A data-driven method, system and medium for accurately identifying the actual operating gear position of a distribution transformer

Abstract

The present application relates to a data-driven method, system and medium for accurately identifying the actual operating gear of a distribution transformer. The method includes data screening, selecting the time range corresponding to the single-phase current of the distribution network every day in a historical month, and determining the reference time node for subsequent voltage analysis; identifying the operating gear of the distribution transformer, judging whether the topology has conductor distance information. When the topology has conductor distance information, the operating gear of the first-end distribution transformer is judged first and then the operating gears of other distribution transformers are judged. When the topology lacks conductor distance information, the difference between the actual voltage and the theoretical voltage is calculated first and then the operating gear of the distribution transformer is judged. The present application accurately identifies the actual operating gear of the distribution transformer by means of data analysis, minimizes the impact of the distribution transformer gear identification work on the operation of the power grid, and provides sufficient basis for the distribution transformer gear adjustment.

Description

Technical Field

[0001] The present application relates to the field of electric power grid technology, and in particular to a data-driven method, system, and medium for accurately identifying the actual operating gear of a distribution transformer. Background Art

[0002] Accurate distribution transformer gear position identification is the foundation of distribution transformer gear adjustment strategies and a key and difficult issue that has plagued many researchers. Currently, the majority of distribution transformers installed in distribution networks are off-load tap changers. The main methods used for distribution transformer gear position identification include manual offline verification, verification using a calibration device, and online identification based on transformer windings.

[0003] The manual verification method requires first issuing a work ticket, shutting down the distribution transformer, and then carrying a verification device to climb onto the transformer for inspection. This is not only a busy process, but also time-consuming and labor-intensive. The transformer winding-based method is prone to interfere with the normal operation of the transformer and may even damage the transformer. In addition, due to frequent voltage fluctuations, manual offline verification at a certain point in time or the raw data of transformer winding identification can hardly truly determine the gear of the distribution transformer. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a data-driven method, system and medium for accurately identifying the actual operating gear of the distribution transformer, accurately identifying the actual operating gear of the distribution transformer through data analysis, minimizing the impact of the distribution transformer gear identification work on the operation of the power grid, and providing sufficient basis for the distribution transformer gear adjustment.

[0005] To achieve the above objectives, this application provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a data-driven method for accurately identifying the actual operating gear position of a distribution transformer, comprising the following steps:

[0007] Data screening: select the time range corresponding to the single-phase power flow of the distribution network every day in the past month to determine the reference time node for subsequent voltage analysis;

[0008] Identify the operating gear of the distribution transformer to determine whether the topology has conductor distance information. If the topology has conductor distance information, first determine the operating gear of the head-end distribution transformer and then determine the operating gear of other distribution transformers. If the topology lacks conductor distance information, first calculate the difference between the actual voltage and the theoretical voltage and then determine the operating gear of the distribution transformer.

[0009] The data screening is specifically as follows:

[0010] (1) Select the time range T corresponding to the single-phase flow of the distribution network every day in the history of one month i ′ , where the value range of i is as follows:

[0011] i∈{1,2,3,…,30}(1)

[0012] (2) Calculate all T i The intersection of is used as the reference time range T′ of the distribution network single-phase power flow required for subsequent calculations.

[0013] T′=T′1∪T′2∪…∪T′ 30 (2)

[0014] (3) Select the time T″ when the busbar outlet current is the smallest every day in a month i And the bus current I at this moment i Establish two-dimensional sample points X i

[0015] X i =(T″ i ,I i ) (3)

[0016] (4) Use K-means clustering algorithm to calculate all sample points X i The center point U of each classification j ,

[0017] a. Randomly select K points from the sample points as the initial cluster centers,

[0018] b. Divide each sample point into the center point U closest to it j , in the cluster represented by j∈{1,…,k},

[0019] c. Replace the original center point with the center point of all samples in each cluster,

[0020] d. Repeat steps b and c until the center point remains unchanged or the predetermined number of iterations is reached, the algorithm terminates, and the objective function of the K-means clustering algorithm is the sum of squared errors within the cluster SSE

[0021]

[0022] (5) Establish the center point U of each classification j The collection U

[0023] U={U1,…,U k} (5)

[0024] (6) Sort all the sample points in set U according to the bus current value and establish a new set U I

[0025]

[0026] In formula (6) Indicates the sample point with the minimum bus current value in the set U, Represents the set U I The sample point with the largest bus current value,

[0027] (7) Select set U I The time corresponding to all sample points in the set T is established I

[0028]

[0029] (8) According to the order in formula (7), traverse T I In the data, select the first one that matches the distribution network single-phase flow reference time range T ′ The overlapping data is used as the reference time node T for subsequent voltage analysis.

[0030] T∈T I (8)

[0031] T∈T ′ (9).

[0032] When the topology has conductor distance information, the operation gear position of the head-end distribution transformer is first determined, and then the operation gear positions of other distribution transformers are determined as follows:

[0033] Determination of the operating gear of the first-end distribution transformer:

[0034] (1) According to the voltage analysis reference time node T in step 1-(8), the busbar or dedicated transformer high-voltage side voltage is used as the line head end distribution transformer high-voltage side voltage, and express,

[0035] (2) Taking the middle gear of the distribution transformer as the first iteration parameter, calculate the theoretical value of the low-voltage side outlet voltage at the head end

[0036]

[0037] (3) Calculate the measured voltage on the low-voltage side of the first end on the target day Theoretical voltage on the low voltage side The difference

[0038]

[0039] (4) Identification of the first end running gear, according to theoretical analysis, It will fluctuate around 0V, ±10V, and ±20V. To judge the operating position of the first end, it should be noted that the 5-speed transformer can be directly determined, while the 3-speed transformer cannot be completely determined and can only be suspected.

[0040]

[0041] The other distribution transformer operating gear judgment,

[0042] (1) After the above steps to determine the operating gear of the first-end distribution transformer, the actual operating gear of the first-end distribution transformer is obtained, and the PD o Indicates that the actual operating gear PD of the first-end distribution transformer o And the measured voltage on the low-voltage side of the head-end distribution transformer on the target day Calculate and reverse the actual voltage value of the high-voltage side of the head-end distribution transformer on the target day

[0043] In the above formula, ZD3 represents the middle gear of the three-gear transformer, and ZD5 represents the middle gear of the five-gear transformer.

[0044] Based on the topological relationship of the distribution transformer in the distribution network, all the distribution transformers directly connected to the head-end distribution transformer are selected, and the high-voltage side voltage is the actual voltage value of the high-voltage side of the head-end distribution transformer target day. Instead, repeat the steps (2)-(4) in the head-end distribution transformer operating gear determination to find the actual operating gear of all distribution transformers directly connected to the head-end distribution transformer and the actual high-voltage side voltage on the target day.

[0045] By looping the steps of judging the operating gear of the head-end distribution transformer and judging the operating gear of other distribution transformers, the actual operating gear of all distribution transformers in the target distribution network can be obtained.

[0046] When the topology lacks conductor distance information, the actual voltage and theoretical voltage difference is calculated first, and then the distribution transformer operating gear is judged. Specifically,

[0047] ① Calculation of the difference between actual voltage and theoretical voltage

[0048] A. According to the voltage analysis reference time node in step 1-(8), establish the target day transformer high voltage side voltage assignment method,

[0049] a. Obtain the topology diagram of 10kV wiring. Based on the topology diagram, define all FTUs, dedicated transformers, and public transformers as primary center points, secondary center points, and points to be classified.

[0050] b. Assume that the number of first-level center points, second-level center points, and points to be classified are P, Q, and N respectively. Calculate the distance between each point to be classified n and each first-level center point and second-level center point, respectively. express,

[0051] c. Randomly select a point n to be classified, select The minimum value of Indicates that the high-voltage side voltage of classification point n is assigned according to the following formula

[0052]

[0053] In formula (15) They represent the voltages of the point to be classified n, the first-level classification point p, and the second-level classification point q at time T, respectively.

[0054] Repeat step c for all remaining points to be classified to assign values ​​to the high-voltage side voltages of all public transformers within the target day.

[0055] B. Take the transformer after each high-voltage side voltage is assigned as the reference, and use the transformer middle gear (high-voltage side rated voltage 10kV) as the first iteration parameter to calculate the theoretical value of the low-voltage side outlet voltage of each transformer.

[0056]

[0057] C. Calculate the target daily measured voltage of each transformer With theoretical voltage The difference

[0058] ② Distribution transformer operating gear judgment

[0059] Distribution transformer operating gear identification, based on theoretical analysis, It will fluctuate around 0V, ±10V, and ±20V. Determine the operating gear of each distribution transformer,

[0060]

[0061] Repeat steps ① to ② for multiple target day data to more accurately determine the actual operating gear of the distribution transformer.

[0062] In a second aspect, the embodiment of the present application provides a data-driven system for accurately identifying the actual operating gear position of a distribution transformer, comprising:

[0063] The data screening module selects the time range corresponding to the single-phase power flow of the distribution network every day in the history of one month to determine the reference time node for subsequent voltage analysis;

[0064] The distribution transformer operating gear identification module determines whether the topology has conductor distance information. If the topology has conductor distance information, the operating gear of the head-end distribution transformer is determined first, and then the operating gear of other distribution transformers is determined. If the topology lacks conductor distance information, the difference between the actual voltage and the theoretical voltage is calculated first, and then the operating gear of the distribution transformer is determined.

[0065] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a program code. When the program code is executed by a processor, the steps of the data-driven method for accurately identifying the actual operating gear of the distribution transformer are implemented as described above.

[0066] Compared with the prior art, the present invention has the following beneficial effects:

[0067] 1. By selecting the data at the time of single-phase power flow of the power grid and the time when the current on the bus outlet side is the smallest as the research object, the final gear recognition result has a higher accuracy.

[0068] 2. By constructing a data-driven method for accurately identifying the actual operating gear position of the distribution transformer, it can effectively solve the problem that the traditional manual gear position verification is labor-intensive and affects the normal operation of the distribution transformer, and provide strong data support for the distribution transformer gear adjustment work. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0070] Figure 1 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0071] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings. It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0072] The terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0073] The terms "first," "second," etc. are only used to distinguish one entity or operation from another entity or operation, and are not to be understood as indicating or implying relative importance, nor are they to be understood as requiring or implying any actual relationship or order between these entities or operations.

[0074] like Figure 1 A data-driven method for accurately identifying the actual operating gear position of a distribution transformer is shown, comprising the following steps:

[0075] Data screening: select the time range corresponding to the single-phase power flow of the distribution network every day in the past month to determine the reference time node for subsequent voltage analysis;

[0076] Identify the operating gear of the distribution transformer to determine whether the topology has conductor distance information. If the topology has conductor distance information, first determine the operating gear of the head-end distribution transformer and then determine the operating gear of other distribution transformers. If the topology lacks conductor distance information, first calculate the difference between the actual voltage and the theoretical voltage and then determine the operating gear of the distribution transformer.

[0077] 1. Data screening

[0078] (1) Select the time range T corresponding to the single-phase flow of the distribution network every day in the history of one month i ′ , where the value range of i is as follows:

[0079] i∈{1,2,3,…,30}(1)

[0080] (2) Calculate all T i The intersection of the two is used as the reference time range T for the distribution network single-phase power flow required for subsequent calculations. ′ .

[0081] T′=T′1∪T′2∪…∪T′ 30 (2)

[0082] (3) Select the time T″ when the busbar outlet current is the smallest every day in a month i And the bus current I at this moment i Establish two-dimensional sample points X i

[0083] X i =(T″ i ,I i ) (3)

[0084] (4) Use K-means clustering algorithm to calculate all sample points X i The center point U of each classification j

[0085] a. Randomly select K points from the sample points as the initial cluster centers.

[0086] b. Divide each sample point into the center point U closest to it j , in the cluster represented by j∈{1,…,k}.

[0087] c. Replace the original center point with the center point of all samples in each cluster.

[0088] d. Repeat steps b and c until the center point remains unchanged or the predetermined number of iterations is reached, at which point the algorithm terminates.

[0089] The objective function of the K-means clustering algorithm is the sum of squared errors within the cluster SSE.

[0090]

[0091] (5) Establish the center point U of each classification j The collection U

[0092] U={U1,…,U k} (5)

[0093] (6) Sort all the sample points in set U according to the bus current value and establish a new set U I

[0094]

[0095] In formula (6) Indicates the sample point with the minimum bus current value in the set U, Represents the set U I The sample point with the largest bus current value.

[0096] (7) Select set U I The time corresponding to all sample points in the set T is established I

[0097]

[0098] (8) According to the order in formula (7), traverse T I In the data, select the first one that matches the distribution network single-phase flow reference time range T ′ The overlapping data serves as the reference time node T for subsequent voltage analysis.

[0099] T∈T I (8)

[0100] T∈T ′ (9)

[0101] 2. Distribution transformer operating gear identification

[0102] First, we need to determine whether the topology has wire distance information

[0103] (1) The topology has wire distance information

[0104] ① Judgment of the operating gear of the first-end distribution transformer

[0105] a. According to the voltage analysis reference time node T in step 1-(8), the busbar or dedicated high-voltage side voltage is used as the line head end distribution transformer high-voltage side voltage, and express.

[0106] b. Using the middle gear of the distribution transformer as the first iteration parameter, calculate the theoretical value of the low-voltage side outlet voltage at the head end

[0107]

[0108] c. Calculate the measured voltage on the low-voltage side of the first end on the target day Theoretical voltage on the low voltage side The difference

[0109]

[0110] d. Identification of the first end running gear, based on theoretical analysis, It will fluctuate around 0V, ±10V, and ±20V. According to formula (12), To determine the operating gear of the first end, it should be noted that the 5-speed transformer can be directly determined, while the 3-speed transformer cannot be completely determined and can only be suspected.

[0111]

[0112] ② Determination of other distribution transformer operating gears

[0113] a. After the above step ①, the actual operating gear of the head-end distribution transformer can be obtained, and PD o Indicates that the actual operating gear PD of the first-end distribution transformer o And the measured voltage on the low-voltage side of the head-end distribution transformer on the target day Calculate and reverse the actual voltage value of the high-voltage side of the head-end distribution transformer on the target day

[0114]

[0115] In the above formula, ZD3 represents the middle gear of the three-speed transformer, and ZD5 represents the middle gear of the five-speed transformer.

[0116] b. Based on the topological relationship of the distribution transformer in the distribution network, select all the distribution transformers directly connected to the head-end distribution transformer, and use the actual voltage value of the high-voltage side of the head-end distribution transformer on the target day. Alternatively, repeat steps ①bd to obtain the actual operating gears of all distribution transformers directly connected to the head-end distribution transformer and the actual high-voltage side voltage on the target day.

[0117] c. Repeat the above steps to obtain the actual operating gear of all distribution transformers in the target distribution network.

[0118] (2) The topology lacks wire distance information

[0119] ① Calculation of the difference between actual voltage and theoretical voltage

[0120] A. Based on the voltage analysis reference time node in step 1-(8), establish a target day transformer high-voltage side voltage assignment method.

[0121] a. Obtain a topology diagram for 10kV wiring. Based on the topology diagram, define all FTUs, dedicated transformers, and public transformers as primary center points, secondary center points, and points to be classified.

[0122] b. Assume that the number of first-level center points, second-level center points, and points to be classified are P, Q, and N respectively. Calculate the distance between each point to be classified n and each first-level center point and second-level center point, respectively. (Unit: meter)

[0123] c. Randomly select a point n to be classified, select The minimum value of Indicates that the high-voltage side voltage of classification point n is assigned according to the following formula

[0124]

[0125] In formula (15) They represent the voltages of the point to be classified n, the first-level classification point p, and the second-level classification point q at time T respectively.

[0126] Repeat step c for all remaining points to be classified to assign values ​​to the high-voltage side voltages of all public transformers within the target day.

[0127] B. Take the transformer after each high-voltage side voltage is assigned as the reference, and use the transformer middle gear (high-voltage side rated voltage 10kV) as the first iteration parameter to calculate the theoretical value of the low-voltage side outlet voltage of each transformer.

[0128]

[0129] C. Calculate the target daily measured voltage for each transformer With theoretical voltage The difference

[0130] ② Distribution transformer operating gear judgment

[0131] Distribution transformer operating gear identification, based on theoretical analysis, It will fluctuate around 0V, ±10V, and ±20V. Determine the operating gear of each distribution transformer.

[0132]

[0133] Repeat steps ① to ② for multiple target day data to more accurately determine the actual operating gear of the distribution transformer.

[0134] 3. Demonstration by Example

[0135] Taking the distribution networks in several regions of Hubei Province as an example, the actual operating gears of all distribution transformers are identified by combining the distribution transformer gear recognition algorithm of the present invention, and the accuracy of the present invention is verified based on the results of manual investigation:

[0136] Table 1 Statistics on the accuracy of transmission gear position recognition in a certain area of ​​Hubei Province

[0137]

[0138]

[0139] It can be seen from the content in Table 1 that the transmission gear position identification method of the present invention has an extremely high accuracy rate. The transmission gear position identification accuracy rate in various regions of Hubei Province is as high as 100%, and it has high application value.

[0140] The embodiment of the present application provides a data-driven distribution transformer actual operating gear accurate identification system, including:

[0141] The data screening module selects the time range corresponding to the single-phase power flow of the distribution network every day in the history of one month to determine the reference time node for subsequent voltage analysis;

[0142] The distribution transformer operating gear identification module determines whether the topology has conductor distance information. If the topology has conductor distance information, the operating gear of the head-end distribution transformer is determined first, and then the operating gear of other distribution transformers is determined. If the topology lacks conductor distance information, the difference between the actual voltage and the theoretical voltage is calculated first, and then the operating gear of the distribution transformer is determined.

[0143] An embodiment of the present application provides a computer-readable storage medium storing program code. When the program code is executed by a processor, the steps of the data-driven method for accurately identifying the actual operating gear position of a distribution transformer are implemented.

[0144] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0145] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0146] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0148] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0149] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0150] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0151] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A data-driven method for accurately identifying the actual operating gear position of a distribution transformer, characterized in that: The steps include: Data screening: select the time range corresponding to the single-phase power flow of the distribution network every day in the past month to determine the reference time node for subsequent voltage analysis; Identify the operating position of the distribution transformer to determine whether the topology has conductor distance information. If the topology has conductor distance information, the operating position of the head-end distribution transformer is determined first, followed by the operating positions of other distribution transformers. If the topology lacks conductor distance information, the difference between the actual voltage and the theoretical voltage is calculated first, followed by the operating position determination. The data screening is specifically as follows: (1) Select the time range corresponding to the single-phase flow of the distribution network every day in the history of one month ,in, The value range of is as follows: (1) (2) Calculate all The intersection of the two is used as the reference time range for the distribution network single-phase flow required for subsequent calculations , (2) (3) Select the moment when the busbar outlet current is the smallest every day in a month And the bus current at that moment Establish two-dimensional sample points , (3) (4) Use K-means clustering algorithm to calculate all sample points The center points of each category , a. Randomly select K points from the sample points as the initial cluster centers, b. Divide each sample point into the center point closest to it , In the cluster represented by c. Replace the original center point with the center point of all samples in each cluster, d. Repeat steps b and c until the center point remains unchanged or the predetermined number of iterations is reached, the algorithm terminates. The objective function of the K-means clustering algorithm is the sum of squared errors within the cluster. , (4)； (5) Establish the center point of each classification Collection , (5) (6) Pair collection All sample points in are sorted according to the bus current value, and a new set is established. , (6) In formula (6) Representing a collection The sample point with the smallest bus current value, Representing a collection The sample point with the largest bus current value, (7) Select a set The time corresponding to all sample points in the time set is established , (7) (8) According to the order in formula (7), traverse In the data, select the first one that matches the distribution network single-phase flow reference time range The overlapping data is used as the reference time node for subsequent voltage analysis , (8) (9)。 2. A data-driven method for accurately identifying the actual operating gear position of a distribution transformer according to claim 1, characterized in that: When the topology has conductor distance information, the operation gear position of the head-end distribution transformer is first determined, and then the operation gear positions of other distribution transformers are determined as follows: Determination of the operating gear of the first-end distribution transformer: (1) Voltage analysis reference time node according to steps (1)-(8) , use the busbar or dedicated transformer high voltage side voltage as the line head end transformer high voltage side voltage, express, (2) Taking the middle gear of the distribution transformer as the first iteration parameter, calculate the theoretical value of the low-voltage side outlet voltage at the head end , (11) (3) Calculate the measured voltage on the low-voltage side of the first end target day Theoretical voltage on the low voltage side The difference , (12) (4) Identification of the first end running gear, according to theoretical analysis, It will fluctuate around 0V, ±10V, and ±20V. According to step 2-(3) , to determine the first end operating gear, it should be noted that the 5-speed transformer can be directly determined, while the 3-speed transformer cannot be completely determined and can only be suspected. (13)。 3. A data-driven method for accurately identifying the actual operating gear position of a distribution transformer according to claim 2, characterized in that: The other distribution transformer operating gear position determination is specifically as follows: (1) After the above steps to determine the operating gear of the first-end distribution transformer, the actual operating gear of the first-end distribution transformer is obtained. Indicates that the actual operating gear of the first-end distribution transformer And the measured voltage on the low-voltage side of the head-end distribution transformer on the target day , calculate and reverse the actual voltage value of the high voltage side of the head-end distribution transformer on the target day , (14) In the above formula, Indicates the middle gear of the three-gear transformer. Indicates the middle gear of the five-speed transformer. Based on the topological relationship of the distribution transformer in the distribution network, all the distribution transformers directly connected to the head-end distribution transformer are selected, and the high-voltage side voltage is the actual voltage value of the high-voltage side of the head-end distribution transformer target day. Instead, repeat the steps (2)-(4) in the first-end distribution transformer operating gear determination to find the actual operating gear of all distribution transformers directly connected to the first-end distribution transformer and the actual high-voltage side voltage on the target day. By looping the steps of judging the operating gear of the head-end distribution transformer and judging the operating gear of other distribution transformers, the actual operating gear of all distribution transformers in the target distribution network can be obtained.

4. A data-driven method for accurately identifying the actual operating gear position of a distribution transformer according to claim 3, characterized in that: When the topology lacks conductor distance information, the actual voltage and theoretical voltage difference is calculated first, and then the distribution transformer operating gear is judged. Specifically, ① Calculation of the difference between actual voltage and theoretical voltage A. According to the voltage analysis reference time node in step 1-(8), establish the target day transformer high voltage side voltage assignment method, a. Obtain the topology diagram of 10kV wiring. Based on the topology diagram, define all FTUs, dedicated transformers, and public transformers as primary center points, secondary center points, and points to be classified. b. Assume that the number of first-level center points, second-level center points, and points to be classified are P, Q, and N respectively. Calculate the distance between each point to be classified n and each first-level center point and second-level center point, respectively. 、 express, c. Randomly select a point n to be classified, select 、 The minimum value of 、 Indicates that the high-voltage side voltage of classification point n is assigned according to the following formula (15) In formula (15) 、 、 They represent the voltages of the point to be classified n, the first-level classification point p, and the second-level classification point q at time T, respectively. Repeat step c for all remaining points to be classified, and you can assign values ​​to the high-voltage side voltages of all public transformers within the target day. B. Take the transformer after each high-voltage side voltage is assigned as the basis, set the transformer middle gear and high-voltage side rated voltage 10kV as the first iteration parameter, and calculate the theoretical value of the low-voltage side outlet voltage of each transformer. , (16) C. Calculate the target daily measured voltage for each transformer With theoretical voltage The difference , (17) ② Distribution transformer operating gear judgment Distribution transformer operating gear identification, based on theoretical analysis, It will fluctuate around 0V, ±10V, and ±20V. , determine the operating gear of each distribution transformer, (18) Repeat steps ① to ② for multiple target day data to more accurately determine the actual operating gear of the distribution transformer.

5. A data-driven distribution transformer actual operating gear accurate identification system, used to implement the method according to any one of claims 1 to 4, characterized in that: include, The data screening module selects the time range corresponding to the single-phase power flow of the distribution network every day in the history of one month to determine the reference time node for subsequent voltage analysis; The distribution transformer operating gear identification module determines whether the topology has conductor distance information. If the topology has conductor distance information, the operating gear of the head-end distribution transformer is determined first, and then the operating gear of other distribution transformers is determined. If the topology lacks conductor distance information, the difference between the actual voltage and the theoretical voltage is calculated first, and then the operating gear of the distribution transformer is determined.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program code, and when the program code is executed by the processor, the steps of the data-driven method for accurately identifying the actual operating gear position of the distribution transformer as claimed in any one of claims 1 to 4 are implemented.

Images