Transformer topology intelligent identification method and system, electronic device, and storage medium

Abstract

The application discloses a kind of transformer area topology intelligent identification method and system, electronic equipment, storage medium, the method is based on energy conservation principle, the load data of upper branch node and the load data and line loss value of lower branch node or subordinate meter box sum balance, therefore, by first constructing meter box load matrix, branch node load matrix, coefficient matrix and line loss value matrix, least square matrix is obtained by constructing again, the optimization objective function of least square matrix is solved to obtain coefficient matrix, transformer area topology structure can be determined based on coefficient matrix.The whole identification process is realized based on the load data of meter box and branch node, is not influenced by the bidirectional flow of tidal current, so that transformer area topology structure can be accurately identified, and the required data amount is less, the sample number needs to reach certain degree to be able to run algorithm, greatly improve the efficiency of transformer area topology identification.

Description

Technical Field

[0001] This invention relates to the field of transformer substation topology identification technology, and in particular, to a transformer substation topology intelligent identification method and system, electronic device, and computer-readable storage medium. Background Technology

[0002] Currently, the distribution system remains one of the main weak links in my country's power grid system. Previously, my country did not pay enough attention to the construction of the distribution system, with investment in the distribution network side being far less than that in the main grid side. Its level of intelligence is lower than that of the transmission system, and its intelligent development is still in its initial stage, facing many challenges and opportunities. Currently, transmission and high-voltage distribution systems are typically equipped with sophisticated state estimation systems. Network topology state estimation, load status, and node voltage can be achieved based on real-time data from SCADA (Supervisory Control and Data Acquisition) systems. Correctly identifying and interpreting the topology is a key task for any state estimation system, as accurate network topology information is a prerequisite for advanced system analysis (such as optimal power flow, security assessment, network reconfiguration, and fault location). When medium-voltage and low-voltage distribution systems are involved, transformer topology identification actually lays an important foundation for their operation monitoring and management. In particular, the transformer topology of low-voltage distribution systems is undoubtedly the basis for power flow analysis and many other advanced operation management functions, such as serving as an essential input for three-phase imbalance management, reducing network losses, and fault location. Furthermore, the continuous development of distributed renewable energy, distributed energy storage, and "vehicle-to-grid interaction" will cause bidirectional power flow in the power distribution system, bringing safety hazards. For example, the rapid increase in load due to the charging demand of electric vehicles will lead to serious problems such as overload of distribution transformers and imbalance in the power distribution system. Existing methods for solving these key problems all rely on the assumption of known transformer topology, but they cannot be implemented when the transformer topology is unknown.

[0003] Regarding transformer substation topology identification schemes, the applicant has previously applied for a series of patents. The general technical concept is based on load change feature matching and identification technology to achieve transformer substation topology identification. Specific solutions can be found in patent CN201910843965.X. However, due to the bidirectional power flow in existing distribution systems, accurate transformer substation topology identification based on load change features is no longer feasible. For example, when distributed photovoltaic power is fully connected to the grid, a load change occurs inside the user's meter box, but this load change cannot be detected at the branch sensing terminal, or the load change characteristics do not match those at the meter box sensing terminal, making it impossible to determine the topological relationship between the meter box and the branch. Conversely, when distributed photovoltaic power has surplus capacity connected to the grid, the load change characteristics may not be detected at either the branch or meter box sensing terminals, making it impossible to determine the topological relationship between the branch and the meter box. Therefore, for low-voltage distribution systems with bidirectional power flow, accurately identifying the transformer substation line topology has become a critical problem that urgently needs to be solved. Summary of the Invention

[0004] This invention provides a method and system for intelligent identification of transformer topology, an electronic device, and a computer-readable storage medium to solve the technical problem of poor prediction accuracy in existing methods for calculating photovoltaic power output curves on sunny days based on physical models.

[0005] According to one aspect of the present invention, a method for intelligent identification of transformer substation topology is provided, comprising the following:

[0006] Periodically collect load data of multiple branch nodes and multiple meter boxes in a certain phase within the transformer area, and construct meter box load matrix and branch node load matrix;

[0007] Construct a coefficient matrix and a line loss matrix to characterize the topological relationship between the table box and the branch nodes;

[0008] Based on the principle of energy conservation, a least squares matrix is ​​constructed using the meter box load matrix, branch node load matrix, coefficient matrix, and line loss matrix. The optimization objective function of the least squares matrix is ​​then solved to obtain the coefficient matrix, thereby identifying the transformer area topology.

[0009] Furthermore, when two adjacent branch nodes within a transformer area are located on a single line, the following is also included:

[0010] The hierarchical relationship between two adjacent branch nodes is determined based on their load data.

[0011] Furthermore, the process of determining the hierarchical relationship between two adjacent branch nodes based on their load data specifically involves:

[0012] The system acquires the power consumption and voltage data of two adjacent branch nodes within a certain period of time. It then fuses the power consumption and voltage data of each branch node at the same moment to obtain fused feature data. The system compares and analyzes the fused feature data of two adjacent branch nodes. If the proportion of cases where the fused feature data of one branch node is greater than that of the other branch node exceeds a preset threshold within that period of time, then one branch node is located above the other branch node.

[0013] Furthermore, the fused feature data is represented as follows:

[0014]

[0015] in, This represents the fused feature data of branch node i at time t. and ω1 and ω2 represent the power consumption data and voltage data of branch node i at time t, respectively, and represent the weight parameters. The accuracy of judging the hierarchical relationship between adjacent branch nodes based on historical single electrical quantities is determined.

[0016] Furthermore, the least squares matrix is: B T =X×A T +Λ, where the superscript T denotes matrix transpose, and A denotes the meter box load matrix. W m,t B represents the electricity consumption recorded by meter box m at time t, and B represents the branch node load matrix. E n,t This represents the electricity consumption recorded by branch node n at time t, and Λ represents the line loss matrix. δ nt Let X represent the line loss value of branch node n at time t, and let X represent the coefficient matrix. Each element in the coefficient matrix takes the value 0 or 1, when x nm =1 indicates that branch node n contains table box m.

[0017] Furthermore, the optimization objective function is:

[0018]

[0019] Where, δ it U represents the line loss value of branch node i at time t. n U represents the voltage at branch node n. m This indicates the voltage in the meter box.

[0020] Furthermore, the steps for identifying the transformer area topology also include the following:

[0021] The fluctuation change value Z of the line loss within the period T was calculated respectively.T The value of Z, representing the fluctuation of line loss within the time period [T, T+t1]. T+t1 If Z T+t1 ≤Z T This indicates that the fluctuation of the line loss value tends to stabilize within the time period [T, T+t1]. Therefore, the coefficient matrix X calculated based on the period T... T Determine the topology of the transformer area; if Z T+t1 >Z T Let T1 = T + t1, then calculate the coefficient matrix within the period T1. and line loss matrix And judge With X T If they match, then determine whether they are consistent. With Λ T Whether the offset of the variance of each row is less than a threshold; if so, then based on the coefficient matrix... or X T Determine the topology of the transformer area.

[0022] In addition, the present invention also provides a transformer area topology intelligent identification system, comprising:

[0023] The data acquisition module is used to periodically collect load data of multiple branch nodes and multiple meter boxes in a certain phase within the transformer area, and to construct the meter box load matrix and the branch node load matrix.

[0024] The matrix construction module is used to construct the coefficient matrix and line loss matrix to represent the topological relationship between the table box and the branch nodes;

[0025] The topology identification module is used to construct a least squares matrix based on the principle of energy conservation using the meter box load matrix, branch node load matrix, coefficient matrix and line loss matrix, and solve the optimization objective function of the least squares matrix to obtain the coefficient matrix, thereby identifying the transformer area topology.

[0026] In addition, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the method described above by calling the computer program stored in the memory.

[0027] In addition, the present invention also provides a computer-readable storage medium for storing a computer program for intelligent identification of transformer area topology, wherein the computer program executes the steps of the method described above when running on a computer.

[0028] The present invention has the following effects:

[0029] The intelligent topology identification method for transformer substations of this invention is based on the principle of energy conservation. It is known that the load data of upper-level branch nodes is balanced by the sum of the load data and line loss values ​​of lower-level branch nodes or subordinate meter boxes. Therefore, by first constructing a meter box load matrix, a branch node load matrix, a coefficient matrix, and a line loss matrix, and then constructing a least-squares matrix, the coefficient matrix can be obtained by solving the optimization objective function of the least-squares matrix. Based on the coefficient matrix, the transformer substation topology can be determined. The entire identification process is based on the load data of meter boxes and branch nodes, and is unaffected by bidirectional power flow, thus accurately identifying the transformer substation topology. Furthermore, it requires less data and does not require a certain number of samples to run the algorithm, greatly improving the efficiency of transformer substation topology identification.

[0030] In addition, the intelligent identification system for transformer topology of the present invention also has the above-mentioned advantages.

[0031] In addition to the objectives, features, and advantages described above, the present invention has other objectives, features, and advantages. The invention will now be described in further detail with reference to the figures. Attached Figure Description

[0032] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0033] Figure 1 This is a schematic diagram of the topological structure of the platform area in this invention.

[0034] Figure 2 This is a flowchart illustrating the intelligent identification method for transformer topology according to a preferred embodiment of the present invention.

[0035] Figure 3 This is a schematic diagram of the incomplete transformer area topology identified in a preferred embodiment of the present invention.

[0036] Figure 4 This is a schematic diagram of the complete transformer substation topology identified in a preferred embodiment of the present invention.

[0037] Figure 5 This is a schematic diagram of the module structure of a transformer topology intelligent identification system according to another embodiment of the present invention. Detailed Implementation

[0038] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, the present invention can be implemented in many different ways as defined and covered below.

[0039] Understandable, such as Figure 1As shown, the transformer substation topology of this invention is a master table-branch-table box structure, where a1 to a6 represent table boxes and b1 to b8 represent branch nodes. Therefore, by identifying the topological relationship between the table box area and the branch area, the transformer substation topology can be obtained. To further... Figure 1 Identify the topological relationships of the transformer substations, such as Figure 2 As shown, a preferred embodiment of the present invention provides a method for intelligent identification of transformer area topology, including the following:

[0040] Step S1: Periodically collect load data of multiple branch nodes and multiple meter boxes in a certain phase within the transformer area, and construct the meter box load matrix and the branch node load matrix;

[0041] Step S2: Construct a coefficient matrix and a line loss matrix to characterize the topological relationship between the table box and the branch nodes;

[0042] Step S3: Based on the principle of energy conservation, the least squares matrix is ​​constructed using the meter box load matrix, branch node load matrix, coefficient matrix and line loss matrix. The optimization objective function of the least squares matrix is ​​solved to obtain the coefficient matrix, thereby identifying the transformer area topology.

[0043] It is understood that the intelligent identification method for transformer substation topology in this embodiment, based on the principle of energy conservation, ensures that the load data of the upper-level branch nodes is balanced by the sum of the load data and line loss values ​​of the lower-level branch nodes or subordinate meter boxes. Therefore, by first constructing the meter box load matrix, branch node load matrix, coefficient matrix, and line loss matrix, and then constructing a least-squares matrix, the coefficient matrix can be obtained by solving the optimization objective function of the least-squares matrix. Based on the coefficient matrix, the transformer substation topology can be determined. The entire identification process is based on the load data of meter boxes and branch nodes, and is not affected by bidirectional power flow, thus accurately identifying the transformer substation topology. Furthermore, it requires less data and does not require a certain number of samples to run the algorithm, greatly improving the efficiency of transformer substation topology identification.

[0044] It is understood that in step S1, load data for any phase of the three phases (A / B / C) of multiple branch nodes and multiple meter boxes within the distribution area are collected at a fixed sampling frequency with a 15-minute cycle. The load data includes electricity consumption data and voltage data. Additionally, when the clock synchronization of the terminal HPLC acquisition is good, the load data may also include current, active power, and reactive power. This invention uses electricity consumption data and voltage data as load data for illustrative purposes, and no specific limitations are made here. It is understood that the electricity consumption data collected from multiple meter boxes during the t=1 time period presents a one-dimensional matrix, which can be represented as a1=[W 1,1 … W m,1 ], W m,1This represents the electricity consumption of meter box m during the time period t=1. The electricity consumption data collected by multiple branch nodes during the time period t=1 also presents a one-dimensional matrix, which can be represented as b1=[E 1,1 … E n,1 ], E n,1 This represents the electricity consumption of branch node n during the time period t=1. Therefore, after collecting data for a period of time, we can construct the meter box load matrix A and the branch node load matrix B, which are represented as follows:

[0045]

[0046]

[0047] It can be understood that in step S2, a coefficient matrix X and a line loss matrix Λ are constructed, wherein, δ nt This represents the line loss value of branch node n at time t. Each element in the coefficient matrix takes the value 0 or 1, for example, when x nm When x = 1, it means that branch node n contains table box m, and when x nm When = 0, it indicates that branch node n does not contain table box m. Therefore, the coefficient matrix X can characterize the topological relationships between table boxes and branch nodes, and between different branch nodes. It can be understood that each row in the coefficient matrix X... The value of each element in the table represents the bin number contained under branch node i. For example, when x... 1 im When the value is 1, it means that branch node i contains table box m.

[0048] It is understood that in step S3, based on the principle of energy conservation, the electricity consumption of the upper-level branch node is balanced by the sum of the electricity consumption and line loss of the lower-level branch node or subordinate meter box. Therefore, a least squares matrix can be constructed using the meter box load matrix, branch node load matrix, coefficient matrix, and line loss matrix. The least squares matrix is ​​represented as: B T =X×A T +Λ, where the superscript T denotes matrix transpose, and A denotes the meter box load matrix. W m,t B represents the electricity consumption recorded by meter box m at time t, and B represents the branch node load matrix. E n,t This represents the electricity consumption recorded by branch node n at time t, and Λ represents the line loss matrix. δ nt Let X represent the line loss value of branch node n at time t, and let X represent the coefficient matrix. Each element in the coefficient matrix takes the value 0 or 1, when x nm=1 indicates that branch node n contains table box m.

[0049] Then, the expression for the least squares matrix is ​​transformed to obtain Λ = B. T -XA T Based on linear model theory, an optimization objective function for the least squares matrix is ​​constructed. Furthermore, the following constraints must be met: 1) The voltage of the branch node is greater than the voltage of the meter box under that branch; 2) The sum of each column is ≥1; 3) The line loss value is less than the power consumption of any meter box. Therefore, the optimization objective function can be expressed as:

[0050]

[0051] Where, δ it U represents the line loss value of branch node i at time t. n U represents the voltage at branch node n. m This indicates the voltage in the meter box. Therefore, it can be calculated. coefficient matrix at time Then it can be based on the coefficient matrix X T The topology of the transformer substation can be determined directly.

[0052] Optionally, step S3 further includes the following:

[0053] The fluctuation change value Z of the line loss within the period T was calculated respectively. T The value of Z, representing the fluctuation of line loss within the time period [T, T+t1]. T+t1 ,in, If Z T+t1 ≤Z T This indicates that the fluctuation of the line loss value within the time period [T, T+t1] is smaller, and the coefficient matrix X calculated based on the period T is... T Determine the transformer area topology. It's understandable that when the fluctuation of line loss values ​​decreases over an extended period, it means the transformer area topology identification result calculated for the current period is accurate.

[0054] If Z T+t1 >Z T Let T1 = T + t1, then calculate the coefficient matrix within the period T1. and line loss matrix And judge With X T If they match, then determine whether they are consistent. With Λ T Whether the offset of the variance of each row is less than the threshold, where matrix Λ T The variance of each row is expressed as: matrix The variance of each row is expressed as: Offset is expressed as like Based on the coefficient matrix or X T Determine the transformer area topology. It is understood that if the calculated load data shows consistency and stability across different time periods, it indicates that the transformer area topology identification results are true and accurate, which helps improve the accuracy and reliability of transformer area topology identification.

[0055] Furthermore, for the load data of each time period, a coefficient matrix can be calculated through the above steps S1 to S3. If only load data from a single time period is used for topology identification, the calculated single coefficient matrix may contain randomness and errors, which may affect the accuracy of transformer area topology identification. Therefore, in order to further improve the accuracy of transformer area topology identification results, multiple coefficient matrices can be calculated for load data from multiple time periods. Then, the coefficient matrix that appears most frequently can be selected as the optimal coefficient matrix, and the transformer area topology relationship can be determined based on the optimal coefficient matrix.

[0056] It is understandable that the transformer topology identified based on the above steps S1 to S3 is as follows: Figure 3 As shown, however, when two adjacent branch nodes within a transformer area are located on a single line, for example, combining... Figure 1 It is known that branch nodes b3 and b6, and branch nodes b4 and b7 are each located on a single line. Therefore, steps S1 to S3 cannot accurately identify the hierarchical relationship between these two adjacent nodes; for example, the hierarchical relationship between b3 and b6 cannot be identified, resulting in an incomplete transformer area topology. Therefore, step S3 further includes the following:

[0057] The hierarchical relationship between two adjacent branch nodes is determined based on their load data.

[0058] It can be understood that the process of determining the hierarchical relationship between two adjacent branch nodes based on their load data specifically involves:

[0059] The system acquires the power consumption and voltage data of two adjacent branch nodes within a certain period of time. It then fuses the power consumption and voltage data of each branch node at the same moment to obtain fused feature data. The system compares and analyzes the fused feature data of two adjacent branch nodes. If the proportion of cases where the fused feature data of one branch node is greater than that of the other branch node exceeds a preset threshold within that period of time, then one branch node is located above the other branch node.

[0060] Specifically, the electricity consumption data and voltage data of two adjacent branch nodes within any given time period are obtained. Then, the electricity consumption data and voltage data of each branch node at the same moment are fused to obtain fused feature data, which can be represented as: This represents the fused feature data of branch node i at time t. This represents the electricity consumption data of branch node i at time t. Let ω1 and ω2 represent the voltage data of branch node i at time t. The values ​​of the weight parameters are determined based on the accuracy of judging the hierarchical relationship between adjacent branch nodes using historical single electrical quantities. For example, using a daily frozen curve of minute-by-minute electrical quantities, the accuracy of judging the hierarchical relationship solely based on electricity consumption is η1, and the accuracy of judging the hierarchical relationship solely based on voltage is η2. Therefore, ω1 = η1, ω2 = η2. This allows us to obtain the fused feature data sequences of two adjacent branch nodes, represented as follows: Then, determine the size of the fused feature data of the two branch nodes at the same time, i.e., determine... and The size relationship, if within the time period t, If the proportion exceeds 50%, then branch node i is determined to be at the next higher level than branch node j. This allows identification of the hierarchical relationship between two adjacent branch nodes on a single line, thereby determining the complete topology of the transformer area. Specifically, as follows... Figure 4 As shown.

[0061] It is understood that this invention integrates voltage data and power consumption data, and uses the integrated feature data to determine the hierarchical relationship between two adjacent branch nodes. Compared with the existing method of using a single electrical quantity data to determine the hierarchical relationship between adjacent nodes, this invention greatly improves accuracy.

[0062] In addition, such as Figure 5 As shown, another embodiment of the present invention also provides a transformer area topology intelligent identification system, preferably employing the method described above, including:

[0063] The data acquisition module is used to periodically collect load data of multiple branch nodes and multiple meter boxes in a certain phase within the transformer area, and to construct the meter box load matrix and the branch node load matrix.

[0064] The matrix construction module is used to construct the coefficient matrix and line loss matrix to represent the topological relationship between the table box and the branch nodes;

[0065] The topology identification module is used to construct a least squares matrix based on the principle of energy conservation using the meter box load matrix, branch node load matrix, coefficient matrix and line loss matrix, and solve the optimization objective function of the least squares matrix to obtain the coefficient matrix, thereby identifying the transformer area topology.

[0066] It is understood that the transformer substation topology intelligent identification system in this embodiment, based on the principle of energy conservation, ensures that the load data of the upper-level branch nodes is balanced by the sum of the load data and line loss values ​​of the lower-level branch nodes or subordinate meter boxes. Therefore, by first constructing the meter box load matrix, branch node load matrix, coefficient matrix, and line loss value matrix, and then constructing a least-squares matrix, the coefficient matrix can be obtained by solving the optimization objective function of the least-squares matrix. Based on the coefficient matrix, the transformer substation topology can be determined. The entire identification process is based on the load data of meter boxes and branch nodes, and is not affected by bidirectional power flow, thus accurately identifying the transformer substation topology. Furthermore, it requires less data and does not require a certain number of samples to run the algorithm, greatly improving the efficiency of transformer substation topology identification.

[0067] In addition, another embodiment of the present invention provides an electronic device including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the method described above by calling the computer program stored in the memory.

[0068] In addition, another embodiment of the present invention provides a computer-readable storage medium for storing a computer program for intelligently identifying the topology of a transformer substation, wherein the computer program executes the steps of the method described above when running on a computer.

[0069] Common computer-readable storage media include: floppy disks, flexible disks, hard disks, magnetic tapes, any other magnetic media, CD-ROMs, any other optical media, punch cards, paper tape, any other physical media with perforated patterns, random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), flash erasable programmable read-only memory (FLASH-EPROM), any other memory chips or cartridges, or any other media readable by a computer. Instructions may further be transmitted or received by a transmission medium. The term transmission medium can include any tangible or intangible medium used to store, encode, or carry instructions for machine execution, and includes digital or analog communication signals or intangible media that facilitate communication of such instructions. Transmission media include coaxial cables, copper wires, and optical fibers, which contain conductors for transmitting a bus of computer data signals.

[0070] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0071] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0072] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0073] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0074] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0075] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0076] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A transformer area topology intelligent identification method, characterized in that, The method comprises the following steps: Periodically collecting load data of a plurality of branch nodes and a plurality of meter boxes in a certain phase in a transformer area, and constructing a meter box load matrix and a branch node load matrix; Constructing a coefficient matrix and a line loss value matrix for representing the topological relationship between the meter boxes and the branch nodes; Based on the principle of energy conservation, the meter box load matrix, the branch node load matrix, the coefficient matrix and the line loss value matrix are used to construct a least squares matrix, and the optimization objective function of the least squares matrix is solved to obtain the coefficient matrix, thereby identifying the transformer area topology. The least square matrix is: B T = X * A T + Λ, wherein the superscript T represents matrix transposition, A represents a meter box load matrix, W m,t represents the power consumption recorded by meter box m at time t, B represents a branch node load matrix, E n,t represents the power consumption recorded by branch node n at time t, and Λ represents a line loss value matrix, δ nt represents the line loss value of branch node n at time t, and X represents a coefficient matrix, The value of each element in the coefficient matrix is 0 or 1, and when x nm = 1, it indicates that branch node n contains meter box m. The optimization objective function is: wherein δ it represents the line loss value of branch node i at time t, U n represents the voltage of branch node n, U m represents the voltage of the meter box.

2. The method of claim 1, wherein the method further comprises: When two adjacent branch nodes in the transformer area are located on a single line, the method further comprises the following steps: Based on the load data of the two adjacent branch nodes, the superior-inferior relationship between the two branch nodes is determined.

3. The method of claim 2, wherein the method further comprises: The process of determining the superior-inferior relationship between the two adjacent branch nodes based on the load data of the two adjacent branch nodes is specifically as follows: Obtaining the power consumption data and voltage data of the two adjacent branch nodes within a period of time, fusing the power consumption data and voltage data of each branch node at the same time to obtain fusion feature data, and comparing and analyzing the fusion feature data of the two adjacent branch nodes, if the proportion of the case that the fusion feature data of one branch node is greater than the fusion feature data of the other branch node exceeds a preset threshold within the period of time, then one branch node is located in the superior of the other branch node.

4. The method of claim 3, wherein the method further comprises: The fusion feature data is represented as: wherein, denotes the fusion feature data of branch node i at time t, and denote the power consumption data and voltage data of branch node i at time t, respectively, and ω1 and ω2 denote weight parameters, the accuracy of determining the superior-inferior relationship between adjacent branch nodes based on historical single electrical quantity.

5. The method of claim 1, wherein the method further comprises: determining a number of transformers in the transformer group; and determining a number of feeders in the transformer group. The step of identifying the transformer area topology further comprises the following steps: The line loss value fluctuation change value Z in the period T is calculated respectively T and the line loss value fluctuation change value Z in the time period [T, T+t1] T+t1 If Z T+t1 ≤ Z T , it indicates that the line loss value fluctuation change tends to be stable in the time period [T, T+t1], and the coefficient matrix X T calculated in the period T is used to determine the transformer area topology; if Z T+t1 >Z T , let T1=T+t1, the coefficient matrix X and the line loss value matrix Λ in the period T1 are calculated, and whether X is consistent with X T is judged, if they are consistent, whether the offset of each row variance of X and Λ T is less than the threshold value is judged, if it is less than, the transformer area topology is determined based on the coefficient matrix X or X T .

6. A transformer area topology intelligent identification system, which adopts the transformer area topology intelligent identification method according to any one of claims 1-5, characterized in that, The method comprises the following steps: A data acquisition module is configured to periodically collect load data of a plurality of branch nodes and a plurality of meter boxes in a certain phase in a transformer area, and construct a meter box load matrix and a branch node load matrix; A matrix construction module is configured to construct a coefficient matrix and a line loss value matrix for representing the topological relationship between the meter boxes and the branch nodes; A topology identification module is configured to, based on the principle of energy conservation, use the meter box load matrix, the branch node load matrix, the coefficient matrix and the line loss value matrix to construct a least squares matrix, and solve the optimization objective function of the least squares matrix to obtain the coefficient matrix, thereby identifying the transformer area topology.

7. An electronic device, comprising: The computer program runs on a computer to perform the steps of the method of any one of claims 1-5.

8. A computer readable storage medium for storing a computer program for intelligently identifying a transformer area topology, characterized in that, The computer program runs on a computer to perform the steps of the method of any one of claims 1-5.

Images