A linear variation relationship verification method and system based on typical correlation analysis
Through the method based on typical correlation analysis, the time-consuming and labor-consuming problems caused by the verification of the wire-change relationship of the distribution network are solved, and more accurate and efficient judgment of the wire-change relationship is achieved, and the load balance of the distribution network is improved. Operational reliability.
Patent Information
- Application Number
- CN202110831181.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-07-22
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-07-22
AI Technical Summary
The existing distribution network line change relationship verification mainly relies on manual methods, which is time-consuming and labor-intensive, prone to errors, and is difficult to accurately calculate, affecting load balancing and line operation reliability.
Using a method based on typical correlation analysis, by obtaining the power consumption data of the distribution transformer and the power consumption of the line outlet, calculating the correlation coefficient, preliminarily determining the line to which the transformer belongs, and re-confirming it through the correlation coefficient algorithm and the typical correlation analysis algorithm to improve the The credibility of judgment.
It improves the credibility of linear-change relationship verification, reduces the calculation process, shortens time, reduces errors, and enhances the accuracy and efficiency of distribution network structure adjustment.
Smart Images

Figure CN113687273B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of line transformer topology relationship verification in a distribution network, and in particular relates to a line transformer relationship verification method and system based on typical correlation analysis. Background Art
[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.
[0003] Accurately calculating the line-transformer relationship of the distribution network is the key to balancing the load of the distribution network and improving the reliability of line operation. For a long time, relying on manual methods to verify the line-transformer relationship of the distribution network has been time-consuming and labor-intensive.
[0004] However, the current relationship between distribution network lines and transformers is rather chaotic. During the operation of the distribution network, in order to reduce active network losses and balance the load, the distribution network structure needs to be adjusted. The adjusted relevant information is usually verified and changed manually, which is a time-consuming and labor-intensive process and prone to negligence and errors. Summary of the invention
[0005] In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides a linear variation relationship verification method based on typical correlation analysis, which improves the credibility of judgment.
[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:
[0007] In a first aspect, a linear variation relationship verification method based on canonical correlation analysis is disclosed, comprising:
[0008] Get the sum of power consumption of all distribution transformers on a certain line and the power consumption at the outlet of the line;
[0009] Define the data error between the two above. If the error is less than or equal to the set value, it is preliminarily determined that all transformers under the line belong to the line. Otherwise, it is preliminarily determined that there is a distribution transformer that does not belong to the line, which is defined as the first suspected transformer.
[0010] Transformers that are initially determined to be in the same line are re-determined using a correlation coefficient algorithm to determine whether they are in the same line. Transformers that are not in the same line after re-determination are defined as the second suspected transformers.
[0011] A typical correlation analysis algorithm is used to determine the lines to which the first suspected transformer and the second suspected transformer belong.
[0012] A further technical solution is to use a correlation coefficient algorithm to re-determine whether the transformers that are initially determined to belong to the same line are under the same line. The correlation coefficient between each transformer under the line and the line substation voltage is calculated separately, and a correlation coefficient threshold is set. If the calculated correlation coefficient is greater than the threshold, it is determined that the transformer is under the same line, otherwise it is determined that it does not belong to the same line.
[0013] A further technical solution is to calculate the correlation coefficient between each transformer and the line area voltage under the line, and the corresponding calculation formula is:
[0014]
[0015] in, They correspond to the voltages of the two transformers in the substation area. for The covariance of for The variance of for The variance of
[0016] The daily average voltage of the transformer in the substation is used to calculate the correlation coefficient for each day of a month, and the average value is taken as the final correlation coefficient.
[0017] A further technical solution is to use a typical correlation analysis algorithm to determine the lines to which the first suspected transformer and the second suspected transformer belong, use one month's voltage data to calculate the correlation coefficient between each transformer and each line substation voltage, take the line corresponding to the highest correlation coefficient, and judge whether it belongs to this line.
[0018] In a second aspect, a linear variation relationship verification system based on canonical correlation analysis is disclosed, comprising:
[0019] The data acquisition module is configured to: acquire the sum of power consumption of all distribution transformers on a certain line and the power consumption at the outlet of the line;
[0020] The preliminary line determination module is configured to: define the error between the above two data, if the error is less than or equal to the set value, preliminarily determine that all transformers under the line belong to the line, otherwise, preliminarily determine that there is a distribution transformer that does not belong to the line, which is defined as the first suspected transformer;
[0021] The module for determining the line to which it belongs is configured to: preliminarily determine that the transformer belongs to the same line, and use the correlation coefficient algorithm to re-determine whether it belongs to the same line, and define the transformer that does not belong to the same line after re-determination as the second suspected transformer;
[0022] A typical correlation analysis algorithm is used to determine the lines to which the first suspected transformer and the second suspected transformer belong.
[0023] One or more of the above technical solutions have the following beneficial effects:
[0024] The typical correlation coefficient-based algorithm proposed in the present invention takes into account the overall correlation degree of the distribution transformer voltage data set and improves the credibility of the judgment.
[0025] The present invention proposes to use the average value of the transformer's daily voltage data and one month's voltage data for correlation judgment, thereby solving the error caused by the voltage imbalance problem at the distribution transformer outlet.
[0026] The present invention firstly adopts the principle of line loss to make a preliminary judgment on the distribution transformer, thereby reducing the calculation process and shortening the calculation time.
[0027] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.
[0029] Figure 1 The figure is a flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION
[0030] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.
[0031] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.
[0032] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.
[0033] The line-transformer relationship of the distribution network refers to the relationship between the distribution transformer in the distribution network substation and its 10kV line, which belongs to a type of distribution network topology. The sorting out of the line-transformer relationship is an important link to ensure the stable operation of the distribution network. Its correctness is of great significance to the calculation of distribution network losses and the emergency repair of distribution network faults.
[0034] With the continuous development and construction of distribution networks, massive amounts of effective data can now be collected, such as distribution transformer outlet voltage, distribution transformer gateway electricity meter electric energy data, etc., which provide data support for the verification of line-transformer relationships.
[0035] Embodiment 1
[0036] See attached Figure 1 As shown, this embodiment discloses a line-variation relationship verification method based on typical correlation analysis, including:
[0037] Step 1: Calculate the total power consumption of all distribution transformers on the line , and the power consumption at the line outlet Comparison, definition error ,like , it is preliminarily determined that all transformers under the line belong to this line; if , it is initially determined that there is a suspected transformer that does not belong to the line. ;
[0038] The above-mentioned line exits and distribution transformers are equipped with meters, and the data can be obtained on site;
[0039] Step 2: For the transformers preliminarily determined to belong to the same line in the first step, a correlation coefficient algorithm is used to calculate the correlation coefficient between each transformer and the line substation voltage. The closer the correlation coefficient is to 1, the stronger the correlation is, and the greater the possibility that the two transformers belong to the same substation; otherwise, the correlation between the transformers in the two substations is weaker.
[0040] The above-mentioned transformer area is actually a transformer.
[0041] The correlation coefficient calculation formula is as follows:
[0042]
[0043] in, They correspond to the voltages of the two transformers in the substation area. for The covariance of for The variance of for The variance of the daily average voltage is used to calculate the correlation coefficient for each day of the month. , take the average as the final correlation coefficient.
[0044] Set the threshold to 0.75 and the correlation coefficient If it is above 0.75, it is judged to be in the same line, otherwise it is judged not to belong to the same line and is defined as a suspected transformer ;
[0045] Step 3: Check the suspected transformer and suspected transformer Using the typical correlation analysis algorithm and one month of voltage data, the correlation coefficient between each transformer and each line station voltage is calculated. ,in, Represents the number of lines, Represents the number of stations; takes the highest correlation coefficient , judge whether it belongs to Lines.
[0046] Canonical correlation analysis algorithm, assuming that the voltage data of the two transformers in one month are , , projection direction , , by studying projection and To determine the correlation between the two sets of transformer voltages.
[0047]
[0048] in, , , , They are and The mean and standard deviation of the typical correlation coefficient are given by
[0049]
[0050] in, and They are and The autocovariance matrix of is the mutual covariance between the two, and .
[0051] The above calculation is to calculate the transformers belonging to the same line. Here we are targeting the transformers that do not belong to the line in the above steps, and then determine which line they belong to through analysis.
[0052] Embodiment 2
[0053] The purpose of this embodiment is to provide a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the above method are implemented when the processor executes the program.
[0054] Embodiment 3
[0055] The purpose of this embodiment is to provide a computer-readable storage medium.
[0056] A computer-readable storage medium stores a computer program, which executes the steps of the above method when executed by a processor.
[0057] Embodiment 4
[0058] The purpose of this embodiment is to provide a line-variation relationship verification system based on canonical correlation analysis, including:
[0059] The data acquisition module is configured to: acquire the sum of power consumption of all distribution transformers on a certain line and the power consumption at the outlet of the line;
[0060] The preliminary line determination module is configured to: define the error between the above two data, if the error is less than or equal to the set value, preliminarily determine that all transformers under the line belong to the line, otherwise, preliminarily determine that there is a distribution transformer that does not belong to the line, which is defined as the first suspected transformer;
[0061] The module for determining the line to which it belongs is configured to: preliminarily determine that the transformer belongs to the same line, and use the correlation coefficient algorithm to re-determine whether it belongs to the same line, and define the transformer that does not belong to the same line after re-determination as the second suspected transformer;
[0062] A typical correlation analysis algorithm is used to determine the lines to which the first suspected transformer and the second suspected transformer belong.
[0063] Embodiment 5
[0064] The purpose of this embodiment is to provide a line-variation relationship verification device based on typical correlation analysis, including:
[0065] The electric energy metering unit is used to calculate the sum of the power consumption of all distribution transformers on the line and the power consumption at the line outlet;
[0066] A server, wherein the server is configured to communicate with the electric energy metering unit, receive the data collected by the electric energy metering unit and make a preliminary judgment that all transformers under the line belong to the line: define the error between the above two data, if the error is less than or equal to a set value, it is preliminarily determined that all transformers under the line belong to the line, otherwise, it is preliminarily determined that there is a distribution transformer that does not belong to the line, which is defined as a first suspected transformer;
[0067] as well as
[0068] Final determination of the line to which the transformer belongs: preliminary determination of transformers belonging to the same line, using correlation coefficient algorithm to re-determine whether they belong to the same line, and those that do not belong to the same line after re-determination are defined as the second suspected transformer;
[0069] A typical correlation analysis algorithm is used to determine the lines to which the first suspected transformer and the second suspected transformer belong.
[0070] The above-mentioned electric energy metering unit data collection is specifically a meter.
[0071] The steps involved in the apparatus of the above embodiment correspond to the method embodiment 1, and the specific implementation method can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.
[0072] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.
[0073] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.
Claims
1. A linear variation relationship verification method based on canonical correlation analysis, characterized in that: include: Get the sum of power consumption of all distribution transformers on a certain line and the power consumption at the outlet of the line; Define the data error between the two above. If the error is less than or equal to the set value, it is preliminarily determined that all transformers under the line belong to the line. Otherwise, it is preliminarily determined that there is a distribution transformer that does not belong to the line, which is defined as the first suspected transformer. The transformers that are initially determined to be in the same line are re-determined using a correlation coefficient algorithm. Transformers that are not in the same line when re-determined are defined as the second suspected transformers. The correlation coefficients between each transformer in the line and the line substation voltage are calculated, and a correlation coefficient threshold is set. If the calculated correlation coefficient is greater than the threshold, the transformer is determined to be in the same line, otherwise it is determined not to be in the same line. Using a typical correlation analysis algorithm for the first suspected transformer and the second suspected transformer to determine the line to which they belong; Using one month's voltage data, calculate the correlation coefficient between each transformer and each line area voltage, and take the line corresponding to the highest correlation coefficient to determine whether it belongs to that line; The typical correlation analysis algorithm, the voltage data of the two transformers in one month are , , projection direction , , through the study of projection and To determine the correlation between the two sets of transformer voltages; in, , , , They are and The mean and standard deviation of the typical correlation coefficient are: in, and They are and The autocovariance matrix of is the mutual covariance between the two, and .
2. A linear variation relationship verification method based on canonical correlation analysis as claimed in claim 1, characterized in that: When calculating the correlation coefficient between each transformer and the line area voltage under the line, the corresponding calculation formula is: in, They correspond to the voltages of the two transformers in the substation area. for The covariance of for The variance of for The variance of The daily average voltage of the transformer in the substation is used to calculate the correlation coefficient for each day of a month, and the average value is taken as the final correlation coefficient.
3. A linear variation relationship verification system based on typical correlation analysis, using a linear variation relationship verification method based on typical correlation analysis as claimed in claim 1, characterized in that: include: The data acquisition module is configured to: acquire the sum of power consumption of all distribution transformers on a certain line and the power consumption at the outlet of the line; The preliminary line determination module is configured to: define the error between the above two data, if the error is less than or equal to the set value, preliminarily determine that all transformers under the line belong to the line, otherwise, preliminarily determine that there is a distribution transformer that does not belong to the line, which is defined as the first suspected transformer; The module for determining the line to which it belongs is configured to: preliminarily determine that the transformer belongs to the same line, and use the correlation coefficient algorithm to re-determine whether it belongs to the same line, and define the transformer that does not belong to the same line after re-determination as the second suspected transformer; A typical correlation analysis algorithm is used to determine the lines to which the first suspected transformer and the second suspected transformer belong.
4. A linear variation relationship verification device based on typical correlation analysis, using a linear variation relationship verification method based on typical correlation analysis as claimed in claim 1, characterized in that: include: The electric energy metering unit is used to calculate the sum of the power consumption of all distribution transformers on the line and the power consumption at the line outlet; A server, wherein the server is configured to communicate with the electric energy metering unit, receive the data collected by the electric energy metering unit and make a preliminary judgment that all transformers under the line belong to the line: define the error between the above two data, if the error is less than or equal to a set value, it is preliminarily determined that all transformers under the line belong to the line, otherwise, it is preliminarily determined that there is a distribution transformer that does not belong to the line, which is defined as a first suspected transformer; as well as Final determination of the line to which the transformer belongs: preliminary determination of transformers belonging to the same line, using correlation coefficient algorithm to re-determine whether they belong to the same line, and those that do not belong to the same line after re-determination are defined as the second suspected transformer; A typical correlation analysis algorithm is used to determine the lines to which the first suspected transformer and the second suspected transformer belong.
5. The linear variation relationship verification device based on typical correlation analysis as claimed in claim 4, characterized in that: The electric energy metering unit is specifically a meter for data collection.
6. A computing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method described in any one of claims 1 to 2 are implemented.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 2 are performed.
