Method, system and equipment for identifying topological structure of LMU (Local Measurement Unit) area based on Transform model and medium

Abstract

The invention discloses a method, a system, equipment and a medium for identifying an LMU area topological structure based on a Transform model, and relates to the technical field of electric power metering and line loss governance, and the method comprises the steps: randomly generating the LMU area topological structure; for each transformer area, generating electric power data of each electricity meter according to the topological structure of the transformer area, and performing data preprocessing according to the transformer area; multiplying the current data by a power factor to obtain new current data, and selecting time points of voltage, current, active power and electric quantity according to rules; the method comprises the following steps of: sorting electric power data information and electric meter types of each electric meter in a transformer area to generate a data matrix and a label matrix, and connecting a position-based classifier to the output of a Transform-based encoder. According to the method, the neural network model is trained based on simulation data, and the problem of insufficient data volume of a large model is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power metering and line loss management, and in particular to a method, system, device and medium for identifying the topological structure of the LMU substation area based on the Transformer model. Background Art

[0002] As an important indicator for measuring the input-output ratio of power grid construction and the operation and management level, line loss management is a key task for the power industry to improve quality and efficiency.

[0003] With the in-depth development of line loss management work, a method has been proposed in the market to install LMU (Line Monitoring Unit) at the branch nodes of key lines and decompose the line loss management of the substation area into the line loss management of line branches. The LMU can measure the electricity consumption of a line branch, similar to the function of the total meter of the substation area. By using the electricity consumption measured by the LMU and the electricity consumption of each household meter under the line branch, the line loss of the line branch can be obtained, and the line loss of the line branch is also called the sectional line loss.

[0004] From the above sectional line loss calculation logic, it can be seen that how to effectively obtain which household meters are included under the LMU is a crucial issue for sectional line loss management work. Although the household meter information included under the line branches of the substation area has been manually entered into the power grid related information system, it cannot be dynamically identified and updated, and there are generally problems of low accuracy and reliability. In the traditional way, the identification of branch household meter information mainly relies on manual on-site inspection. Although this method has a high accuracy rate (but only for non-buried lines), it is time-consuming and laborious, greatly reducing the efficiency of the verification work. Currently, it is also possible to use the method of injecting characteristic signals and physically distinguish at the level of on-site collection equipment based on the principles of carrier communication and voltage zero-crossing time division comparison. Although this method has a high identification accuracy rate, it is necessary to upgrade and transform all collection terminals and household meters, with a high investment cost, a long transformation period, and high requirements for equipment reliability, which is not convenient for full-scale popularization and application. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method for identifying the topological structure of the LMU substation area based on the Transformer model, which can solve the problems that the power grid related information system cannot be dynamically identified and updated and generally has low accuracy and reliability.

[0007] To solve the above technical problems, the present invention provides the following technical solution. The method for identifying the topological structure of the LMU substation area based on the Transformer model includes: Randomly generate the topological structure of the LMU substation area; for each substation area, generate the power data of each electric meter according to its topological structure, and perform data preprocessing by substation area. Multiply the current data by the power factor as the new current data, and select the time points of voltage, current, active power, and electricity consumption according to the rules. Organize the power data information and electric meter types of each electric meter in the substation area to generate a data matrix and a label matrix. Based on the encoder of the Transformer, connect a position-based classifier to the output of the encoder.

[0008] As a preferred solution of the method for identifying the topological structure of the LMU substation area based on the Transformer model of the present invention, wherein: the power data includes voltage, current, active power, power factor, and total forward active data.

[0009] As a preferred solution of the method for identifying the topological structure of the LMU substation area based on the Transformer model of the present invention, wherein: the data preprocessing includes calculating the hourly electricity consumption of each electric meter per day, with 24 electricity consumption data for each meter per day, and sorting the electric meters in the substation area according to type and average electricity consumption.

[0010] As a preferred solution of the method for identifying the topological structure of the LMU substation area based on the Transformer model of the present invention, wherein: the generation of the topological structure of the LMU substation area includes randomly generating a multi-way weighted tree structure, representing the topological structure of the substation area with the current multi-way tree, non-leaf nodes representing LMU, leaf nodes representing user meters, and the weight value representing the resistance value of the line between two nodes.

[0011] As a preferred solution of the method for identifying the topological structure of the LMU substation area based on the Transformer model of the present invention, wherein: the random generation includes defining that the level value of the tree is between [3, 9], the number of non-leaf nodes is between [3, 30], the resistance value of each node to the upper-level node is in the range of [0.01, 0.07] ohms, and at the same time defining the value range of the leaf node tree.

[0012] As a preferred solution of the method for identifying the topological structure of the LMU substation area based on the Transformer model of the present invention, wherein: the selection according to the rules includes that the selection rules for voltage, current, power, and electricity consumption data are: select the voltage values at 127 time points with the largest average current of all meters in the substation area; select the current values at 128 time points with the largest average current value; select the active power values at 128 time points with the largest average active power; select the electricity consumption data corresponding to the 128 time points with the largest average electricity consumption.

[0013] As a preferred solution of the method for identifying the LMU substation area topology structure based on the Transformer model of the present invention, wherein: the format of the data matrix is: , wherein, , is the number of electricity meters in the substation area. The three-phase meter is regarded as 3 meters, and each meter is represented as a 512-dimensional vector; represents whether the th electricity meter is an LMU meter. If the electricity meter is an LMU meter, the value is 1, otherwise it is 0; represents the voltage data of the th electricity meter. There are 127 moments of voltage data. The acquisition time of the voltage values of all meters corresponding to the dimension is the same; represents the current data of the th electricity meter. There are 128 moments of current data. The acquisition time of the current values of all meters corresponding to the dimension is the same; represents the active power data of the th electricity meter. There are 128 moments of active power data. The acquisition time of the active power of all meters corresponding to the dimension is the same; represents the electricity quantity data of the th electricity meter. There are 128 time periods of electricity quantity data. The acquisition time period of the electricity quantity values of all meters corresponding to the dimension is the same.

[0014] As a preferred solution of the system for identifying the LMU substation area topology structure based on the Transformer model of the present invention, wherein: the system includes a data acquisition module, a data processing module, and an algorithm module; the data acquisition module is used to acquire data information; the data processing module is used to perform data preprocessing operations; the algorithm module is used to run by carrying the algorithm.

[0015] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method for identifying the LMU substation area topology structure based on the Transformer model are implemented.

[0016] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the method for identifying the LMU substation area topology structure based on the Transformer model are implemented.

[0017] Advantages of the present invention: 1. Based on the neural network model, the present invention provides a method for automatically predicting the LMU substation area topology structure, saving a large amount of labor costs and providing technical support for the popularization of line loss control by installing LMU.

[0018] 2. The present invention conducts model training based on simulation data. The simulation data is generated randomly and has the characteristic of data diversity, being applicable to various types of LMU substation area topologies and electricity consumption situations.

[0019] 3. The calculation process of the method described in the present invention is simple and reliable. It only needs to organize the data obtained from the simulation, input it into the model for offline training, and then use it online. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 It is a schematic flowchart of a method for identifying the topology structure of an LMU substation area based on a Transformer model provided by an embodiment of the present invention.

[0022] Figure 2 It is a schematic diagram of the topology structure of an LMU substation area of a method for identifying the topology structure of an LMU substation area based on a Transformer model provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0024] Example 1, referring to Figure 1 - Figure 2 , which is the first embodiment of the present invention. This embodiment provides a method for identifying the topology structure of an LMU substation area based on a Transformer model, including: S1: Generate simulation data: Randomly generate the topology structure of the LMU substation area; for each substation area, generate the power data of each electricity meter according to its topology structure, including voltage, current, active power, power factor, and total forward active data; S2: Data preprocessing: It is carried out by transformer substation area. Calculate the hourly power consumption (abbreviated as power) of each electric meter every day. There are 24 power data for each meter every day. Sort the electric meters under the transformer substation area according to type and average power; Multiply the current data by the power factor as the new current data; Select the time points of voltage, current, active power and power according to the rules; Organize the power data information and meter type of each electric meter under the transformer substation area into a 512-dimensional vector, and generate a data matrix and a label matrix; S3: Model design: Based on the encoder of Transformer, a position-based classifier is connected to the output of the encoder.

[0025] In S1, simulation data generation includes the following two steps: S11: Generate a topological structure, such as Figure 2 , randomly generate a multi-fork weighted tree structure, and use this multi-fork tree to represent the topological structure of the transformer substation area. Non-leaf nodes (light blue nodes in the figure) represent LMU, and leaf nodes (red nodes in the figure) represent user meters. The weight value (the value on the connection line between two nodes in the figure) represents the resistance value of the line between the two nodes. The randomness is reflected in: (1) The level of the tree takes values in the range of [3, 9]; (2) The number of non-leaf nodes takes values in [3, 30]. In actual situations, the number of LMU meters installed under a transformer substation area generally does not exceed 30; (3) The resistance value from each node to its upper-level node takes values in the range of [0.001, 0.07] ohms; Define the value range of the leaf node tree, including that the leaf node tree included in the non-leaf node takes values in [0, 10].

[0026] In S2, data processing includes the following steps: S21: Meter sorting. The meter sorting follows the following rules: (1) Three-phase meters are split into 3 meters according to the phase; (2) All LMU meters are before non-LMU meters; (3) For LMU meters, sort them in descending order of average power; (4) For non-LMU meters, sort them in descending order of average power; (5) Use the sorting result to number the LMU meters, starting from 1.

[0027] S22: Selection of voltage, current, power and power data. The basic rules are: [[ID=3--7]] (1) Select the voltage values at the 127 time points with the largest average current of all meters under the transformer substation area; (2) Select the current values at the 128 time points with the largest average current value; (3) Select the active power values at 128 time points with the largest average active power; (4) Select the electricity quantity data corresponding to the 128 times with the largest average electricity quantity.

[0028] S23: Organize the data matrix, which will be used as the input of the neural network. The format of the data matrix is: , where , is the number of electricity meters in the distribution transformer area. Here, a three-phase meter is regarded as 3 meters. Each meter is represented as a 512-dimensional vector. The meanings of the data in each dimension are as follows: represents whether the th electricity meter is an LMU meter. If the electricity meter is an LMU meter, the value is 1; otherwise, it is 0.

[0029] represents the voltage data of the th electricity meter, with voltage data at 127 moments. Here, the acquisition times of the voltage values in the corresponding dimensions of all meters are the same.

[0030] represents the current data of the th electricity meter, with current data at 128 moments. Here, the acquisition times of the current values in the corresponding dimensions of all meters are the same.

[0031] represents the active power data of the th electricity meter, with active power data at 128 moments. Here, the acquisition times of the active power in the corresponding dimensions of all meters are the same.

[0032] represents the electricity quantity data of the th electricity meter, with electricity quantity data for 128 time periods. Here, the acquisition time periods of the electricity quantity values in the corresponding dimensions of all meters are the same.

[0033] S24: Organize the label matrix, and its format is: , where , each column is a one-hot vector, representing the LMU information to which a meter belongs. If the value of a certain column is , it means that the meter belongs to the LMU meter numbered 2. Here, the number of the LMU is the number specified in item (5) of S21.

[0034] In S3, based on the Transformer encoder, a position-based classifier is connected to the output of the encoder.

[0035] Model structure description: (1) The model only uses the encoder of the Transformer and does not use the decoder.

[0036] (2) The model input is a matrix of , corresponding to matrix X in S23; the output is a matrix of , and the matrix shape is the same as Y in S24.

[0037] (3) Each vector of the model input needs to be added with a positional encoding as the input of the Transformer Encoder; the dimension of the positional encoding is the same as that of the input vector, both being 512 dimensions.

[0038] (4) The output of the Transformer Encoder is a matrix of , with the same shape as the input.

[0039] (5) Each vector of the output of the Transformer Encoder passes through the same fully connected neural network FC. The input of FC is a vector of length 512, and the output is a vector of length 90.

[0040] Based on the neural network model, this embodiment predicts the topological structure of the LMU area. It has innovative significance in terms of applicable scope and data quality compatibility, can accurately identify the area topology, plays an important role in the process of sectional line loss control, and saves a large amount of labor costs.

[0041] Example 2, referring to Figure 2 , is an embodiment of the present invention, which provides a method for identifying the topological structure of the LMU area based on the Transformer model. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0042] S11: Generate a topological structure, such as Figure 2 , randomly generate a multi-way weighted tree structure, and use this multi-way tree to represent the topological structure of the area. The non-leaf nodes (light blue nodes in the figure) represent LMU, and the leaf nodes (red nodes in the figure) represent user meters. The weight value (the value on the connection line between two nodes in the figure) represents the resistance value of the line between the two nodes. The randomness is reflected in: (1) The level of the tree takes values in the range of [3, 9]; (2) The number of non-leaf nodes takes values in [3, 30]. In actual situations, the number of LMU meters installed under a substation area generally does not exceed 30; (3) The resistance value of each node to its upper-level node takes values in the interval [0.001, 0.07] ohms; The range of leaf node tree values is defined to include setting the number of leaf nodes included in the nodes that do not include non-leaf nodes to [10, 30].

[0043] S12: Generate power data. Each row in the table represents simulation data at a time point: (1) Input LMU area topology (multi-branch tree); (2) Initialize the leaf node current attribute to 0; initialize the root node voltage attribute to u; where , (3) Each leaf node is randomly assigned a current value i, where i takes the following values: , (4) Traverse the topology from bottom to top and add the current of the child node to the parent node.

[0044] (5) Traverse the topology from top to bottom and calculate the voltage drop on each branch. Calculate the voltage value of each non-root node through the root node voltage and the voltage drop of each branch; (6) Calculate the active power of each node based on the voltage and current of each node; (7) The power of each node is multiplied by a time constant (here 1 minute) to obtain the power consumption of this simulation; (8) Repeat steps 1 to 7 several times, each time representing the simulation data at a time point; (9) Accumulate and calculate the sequence of power data (data generated in step 7) obtained from multiple simulation results to obtain the total active power sequence.

[0045] In S2, data processing includes the following steps: S21: Electricity meter sorting. Electricity meter sorting follows the following rules: (1) The three-phase meter is split into three meters according to the phase; (2) All LMU tables are placed before non-LMU tables; (3) LMU table, sorted in descending order by average power; (4) Non-LMU table, sorted in descending order by average power; (5) Use the sorting result to number the LMU table, starting from 1.

[0046] S22: Voltage, current, power, and electricity data selection. The basic rules are as follows: (1) Select the voltage values of the 127 time points where the average current of all meters in the substation is the largest; (2) Select the current values of the 128 time points with the largest average current values; (3) Select the active power values at 128 time points with the maximum average active power; (4) Select the electricity quantity data corresponding to the 128 times with the maximum average electricity quantity.

[0047] S23: Organize the data matrix, which will be used as the input of the neural network. The format of the data matrix is: , where , is the number of electricity meters in the transformer substation area. Here, a three-phase meter is regarded as 3 meters. Each meter is represented as a 512-dimensional vector. The meanings of the data in each dimension are: represents whether the -th electricity meter is an LMU meter. If the electricity meter is an LMU meter, the value is 1; otherwise, it is 0.

[0048] represents the voltage data of the -th electricity meter, with the voltage data at 127 moments. Here, the acquisition times of the voltage values in the corresponding dimensions of all meters are the same.

[0049] represents the current data of the -th electricity meter, with the current data at 128 moments. Here, the acquisition times of the current values in the corresponding dimensions of all meters are the same.

[0050] represents the active power data of the -th electricity meter, with the active power data at 128 moments. Here, the acquisition times of the active power in the corresponding dimensions of all meters are the same.

[0051] represents the electricity quantity data of the -th electricity meter, with the electricity quantity data in 128 time periods. Here, the acquisition time periods of the electricity quantity values in the corresponding dimensions of all meters are the same.

[0052] S24: Organize the label matrix, and its format is: , where , each column is a one-hot vector, representing the LMU information to which a meter belongs. If the value of a certain column is , it means that the meter belongs to the LMU meter numbered 2. Here, the number of the LMU is the number specified in item (5) of S21.

[0053] In S3, based on the Transformer encoder, a position-based classifier is connected to the output of the encoder.

[0054] Model structure description: (1) The model only uses the encoder of the Transformer and does not use the decoder.

[0055] (2) The model input is a matrix of , corresponding to the matrix X in S23; the output is a matrix of , and the matrix shape is the same as Y in S24.

[0056] (3) Each vector of the model input needs to be added with a positional encoding as the input of the Transformer Encoder; the dimension of the positional encoding is the same as that of the input vector, both being 512 dimensions.

[0057] (4) The output of the Transformer Encoder is a matrix of , with the same shape as the input.

[0058] (5) Each vector of the output of the Transformer Encoder passes through the same fully connected neural network FC. The input of FC is a vector of length 512, and the output is a vector of length 90.

[0059] This application trains the neural network model based on simulation data, solving the problem of insufficient data volume of large models.

[0060] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

[0061] Embodiment 3 is the third embodiment of the present invention. This embodiment provides a system for identifying the topological structure of the LMU substation area based on the Transformer model, including: a data acquisition module, a data processing module, and an algorithm module.

[0062] The data acquisition module is used to collect data information; the data processing module is used to perform data preprocessing operations; the algorithm module is used to run by carrying algorithms.

[0063] If the functions of this embodiment are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., all of which can store program codes.

[0064] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0065] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), fiber optic devices, and portable compact disc read-only memories (CDROMs). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as necessary, and then storing it in a computer memory.

[0066] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by a combination of any of the following technologies well known in the art: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

Claims

1. A method for identifying the topological structure of the LMU substation area based on the Transformer model, characterized in that: Including, Randomly generate the topological structure of the LMU substation area; For each substation area, generate the power data of each electric meter according to its topological structure, and perform data preprocessing by substation area; Multiply the current data by the power factor as the new current data, and select the time points of voltage, current, active power, and electricity consumption according to the rules; Sort out the power data information and electric meter types of each electric meter under the substation area, generate a data matrix and a label matrix, and connect a position-based classifier to the output of the encoder based on the Transformer.

2. The method for identifying the topological structure of the LMU substation area based on the Transformer model according to claim 1, wherein: The power data includes voltage, current, active power, power factor, and total forward active data.

3. The method for identifying the LMU substation topology structure based on the Transformer model according to claim 2, wherein: The data preprocessing includes calculating the hourly electricity consumption of each electric meter every day, 24 electricity consumption data for each meter every day, and sorting the electric meters under the substation area according to type and average electricity consumption.

4. The method for identifying the topological structure of the LMU substation area based on the Transformer model according to claim 3, wherein: The generation of the topological structure of the LMU substation area includes randomly generating a multi-way weighted tree structure, representing the topological structure of the substation area with the current multi-way tree, non-leaf nodes representing LMU, leaf nodes representing user meters, and the weight representing the resistance value of the line between two nodes.

5. The method for identifying the LMU substation topology structure based on the Transformer model according to claim 4, wherein: The random generation includes defining that the level value of the tree is between [3, 9], the number of non-leaf nodes is between [3, 30], the resistance value of each node to the upper-level node is between the intervals [0.01, 0.07] ohms, and at the same time defining the value range of the leaf node tree.

6. The method for identifying the LMU substation topology structure based on the Transformer model according to claim 5, wherein: The selection according to the rules includes that the selection rules for voltage, current, power, and electricity consumption data are: select the voltage values at 127 time points with the largest average current of all meters under the substation area; Select the current values at 128 time points with the largest average current value; select the active power values at 128 time points with the largest average active power; select the electricity consumption data corresponding to 128 time points with the largest average electricity consumption.

7. The method for identifying the LMU substation topology structure based on the Transformer model according to claim 6, wherein: The format of the data matrix is: ， Among them, , is the number of electricity meters under the transformer substation area. A three-phase meter is regarded as 3 meters, and each meter is represented as a 512-dimensional vector; indicates whether the th electricity meter is an LMU meter. If the electricity meter is an LMU meter, the value is 1, otherwise it is 0; indicates the voltage data of the th electricity meter, with voltage data at 127 moments. The acquisition time of the voltage values of all meters corresponding to the dimension is the same; indicates the current data of the th electricity meter, with current data at 128 moments. The acquisition time of the current values of all meters corresponding to the dimension is the same; indicates the active power data of the th electricity meter, with active power data at 128 moments. The acquisition time of the active power of all meters corresponding to the dimension is the same; indicates the electricity consumption data of the th electricity meter, with electricity consumption data in 128 time periods. The acquisition time period of the electricity consumption values of all meters corresponding to the dimension is the same.

8. A system for identifying the topology structure of the LMU substation area based on the Transformer model, which applies the method for identifying the topology structure of the LMU substation area based on the Transformer model as described in any one of claims 1 to 7, characterized in that, Including: Data acquisition module, data processing module, algorithm module; The data acquisition module is used to acquire data information; The data processing module is used to perform data preprocessing operations; The algorithm module is used to run with the algorithm loaded.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for identifying the topological structure of the LMU substation area based on the Transformer model described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for identifying the topological structure of the LMU substation area based on the Transformer model described in any one of claims 1 to 7.

Images