CN112345972B - Method, device and system for abnormal diagnosis of distribution network line-transformation relationship based on blackout events - Google Patents

Abstract

The invention discloses a power distribution network line transformation relation abnormity diagnosis method, device and system based on a power failure event, wherein the method comprises the steps of generating a historical power failure distribution transformer set based on acquired power data of a distribution transformer; acquiring a bus and a distribution transformer nearby based on longitude and latitude information of a power failure distribution transformer in the power failure distribution transformer set; calculating the related coefficient indexes of the power failure distribution transformer and the bus nearby to find out the suspected bus; screening all lines under suspected corresponding buses of the power failure distribution transformer; calculating the power outage distribution transformer number duty ratio index corresponding to all lines under the suspected bus, and searching for a power outage distribution transformer number duty ratio index threshold; and screening out suspected corresponding lines of the power outage distribution transformer based on the threshold value, and finding out the power outage distribution transformer with wrong line transformation relation and the suspected corresponding lines. The invention has simple calculation, can help operators to find abnormal line transformation relation distribution transformers in time and recommend the line to which the transformer belongs.

Description

Method, device and system for abnormal diagnosis of distribution network line-transformation relationship based on blackout events

technical field

The invention belongs to the field of abnormal diagnosis of medium-voltage distribution network line-transformation relationship, and specifically relates to a method, device and system for abnormal diagnosis of distribution network line-transformation relationship based on power failure events, which are suitable for medium-voltage distribution network.

Background technique

The line-to-line transformation relationship of the medium-voltage distribution network is the relationship between the medium-voltage bus, the distribution transformer load, and the tie switch. It describes the power supply path from the medium-voltage bus to the distribution transformer load. The manually maintained Power Management System (PMS) mainly relies on on-site inspections by grassroots employees. Due to factors such as complex equipment, long time-consuming, and difficult inspections, it is difficult to obtain the correct relationship between the medium-voltage distribution network line transformer, which makes the relationship between the actual site and the PMS mid-line transformer inconsistent.

Therefore, the abnormal diagnosis method of the line-to-line transformation relationship in the medium-voltage distribution network is an important research topic. The research results can help the operators to find out the wrong line-to-line transformation relationship in time for the distribution transformer, and recommend that the distribution transformer should belong to a specific line, which can effectively consolidate the basis of the power grid operation and maintenance account.

Contents of the invention

In view of the above problems, the present invention proposes a method, device, and system for abnormal diagnosis of distribution network line-to-transformation relationships based on power outage events, which can be used to identify connection errors in distribution network line-to-transformation relationships of any scale, and recommend correct connection lines.

In order to achieve the above-mentioned technical purpose and achieve the above-mentioned technical effect, the present invention is realized through the following technical solutions:

In the first aspect, the present invention provides a method for diagnosing an abnormality of distribution network line change relationship based on a power outage event, including:

Based on the obtained power data of distribution transformers, generate a set of historical power outage distribution transformers;

Based on the longitude and latitude information of the power outage distribution transformer in the power outage distribution transformer set, obtain the bus bar and distribution transformer near it, and the voltage measurement data of the bus bar near it;

Calculate the correlation coefficient index between the power outage distribution transformer and its nearby busbars, and find out the suspected busbars;

Screen out all the lines corresponding to the power outage distribution transformer that are suspected to be under the bus;

Calculate the proportion index of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, evaluate and seek the threshold value of power outage distribution transformer number proportion index;

Based on the obtained threshold value, the outage distribution transformer is screened out and suspected to belong to the line, and finally the power outage distribution transformer with the wrong line-to-transformation relationship and its suspected line are found.

Optionally, the method for generating the historical power outage distribution transformer set includes:

A distribution transformer M _j is connected to the line f, the active power measurement data of the distribution transformer M _j is P _k = [p _k,1 ,p _k,2 ,...,p _k,i ,...,p _k,n ], n represents the number of sampling points of the distribution transformer measurement data;

If the active power measurement data P _k of the distribution transformer M _j is 0 or empty in the continuous data segment [p _k,i ,...,p _k,j ], then the data segment [i,...,j] of the distribution transformer M _j is generated as a power failure fragment, and the distribution transformer M _j is a power failure distribution transformer;

Based on the above rules for screening outage distribution transformers, historical outage distribution transformers are screened out from the acquired power data of distribution transformers, and a power outage distribution transformer set M={M ₁ ,M ₂ ,...,M _l } is generated, where l is the number of outage distribution transformers after screening.

Optionally, the obtaining the nearby busbars and distribution transformers, and the voltage measurement data of the nearby busbars based on the latitude and longitude information of the outage distribution transformers in the outage distribution transformer set includes the following steps:

For each distribution transformer in the outage distribution transformer set, based on its longitude and latitude information, calculate the busbar set within the set threshold from the geographical range of the outage distribution transformer, and obtain the statistical voltage measurement data of the busbar set and its lower lines.

Optionally, the method for finding the suspected busbar includes:

The calculation formula of the correlation coefficient index between the power outage distribution transformer and its nearby bus bars is obtained, and the calculation formula of the correlation coefficient index is:

Among them, R represents the correlation coefficient index; X _i represents the voltage measurement data of power outage distribution transformer; Indicates the average value of the voltage measurement data of the power outage distribution transformer; Y _i represents the bus voltage measurement data near the power outage distribution transformer; /> Indicates the average value of the bus voltage measurement data near the power outage distribution transformer; n indicates the length of the power outage distribution transformer and nearby bus voltage measurement data;

From the obtained statistical voltage measurement data of power outage distribution transformers and their nearby busbars, appropriate data is selected and brought into the calculation formula of the correlation coefficient index. After calculation, the correlation coefficient index values between each power outage power distribution transformer and all buses in the nearby busbar set are obtained. Based on the correlation coefficient index values, the suspected busbars and their lower lines are screened out.

Optionally, the calculation of the proportion index of the number of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, and evaluating and seeking the threshold value of the number of power outage distribution transformers, includes the following steps:

Calculate the proportion index P _j of the number of power outage distribution transformers of all lines, and form the data set P of the proportion index of the number of power outage distribution transformers in history;

Using the confusion matrix method used in artificial intelligence for supervised learning, the threshold value of the proportion index of power outage distribution transformers is obtained, including:

Calculate the precision rate and recall rate of the distribution transformers corresponding to the different values P _j in the data set P respectively;

The derived index F1 _j is calculated based on the precision rate and recall rate:

Among them, A _j is the precision rate, R _j is the recall rate;

After the calculation is completed, an evaluation index set F1={F1 ₁ ,F1 ₂ ,...,F1 _j ,...,F1 _k } is formed, where k is the number of bus lines suspected to belong to the bus;

Find the maximum value in the evaluation index set F1, and use the proportion index of the number of power outage distribution transformers corresponding to the maximum value as the threshold value of the proportion index of power outage distribution transformers.

Optionally, the calculation method of the proportion index P _j of the number of power outage distribution transformers is:

For all the lines suspected to be under the bus in a certain area, calculate the number T _j of distribution transformers that are suspected to be under the bus and the total number of distribution transformers Z _j , and then calculate the proportion index P _j of the number of power outage distribution transformers.

Optionally, based on the obtained threshold value, the screening out the power outage distribution transformer suspected to belong to the line, and finally finding the power outage distribution transformer with the wrong line-to-transformation relationship and its suspected line should include the following steps:

The preset judgment steps are carried out for all power outage distribution transformers and the lines under the nearby busbar, and finally obtain the power outage distribution transformer set, the power outage distribution transformer ratio index data set of all lines under the power outage distribution transformer near the busbar, the power outage distribution transformer ratio index threshold value of all lines suspected to belong to the busbar, all the suspected distribution transformers with abnormal relationship between the line change and the suspected line under the busbar;

The preset judging step includes: if there is a power outage distribution transformer that is suspected to belong to the line under the bus during a typical period of time, and the index value of the number of distribution transformers under the power outage is higher than the percentage index threshold value of the number of power outage distribution transformers, then it is determined that the power outage distribution transformer is a distribution transformer suspected of having an abnormal line-change relationship, otherwise it is determined that the power-off distribution transformer is a distribution transformer with a normal line-change relationship.

In the second aspect, the present invention provides a device for diagnosing abnormality of distribution network line change relationship based on power outage events, including:

A generating unit, configured to generate a set of historical power outage distribution transformers based on the obtained power data of the distribution transformer;

The first calculation unit is used to obtain busbars and distribution transformers near it based on the longitude and latitude information of the poweroutage distribution transformer set in the poweroutage distribution transformer set, and the voltage measurement data of the nearby busbars;

The second calculation unit is used to calculate the correlation coefficient index between the power outage distribution transformer and its nearby busbars, and find out the suspected busbars;

The first screening unit is used to screen out all lines corresponding to the power outage distribution transformer that are suspected to belong to the busbar;

The third calculation unit is used to calculate the proportion index of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, evaluate and seek the threshold value of power outage distribution transformer number proportion index;

The judging unit is used to screen out the power outage distribution transformer that is suspected to belong to the line based on the obtained threshold, and finally find the power outage distribution transformer and its suspected line that have a wrong line-to-transformation relationship.

Optionally, the method for generating the historical power outage distribution transformer set includes:

A distribution transformer M _j is connected to the line f, the active power measurement data of the distribution transformer M _j is P _k = [p _k,1 ,p _k,2 ,...,p _k,i ,...,p _k,n ], n represents the number of sampling points of the distribution transformer measurement data;

If the active power measurement data P _k of the distribution transformer M _j is 0 or empty in the continuous data segment [p _k,i ,...,p _k,j ], then the data segment [i,...,j] of the distribution transformer M _j is generated as a power failure fragment, and the distribution transformer M _j is a power failure distribution transformer;

Based on the above rules for screening outage distribution transformers, historical outage distribution transformers are screened out from the acquired power data of distribution transformers, and a power outage distribution transformer set M={M ₁ ,M ₂ ,...,M _l } is generated, where l is the number of outage distribution transformers after screening.

Optionally, the method for finding the suspected busbar includes:

The calculation formula of the correlation coefficient index between the power outage distribution transformer and its nearby bus bars is obtained, and the calculation formula of the correlation coefficient index is:

Among them, R represents the correlation coefficient index; X _i represents the voltage measurement data of power outage distribution transformer; Indicates the average value of the voltage measurement data of the power outage distribution transformer; Y _i represents the bus voltage measurement data near the power outage distribution transformer; /> Indicates the average value of the bus voltage measurement data near the power outage distribution transformer; n indicates the length of the power outage distribution transformer and nearby bus voltage measurement data;

From the obtained statistical voltage measurement data of power outage distribution transformers and their nearby busbars, appropriate data is selected and brought into the calculation formula of the correlation coefficient index. After calculation, the correlation coefficient index values between each power outage power distribution transformer and all buses in the nearby busbar set are obtained. Based on the correlation coefficient index values, the suspected busbars and their lower lines are screened out.

Optionally, the method for finding the suspected busbar includes:

The calculation formula of the correlation coefficient index between the power outage distribution transformer and its nearby bus bars is obtained, and the calculation formula of the correlation coefficient index is:

Among them, R represents the correlation coefficient index; X _i represents the voltage measurement data of power outage distribution transformer; Indicates the average value of the voltage measurement data of the power outage distribution transformer; Y _i represents the bus voltage measurement data near the power outage distribution transformer; /> Indicates the average value of the bus voltage measurement data near the power outage distribution transformer; n indicates the length of the power outage distribution transformer and nearby bus voltage measurement data;

From the obtained statistical voltage measurement data of power outage distribution transformers and their nearby busbars, appropriate data is selected and brought into the calculation formula of the correlation coefficient index. After calculation, the correlation coefficient index values between each power outage power distribution transformer and all buses in the nearby busbar set are obtained. Based on the correlation coefficient index values, the suspected busbars and their lower lines are screened out.

Optionally, the calculation of the proportion index of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, and evaluating and seeking the threshold value of the proportion index of power outage distribution transformers include the following steps:

Calculate the proportion index P _j of the number of power outage distribution transformers of all lines, and form the data set P of the proportion index of the number of power outage distribution transformers in history;

Using the confusion matrix method used in artificial intelligence for supervised learning, the threshold value of the proportion index of power outage distribution transformers is obtained, including:

Calculate the precision rate and recall rate of the distribution transformers corresponding to the different values P _j in the data set P respectively;

The derived index F1 _j is calculated based on the precision rate and recall rate:

Among them, A _j is the precision rate, R _j is the recall rate;

After the calculation is completed, an evaluation index set F1={F1 ₁ ,F1 ₂ ,...,F1 _j ,...,F1 _k } is formed, where k is the number of bus lines suspected to belong to the bus;

Find the maximum value in the evaluation index set F1, and use the proportion index of the number of power outage distribution transformers corresponding to the maximum value as the threshold value of the proportion index of power outage distribution transformers.

Optionally, the calculation method of the proportion index P _j of the number of power outage distribution transformers is:

For all the lines suspected to be under the bus in a certain area, calculate the number T _j of distribution transformers that are suspected to be under the bus and the total number of distribution transformers Z _j , and then calculate the proportion index P _j of the number of power outage distribution transformers.

Optionally, based on the obtained threshold value, the screening out the power outage distribution transformer suspected to belong to the line, and finally finding the power outage distribution transformer with the wrong line-to-transformation relationship and its suspected line should include the following steps:

The preset judgment steps are carried out for all power outage distribution transformers and the lines under the nearby busbar, and finally obtain the power outage distribution transformer set, the power outage distribution transformer ratio index data set of all lines under the power outage distribution transformer near the busbar, the power outage distribution transformer ratio index threshold value of all lines suspected to belong to the busbar, all the suspected distribution transformers with abnormal relationship between the line change and the suspected line under the busbar;

The preset judging step includes: if there is a power outage distribution transformer that is suspected to belong to the line under the bus during a typical period of time, and the index value of the number of distribution transformers under the power outage is higher than the percentage index threshold value of the number of power outage distribution transformers, then it is determined that the power outage distribution transformer is a distribution transformer suspected of having an abnormal line-change relationship, otherwise it is determined that the power-off distribution transformer is a distribution transformer with a normal line-change relationship.

In the third aspect, the present invention provides a system for diagnosing abnormality of distribution network line change relationship based on power outage events, including a storage medium and a processor;

The storage medium is used to store instructions;

The processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of the first aspects.

Compared with prior art, the beneficial effect of the present invention:

(1) The present invention learns the changing trend of historical massive data in a data-driven manner, and calculates the proportion threshold value of the proportion of line outage distribution transformers for judging whether the line-change relationship is abnormal, avoiding artificial designation.

(2) According to the longitude and latitude information, the present invention can directly determine that a power outage distribution transformer with a wrong line-to-transformation relationship is suspected to belong to a specific line, which avoids blind line inspection by on-site operators.

(3) The present invention is simple in calculation and clear in principle, and can help distribution network operators to find distribution transformers with wrong line-to-line relationship in time and recommend the suspected line, so that operators can adjust the line-to-line relationship in time, and has a good application prospect.

Description of drawings

In order to make the content of the present invention easier to understand clearly, the present invention will be described in further detail below according to specific embodiments in conjunction with the accompanying drawings, wherein:

Fig. 1 is the flow chart of the method for diagnosing abnormality of the medium-voltage distribution network line-transformation relationship based on a power outage event of the present invention;

Figure 2 is a schematic diagram of the relationship between medium-voltage distribution network line transformers.

Detailed ways

In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, and are not intended to limit the protection scope of the present invention.

The application principle of the present invention will be described in detail below in conjunction with the accompanying drawings.

Example 1

An embodiment of the present invention provides a method for diagnosing an abnormality of a distribution network line change relationship based on a power outage event, including the following steps:

Step (A) is based on the obtained power data of the distribution transformer, generating a set of distribution transformers for historical power outages;

In a specific implementation manner of the embodiment of the present invention, the specific implementation process of the step (A) is:

In the energy management system (this system exists in the prior art), the distribution transformers to be processed are screened out based on the power information of the distribution transformers, and the power measurement data and basic equipment information stored in the existing system corresponding to the distribution transformers are read. For a distribution transformer M _j connected to the line _f , the active power measurement data of the distribution transformer M _j is P _k = [p _k,1 ,p _{k ,2} ,..., _{p k,i} ,...,p _{k, n} ], n represents the number of distribution transformer measurement data sampling points; The data segment [i,...,j] of _j is the outage fragment of the distribution transformer, and _{M j is} the outage distribution transformer.

Repeat the above steps until all distribution transformers complete the judgment, and generate a power outage distribution transformer information set M={M ₁ ,M ₂ ,...,M _l }, where l is the number of power outage distribution transformers after screening.

Step (B) based on the longitude and latitude information of the power outage distribution transformer in the power outage distribution transformer set, obtain the bus bar and distribution transformer near it, and the voltage measurement data of the bus bar near it;

In a specific implementation manner of the embodiment of the present invention, the step (B) specifically includes the following sub-steps:

Step 1: For the power-off distribution transformer M _j , based on the latitude and longitude information, calculate the busbar set F that is 5km away from the geographical range of the distribution transformer;

Step 2: Select the medium-voltage distribution network to be processed in the energy management system (this system is a system in the prior art), read the line-change relationship of "busbar-distribution transformer load" stored in the existing system, and derive the statistical voltage data of the power-off distribution transformer and nearby busbars that are sampled every 15 minutes. The aforementioned sampling frequency of sampling every 15 minutes can be modified according to the actual situation.

Further, the method further includes performing complementary processing on the voltage measurement data of the bus, and specifically adopting a linear interpolation method to perform complementary processing on the original collected voltage data. The basic idea is to enable the interpolation function to approximately replace the original function. The interpolation function is a first-degree polynomial, and the error of the interpolation at each interpolation node is required to be 0. Suppose the original data f( _xi ) is known, where x _i (i=0,1,2,3,…,n), n is the length of the sampled original data, now linear interpolation constructs a function The absolute value of the error |R(x)| is relatively small over the entire original data interval, namely:

Now based on the constructed interpolation function If the original data has missing data at i=m, that is, f(m) is empty, then /> Complement the lack of voltage data of the original sampling.

Step (C) Calculate the correlation coefficient index between the power outage distribution transformer and its nearby busbars, and find out the suspected busbars;

In a specific implementation manner of the embodiments of the present invention, the step (C) specifically includes the following steps:

Obtain the calculation formula of related indicators between each power outage distribution transformer and its nearby busbars. The related indicators are used to measure the connection relationship between distribution transformers and busbars. It is obtained by comparing the similarity between the distribution transformer voltage data and the busbar voltage data. This similarity is calculated by Pearson correlation coefficient, as shown in Figure 2. When the bus voltage fluctuates, it will drive the voltage of the distribution transformer on this line to fluctuate accordingly, that is, the voltage curves of the two are similar. If a distribution transformer is incorrectly connected to this line, the voltage fluctuation of the distribution transformer is not similar to the bus voltage fluctuation, and the Pearson correlation coefficient is low. The formula for calculating the correlation coefficient index is:

Among them, R represents the correlation coefficient index; X _i represents the voltage measurement data of power outage distribution transformer; Indicates the average value of the voltage measurement data of the power outage distribution transformer; Y _i indicates the measurement data of the nearby bus voltage; /> Indicates the average value of the nearby bus voltage measurement data; n indicates the length of the power outage distribution transformer and the nearby bus voltage measurement data;

Select appropriate data from the obtained voltage measurement data of power outage distribution transformers and nearby busbars and bring them into the calculation formula of related indicators. After calculation, the correlation coefficient index values between each power outage distribution transformer and its nearby busbars are obtained to form a correlation coefficient index data set.

Step (D) screens out all lines corresponding to the power outage distribution transformer that are suspected to be under the busbar;

Step (E) Calculate the percentage index of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, evaluate and seek the threshold value of power outage distribution transformer number percentage index;

In a specific implementation manner of the embodiments of the present invention, the step (E) specifically includes the following sub-steps:

Step 1: Taking a certain day in history as a typical historical time period, read all power outage distribution transformers in the city as T={T ₁ , T ₂ ...T _k }, where k is the number of power outage distribution transformers in the city;

Step 2: According to step (D), select the one-day outage debris of M _j in the outage distribution transformer set as a typical time period, and calculate the number T _j of distribution transformers suspected to be under the bus for all lines under the bus in a certain city and the total number of distribution transformers Z _j , and then calculate the proportion index P _j of the number of power outage distribution transformers:

Repeat the above steps to calculate the proportion index P _j of power outage distribution transformers for all lines, and form the historical power outage distribution transformer number proportion index data set P={P ₁ ,P ₂ ,…,P _l }.

Step 3: Use the confusion matrix method used in artificial intelligence for supervised learning to obtain the threshold value of the proportion index of power outage distribution transformers, including:

Calculate the precision rate and recall rate of the distribution transformers corresponding to the different values P _j in the data set P respectively;

The derived index F1 _j is calculated based on the precision rate and recall rate:

Among them, A _j is the precision rate, R _j is the recall rate;

After the calculation is completed, an evaluation index set F1={F1 ₁ ,F1 ₂ ,...,F1 _j ,...,F1 _k } is formed, where k is the number of bus lines suspected to belong to the bus;

Find the maximum value in the evaluation index set F1, and use the proportion index of the number of power outage distribution transformers corresponding to the maximum value as the threshold value of the proportion index of power outage distribution transformers.

Step (F) Based on the obtained threshold value, screen out the power outage distribution transformer that is suspected to belong to the line, and finally find the power outage distribution transformer with the wrong line-to-transformation relationship and its suspected line;

In a specific implementation manner of the embodiment of the present invention, the step (F) specifically includes the following sub-steps:

If there is a power outage distribution transformer and the proportion index value of the number of power outage distribution transformers in the nearby busbars is lower than the power outage distribution transformer _number ratio threshold value, it is determined that the distribution transformer is a distribution transformer with a normal line-to-line relationship; The number of power _outage distribution transformers suspected of having an abnormal line-to-transformation _relationship .

Repeat the above steps until all power outage distribution transformers in the set M are judged and find out the suspected line corresponding to the wrong power outage distribution transformer.

Example 2

Based on the same inventive concept as that of Embodiment 1, the embodiment of the present invention provides a device for diagnosing abnormality of distribution network line change relationship based on power outage events, including:

A generating unit, configured to generate a set of historical power outage distribution transformers based on the obtained power data of the distribution transformer;

The first calculation unit is used to obtain busbars and distribution transformers near it based on the longitude and latitude information of the poweroutage distribution transformer set in the poweroutage distribution transformer set, and the voltage measurement data of the nearby busbars;

The second calculation unit is used to calculate the correlation coefficient index between the power outage distribution transformer and its nearby busbars, and find out the suspected busbars;

The first screening unit is used to screen out all lines corresponding to the power outage distribution transformer that are suspected to belong to the busbar;

The third calculation unit is used to calculate the proportion index of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, evaluate and seek the threshold value of power outage distribution transformer number proportion index;

The judging unit is used to screen out the power outage distribution transformer that is suspected to belong to the line based on the obtained threshold, and finally find the power outage distribution transformer and its suspected line that have a wrong line-to-transformation relationship.

In a specific implementation manner of the embodiment of the present invention, the generation method of the historical power outage distribution transformer set includes:

A distribution transformer M _j is connected to the line f, the active power measurement data of the distribution transformer M _j is P _k = [p _k,1 ,p _k,2 ,...,p _k,i ,...,p _k,n ], n represents the number of sampling points of the distribution transformer measurement data;

If the active power measurement data P _k of the distribution transformer M _j is 0 or empty in the continuous data segment [p _k,i ,...,p _k,j ], then the data segment [i,...,j] of the distribution transformer M _j is generated as a power failure fragment, and the distribution transformer M _j is a power failure distribution transformer;

Based on the above rules for screening outage distribution transformers, historical outage distribution transformers are screened out from the acquired power data of distribution transformers, and a power outage distribution transformer set M={M ₁ ,M ₂ ,...,M _l } is generated, where l is the number of outage distribution transformers after screening.

In a specific implementation manner of the embodiment of the present invention, the method for finding the suspected busbar includes:

The calculation formula of the correlation coefficient index between the power outage distribution transformer and its nearby bus bars is obtained, and the calculation formula of the correlation coefficient index is:

Among them, R represents the correlation coefficient index; X _i represents the voltage measurement data of power outage distribution transformer; Indicates the average value of the voltage measurement data of the power outage distribution transformer; Y _i represents the bus voltage measurement data near the power outage distribution transformer; /> Indicates the average value of the bus voltage measurement data near the power outage distribution transformer; n indicates the length of the power outage distribution transformer and nearby bus voltage measurement data;

From the obtained statistical voltage measurement data of power outage distribution transformers and their nearby busbars, appropriate data is selected and brought into the calculation formula of the correlation coefficient index. After calculation, the correlation coefficient index values between each power outage power distribution transformer and all buses in the nearby busbar set are obtained. Based on the correlation coefficient index values, the suspected busbars and their lower lines are screened out.

In a specific implementation manner of the embodiment of the present invention, the method for finding the suspected busbar includes:

The calculation formula of the correlation coefficient index between the power outage distribution transformer and its nearby bus bars is obtained, and the calculation formula of the correlation coefficient index is:

Among them, R represents the correlation coefficient index; X _i represents the voltage measurement data of power outage distribution transformer; Indicates the average value of the voltage measurement data of the power outage distribution transformer; Y _i represents the bus voltage measurement data near the power outage distribution transformer; /> Indicates the average value of the bus voltage measurement data near the power outage distribution transformer; n indicates the length of the power outage distribution transformer and nearby bus voltage measurement data;

From the obtained statistical voltage measurement data of power outage distribution transformers and their nearby busbars, appropriate data is selected and brought into the calculation formula of the correlation coefficient index. After calculation, the correlation coefficient index values between each power outage power distribution transformer and all buses in the nearby busbar set are obtained. Based on the correlation coefficient index values, the suspected busbars and their lower lines are screened out.

In a specific implementation manner of the embodiment of the present invention, the calculation of the proportion index of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, and evaluating and seeking the threshold value of the proportion index of power outage distribution transformers include the following steps:

Calculate the proportion index P _j of the number of power outage distribution transformers of all lines, and form the data set P of the proportion index of the number of power outage distribution transformers in history;

Using the confusion matrix method used in artificial intelligence for supervised learning, the threshold value of the proportion index of power outage distribution transformers is obtained, including:

Calculate the precision rate and recall rate of the distribution transformers corresponding to the different values P _j in the data set P respectively;

The derived index F1 _j is calculated based on the precision rate and recall rate:

Among them, A _j is the precision rate, R _j is the recall rate;

After the calculation is completed, an evaluation index set F1={F1 ₁ ,F1 ₂ ,...,F1 _j ,...,F1 _k } is formed, where k is the number of bus lines suspected to belong to the bus;

Find the maximum value in the evaluation index set F1, and use the proportion index of the number of power outage distribution transformers corresponding to the maximum value as the threshold value of the proportion index of power outage distribution transformers.

In a specific implementation manner of the embodiment of the present invention, the calculation method of the proportion index P _j of the number of power outage distribution transformers is:

For all the lines suspected to be under the bus in a certain area, calculate the number T _j of distribution transformers that are suspected to be under the bus and the total number of distribution transformers Z _j , and then calculate the proportion index P _j of the number of power outage distribution transformers.

In a specific implementation manner of the embodiment of the present invention, based on the obtained threshold value, screening out the power outage distribution transformer suspected to belong to the line, and finally finding the power outage distribution transformer with the wrong line-to-transformation relationship and its suspected line, includes the following steps:

The preset judgment steps are carried out for all power outage distribution transformers and the lines under the nearby busbar, and finally obtain the power outage distribution transformer set, the power outage distribution transformer number ratio index data set of all lines under the power outage distribution transformer near the busbar, the power outage distribution transformer number ratio threshold value of all lines suspected to belong to the busbar, all the suspected distribution transformers with abnormal relationship between the line change and the suspected line under the busbar;

The preset judging step includes: if there is a power outage distribution transformer that is suspected to belong to the line under the bus during a typical period of time, and the index value of the number of distribution transformers under the power outage is higher than the percentage index threshold value of the number of power outage distribution transformers, then it is determined that the power outage distribution transformer is a distribution transformer suspected of having an abnormal line-change relationship, otherwise it is determined that the power-off distribution transformer is a distribution transformer with a normal line-change relationship.

Example 3

Based on the same inventive concept as that of Embodiment 1, the embodiment of the present invention provides a system for diagnosing abnormality of distribution network line change relationship based on power outage events, including a storage medium and a processor;

The storage medium is used to store instructions;

The processor is configured to operate according to the instructions to execute the steps of the method according to any one of Embodiment 1.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowcharts and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors or other programmable data processing devices to produce a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate means for realizing the functions specified in one or more processes of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be stored in a computer-readable memory capable of directing a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means that implement the functions specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to generate computer-implemented processing, so that the instructions executed on the computer or other programmable equipment provide steps for realizing the functions specified in one or more processes of the flow chart and/or one or more blocks of the block diagram.

The embodiments of the present invention have been described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific embodiments. The above-mentioned specific embodiments are only illustrative and not restrictive. Under the inspiration of the present invention, those skilled in the art can also make many forms without departing from the purpose of the present invention and the scope of protection of the claims, and these all belong to the protection of the present invention.

The basic principles and main features of the present invention and the advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited by the above-mentioned embodiments. What are described in the above-mentioned embodiments and the description only illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention also has various changes and improvements, and these changes and improvements all fall within the scope of the claimed invention. The protection scope of the present invention is defined by the appended claims and their equivalents.

Claims (12)

1. A method for diagnosing abnormality of power distribution network line change relationship based on blackout events, characterized in that, comprising: Based on the obtained power data of distribution transformers, generate a set of historical power outage distribution transformers; Based on the longitude and latitude information of the power outage distribution transformer in the power outage distribution transformer set, obtain the bus bar and distribution transformer near it, and the voltage measurement data of the bus bar near it; Calculate the correlation coefficient index between the power outage distribution transformer and its nearby busbars, and find out the suspected busbars; Screen out all the lines corresponding to the power outage distribution transformer that are suspected to be under the bus; Calculate the proportion index of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, evaluate and seek the threshold value of power outage distribution transformer number proportion index; Based on the obtained threshold, screen out the power outage distribution transformer that is suspected to belong to the line, and finally find the power outage distribution transformer with the wrong line-to-line relationship and its suspected line; The calculation of the ratio index of the number of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, and evaluating and seeking the threshold value of the ratio index of power outage distribution transformers include the following steps: Calculate the proportion index P _j of the number of power outage distribution transformers of all lines, and form the data set P of the proportion index of the number of power outage distribution transformers in history; Using the confusion matrix method used in artificial intelligence for supervised learning, the threshold value of the proportion index of power outage distribution transformers is obtained, including: Calculate the precision rate and recall rate of the distribution transformers corresponding to the different values P _j in the data set P respectively; The derived index F1 _j is calculated based on the precision rate and recall rate: Among them, A _j is the precision rate, R _j is the recall rate; After the calculation is completed, an evaluation index set F1={F1 ₁ ,F1 ₂ ,...,F1 _j ,...,F1 _k } is formed, where k is the number of bus lines suspected to belong to the bus; Find the maximum value in the evaluation index set F1, and use the proportion index of the number of power outage distribution transformers corresponding to the maximum value as the threshold value of the proportion index of power outage distribution transformers. 2. A method for diagnosing abnormality of distribution network line change relationship based on power outage events according to claim 1, wherein the generation method of the historical power outage distribution transformer set comprises: The distribution transformer M _j is connected to the line f, the active power measurement data of the distribution transformer M _j is P _k =[p _k,1 ,p _k,2 ,...,p _{k,i ,} ...,p _k,n ], n represents the number of sampling points of the distribution transformer measurement data; If the active power measurement data P _k of the distribution transformer M _j is 0 or empty in the continuous data segment [p _k,i ,...,p _k,j ], then the data segment [i,...,j] of the distribution transformer M _j is generated as a power failure fragment, and the distribution transformer M _j is a power failure distribution transformer; Based on the above rules for screening outage distribution transformers, historical outage distribution transformers are screened out from the acquired power data of distribution transformers, and a power outage distribution transformer set M={M ₁ ,M ₂ ,...,M _l } is generated, where l is the number of outage distribution transformers after screening. 3. A kind of method for diagnosing abnormality of distribution network line change relationship based on power outage event according to claim 1, characterized in that: said based on the latitude and longitude information of power outage distribution transformer in said power outage distribution transformer set, obtain bus bar and distribution transformer near it, and the voltage measurement data of bus bar near it, comprising the following steps: For each distribution transformer in the power outage distribution transformer set, based on its latitude and longitude information, calculate the bus set within the set threshold from the geographical range of the power outage distribution transformer, and obtain the bus set and bus voltage measurement data. 4. A method for diagnosing abnormalities in distribution network line-transformation relationships based on power outage events according to claim 1, characterized in that: the method for finding the suspected busbar comprises: The calculation formula of the correlation coefficient index between the power outage distribution transformer and its nearby bus bars is obtained, and the calculation formula of the correlation coefficient index is: Among them, R represents the correlation coefficient index; X _i represents the voltage measurement data of power outage distribution transformer; Indicates the average value of the voltage measurement data of the power outage distribution transformer; Y _i represents the bus voltage measurement data near the power outage distribution transformer; /> Indicates the average value of the bus voltage measurement data near the power outage distribution transformer; n indicates the length of the power outage distribution transformer and nearby bus voltage measurement data; From the obtained statistical voltage measurement data of power outage distribution transformers and their nearby busbars, appropriate data is selected and brought into the calculation formula of the correlation coefficient index. After calculation, the correlation coefficient index values between each power outage power distribution transformer and all buses in the nearby busbar set are obtained. Based on the correlation coefficient index values, the suspected busbars and their lower lines are screened out. 5. a kind of abnormal diagnosis method based on power outage event of distribution network line change relationship according to claim 1, is characterized in that, the computing method of described power outage distribution transformer number proportion index P _j is: For all the lines suspected to be under the bus in a certain area, calculate the number T _j of distribution transformers that are suspected to be under the bus and the total number of distribution transformers Z _j , and then calculate the proportion index P _j of the number of power outage distribution transformers. 6. A method for diagnosing abnormality of distribution network line-to-transformation relationship based on a power outage event according to claim 1, wherein, based on the obtained threshold value, the power outage distribution transformer is suspected to belong to the line, and finally the power outage distribution transformer and the suspected line to which the line change relationship is wrong are found, including the following steps: The preset judgment steps are carried out for all power outage distribution transformers and the lines under the nearby busbar, and finally obtain the power outage distribution transformer set, the power outage distribution transformer ratio index data set of all lines under the power outage distribution transformer near the busbar, the power outage distribution transformer ratio index threshold value of all lines suspected to belong to the busbar, all the suspected distribution transformers with abnormal relationship between the line change and the suspected line under the busbar; The preset judging step includes: if there is a power outage distribution transformer that is suspected to belong to the line under the bus during a typical period of time, and the index value of the number of distribution transformers under the power outage is higher than the percentage index threshold value of the number of power outage distribution transformers, then it is determined that the power outage distribution transformer is a distribution transformer suspected of having an abnormal line-change relationship, otherwise it is determined that the power-off distribution transformer is a distribution transformer with a normal line-change relationship. 7. A device for diagnosing abnormality of distribution network line change relationship based on power outage events, characterized in that it includes: A generating unit, configured to generate a set of historical power outage distribution transformers based on the obtained power data of the distribution transformer; The first calculation unit is used to obtain busbars and distribution transformers near it based on the longitude and latitude information of the poweroutage distribution transformer set in the poweroutage distribution transformer set, and the voltage measurement data of the nearby busbars; The second calculation unit is used to calculate the correlation coefficient index between the power outage distribution transformer and its nearby busbars, and find out the suspected busbars; The first screening unit is used to screen out all lines corresponding to the power outage distribution transformer that are suspected to belong to the busbar; The third calculation unit is used to calculate the proportion index of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, evaluate and seek the threshold value of power outage distribution transformer number proportion index; The judging unit is used to screen out the power outage distribution transformer that is suspected to belong to the line based on the obtained threshold value, and finally find the power outage distribution transformer and its suspected line that have the wrong line-to-transformation relationship; The calculation of the ratio index of the number of power outage distribution transformers corresponding to all lines suspected to belong to the busbar, and evaluating and seeking the threshold value of the number ratio index of power outage distribution transformers include the following steps: Calculate the proportion index P _j of the number of power outage distribution transformers of all lines, and form the data set P of the proportion index of the number of power outage distribution transformers in history; Using the confusion matrix method used in artificial intelligence for supervised learning, the threshold value of the proportion index of power outage distribution transformers is obtained, including: Calculate the precision rate and recall rate of the distribution transformers corresponding to the different values P _j in the data set P respectively; The derived index F1 _j is calculated based on the precision rate and recall rate: Among them, A _j is the precision rate, R _j is the recall rate; After the calculation is completed, an evaluation index set F1={F1 ₁ ,F1 ₂ ,...,F1 _j ,...,F1 _k } is formed, where k is the number of bus lines suspected to belong to the bus; Find the maximum value in the evaluation index set F1, and use the proportion index of the number of power outage distribution transformers corresponding to the maximum value as the threshold value of the proportion index of power outage distribution transformers. 8. A device for diagnosing abnormality of distribution network line change relationship based on power outage events according to claim 7, wherein the generation method of the historical power outage distribution transformer set comprises: A certain distribution transformer M _j is connected to the line f, the active power measurement data of the distribution transformer M _j is P _k = [p _k,1 ,p _k,2 ,...,p _k,i ,...,p _k,n ], n represents the number of sampling points of the distribution transformer measurement data; If the active power measurement data P _k of the distribution transformer M _j is 0 or empty in the continuous data segment [p _k,i ,...,p _k,j ], then the data segment [i,...,j] of the distribution transformer M _j is generated as a power failure fragment, and the distribution transformer M _j is a power failure distribution transformer; based on the above-mentioned rules for screening power failure distribution transformers, historical power failure distribution transformers are selected from the obtained power data of distribution transformers to generate a power failure distribution transformer set M={M ₁ ,M ₂ ,...,M _l }, where l is the number of distribution transformers that are blacked out after screening. 9. A device for diagnosing abnormality of distribution network line change relationship based on a power outage event according to claim 7, wherein the method for finding the suspected busbar comprises: The calculation formula of the correlation coefficient index between the power outage distribution transformer and its nearby bus bars is obtained, and the calculation formula of the correlation coefficient index is: Among them, R represents the correlation coefficient index; X _i represents the voltage measurement data of power outage distribution transformer; Indicates the average value of the voltage measurement data of the power outage distribution transformer; Y _i represents the bus voltage measurement data near the power outage distribution transformer; /> Indicates the average value of the bus voltage measurement data near the power outage distribution transformer; n indicates the length of the power outage distribution transformer and nearby bus voltage measurement data; From the obtained statistical voltage measurement data of power outage distribution transformers and their nearby busbars, appropriate data is selected and brought into the calculation formula of the correlation coefficient index. After calculation, the correlation coefficient index values between each power outage power distribution transformer and all buses in the nearby busbar set are obtained. Based on the correlation coefficient index values, the suspected busbars and their lower lines are screened out. 10. A kind of abnormal diagnosis device based on power failure event of distribution network line change relationship according to claim 7, characterized in that, the calculation method of the proportion index P _j of the number of power failure distribution transformers is: For all the lines suspected to be under the bus in a certain area, calculate the number T _j of distribution transformers that are suspected to be under the bus and the total number of distribution transformers Z _j , and then calculate the proportion index P _j of the number of power outage distribution transformers. 11. The device for diagnosing abnormality of a distribution network line-to-transformation relationship based on a power outage event according to claim 7, characterized in that, based on the obtained threshold value, the power outage distribution transformer is screened out to be suspected of belonging to the line, and finally the power outage distribution transformer and its suspected line to which the line-to-transformation relationship is wrong are found, comprising the following steps: The preset judgment steps are carried out for all power outage distribution transformers and the lines under the nearby busbar, and finally obtain the power outage distribution transformer set, the power outage distribution transformer ratio index data set of all lines under the power outage distribution transformer near the busbar, the power outage distribution transformer ratio index threshold value of all lines suspected to belong to the busbar, all the suspected distribution transformers with abnormal relationship between the line change and the suspected line under the busbar; The preset judging step includes: if there is a power outage distribution transformer that is suspected to belong to the line under the bus during a typical period of time, and the index value of the number of distribution transformers under the power outage is higher than the percentage index threshold value of the number of power outage distribution transformers, then it is determined that the power outage distribution transformer is a distribution transformer suspected of having an abnormal line-change relationship, otherwise it is determined that the power-off distribution transformer is a distribution transformer with a normal line-change relationship. 12. A power outage event-based abnormality diagnosis system for distribution network line-transformation relationship, characterized in that: it includes a storage medium and a processor; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1-6.