Low-voltage transformer area branch topology identification method and device based on dynamic weight value optimization, electronic equipment and storage medium

Abstract

The invention discloses a low-voltage transformer area branch topology identification method and device based on dynamic weight value optimization, electronic equipment and a storage medium. The method comprises the following steps: acquiring report information of preset continuous batches of a transformer area to be analyzed and an initial meter-box relation matrix; the meter box relation matrix maintenance operation is repeatedly executed until the sum of the effective maintenance times of all the meter boxes reaches the preset maintenance times, and a final meter box relation matrix is generated; according to the final meter box relation matrix, generating a transformer area branch topological structure result; according to the invention, the robustness and accuracy of the branch topological relation identification of the low-voltage transformer area are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to a low-voltage substation branch topology identification method, device, electronic device and storage medium based on dynamic weight value optimization. Background Art

[0002] Low-voltage substations are the key link in the power system that connects users and power companies. Ensuring a clear topological structure of low-voltage substations is of great significance to improving the intelligent management of power grid operation, power supply reliability, and user power experience. By accurately identifying the topological relationship of low-voltage substations, it can not only provide a decision-making basis for power supply services and emergency repairs, but also effectively reduce power loss, extend the life of electrical equipment, and improve the efficiency of load balancing management in substations. Therefore, accurate low-voltage substation topology identification is crucial to building a modern smart grid.

[0003] Existing low-voltage substation topology identification methods include manual investigation, signal injection method and data-driven method. Although manual investigation can obtain on-site information, it is inefficient and costly, and it is difficult to adapt to the needs of smart grids. The signal injection method identifies the topology by installing equipment at the topological nodes and analyzing the characteristic signals. However, this method is costly, easily affected by the load, and difficult to deploy. The data-driven method relies on data analysis of smart meters and acquisition systems. Although it does not require additional equipment and can reduce costs, most existing data-driven methods only focus on static weight values ​​when judging the correlation between meter boxes, and cannot adapt to the dynamic changes of current and voltage in low-voltage substations, resulting in limited ability to distinguish the topological structures of different branches, making the confidence of topological identification low and difficult to ensure accuracy. Summary of the invention

[0004] The embodiment of the present invention provides a low-voltage substation branch topology identification method, device, electronic device and storage medium based on dynamic weight value optimization. By implementing the present invention, low-voltage substation branch topology identification can be achieved. By paying attention to the dynamic weight value when judging the correlation between meter boxes, it is possible to adapt to the dynamic changes of current and voltage in the low-voltage substation, improve the confidence of topology identification, and ensure the accuracy of topology identification.

[0005] An embodiment of the present invention provides a low voltage station area branch topology identification method based on dynamic weight value optimization, comprising:

[0006] Obtaining preset continuous batches of reporting information of the area to be analyzed and an initial meter box relationship matrix; wherein each batch of reporting information includes current values ​​and voltage values ​​of all meter boxes collected at a preset sampling frequency;

[0007] Repeat the meter box relationship matrix maintenance operation until the total effective maintenance times of all meter boxes reaches the preset maintenance times, and generate the final meter box relationship matrix;

[0008] Generate the substation branch topology structure result according to the final meter box relationship matrix;

[0009] The table-box relationship matrix maintenance operation includes:

[0010] Get the current reporting information; the initial reporting information is the earliest batch of reporting information that has not been processed;

[0011] Calculate the current change value and voltage change value corresponding to each meter box at the current sampling time point;

[0012] If there is only one meter box whose current change value is greater than the preset current threshold, the meter box whose current change value is greater than the current threshold is set as the reference meter box, and the remaining meter boxes are set as target meter boxes;

[0013] Calculate the voltage threshold value according to the voltage change value of the corresponding reference meter box; compare each corresponding target meter box with the voltage threshold value;

[0014] The target meter box whose voltage change value is greater than the voltage threshold is regarded as the meter box to be updated; the corresponding element of the meter box to be updated in the meter box relationship matrix is ​​updated according to the dynamic weight value, and the effective maintenance times of the reference meter box are increased by 1;

[0015] After determining that the effective maintenance times of all meter boxes have not reached the preset maintenance times, determine whether the current sampling time point is the last sampling time point of the current reporting information; if so, reselect the earliest batch of reporting information that has not been processed and update the current reporting information; if not, select the next sampling time point to update the current sampling time point.

[0016] Furthermore, the initial table-box relationship matrix is ​​generated in the following way:

[0017] Get the number of meter boxes in the area to be analyzed;

[0018] According to the number of meter boxes in the area to be analyzed, a meter box relationship matrix with the number of rows and columns equal to the number of meter boxes is generated; wherein each row and each column in the matrix corresponds to a meter box, respectively, to represent the association relationship between the meter box and other meter boxes.

[0019] Furthermore, the calculation of the current change value and the voltage change value corresponding to each meter box at the current sampling time point includes:

[0020] According to the current reporting information, the difference between the current value corresponding to the current sampling time point of each meter box and the current value corresponding to the previous sampling time point is calculated to obtain the current change value corresponding to each meter box;

[0021] According to the current reporting information, the difference between the voltage value corresponding to the current sampling time point of each meter box and the voltage value corresponding to the previous sampling time point is calculated to obtain the voltage change value corresponding to each meter box.

[0022] Furthermore, dynamic weight values ​​are generated in the following ways:

[0023] Get the effective maintenance times of the current benchmark meter box;

[0024] The quotient of the effective maintenance times of the current reference meter box and the preset continuous batches is calculated to generate a dynamic weight value.

[0025] Furthermore, the generating of the substation branch topology result according to the final meter box relationship matrix includes:

[0026] Performing denoising on the final table-box relationship matrix to generate a denoised table-box relationship matrix;

[0027] Search and access the meter box relationship matrix after noise reduction, and output the branch topology structure results of the substation area.

[0028] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0029] An embodiment of the present invention provides a low-voltage substation branch topology identification device based on dynamic weight value optimization, including: a data acquisition module, a matrix generation module and a topology structure generation module.

[0030] The data acquisition module is used to obtain the reporting information of preset continuous batches of the area to be analyzed and the initial meter-box relationship matrix.

[0031] The matrix generation module is used to repeatedly perform meter box relationship matrix maintenance operations until the sum of the effective maintenance times of all meter boxes reaches a preset maintenance time, thereby generating a final meter box relationship matrix. The meter box relationship matrix maintenance operation includes: obtaining current reporting information; wherein the initial reporting information is the earliest batch reporting information that has not been processed; calculating the current change value and voltage change value corresponding to each meter box at the current sampling time point; if there is only one meter box whose current change value is greater than the preset current threshold, setting the meter box whose current change value is greater than the current threshold as the reference meter box, and setting the remaining meter boxes as target meter boxes; calculating the voltage threshold according to the voltage change value of the corresponding reference meter box; comparing each corresponding target meter box with the voltage threshold; taking the target meter box whose voltage change value is greater than the voltage threshold as the meter box to be updated; updating the corresponding elements of the meter box to be updated in the meter box relationship matrix according to the dynamic weight value, and adding 1 to the effective maintenance number of the reference meter box; after determining that the effective maintenance number of all meter boxes does not reach the preset maintenance number, judging whether the current sampling time point is the last sampling time point of the current reporting information; if so, reselecting the earliest batch reporting information that has not been processed to update the current reporting information; if not, selecting the next sampling time point to update the current sampling time point.

[0032] The topology structure generation module is used to generate a substation branch topology structure result according to the final meter box relationship matrix.

[0033] Furthermore, the data acquisition module generates an initial table-box relationship matrix in the following way:

[0034] Get the number of meter boxes in the area to be analyzed;

[0035] According to the number of meter boxes in the area to be analyzed, a meter box relationship matrix with the number of rows and columns equal to the number of meter boxes is generated; wherein each row and each column in the matrix corresponds to a meter box, respectively, to represent the association relationship between the meter box and other meter boxes.

[0036] Furthermore, the matrix maintenance module calculates the current change value and voltage change value corresponding to each meter box at the current sampling time point, including:

[0037] According to the current reporting information, the difference between the current value corresponding to the current sampling time point of each meter box and the current value corresponding to the previous sampling time point is calculated to obtain the current change value corresponding to each meter box.

[0038] According to the current reporting information, the difference between the voltage value corresponding to the current sampling time point of each meter box and the voltage value corresponding to the previous sampling time point is calculated to obtain the voltage change value corresponding to each meter box.

[0039] Furthermore, the topology structure generation module includes: a noise reduction processing unit and a topology structure output unit;

[0040] The noise reduction processing unit is used to perform noise reduction processing on the final meter-box relationship matrix to generate a noise-reduced meter-box relationship matrix.

[0041] The topology structure output unit is used to search and access the meter box relationship matrix after noise reduction, and output the station area branch topology structure result.

[0042] Based on the above method embodiment, the present invention provides a corresponding electronic device embodiment.

[0043] An embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the low-voltage substation branch topology identification method based on dynamic weight value optimization as described in any one of the above method embodiments can be implemented.

[0044] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.

[0045] An embodiment of the present invention provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for identifying low-voltage substation branch topology based on dynamic weight value optimization as described in any one of the above method embodiments can be implemented.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The embodiment of the present invention provides a low-voltage substation branch topology identification method, device, electronic device and storage medium based on dynamic weight value optimization. The method selects the earliest batch of reported information that has not been processed as the current processing object, and calculates the current and voltage change values ​​of each meter box. If the current change value of a meter box exceeds the preset threshold, while other meter boxes do not exceed it, the meter box is marked as a maintenance node and set as a reference meter box, and the remaining meter boxes are set as target meter boxes. The corresponding voltage threshold is calculated according to the voltage change value of the reference meter box. If the voltage change value of the target meter box exceeds the threshold, the dynamic weight of the corresponding element in the meter box relationship matrix is ​​increased, and an effective maintenance is recorded. The maintenance operation of the meter box relationship matrix is ​​continued until the sum of the effective maintenance times of all meter boxes reaches the predetermined requirements, and the final meter box relationship matrix is ​​generated. Finally, based on the final meter box relationship matrix, the branch topology structure of the substation is generated.

[0048] The present invention maintains the meter box relationship matrix through dynamic weight values, and infers whether the target meter box and the reference meter box have a similar topological relationship by comparing the voltage change value of the target meter box with the voltage change value of the reference meter box. Then, the weight of the target meter box is dynamically adjusted according to the effective maintenance times of the meter box to adapt to the dynamic changes of the current and voltage in the low-voltage substation, thereby enhancing the robustness and accuracy of the low-voltage substation branch topological relationship identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of a low-voltage substation branch topology identification method based on dynamic weight value optimization provided by an embodiment of the present invention.

[0050] Figure 2 It is a flowchart of a meter box relationship matrix maintenance operation provided by an embodiment of the present invention.

[0051] Figure 3 It is a structural schematic diagram of a low-voltage area branch topology identification device based on dynamic weight value optimization provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] like Figure 1 As shown, an embodiment of the present invention provides a low voltage area branch topology identification method based on dynamic weight value optimization, which at least includes the following steps:

[0054] Step S1, obtaining the reporting information of preset continuous batches of the area to be analyzed and the initial meter-box relationship matrix;

[0055] It should be noted here that each batch of reported information contains the current and voltage values ​​of all meter boxes collected at a preset sampling frequency. Each batch of reported information uses a time period of the same length as the sampling interval, and obtains samples at the same sampling frequency in each time period. For example, if the sampling time period is one hour and the sampling frequency is 20 minutes, then in one embodiment, sampling can be performed in time periods such as 0 to 1 hour, 1 to 2 hours, etc. According to the sampling frequency of once every 20 minutes, the current and voltage values ​​of the meter boxes at 0:20, 0:40, 1:00, etc. can be obtained.

[0056] Specifically, the number of rows and columns of the meter box relationship matrix is ​​equal to the number of meter boxes, and each row and column in the matrix corresponds to a meter box, which is used to represent the relationship between the meter box and other meter boxes; the meter box relationship matrix is ​​a zero matrix initially. By continuously maintaining the meter box relationship matrix, the branch topology structure of the low-voltage substation can be output according to the final meter box relationship matrix.

[0057] Step S2: Repeat the meter-box relationship matrix maintenance operation until the total number of effective maintenance times of all meter boxes reaches a preset maintenance time, and generate a final meter-box relationship matrix.

[0058] like Figure 2 As shown, in one embodiment of the present invention, the meter box relationship matrix maintenance operation includes at least the following steps:

[0059] Step S2.1, obtaining current reporting information;

[0060] Specifically, the initial reporting information is the earliest batch of unprocessed reporting information, wherein the reporting information includes the current values ​​and voltage values ​​of all meter boxes collected at a preset sampling frequency.

[0061] Step S2.2: Calculate the current change value and voltage change value corresponding to each meter box at the current sampling time point.

[0062] In actual operation, the calculation of the current change value and voltage change value corresponding to each meter box at the current sampling time point includes:

[0063] According to the current reporting information, the difference between the current value corresponding to the current sampling time point of each meter box and the current value corresponding to the previous sampling time point is calculated to obtain the current change value corresponding to each meter box.

[0064] According to the current reporting information, the difference between the voltage value corresponding to the current sampling time point of each meter box and the voltage value corresponding to the previous sampling time point is calculated to obtain the voltage change value corresponding to each meter box.

[0065] Preferably, the dynamic weight value is generated by:

[0066] Get the effective maintenance times of the current benchmark meter box;

[0067] The quotient of the effective maintenance times of the current reference meter box and the preset continuous batches is calculated to generate a dynamic weight value.

[0068] According to the calculation of the current sampling time point and the previous sampling time point, the current change value and voltage change value of each meter box at the current sampling time point can be obtained. It should be particularly noted that the present invention uses these change values ​​to determine the correlation between meter boxes. However, since it is impossible to obtain the data of the previous sampling time point of the first sampling point, in order to avoid adverse effects on the implementation of the scheme of the present invention, in all embodiments, the current change value and voltage change value of each meter box at the first sampling time point are defaulted to zero.

[0069] Step S2.3: If there is only one meter box whose current change value is greater than the preset current threshold, the meter box whose current change value is greater than the current threshold is set as the reference meter box, and the remaining meter boxes are set as target meter boxes.

[0070] In actual operation, the preset current threshold can be selected according to the actual situation, and the recommended value 0.5A can be selected here. Traverse all sampling time points. If there is only one meter box with a current change value greater than the preset current threshold, the meter box with a current change value greater than the current threshold is set as the reference meter box, and the remaining meter boxes are set as target meter boxes. The voltage change value of the reference meter box will serve as an important judgment basis for the subsequent target meter box to maintain the meter box relationship matrix.

[0071] Step S2.4, calculating a voltage threshold value according to the voltage change value of the corresponding reference meter box; comparing each corresponding target meter box with the voltage threshold value.

[0072] In a specific implementation, the product of the voltage change value of the reference meter box and the preset adjustment factor is calculated to generate a voltage threshold value: wherein the preset adjustment factor can be selected according to actual conditions.

[0073] Step S2.5, taking the target meter box whose voltage change value is greater than the voltage threshold as the meter box to be updated; updating the corresponding element of the meter box to be updated in the meter box relationship matrix according to the dynamic weight value, and adding 1 to the effective maintenance times of the reference meter box;

[0074] In a preferred embodiment, the dynamic weight value is calculated and generated by the ratio of the effective maintenance times of the reference meter box to the preset continuous batch. The corresponding elements of the meter box to be updated in the meter box relationship matrix are updated according to the dynamic weight value, and the effective maintenance times of the reference meter box are increased by 1. For example, there are target meter box A and reference meter box B. The target meter box A is the meter box to be updated at this time. The corresponding elements in the meter box relationship matrix need to be updated according to the dynamic weight value. First, the corresponding dynamic weight value is calculated and generated according to the ratio of the effective maintenance times of the reference meter box B at this time to the preset continuous batch. Then, the dynamic weight value is added to the element value corresponding to the row where the target meter box A is located and the column where the reference meter box B is located in the meter box relationship matrix to generate the updated element value. And the effective maintenance times of the reference meter box B are increased by 1 to complete the update of the meter box relationship matrix this time. After continuous updating of the meter box relationship matrix, the meter box relationship matrix that characterizes the connection relationship of each meter box will eventually be obtained. A method similar to the method of outputting the node information of the adjacency relationship matrix can be used to obtain the direct connection status of each meter box. According to the connection status, the branch topology of the meter box can be generated.

[0075] Step S2.6: After determining that the effective maintenance times of all meter boxes have not reached the preset maintenance times, determine whether the current sampling time point is the last sampling time point of the current reporting information; if so, reselect the earliest batch of reporting information that has not been processed and update the current reporting information; if not, select the next sampling time point to update the current sampling time point.

[0076] In actual operation, the preset maintenance times can be selected according to actual conditions. If the effective maintenance times of all meter boxes do not reach the preset maintenance times, it is further determined whether the current sampling time point is the last sampling time point of the current reporting information. If so, the current reporting information has been processed, and the earliest batch of reported information that has not been processed is reselected to update the current reporting information and continue to update and maintain the meter box relationship matrix; if not, the next sampling time point is reselected to update the current sampling time point and continue to update the meter box relationship matrix.

[0077] Step S3: Generate the substation branch topology structure result according to the final meter box relationship matrix.

[0078] The final meter box relationship matrix can be compared to the adjacency relationship matrix, which records the connection relationship between each meter box and other meter boxes. Each row and each column in the matrix corresponds to a meter box, which is used to represent the association relationship between the meter box and other meter boxes. In an optional embodiment, the generation of the substation branch topology structure result according to the final meter box relationship matrix includes:

[0079] Performing denoising on the final table-box relationship matrix to generate a denoised table-box relationship matrix;

[0080] Search and access the meter box relationship matrix after noise reduction, and output the branch topology structure results of the substation area.

[0081] In a specific implementation, the noise reduction process includes:

[0082] According to the element values ​​of the table-box relationship matrix, the average value of the element values ​​of the table-box relationship matrix is ​​calculated;

[0083] Calculate the average value of the matrix element values ​​and multiply it by a preset ratio to generate a noise reduction reference value;

[0084] Set the elements in the meter-box relationship matrix whose values ​​are less than the noise reduction reference value to zero, and then search and access the matrix elements after noise reduction, and the accessed nodes are in the same branch. When this search and access to a certain path is completed, start searching and accessing other nodes, and assign them to the next branch, and then obtain the meter-box branch relationship of the substation to be analyzed.

[0085] According to the meter box branch relationship of the substation to be analyzed, the substation branch topology structure results are output.

[0086] In a specific implementation, the search access may use a depth-first search algorithm to traverse the table-box relationship matrix and output the connection status of each node. The preset proportional product may be selected according to actual conditions, and a recommended value of 10% may be selected here.

[0087] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0088] like Figure 3 As shown, an embodiment of the present invention provides a low-voltage substation branch topology identification device based on dynamic weight value optimization, including: a data acquisition module 101, a matrix generation module 102 and a topology structure generation module 103.

[0089] The data acquisition module 101 is used to acquire the reporting information of preset continuous batches of the area to be analyzed and the initial meter-box relationship matrix;

[0090] The matrix generation module 102 is used to repeatedly perform the meter box relationship matrix maintenance operation until the total effective maintenance times of all meter boxes reaches the preset maintenance times, and generate the final meter box relationship matrix; wherein, the meter box relationship matrix maintenance operation includes: obtaining the current reporting information; wherein the initial reporting information is the earliest batch reporting information that has not been processed; calculating the current change value and voltage change value corresponding to each meter box at the current sampling time point; if there is only one meter box whose current change value is greater than the preset current threshold, the meter box whose current change value is greater than the current threshold is set as the reference meter box, and the remaining meter boxes are set as the target meter boxes; according to the current change value of the corresponding reference meter box, The voltage change value is used to calculate the voltage threshold; each corresponding target meter box is compared with the voltage threshold; the target meter box whose voltage change value is greater than the voltage threshold is used as the meter box to be updated; the corresponding element of the meter box to be updated in the meter box relationship matrix is ​​updated according to the dynamic weight value, and the effective maintenance number of the benchmark meter box is increased by 1; after determining that the effective maintenance number of all meter boxes has not reached the preset maintenance number, it is determined whether the current sampling time point is the last sampling time point of the current reporting information; if so, the earliest batch of reported information that has not been processed is reselected to update the current reporting information; if not, the next sampling time point is selected to update the current sampling time point;

[0091] The topology structure generating module 103 is used to generate a substation branch topology structure result according to the final meter box relationship matrix.

[0092] In an optional embodiment, the topology structure generating module 103 includes: a noise reduction processing unit 1031 and a topology structure output unit 1032;

[0093] The noise reduction processing unit 1031 is used to perform noise reduction processing on the final meter-box relationship matrix to generate a noise-reduced meter-box relationship matrix;

[0094] The topology structure output unit 1032 is used to search and access the meter box relationship matrix after noise reduction, and output the station area branch topology structure result.

[0095] It should be noted that the embodiments of the device described above correspond to the above embodiments of the present invention, and can implement any of the methods described above in the present invention. In addition, the embodiments of the above-mentioned device are merely schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0096] Based on the above method embodiment of the present invention, a corresponding electronic device embodiment is provided.

[0097] An embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the low-voltage substation branch topology identification method based on dynamic weight value optimization as described in any one of the present invention, or, when the processor executes the computer program, it implements the functions of each module in the above-mentioned device embodiments.

[0098] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0099] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0100] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0101] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0102] Based on the above method embodiment, the present invention provides a storage medium embodiment;

[0103] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute any one of the low-voltage substation branch topology identification methods based on dynamic weight value optimization of the present invention.

[0104] The storage medium is a computer-readable storage medium, and the computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0105] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0106] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A low voltage station branch topology identification method based on dynamic weight value optimization, characterized in that: include: Obtaining preset continuous batches of reporting information of the area to be analyzed and an initial meter box relationship matrix; wherein each batch of reporting information includes current values ​​and voltage values ​​of all meter boxes collected at a preset sampling frequency; Repeat the meter box relationship matrix maintenance operation until the total effective maintenance times of all meter boxes reaches the preset maintenance times, and generate the final meter box relationship matrix; Generate the substation branch topology structure result according to the final meter box relationship matrix; The table-box relationship matrix maintenance operation includes: Get the current reporting information; the initial reporting information is the earliest batch of reporting information that has not been processed; Calculate the current change value and voltage change value corresponding to each meter box at the current sampling time point; If there is only one meter box whose current change value is greater than the preset current threshold, the meter box whose current change value is greater than the current threshold is set as the reference meter box, and the remaining meter boxes are set as target meter boxes; Calculate the voltage threshold value according to the voltage change value of the corresponding reference meter box; compare each corresponding target meter box with the voltage threshold value; The target meter box whose voltage change value is greater than the voltage threshold is regarded as the meter box to be updated; the corresponding element of the meter box to be updated in the meter box relationship matrix is ​​updated according to the dynamic weight value, and the effective maintenance times of the reference meter box are increased by 1; After determining that the effective maintenance times of all meter boxes have not reached the preset maintenance times, determine whether the current sampling time point is the last sampling time point of the current reporting information; if so, reselect the earliest batch of reporting information that has not been processed and update the current reporting information; if not, select the next sampling time point to update the current sampling time point.

2. The low voltage area branch topology identification method based on dynamic weight value optimization according to claim 1, characterized in that: Generate the initial table-box relationship matrix in the following way: Get the number of meter boxes in the area to be analyzed; According to the number of meter boxes in the area to be analyzed, a meter box relationship matrix with the number of rows and columns equal to the number of meter boxes is generated; wherein each row and each column in the matrix corresponds to a meter box, respectively, to represent the association relationship between the meter box and other meter boxes.

3. The low voltage area branch topology identification method based on dynamic weight value optimization according to claim 1, characterized in that: The calculation of the current change value and the voltage change value corresponding to each meter box at the current sampling time point includes: According to the current reporting information, the difference between the current value corresponding to the current sampling time point of each meter box and the current value corresponding to the previous sampling time point is calculated to obtain the current change value corresponding to each meter box; According to the current reporting information, the difference between the voltage value corresponding to the current sampling time point of each meter box and the voltage value corresponding to the previous sampling time point is calculated to obtain the voltage change value corresponding to each meter box.

4. The low voltage area branch topology identification method based on dynamic weight value optimization according to claim 1, characterized in that: Dynamic weight values ​​are generated in the following ways: Get the effective maintenance times of the current benchmark meter box; The quotient of the effective maintenance times of the current reference meter box and the preset continuous batches is calculated to generate a dynamic weight value.

5. The low voltage area branch topology identification method based on dynamic weight value optimization according to claim 1, characterized in that: The generating of the substation branch topology structure result according to the final meter box relationship matrix includes: Performing denoising on the final table-box relationship matrix to generate a denoised table-box relationship matrix; Search and access the meter box relationship matrix after noise reduction, and output the branch topology structure results of the substation area.

6. A low voltage area branch topology identification device based on dynamic weight value optimization, characterized in that: include: Data acquisition module, matrix generation module and topology structure generation module; The data acquisition module is used to obtain the reporting information of preset continuous batches of the area to be analyzed and the initial meter-box relationship matrix; The matrix generation module is used to repeatedly perform the meter box relationship matrix maintenance operation until the total number of effective maintenance times of all meter boxes reaches the preset maintenance times, and the final meter box relationship matrix is ​​generated; wherein, the meter box relationship matrix maintenance operation includes: obtaining the current reporting information; wherein the initial reporting information is the earliest batch reporting information that has not been processed; calculating the current change value and voltage change value corresponding to each meter box at the current sampling time point; if there is only one meter box whose current change value is greater than the preset current threshold, the meter box whose current change value is greater than the current threshold is set as the reference meter box, and the remaining meter boxes are set as the target meter boxes; according to the voltage of the corresponding reference meter box The voltage threshold is calculated based on the change value; each corresponding target meter box is compared with the voltage threshold; the target meter box with a voltage change value greater than the voltage threshold is used as the meter box to be updated; the corresponding element of the meter box to be updated in the meter box relationship matrix is ​​updated according to the dynamic weight value, and the effective maintenance number of the benchmark meter box is increased by 1; after determining that the effective maintenance number of all meter boxes has not reached the preset maintenance number, it is determined whether the current sampling time point is the last sampling time point of the current reporting information; if so, the earliest batch of reported information that has not been processed is reselected to update the current reporting information; if not, the next sampling time point is selected to update the current sampling time point; The topology structure generation module is used to generate a substation branch topology structure result according to the final meter box relationship matrix.

7. The low voltage area branch topology identification device based on dynamic weight value optimization according to claim 5, characterized in that: The matrix maintenance module calculates the current change value and voltage change value corresponding to each meter box at the current sampling time point, including: According to the current reporting information, the difference between the current value corresponding to the current sampling time point of each meter box and the current value corresponding to the previous sampling time point is calculated to obtain the current change value corresponding to each meter box; According to the current reporting information, the difference between the voltage value corresponding to the current sampling time point of each meter box and the voltage value corresponding to the previous sampling time point is calculated to obtain the voltage change value corresponding to each meter box.

8. The low voltage area branch topology identification device based on dynamic weight value optimization according to claim 5, characterized in that: The topology structure generation module includes: a noise reduction processing unit and a topology structure output unit; The noise reduction processing unit is used to perform noise reduction processing on the final meter-box relationship matrix to generate a noise-reduced meter-box relationship matrix; The topology structure output unit is used to search and access the meter box relationship matrix after noise reduction, and output the station area branch topology structure result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it can implement the low-voltage substation branch topology identification method based on dynamic weight value optimization as described in any one of claims 1 to 5.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it can implement the low-voltage substation branch topology identification method based on dynamic weight value optimization as described in any one of claims 1 to 5.

Images