diagram of the principle framework of a preferred embodiment of the present invention. DETAILED DESCRIPTION
[0026] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0027] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.
[0028] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application; as used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or their combinations.
[0029] like Figure 1 As shown, a charging pile user household change relationship abnormality identification method includes the use of a data preprocessing module and a data analysis module, including the following steps;
[0030] Step A: The data preprocessing module cleans the acquired area line loss data and charging pile user daily power consumption data to obtain valid data for subsequent data analysis;
[0031] Step B: The data analysis module calculates the correlation between the line loss rate of the substation area and the daily power consumption of the charging pile users, and preliminarily screens out the user data suspected of having abnormal household-to-household relationship;
[0032] Step C: The data analysis module calculates the complementarity between the daily power consumption of charging pile users and the power consumption of the distribution area to improve the accuracy of model recognition; and obtains the final investigation list of suspected abnormal household-to-household relationship.
[0033] Step A comprises the following steps:
[0034] Step A1. Obtain the line loss data of the area in the past month and the daily power consumption data of all charging pile users in the area from the power consumption information collection system; the line loss data includes the power loss and the line loss rate, where the power loss = power supply - power sales, and the line loss rate = power loss / power supply;
[0035] Step A2. Data cleaning: The wrong relationship between charging pile users and users will cause the line loss rate of the current area to be reduced during charging, and the line loss of the actual area to be increased. The greater the power consumption, the greater the impact on the line loss rate of the area. If the power consumption information collection system fails to collect daily line loss data, which may cause abnormal values of line loss on that day, the daily line loss data of the area with a collection success rate of less than 100% and the daily power data of the charging pile users in the area will be eliminated; in addition, the user data with all daily power values of 0 or all null values will be regarded as users who have not used electricity and have no analysis value, and this part of the data will be eliminated.
[0036] Step B comprises the following steps:
[0037] Step B1, assuming that the daily power consumption of the charging pile user is negatively correlated with the line loss rate of the substation, the power supply of the substation remains unchanged, and the user's power sales collected by the metering device during electricity use increases, so the power consumption of the substation decreases, resulting in a decrease in the line loss rate of the substation. On the contrary, the line loss rate of the substation is normal when electricity is not used;
[0038] Step B2: According to the above rules, by calculating the correlation between the daily power consumption of charging pile users and the line loss rate of the station area, the user data with suspected errors in the household-to-household relationship can be preliminarily screened out. The stronger the negative correlation, the greater the possibility that the user has an abnormal household-to-household relationship;
[0039] Let X n :{X1,X2,...,X n} is the daily line loss rate data of the station area in that month, Y n :{Y1,Y2,...,Y n} is the daily power consumption data of the charging pile user in the current month, and n is the number of days of data taken; the formula is as follows:
[0040]
[0041] Among them, ρ XY is the Pearson correlation coefficient, E(X) and E(Y) are the means of X and Y respectively, σ x ,σ y are the standard deviations of X and Y respectively. When -1<ρ XY When <0, X and Y are negatively correlated, ρ XY The smaller the negative correlation, the stronger the negative correlation. XY For charging pile users with a household change relationship of <-0.7 and suspected errors, the next step of data analysis will be carried out.
[0042] Step C comprises the following steps:
[0043] Step C1, assume that there is a complementary relationship between the daily power consumption of the charging pile user and the power consumption of the substation, that is, when the electricity is used, the user's power sales collected by the metering device increases, and the power consumption of the current substation decreases. When the electricity is not used, the user's daily power consumption is normal, the power consumption of the substation does not fluctuate, and the sum of the user's daily power consumption and the power consumption of the substation tends to a stable value; on the contrary, there is no complementary relationship between the daily power consumption of the charging pile user and the power consumption of the substation with a normal household-to-substation relationship;
[0044] Step C2, based on the above settings, on the basis of the user data with suspected abnormal household-to-substation relationship preliminarily screened out by using correlation in step B, further screen out user data with a higher possibility of household-to-substation relationship error by comparing the sum of the user's daily electricity consumption and the corresponding area's power loss in two periods when the user's daily electricity consumption tends to 0 and when the daily electricity consumption is normal; the daily electricity consumption tends to 0 means that the daily electricity consumption is between 0 and 1; the daily electricity consumption is normal means that the daily electricity consumption is greater than 1;
[0045] Let A p :{A a ,A b ,...,A p} is the daily power consumption of the user during the period when the daily power consumption tends to 0, B p :{B a ,B b ,...,B p} is the corresponding area power consumption, A q :{A r ,A s ,...,A q} is the daily power consumption of the user in the normal daily power cycle, B q :{B r ,B s ,...,B q} is the corresponding area power consumption, where p+q=n, n is the number of days for the data taken.
[0046]
[0047] Among them, δ AB is the complementarity, which represents the difference between the mean of the sum of the daily power consumption of users and the power consumption of the corresponding area in two periods. AB When <5, it is considered that there is a complementary relationship between the user's daily power consumption and the power loss in the substation area, that is, there is a possibility that the user has a wrong household-to-household relationship.
[0048] Step C3: Obtain a user investigation list of suspected errors in household change relationships output by the model for subsequent on-site investigation.
Claims
1. A method for identifying abnormal relationship between charging pile users, characterized by: The use of the data preprocessing module and the data analysis module includes the following steps; Step A: The data preprocessing module cleans the acquired area line loss data and charging pile user daily power consumption data to obtain valid data for subsequent data analysis; Step B: The data analysis module calculates the correlation between the line loss rate of the substation area and the daily power consumption of the charging pile users, and preliminarily screens out the user data suspected of having abnormal household-to-household relationship; Step C: The data analysis module calculates the complementarity between the daily power consumption of the charging pile users and the power consumption of the substation area to improve the accuracy of model recognition; Obtain the final investigation list of suspected abnormal household change relationships.
2. A charging pile user relationship abnormality identification method according to claim 1, characterized in that: Step A comprises the following steps: Step A1: Obtain the line loss data of the area in the past month and the daily power consumption data of all charging pile users in the area from the power consumption information collection system; the line loss data includes the power loss and line loss rate, where the power loss = power supply - power sales, and the line loss rate = power loss / power supply; Step A2: Data cleaning; the wrong relationship between charging pile users will cause the line loss rate of the current area to be reduced during charging, and the line loss of the actual area to be increased. The greater the power consumption, the greater the impact on the line loss rate of the area; If the electricity consumption information collection system fails to collect daily line loss data, which may cause abnormal line loss values on that day, the daily line loss data of the substation where the collection success rate is less than 100% and the daily electricity consumption data of the charging pile users in the substation will be eliminated; in addition, the user data with daily electricity consumption of all 0 or all null values will be regarded as users who have not used electricity and have no analysis value, and this part of the data will be eliminated.
3. A charging pile user relationship abnormality identification method according to claim 1, characterized in that: Step B comprises the following steps: Step B1: Assume that the daily power consumption of charging pile users is negatively correlated with the line loss rate of the substation. The power supply of the substation remains unchanged. When the power is used, the user's power sales collected by the metering device increases, so the power consumption of the substation decreases, resulting in a decrease in the line loss rate of the substation. On the contrary, when the power is not used, the line loss rate of the substation is normal; Step B2: By calculating the correlation between the daily power consumption of charging pile users and the line loss rate of the substation area, the user data with suspected errors in the household-to-substation relationship can be preliminarily screened out. The stronger the negative correlation, the greater the possibility that the user has an abnormal household-to-substation relationship; Let X n :{X1,X2,...,X n } is the daily line loss rate data of the station area in that month, Y n :{Y1,Y2,...,Y n } is the daily power consumption data of the charging pile user in the current month, and n is the number of days of data taken; then formula (1) is as follows: Among them, ρ XY is the Pearson correlation coefficient, E(X) and E(Y) are the means of X and Y respectively, σ x ,σ y are the standard deviations of X and Y respectively; when -1<ρ XY When <0, X and Y are negatively correlated, ρ XY The smaller the negative correlation, the stronger the negative correlation. XY For users of charging piles with a household change relationship of <-0.7 and suspected errors, the next step of data analysis will be carried out.
4. A charging pile user relationship abnormality identification method according to claim 1, characterized in that: Step C comprises the following steps: Step C1: Assume that there is a complementary relationship between the daily power consumption of the charging pile user and the power consumption of the substation, that is, when the electricity is used, the user's power sales collected by the metering device increases, and the power consumption of the current substation decreases. When the electricity is not used, the user's daily power consumption is normal, and the power consumption of the substation does not fluctuate. The sum of the user's daily power consumption and the power consumption of the substation tends to a stable value; On the contrary, there is no complementary relationship between the daily power consumption of charging pile users and the power consumption of the substation area when the household-to-substation relationship is normal; Step C2: = Based on the user data with suspected abnormal household-to-substation relationship initially screened out by using correlation in step B, further screen out user data with a higher possibility of household-to-substation relationship error by comparing the sum of the user's daily power consumption and the corresponding area power loss in two periods when the user's daily power consumption tends to 0 and the daily power consumption is normal; the daily power consumption tends to 0 means that the daily power consumption is between 0 and 1; the daily power consumption is normal means that the daily power consumption is greater than 1; Let A p :{A a ,A b ,...,A p } is the daily power consumption of the user during the period when the daily power consumption tends to 0, B p :{B a ,B b ,...,B p } is the corresponding area power consumption, A q :{A r ,A s ,...,A q } is the daily power consumption of the user in the normal daily power cycle, B q :{B r ,B s ,...,B q } is the corresponding area power consumption, where p+q=n, n is the number of days of data taken; Among them, δ AB is the complementarity, which represents the difference between the mean of the sum of the daily power consumption of users and the power consumption of the corresponding area in two periods. AB When the value is less than 5, it is considered that there is a complementary relationship between the daily power consumption of the user and the power consumption of the substation area, that is, the user may have a wrong household-to-household relationship; Step C3: Obtain the user investigation list of suspected errors in household change relations output by the model for subsequent on-site investigation.