CN114024308A - Power distribution network platform relationship identification method and system - Google Patents

Abstract

The invention discloses a power distribution network station relationship identification method and a power distribution network station relationship identification system, which are used for acquiring power distribution network distribution transformer voltage data and low-voltage user voltage data, calculating correlation coefficients of low-voltage users and station account transformers after the data cleaning and the data reconstruction are carried out on the distribution transformer voltage data and the low-voltage user voltage data, judging whether the station relationship of the station accounts is correct according to the correlation coefficients of the low-voltage users and the station account transformers, and solving the technical problems that the traditional manual identification method and the method for identifying the station relationship by using special station area identification equipment are low in intelligence degree and cannot meet the intelligent development requirement of a power distribution network station area.

Description

A method and system for identifying the relationship between households in a distribution network

technical field

The invention relates to the technical field of distribution network data analysis, in particular to a method and system for identifying the relationship between power distribution network stations and households.

Background technique

There are a large number of users in the distribution network station area, and the network structure is complex. After the user wiring is changed or the power grid company carries out line reconstruction for load balancing distribution, the user's incoming line end and the concentrator will be caused by reasons such as untimely recording or adjustment of rights and responsibilities. The attribution records are inaccurate, the relationship between the station and the household is inconsistent with the actual situation, and the difficulty of defining the station area for the users of the ground cable power supply is in confusion in the station area file.

The traditional identification methods for the relationship between stations and households include manual identification and identification methods using special station area identification equipment. The manual identification method requires electric power personnel to go to the site to check the belonging of users in the station area one by one, which is inefficient. The special station area equipment identification method is mainly used. It is to use the carrier communication method or the pulse current method. The carrier communication method has the problem of "series station area". The pulse current method cannot communicate in two directions. The carrier communication method needs to be used as an auxiliary communication. There are potential safety hazards in the process, and the cost of dedicated station equipment is high, which also cannot meet the intelligent development needs of distribution network stations. Therefore, it is necessary to provide a new method for identifying the relationship between power distribution networks and households, which avoids the problems existing in the traditional identification methods for power distribution network relationships, and improves the intelligence of the identification of power distribution network relationships between users.

SUMMARY OF THE INVENTION

The embodiments of the present invention provide a method and system for identifying the relationship between power distribution network stations and households, which are used to solve the problem that the traditional manual identification and the use of special station area identification equipment for identifying the relationship between stations and households have a low degree of intelligence and cannot meet the requirements of power distribution. The technical problems of the intelligent development needs of the network station area.

In view of this, the present invention provides a method for identifying the relationship between power distribution network users, including the following steps:

S1. Obtain the distribution and transformation voltage data of the distribution network and the low-voltage user voltage data;

S2. Data cleaning is performed on the distribution voltage data and the low-voltage user voltage data. The data cleaning includes the normalization processing of data abnormal values and the filling processing of missing data values;

S3. Perform data reconstruction on the distribution transformer voltage data and the low-voltage user voltage data after data cleaning, and obtain the distribution transformer voltage time series and the low-voltage user voltage time series conforming to the preset length;

S4. Calculate the correlation coefficient between low-voltage users and distribution transformers according to the distribution transformer voltage time series and the low-voltage user voltage time series;

S5. Determine whether the ledger is correct according to the correlation coefficient between the low-voltage user and the ledger transformer. If the correlation coefficient between the low-voltage user and the ledger transformer is not less than the first threshold, the account-to-account relationship in the ledger is correct.

Optionally, after step S5, it also includes:

S6. If the correlation coefficient between the low-voltage user and the ledger transformer is less than the first threshold, determine whether the correlation coefficient between the low-voltage user and the most relevant transformer is greater than the second threshold, and is greater than the correlation coefficient of the secondary related transformer by more than a preset difference, and at the same time The most relevant transformer is the same as the ledger transformer. If so, the account-to-account relationship in the ledger is correct.

Optionally, after step S6, it also includes:

S7. If the correlation coefficient between the low-voltage user and the most relevant transformer is not greater than the second threshold, or cannot reach the preset difference greater than the correlation coefficient of the second-related transformer, or the most relevant transformer is inconsistent with the ledger transformer, calculate the low-voltage user For the voltage error caused by belonging to a specific transformer, the transformer with the smallest error is selected as the calculation result, and it is judged whether the transformer with the smallest error is consistent with the ledger transformer.

Optionally, after step S7, it also includes:

S8. If the transformer with the smallest error in step S7 is inconsistent with the ledger transformer, calculate the distance between the area where the correct ledger has been confirmed and the low-voltage user whose relationship has not been determined, and select the transformer corresponding to the closest area. If the transformer corresponding to the area is consistent with the ledger transformer, then the relationship between the account and the account is correct. The distance between the area whose account has been confirmed to be correct and the low-voltage user whose relationship has not been determined is defined as 1 minus the low-voltage user and the account. The account confirms the correlation coefficient of the transformers in the area.

Optionally, after step S8, it also includes:

S9. If the transformer corresponding to the nearest area in step S8 is inconsistent with the ledger transformer, calculate the correlation coefficient between the low-voltage user and the low-voltage user, and obtain all confirmed users whose correlation coefficient with the undetermined user is greater than the first threshold. Vote for your own subordinate transformer, and the transformer with the highest vote wins. If the transformer with the highest vote is the same as the ledger transformer, then the account-to-household relationship in the ledger is correct.

Optionally, after step S9, it also includes:

S10. If the transformer with the highest vote is inconsistent with the ledger transformer, for each undetermined user, select the transformer with the largest correlation coefficient. If the transformer with the largest correlation coefficient is consistent with the ledger transformer, the account-to-account relationship in the ledger is correct.

Optionally, after step S9, it also includes:

S10. If the transformer with the highest vote is inconsistent with the ledger transformer, for each undetermined user, select the transformer with the largest correlation coefficient. If the transformer with the largest correlation coefficient is consistent with the ledger transformer, the account-to-account relationship in the ledger is correct.

Optionally, in step S4, the correlation coefficient between the low-voltage user and the distribution transformer is the Pearson correlation coefficient.

Optionally, in step S2, data cleaning further includes normalization processing and principal component analysis processing;

Normalization was performed using Z-score normalization.

A second aspect of the present invention also provides a system for identifying the relationship between power distribution network stations and households, including the following modules:

The data acquisition module is used to acquire the distribution and transformation voltage data of the distribution network and the low-voltage user voltage data;

The data cleaning module is used for data cleaning of distribution transformer voltage data and low-voltage user voltage data. Data cleaning includes data abnormal value normalization processing and data missing value filling processing;

The data reconstruction module is used for data reconstruction of the distribution transformer voltage data and the low-voltage user voltage data after data cleaning, so as to obtain the distribution transformer voltage time series and the low-voltage user voltage time series conforming to the preset length;

The correlation coefficient calculation module is used to calculate the correlation coefficient between low-voltage users and distribution transformers according to the distribution transformer voltage time series and the low-voltage user voltage time series;

The account relationship identification module is used to judge whether the account is correct according to the correlation coefficient between the low-voltage user and the account transformer. If the correlation coefficient between the low-voltage user and the account transformer is not less than the first threshold, the account relationship in the account is correct. .

Optionally, the station-user relationship identification module is also used for:

If the correlation coefficient between the low-voltage user and the ledger transformer is less than the first threshold, it is determined whether the correlation coefficient between the low-voltage user and the most relevant transformer is greater than the second threshold, and is greater than the correlation coefficient of the secondary related transformer by more than a preset difference, and the most relevant transformer is at the same time. The transformer and the ledger transformer are the same, if so, the account relationship of the ledger is correct.

As can be seen from the above technical solutions, the embodiments of the present invention have the following advantages:

The method for identifying the relationship between the distribution network and the households provided by the embodiment of the present invention obtains the distribution and transformation voltage data of the distribution network and the low-voltage user voltage data. Correlation coefficient between low-voltage users and ledger transformers, according to the correlation coefficient between low-voltage users and ledger transformers to determine whether the account-to-account relationship is correct, no manual identification is required, and no need to rely on special identification equipment to use the carrier communication method or The pulse current method is used for identification, which has a high degree of intelligence. It solves the problem that the traditional manual identification and the use of special station area identification equipment to identify the relationship between stations and households have a low degree of intelligence and cannot meet the intelligent development needs of distribution network station areas technical issues.

Description of drawings

1 is a schematic flowchart of a method for identifying a relationship between a distribution network station and households provided in an embodiment of the present invention;

FIG. 2 is another schematic flowchart of a method for identifying a relationship between a distribution network station and households provided in an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of a system for identifying the relationship between power distribution network users according to an embodiment of the present invention.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

For ease of understanding, please refer to FIG. 1 , the present invention provides an embodiment of a method for identifying the relationship between power distribution network users, including the following steps:

S1. Obtain the distribution and transformation voltage data of the distribution network and the low-voltage user voltage data;

S2. Data cleaning is performed on the distribution voltage data and the low-voltage user voltage data. The data cleaning includes the normalization processing of data abnormal values and the filling processing of missing data values;

S3. Perform data reconstruction on the distribution transformer voltage data and the low-voltage user voltage data after data cleaning, and obtain the distribution transformer voltage time series and the low-voltage user voltage time series conforming to the preset length;

S4. Calculate the correlation coefficient between low-voltage users and distribution transformers according to the distribution transformer voltage time series and the low-voltage user voltage time series;

S5. Determine whether the ledger is correct according to the correlation coefficient between the low-voltage user and the ledger transformer. If the correlation coefficient between the low-voltage user and the ledger transformer is not less than the first threshold, the account-to-account relationship in the ledger is correct.

It should be noted that, in the embodiment of the present invention, the distribution network distribution and transformation voltage data and the low-voltage user voltage data are first obtained, and then data cleaning is performed on the distribution network distribution and transformation voltage data and the low-voltage user voltage data. On the one hand, data cleaning includes data Outliers are handled in a standardized manner, and the abnormal data is standardized to its upper and lower limits. On the other hand, the missing values of the data are filled up, and the gaps are filled according to the distribution data corresponding to the ledger. Data cleaning can also include normalization and principal component analysis of the data. Considering the power consumption inertia of low-voltage users, the variance of the mean value of power data generally does not change greatly, and when distance is needed to measure similarity in classification and clustering algorithms, or when using principal component analysis technology for dimensionality reduction , Z-score normalization has better performance, therefore, Z-score normalization is used for normalization, namely:

Among them, x ^* is the sample value after normalization, x is the sample value before normalization, μ is the mean of all sample data, and σ is the standard deviation of all sample data.

For the problem that the data dimension is large, which leads to a large amount of calculation, the multi-dimensional voltage data can be converted into a few principal components for analysis by dimensionality reduction technology. The components after dimension reduction can well express the large size of the original multidimensional data partial information. The specific process of principal component analysis processing is as follows:

(1) Form a matrix of the voltage data on the low-voltage side of the transformer in the Taiwan area and the voltage of the low-voltage user's meter:

表示第1～l个变压器的电压数据，

表示第1～m个低压用户的电压数据。in,

Indicates the voltage data of the 1st to 1st transformers,

Indicates the voltage data of the 1st to mth low-voltage users.

(2) Decentralize all voltage data:

Among them, X' is a new sample matrix composed of all decentralized voltage data, and X _id is the d-th voltage data of the i-th type of voltage data.

(3) Calculate the covariance matrix C of the sample:

C= ^X'X'T

(4) Perform eigenvalue decomposition on the covariance matrix C.

(5) Take out the eigenvectors (w ₁ ,...w _n' ) corresponding to the largest n' eigenvalues, and normalize all the eigenvectors to form an eigenvector matrix W.

其中，Z_f＝[z_f1,z_f2,...,z_fn]^T,f∈[1,l]∪[1,m]，z_f1～z_fn为表征降维后的电压数值的元素。(6) Convert each sample X in the sample set into a new sample Z=W ^T X, and obtain the matrix after dimension reduction

Among them, Z _f =[z _f1 ,z _f2 ,...,z _fn ] ^T ,f∈[1,l]∪[1,m], z _f1 ～z _fn are elements representing the voltage value after dimension reduction .

Each row vector in the matrix Z can well express most of the information of each corresponding row vector (transformer and user meter voltage data) in the original matrix X, that is, the Z matrix can be used for classification and analysis in the future, so as to realize the identification of users in the station area.

Data reconstruction is performed on the cleaned data, that is, data segmentation and segment segmentation. Each distribution transformer and each low-voltage user adopts the whole-point data, according to 30 days a month, 24 points a day, and each data index obtains a voltage time series with a length of 720.

The correlation coefficient between low-voltage users and distribution transformers is calculated according to the distribution transformer voltage time series and the low-voltage user voltage time series, and the Pearson correlation coefficient is used. The calculation formula is:

为单位行向量。Among them, R _ij is the correlation coefficient between the voltage of the ith user and the voltage data of the jth user, x _i is the voltage vector of the ith user, x _j is the voltage vector of the jth user,

is a unit row vector.

After calculating the correlation coefficient between low-voltage users and distribution transformers, the loose criterion is used to judge the correctness of the account-account relationship. , then the account relationship of the ledger is correct. The first threshold value is 0.8.

The method for identifying the relationship between the distribution network and the households provided by the embodiment of the present invention obtains the distribution and transformation voltage data of the distribution network and the low-voltage user voltage data. Correlation coefficient between low-voltage users and ledger transformers, according to the correlation coefficient between low-voltage users and ledger transformers to determine whether the account-to-account relationship is correct, no manual identification is required, and no need to rely on special identification equipment to use the carrier communication method or The pulse current method is used for identification, which has a high degree of intelligence. It solves the problem that the traditional manual identification and the use of special station area identification equipment to identify the relationship between stations and households have a low degree of intelligence and cannot meet the intelligent development needs of distribution network station areas technical issues.

Referring to FIG. 2, in one embodiment, after step S5, it may further include:

S6. If the correlation coefficient between the low-voltage user and the ledger transformer is less than the first threshold, determine whether the correlation coefficient between the low-voltage user and the most relevant transformer is greater than the second threshold, and is greater than the correlation coefficient of the secondary related transformer by more than a preset difference, and at the same time The most relevant transformer is the same as the ledger transformer. If so, the account-to-account relationship in the ledger is correct.

After step S5, for the case where the correlation coefficient between the low-voltage user and the ledger transformer is not less than the first threshold, it can be determined that the ledger relationship is correct, but the correlation coefficient between the low-voltage user and the ledger transformer is less than the first threshold In the case of , the correlation coefficient criterion can be used for further judgment, that is, when the correlation coefficient between the low-voltage user and the most relevant transformer is greater than the second threshold (take 0.7), and is larger than the correlation coefficient of the sub-correlated transformer by a preset difference (take 0.08) The above, and the most relevant transformer is consistent with the ledger transformer, it is considered that the account relationship of the ledger is correct.

Referring to FIG. 2, in one embodiment, after step S6, it may further include:

S7. If the correlation coefficient between the low-voltage user and the most relevant transformer is not greater than the second threshold, or cannot reach the preset difference greater than the correlation coefficient of the second-related transformer, or the most relevant transformer is inconsistent with the ledger transformer, calculate the low-voltage user For the voltage error caused by belonging to a specific transformer, the transformer with the smallest error is selected as the calculation result, and it is judged whether the transformer with the smallest error is consistent with the ledger transformer.

After step S6, for the case where the transformer with the smallest error is consistent with the ledger transformer, it can be determined that the account-to-household relationship in the ledger is correct, but for the case where the transformer with the smallest error is inconsistent with the ledger transformer, the error criterion can be used to carry out Further judgment is to calculate the voltage error caused by the low-voltage user belonging to a specific transformer, select the transformer with the smallest error as the calculation result, and judge whether the transformer with the smallest error is consistent with the ledger transformer.

According to the distribution transformer voltage time series and the low voltage user voltage time series, the voltage error caused by the low voltage user belonging to a specific transformer is calculated. The calculation formula is:

Among them, e _ij is the error between the i-th voltage time series and the j-th voltage time series, x _i is the i-th low-voltage user voltage time series, y _j is the j-th distribution transformer voltage time series, diag( _xi ) is a diagonal matrix in which the elements on the diagonal are x _i , and the elements not on the diagonal are all 0s.

Referring to FIG. 2, in one embodiment, after step S7, it may further include:

S8. If the transformer with the smallest error in step S7 is inconsistent with the ledger transformer, calculate the distance between the area where the correct ledger has been confirmed and the low-voltage user whose relationship has not been determined, and select the transformer corresponding to the closest area. If the transformer corresponding to the area is consistent with the ledger transformer, then the relationship between the account and the account is correct. The distance between the area whose account has been confirmed to be correct and the low-voltage user whose relationship has not been determined is defined as 1 minus the low-voltage user and the account. The account confirms the correlation coefficient of the transformers in the area.

After step S7, for the case that the transformer corresponding to the nearest area is consistent with the ledger transformer, it can be determined that the account-to-household relationship in the ledger is correct, but for the case that the transformer corresponding to the nearest area is inconsistent with the ledger transformer, you can use The distance criterion is further judged, that is, the calculation is made between the area that has confirmed the correct account and the low-voltage users who have not determined the account-account relationship (referring to the users who still cannot determine that the account-account relationship is correct after steps S5, S6 and S7). Select the transformer corresponding to the closest area. If the transformer corresponding to the closest area is the same as the ledger transformer, the account-account relationship is correct.

Referring to FIG. 2, in one embodiment, after step S8, it may further include:

S9. If the transformer corresponding to the nearest area in step S8 is inconsistent with the ledger transformer, calculate the correlation coefficient between the low-voltage user and the low-voltage user, and obtain all confirmed users whose correlation coefficient with the undetermined user is greater than the first threshold. Vote for your own subordinate transformer, and the transformer with the highest vote wins. If the transformer with the highest vote is the same as the ledger transformer, then the account-to-household relationship in the ledger is correct.

After step S8, for the case that the transformer corresponding to the nearest area is consistent with the ledger transformer, it can be determined that the account-to-household relationship in the ledger is correct, but for the case that the transformer corresponding to the nearest area is inconsistent with the ledger transformer, you can use The hand-in-hand criterion is used for further judgment, that is, all confirmed users whose correlation coefficients with unidentified users are greater than the first threshold are screened, and each confirmed user casts a vote for its own affiliated transformer, and the transformer with the highest vote wins. If the ledger transformers are the same, the account-to-account relationship in the ledger is correct.

Referring to FIG. 2, in one embodiment, after step S9, it may further include:

S10. If the transformer with the highest vote is inconsistent with the ledger transformer, for each undetermined user, select the transformer with the largest correlation coefficient. If the transformer with the largest correlation coefficient is consistent with the ledger transformer, the account-to-account relationship in the ledger is correct.

After step S9, for the case where the transformer with the highest vote is consistent with the ledger transformer, it can be determined that the account relationship in the ledger is correct, but for the case where the transformer with the highest vote is inconsistent with the ledger transformer, the one-handed criterion can be used Further judgment is made, that is, for each undetermined user, the transformer with the largest correlation coefficient is selected. If the transformer with the largest correlation coefficient is consistent with the ledger transformer, the account-to-account relationship in the ledger is correct.

The method for identifying the relationship between the distribution network and the households provided in the present invention provides 6 criteria for judgment, and uses 6 criteria according to the method of order judgment. The sequence of the criteria is: 1. loose criterion, 2. correlation coefficient According to, 3. Error criterion, 4. Distance criterion, 5. Hand-in-hand criterion, 6. One-hand criterion, those skilled in the art can choose the number of criteria in turn according to actual needs, as long as the current criterion is satisfied, that is Stop the judgment and return the result: the ledger is correct; if the current criterion is not satisfied, continue to make a judgment; if the last criterion is reached, the ledger still cannot be judged to be correct, so far, the ledger is judged to be wrong, that is, the result is returned: ledger error . The identification of the relationship between Taiwan and households based on multi-dimensional criteria can reduce the requirements for sample size on the basis of ensuring the accuracy of the algorithm, and obtain prediction and analysis results that are more in line with the actual engineering.

For ease of understanding, please refer to FIG. 3, the present invention provides an embodiment of a distribution network station-household relationship identification system, including the following modules:

The data acquisition module 301 is used for acquiring distribution network distribution and transformation voltage data and low-voltage user voltage data;

The data cleaning module 302 is configured to perform data cleaning on the distribution transformer voltage data and the low-voltage user voltage data, and the data cleaning includes data abnormal value normalization processing and data missing value filling processing. Data cleaning also includes normalization processing and principal component analysis processing, and the normalization processing adopts Z-score standardization.

The data reconstruction module 303 is configured to perform data reconstruction on the distribution transformer voltage data and the low-voltage user voltage data after data cleaning, so as to obtain the distribution transformer voltage time series and the low-voltage user voltage time series conforming to the preset length;

The correlation coefficient calculation module 304 is configured to calculate the correlation coefficient between the low voltage user and the distribution transformer according to the distribution transformer voltage time series and the low voltage user voltage time series, and the correlation coefficient is a Pearson correlation coefficient.

The account relationship identification module 305 is used to judge whether the account is correct according to the correlation coefficient between the low-voltage user and the account transformer, wherein, if the correlation coefficient between the low-voltage user and the account transformer is not less than the first threshold, the account relationship of the account is correct.

The station-user relationship identification module 305 is also used for:

If the correlation coefficient between the low-voltage user and the ledger transformer is less than the first threshold, it is determined whether the correlation coefficient between the low-voltage user and the most relevant transformer is greater than the second threshold, and is greater than the correlation coefficient of the secondary related transformer by more than a preset difference, and the most relevant transformer is at the same time. The transformer and the ledger transformer are the same, if so, the account relationship of the ledger is correct.

The station-user relationship identification module 305 is also used for:

If the correlation coefficient between the low-voltage user and the most relevant transformer is not greater than the second threshold, or is not greater than the preset difference than the correlation coefficient of the second-related transformer, or the most relevant transformer is inconsistent with the ledger transformer, the low-voltage user is calculated as belonging to For the voltage error caused by a specific transformer, the transformer with the smallest error is selected as the calculation result, and it is judged whether the transformer with the smallest error is consistent with the ledger transformer.

The station-user relationship identification module 305 is also used for:

If the transformer with the smallest error is inconsistent with the ledger transformer, calculate the distance between the area that has confirmed the correct ledger and the low-voltage user for whom the relationship between the account and household has not been determined, and select the transformer corresponding to the closest area. If the transformers in the ledger are consistent, the relationship between the accounts in the ledger is correct. Among them, the distance between the area where the correct account has been confirmed and the low-voltage users whose relationship has not been determined is defined as 1 minus the distance between the low-voltage user and the transformer in the area confirmed by the ledger. correlation coefficient.

The station-user relationship identification module 305 is also used for:

If the transformer corresponding to the nearest area is inconsistent with the ledger transformer, the correlation coefficient between low-voltage users and low-voltage users is calculated, and all confirmed users whose correlation coefficient with unidentified users is greater than the first threshold are obtained by screening, and each confirmed user invests in its own affiliated transformer. With one vote, the transformer with the highest vote wins. If the transformer with the highest vote is consistent with the ledger transformer, the account-to-account relationship in the ledger is correct.

The station-user relationship identification module 305 is also used for:

If the transformer with the highest vote is inconsistent with the ledger transformer, for each undetermined user, select the transformer with the largest correlation coefficient. If the transformer with the largest correlation coefficient is consistent with the ledger transformer, the account-to-account relationship in the ledger is correct.

The system for identifying the relationship between the distribution network and the households provided by the embodiment of the present invention acquires the distribution and transformation voltage data of the distribution network and the low-voltage user voltage data. Correlation coefficient between low-voltage users and ledger transformers, according to the correlation coefficient between low-voltage users and ledger transformers to determine whether the account-to-account relationship is correct, no manual identification is required, and no need to rely on special identification equipment to use the carrier communication method or The pulse current method is used for identification, which has a high degree of intelligence. It solves the problem that the traditional manual identification and the use of special station area identification equipment to identify the relationship between stations and households have a low degree of intelligence and cannot meet the intelligent development needs of distribution network station areas technical issues.

The system for identifying the relationship between power distribution network and households provided in the embodiment of the present invention is used to execute the method for identifying the relationship between power distribution network and households in the foregoing embodiment, and its working principle is the same as the method for identifying the relationship between power distribution network and households in the foregoing embodiment. The same, the same technical effect can be obtained, which is not repeated here.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions described in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A power distribution network platform relationship identification method is characterized by comprising the following steps:

s1, acquiring distribution transformer voltage data and low-voltage user voltage data of the power distribution network;

s2, carrying out data cleaning on the distribution transformer voltage data and the low-voltage user voltage data, wherein the data cleaning comprises data abnormal value standard processing and data missing value supplementing processing;

s3, carrying out data reconstruction on the distribution transformer voltage data and the low-voltage user voltage data after data cleaning to obtain a distribution transformer voltage time sequence and a low-voltage user voltage time sequence which accord with preset lengths;

s4, calculating a correlation coefficient of the low-voltage user and the distribution transformer according to the distribution transformer voltage time sequence and the low-voltage user voltage time sequence;

and S5, judging whether the standing book is correct according to the correlation coefficient of the low-voltage user and the transformer of the standing book, wherein if the correlation coefficient of the low-voltage user and the transformer of the standing book is not less than a first threshold value, the standing book relationship is correct.

2. The method for identifying relationships between power distribution network users according to claim 1, wherein step S5 is followed by further comprising:

and S6, if the correlation coefficient of the low-voltage user and the transformer of the account book is smaller than the first threshold value, judging whether the correlation coefficient of the low-voltage user and the most relevant transformer is larger than the second threshold value and is larger than the correlation coefficient of the secondary relevant transformer by more than a preset difference value, and if so, judging that the account relation of the account book is correct.

3. The method for identifying relationships between power distribution network bays as claimed in claim 2, wherein step S6 is followed by further comprising:

and S7, if the correlation coefficient of the low-voltage user and the most relevant transformer is not larger than a second threshold value, or the correlation coefficient of the low-voltage user and the most relevant transformer is not larger than a preset difference value, or the most relevant transformer and the account transformer are inconsistent, calculating a voltage error caused by the fact that the low-voltage user belongs to a specific transformer, selecting the transformer with the minimum error as a calculation result, judging whether the transformer with the minimum error is consistent with the account transformer, and if so, judging that the account relationship of the account is correct.

4. The method for identifying relationships between power distribution network users according to claim 3, wherein step S7 is followed by further comprising:

and S8, if the transformer with the minimum error in the step S7 is inconsistent with the transformer of the account, calculating the distance between the correct section of the account and the low-voltage user who does not determine the account relationship, selecting the transformer corresponding to the section with the closest distance, and if the transformer corresponding to the section with the closest distance is consistent with the transformer of the account, determining the account relationship of the account is correct, wherein the distance between the correct section of the account and the low-voltage user who does not determine the account relationship is defined as 1 minus the correlation coefficient between the low-voltage user and the transformer of the confirmed section of the account.

5. The method for identifying relationships between power distribution network users according to claim 4, wherein step S8 is followed by further comprising:

and S9, if the transformer corresponding to the nearest parcel is inconsistent with the transformer of the account in the step S8, calculating the correlation coefficient between the low-voltage users and the low-voltage users, screening all the determined users of which the correlation coefficient with the undetermined users is greater than a first threshold value, voting one ticket for the subordinate transformer of each determined user, winning the transformer with the highest vote, and if the transformer with the highest vote is consistent with the transformer of the account, determining that the account relationship of the account is correct.

6. The method for identifying relationships between power distribution network bays as claimed in claim 5, wherein step S9 is followed by further comprising:

and S10, if the transformer with the highest voting rate is inconsistent with the transformer of the standing book, selecting the transformer with the largest correlation coefficient for each undetermined user, and if the transformer with the largest correlation coefficient is consistent with the transformer of the standing book, determining that the standing relation of the standing book is correct.

7. The method of claim 1, wherein in step S4, the correlation coefficient between the low voltage users and the distribution transformer is a pearson correlation coefficient.

8. The method for identifying relationships between power distribution network users according to claim 1, wherein in step S2, the data cleansing further includes a normalization process and a principal component analysis process;

normalization was done using Z-score normalization.

9. A power distribution network platform family relation identification system is characterized by comprising the following modules:

the data acquisition module is used for acquiring distribution transformer voltage data and low-voltage user voltage data of the power distribution network;

the data cleaning module is used for cleaning the distribution transformer voltage data and the low-voltage user voltage data, and the data cleaning comprises data abnormal value standard processing and data missing value supplementing processing;

the data reconstruction module is used for carrying out data reconstruction on the distribution transformer voltage data and the low-voltage user voltage data after data cleaning to obtain a distribution transformer voltage time sequence and a low-voltage user voltage time sequence which accord with preset lengths;

the correlation coefficient calculation module is used for calculating the correlation coefficient between the low-voltage user and the distribution transformer according to the distribution transformer voltage time sequence and the low-voltage user voltage time sequence;

and the account relation identification module is used for judging whether the account is correct or not according to the correlation coefficient of the low-voltage user and the transformer of the account, wherein if the correlation coefficient of the low-voltage user and the transformer of the account is not less than a first threshold value, the account relation of the account is correct.

10. The electrical distribution network subscriber relationship identification system of claim 1, wherein the subscriber relationship identification module is further configured to:

if the correlation coefficient of the low-voltage user and the transformer of the account book is smaller than the first threshold value, whether the correlation coefficient of the low-voltage user and the most relevant transformer is larger than the second threshold value and larger than the correlation coefficient of the secondary relevant transformer by more than a preset difference value is judged, and meanwhile, the most relevant transformer and the transformer of the account book are consistent, if yes, the account relation of the account book is correct.

Images