Power distribution network topology identification method and system based on neural network

Abstract

This invention provides a distribution network topology identification method and system based on neural networks. First, it acquires the first topology of the target distribution network at the previous time step and the SCADA measurement information at the current time step. The SCADA measurement information includes node power, node voltage amplitude, and switching signals. Based on the first topology and the switching signals, a second topology of the target distribution network is determined. Then, based on the node power and the node voltage amplitude, the second topology of the target distribution network is corrected to obtain a third topology. This invention first estimates the second topology of the distribution network simply based on the switching signals in the SCADA measurement information, and then corrects it based on node power and voltage amplitude. This eliminates the need for multiple power flow calculations, resulting in high efficiency in distribution network topology estimation.

Description

Technical Field

[0001] This invention belongs to the field of power system operation and management technology, and in particular relates to a distribution network topology identification method and system based on neural networks. Background Technology

[0002] Numerous distributed power sources, electric vehicle charging stations, and energy storage systems are being connected to the distribution network in a distributed manner, flexibly and decentralizedly realizing the input and output of electrical energy. To meet the increasingly complex power transmission and distribution needs of the distribution network system, timely and accurate acquisition of the real-time status of the distribution network is crucial.

[0003] In existing technologies, SCADA (Supervisory Control and Data Acquisition) is commonly used for topology identification of distribution networks. SCADA has a wide range of applications, mature technology, and occupies an important position in power system applications. Typically, identifying a distribution network requires first inferring its possible topology, and then performing power flow calculations for each topology. For power grids with a large number of distributed generation sources, the power flow distribution is complex and difficult to calculate. Moreover, the larger the distribution network, the greater the time and computational load required for power flow calculations, resulting in low efficiency in distribution network topology estimation. Summary of the Invention

[0004] In view of this, the present invention provides a distribution network topology identification method and system based on neural networks, aiming to solve the problem of low efficiency in the prior art for distribution network topology estimation.

[0005] A first aspect of this invention provides a distribution network topology identification method based on a neural network, comprising:

[0006] Obtain the first topology of the target distribution network at the previous moment, and obtain the SCADA measurement information at the current moment; wherein, the SCADA measurement information includes: node power, node voltage amplitude and switching quantity;

[0007] Based on the first topology and the switching quantities, determine the second topology of the target distribution network;

[0008] Based on the node power and node voltage amplitude, the second topology of the target distribution network is modified to obtain the third topology.

[0009] A second aspect of this invention provides a distribution network topology identification device based on a neural network, comprising:

[0010] The acquisition module is used to acquire the first topology of the target distribution network at the previous moment, and to acquire the SCADA measurement information at the current moment; wherein, the SCADA measurement information includes: node power, node voltage amplitude and switching quantity;

[0011] The determination module is used to determine the second topology of the target distribution network based on the first topology and the switching quantity;

[0012] The correction module is used to correct the second topology of the target distribution network based on the node power and node voltage amplitude to obtain the third topology.

[0013] A third aspect 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, wherein the processor executes the computer program to implement the steps of the neural network-based power distribution network topology identification method of the first aspect above.

[0014] A fourth aspect of the present invention provides a topology identification system, including: a SCADA measurement device and an electronic device as described in the third aspect above.

[0015] A fifth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the neural network-based distribution network topology identification method of the first aspect above.

[0016] The distribution network topology identification method and system based on neural networks provided in this invention first acquires the first topology of the target distribution network at the previous time step and acquires the SCADA measurement information at the current time step. The SCADA measurement information includes node power, node voltage amplitude, and switching signals. Based on the first topology and the switching signals, a second topology of the target distribution network is determined. Based on the node power and node voltage amplitude, the second topology of the target distribution network is corrected to obtain a third topology. This invention first estimates the second topology of the distribution network simply based on the switching signals in the SCADA measurement information, and then corrects it based on node power and voltage amplitude. This eliminates the need for multiple power flow calculations, resulting in high efficiency in distribution network topology estimation. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1This is a schematic diagram of the topology identification system provided in an embodiment of the present invention;

[0019] Figure 2 This is a flowchart illustrating the implementation of the neural network-based distribution network topology identification method provided in this embodiment of the invention.

[0020] Figure 3 This is a schematic diagram of the structure of the distribution network topology identification device based on neural networks provided in an embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0023] Figure 1 This is a schematic diagram of the topology identification system provided in an embodiment of the present invention. Figure 1 As shown, in some embodiments, the topology identification system includes SCADA measurement equipment 11 and electronic equipment 12 as described in the third aspect above.

[0024] SCADA measurement equipment 11 collects SCADA measurement data via RTU, specifically including node injected power, branch power, node voltage amplitude, branch current amplitude, and switching quantities. SCADA measurement equipment 13 is typically installed in feeder switches, distribution transformer outlets, and open-loop control cabinets. Electronic equipment 14 can be a terminal or a server; the terminal can be a computer in a power management or dispatch center, and the server can be a physical server or a cloud server, without limitation.

[0025] Figure 2 This is a flowchart illustrating the implementation of the neural network-based distribution network topology identification method provided in this embodiment of the invention. Figure 2 As shown, in some embodiments, the distribution network topology identification method based on neural networks is applied to... Figure 1 The electronic device shown, the method includes:

[0026] S210: Obtain the first topology of the target distribution network at the previous moment, and obtain the SCADA measurement information at the current moment; wherein, the SCADA measurement information includes: node power, node voltage amplitude and switching quantity;

[0027] In this embodiment of the invention, when the load or distributed energy in the distribution network is not connected to / disconnected from the network, the topology of the distribution network is known, namely the first topology mentioned above. After a connection / disconnection event occurs at a certain moment, the topology of the distribution network changes. In order to ensure the operation of the distribution network, the topology needs to be re-identified.

[0028] In this embodiment of the invention, SCADA is an important subsystem in the energy management system of the power distribution network, with high coverage. Its sampling period is between 2 and 10 seconds.

[0029] S220, determine the second topology of the target distribution network based on the first topology and the switching quantity.

[0030] In this embodiment of the invention, the second topology can be obtained by directly connecting / disconnecting branches in the first topology based on the switching signals. Since SCADA measurement equipment is installed on feeder switches, distribution transformer outlets, and open-loop cabinets, its switching signals can reflect the on / off status of these nodes. However, SCADA measurement equipment does not cover all nodes and there are instances of false alarms. Therefore, the second topology needs to be corrected to identify the true distribution network topology.

[0031] Traditional methods use specific power, voltage, and other data to predict multiple possible topologies, and then perform power flow calculations for each topology. This approach is typically only suitable for small, radial distribution networks, and its performance is poor for multidirectional power flow and large-scale distribution networks due to excessive computational demands.

[0032] After obtaining the second topology, the present invention can achieve topology identification of the distribution network through the following steps:

[0033] S230, based on the node power and node voltage amplitude, corrects the second topology of the target distribution network to obtain the third topology.

[0034] In some embodiments, S230 may include: dividing the second topology according to preset key nodes to obtain multiple branches to be corrected; performing power flow calculation on the second topology based on node power and node voltage amplitude to obtain the voltage calculation value and power calculation value of each node in each branch to be corrected; for each branch to be corrected, determining the first similarity matrix of the branch to be corrected based on the power calculation value and node power; determining the topology change information of the branch to be corrected based on the first similarity matrix, voltage calculation value and power calculation value of each branch to be corrected, and correcting the second topology to obtain a third topology.

[0035] In this embodiment of the invention, the preset critical nodes are any number of nodes in the power grid, specifically set by expert experience, and are not limited here. Multiple SCADA measurement devices can be redundantly configured in the critical nodes, and the average value of the data collected by each device is used as the value to ensure the validity of the critical node data. Each critical node and all its downstream nodes form a branch to be corrected.

[0036] This invention also requires power flow calculation, but unlike the prior art, this invention only performs power flow calculation on a second topology. After multiple iterations, the voltage and power calculation values ​​of each node are obtained.

[0037] At this point, it is necessary to calculate the first similarity matrix based on the node power measured by the SCADA measurement equipment of the key nodes and the calculated power value, so as to reflect the deviation between the second topology and the actual topology.

[0038] The expression for the first similarity matrix L is:

[0039]

[0040] Among them, P ai P represents the active power component of the node power of the i-th node. bi Q is the calculated active power value of the i-th node. ai Q is the reactive component of the node power of the i-th node. bi The power calculation value of the reactive power of the i-th node, where N is the total number of nodes in the branch to be corrected.

[0041] Although SCADA measurement devices have a high coverage rate, they are not present in all nodes of the power grid. For nodes without SCADA measurement devices, linear interpolation can be performed based on the node power of adjacent upstream and downstream nodes. If SCADA measurement devices are not installed in both upstream and downstream nodes, the node power of that point is set to a specified value, where the specified value is the sum of the calculated power value of the node and the target mean, and the target mean is the average difference between the node power of nodes with SCADA measurement devices and the calculated power value of the node.

[0042] In some embodiments, for each branch to be corrected, determining the first similarity matrix of the branch to be corrected based on the calculated power value and the node power includes: calculating a power deviation matrix based on the calculated power value and the node power; and normalizing the power deviation matrix to obtain the first similarity matrix.

[0043] In some embodiments, determining the topology change information of the branch to be corrected based on the first similarity matrix, the calculated voltage value, and the calculated power value of each branch to be corrected includes: if the mean value of each element of the first similarity matrix is ​​less than a preset threshold, the branch to be corrected remains unchanged; if the mean value of each element of the first similarity matrix is ​​greater than or equal to the preset threshold, the topology change information of the branch to be corrected is determined based on the calculated node voltage value and the calculated power value of each node of the branch to be corrected.

[0044] In this embodiment of the invention, when the mean value of the first similarity is small, it can be considered that the structure of the branch in the second topology is the same as the branch structure of the actual topology, and the resulting deviation is a measurement deviation and a power flow calculation error. However, when the mean value of the first similarity is large, it indicates that the structure of the branch in the second topology differs significantly from the branch structure of the actual topology, and the branch needs to be corrected.

[0045] In some embodiments, determining the topology change information of the branch to be corrected based on the calculated voltage and power values ​​of each node of the branch to be corrected includes: obtaining adjacent nodes in the branch to be corrected; determining the impedance matrix corresponding to the adjacent nodes based on the difference in the calculated voltage values ​​of the adjacent nodes; determining the topology change information of the branch to be corrected based on the impedance matrix corresponding to the adjacent nodes; and determining the impedance matrix corresponding to the adjacent nodes based on the difference in the calculated voltage values ​​of the adjacent nodes, including:

[0046]

[0047] Wherein, U1 is the calculated voltage value of the first node among two adjacent nodes, U2 is the calculated voltage value of the second node among two adjacent nodes, P1 is the difference in calculated active power between the first node and the critical node, P2 is the difference in calculated active power between the second node and the critical node, Q1 is the difference in calculated reactive power between the first node and the critical node, Q2 is the difference in calculated reactive power between the second node and the critical node, R1 is the resistance between the first node and the critical node, R2 is the resistance between the second node and the critical node, X1 is the reactance between the first node and the critical node, X2 is the reactance between the second node and the critical node, λ1 and λ2 are preset coefficients, m1 is the active power corresponding value of the first node in the first similarity matrix, m2 is the active power corresponding value of the second node in the first similarity matrix, n1 is the reactive power corresponding value of the first node in the first similarity matrix, and n2 is the reactive power corresponding value of the second node in the first similarity matrix.

[0048] In this embodiment of the invention, let the key node on the branch be U0. The nodes under the key node are combined to obtain multiple adjacent node groups, where each node can exist in different adjacent node groups simultaneously. For example, downstream of node 1 are nodes 11 and 12, and downstream of node 11 are nodes 111, 112, and 113. For node 11, its only adjacent node is node 12, while for node 111, its adjacent nodes are either node 112 or node 113.

[0049] The critical node is the upstream node shared by two adjacent nodes in an adjacent node group. Since the two nodes are adjacent, the impedance values ​​of the two nodes relative to the critical node are not significantly different, and the voltage difference between the two points is:

[0050]

[0051] The calculated impedance values ​​R1, X1, R2, and X2 are used to determine the correctness of the topology. These impedance values ​​are derived from power flow calculations, which are based on a second topology. Since the second topology is not the actual distribution network topology, the calculated impedance values ​​are inaccurate. Furthermore, because SCADA measurement equipment does not cover all nodes, the data for some nodes is interpolated or specified, which is also inaccurate. Therefore, this invention utilizes the power calculation values ​​of each node and introduces elements from the first matrix along with preset coefficients λ1 and λ2 to ensure the accuracy of the calculated impedance values.

[0052] Taking the active power of the first node as an example, P1 represents the difference between the calculated active power values ​​of the first node and the critical node, while m1 is an element in the first similarity matrix, representing the deviation between the calculated and measured values ​​of the first node. For P1+λ1m1, it represents the power value obtained by correcting P1 based on m1, which can be considered close to the actual power. The same applies to m2, n1, n2, λ1, and λ2.

[0053] Because nodes influence each other, if the power of one node deviates from the actual value during power flow calculation, the power of other nodes will also deviate accordingly. For nodes equipped with SCADA measurement devices, the measured power value can be considered the actual value. Therefore, λ1 and λ2 of these nodes can be calculated. Then, the λ1 and λ2 of all nodes on the branch are initialized with the average of λ1 and λ2 of these nodes. Subsequently, the λ1 and λ2 corresponding to devices without SCADA installation are optimized. Specifically, the optimization process involves forming a first matrix from the λ1 and λ2 of key nodes, calculating the eigenvalues ​​of the first matrix, and simultaneously forming a second matrix from the λ1 and λ2 of all nodes, calculating the eigenvalues ​​of the second matrix. The objective is to minimize the difference between the eigenvalues ​​of the second matrix and the eigenvalues ​​of the first matrix. Under the constraints of the power grid physical structure, optimization is performed using a particle swarm optimization algorithm.

[0054] Since the voltage and power calculation values ​​are known, if λ1 and λ2 of all nodes are determined, R1, X1, R2, and X2 can be calculated. By comparing these values ​​with the R1, X1, R2, and X2 recorded for the two nodes in the branch in the second topology, it can be determined whether to add or remove nodes / load branches between the two nodes.

[0055] In some embodiments, determining the topology change information of the branch to be corrected based on the calculated voltage and power values ​​of each node of the branch to be corrected includes: obtaining adjacent nodes in the branch to be corrected; determining the impedance matrix corresponding to the adjacent nodes based on the difference in the calculated voltage values ​​of the adjacent nodes; determining the correction value of the calculated voltage values ​​in the branch to be corrected based on the impedance matrix, and jumping to the step of determining the impedance matrix corresponding to the adjacent nodes based on the difference in the calculated voltage values ​​of the adjacent nodes; if the difference between the correction value of the calculated voltage values ​​before the current iteration and the correction value of the calculated voltage values ​​before the previous iteration is less than a preset difference, then determining the topology change information of the branch to be corrected based on the impedance matrix corresponding to the current iteration.

[0056] In the previous embodiment, after calculating the impedance matrix, the topology of the power grid can be roughly estimated. The power flow calculation is then performed on this topology to obtain the correction value of the voltage calculation. If the calculated correction value differs significantly from the previous calculation value, the topology may still be inaccurate. Therefore, the impedance matrix is ​​recalculated based on the correction value as the new voltage calculation value. After repeated iterations, the final topology can be obtained.

[0057] In some embodiments, determining the topology change information of the branch to be corrected based on the voltage and power calculation values ​​of each node of the branch to be corrected includes: inputting the voltage calculation values, power calculation values, and a first similarity matrix of each node of the branch to be corrected into a pre-established neural network to determine the topology change information of the branch to be corrected.

[0058] In this embodiment of the invention, in addition to the two methods described above, the above process can also be implemented through a neural network.

[0059] In summary, the beneficial effects of the present invention are as follows:

[0060] 1. Based on the switching quantities in the SCADA measurement information, the second topology of the distribution network is simply estimated, and then corrected according to the node power and voltage amplitude. This eliminates the need for multiple power flow calculations and makes the distribution network topology estimation highly efficient.

[0061] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0062] Figure 3 This is a schematic diagram of the structure of a distribution network topology identification device based on a neural network provided in an embodiment of the present invention. Figure 3 As shown, in some embodiments, the distribution network topology identification device 3 based on neural networks includes:

[0063] The acquisition module 310 is used to acquire the first topology of the target distribution network at the previous moment and to acquire the SCADA measurement information at the current moment; wherein, the SCADA measurement information includes: node power, node voltage amplitude and switching quantity;

[0064] The determination module 320 is used to determine the second topology of the target distribution network based on the first topology and the switching quantity;

[0065] The correction module 330 is used to correct the second topology of the target distribution network based on the node power and node voltage amplitude to obtain the third topology.

[0066] Optionally, the correction module 330 is used to: divide the second topology according to preset key nodes to obtain multiple branches to be corrected; perform power flow calculation on the second topology based on node power and node voltage amplitude to obtain the voltage calculation value and power calculation value of each node in each branch to be corrected; for each branch to be corrected, determine the first similarity matrix of the branch to be corrected based on the power calculation value and node power; determine the topology change information of the branch to be corrected based on the first similarity matrix, voltage calculation value and power calculation value of each branch to be corrected, and correct the second topology to obtain the third topology.

[0067] Optionally, the correction module 330 is used to: if the mean value of each element of the first similarity matrix is ​​less than a preset threshold, then the branch to be corrected remains unchanged; if the mean value of each element of the first similarity matrix is ​​greater than or equal to the preset threshold, then the topology change information of the branch to be corrected is determined based on the node voltage calculation value and power calculation value of each node of the branch to be corrected.

[0068] Optionally, the correction module 330 is used to obtain the adjacent nodes in the branch to be corrected; determine the impedance matrix corresponding to the adjacent nodes based on the difference in the voltage calculation values ​​of the adjacent nodes; and determine the topology change information of the branch to be corrected based on the impedance matrix corresponding to the adjacent nodes.

[0069] Based on the difference in voltage calculations between adjacent nodes, determine the impedance matrix corresponding to the adjacent nodes, including:

[0070]

[0071] Wherein, U1 is the calculated voltage value of the first node among two adjacent nodes, U2 is the calculated voltage value of the second node among two adjacent nodes, P1 is the difference in the calculated active power between the first node and the critical node, P2 is the difference in the calculated active power between the second node and the critical node, Q1 is the difference in the calculated reactive power between the first node and the critical node, Q2 is the difference in the calculated reactive power between the second node and the critical node, R1 is the resistance between the first node and the critical node, R2 is the resistance between the second node and the critical node, X1 is the reactance between the first node and the critical node, X2 is the reactance between the second node and the critical node, λ1 and λ2 are random numbers between [0, 1], m1 is the corresponding active power value of the first node in the first similarity matrix, m2 is the corresponding active power value of the second node in the first similarity matrix, n1 is the corresponding reactive power value of the first node in the first similarity matrix, n2 is the corresponding reactive power value of the second node in the first similarity matrix.

[0072] Optionally, the correction module 330 is used to obtain adjacent nodes in the branch to be corrected; determine the impedance matrix corresponding to the adjacent nodes based on the difference between the voltage calculation values ​​of the adjacent nodes; determine the correction value of the voltage calculation value in the branch to be corrected based on the impedance matrix, and jump to the step of determining the impedance matrix corresponding to the adjacent nodes based on the difference between the voltage calculation values ​​of the adjacent nodes; if the difference between the correction value of the voltage calculation value before the current iteration and the correction value of the voltage calculation value before the previous iteration is less than a preset difference, then the topology change information of the branch to be corrected is determined based on the impedance matrix corresponding to the current iteration.

[0073] Optionally, the correction module 330 is used to input the voltage calculation value, power calculation value and the first similarity matrix of each node of the branch to be corrected into a pre-established neural network to determine the topology change information of the branch to be corrected.

[0074] Optionally, the correction module 330 is used to calculate the power deviation matrix based on the calculated power value and the node power; and to normalize the power deviation matrix to obtain the first similarity matrix.

[0075] The distribution network topology identification device based on neural networks provided in this embodiment can be used to execute the above method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0076] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. For example... Figure 4 As shown, an embodiment of the present invention provides an electronic device 4, which includes a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, it implements the steps described in the embodiments of the neural network-based distribution network topology identification method, for example... Figure 2 The steps shown. Alternatively, when processor 40 executes computer program 42, it implements the functions of each module / unit in the above system embodiments, for example... Figure 3 The functions of each module are shown.

[0077] For example, computer program 42 may be divided into one or more modules / units, one or more of which are stored in memory 41 and executed by processor 40 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 42 in electronic device 4.

[0078] Electronic device 4 may be a terminal or a server, and may include, but is not limited to, processor 40 and memory 41. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal may also include input / output devices, network access devices, buses, etc.

[0079] The processor 40 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0080] The memory 41 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM. The memory 41 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 41 can include both internal and external storage units of the electronic device 4. The memory 41 is used to store computer programs and other programs and data required by the terminal. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0081] This invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps described in the embodiments of the distribution network topology identification method based on neural networks.

[0082] A computer-readable storage medium stores a computer program 42. The computer program 42 includes program instructions. When executed by the processor 40, the program instructions implement all or part of the processes in the methods described in the above embodiments. The computer program 42 can also instruct related hardware to complete the process. The computer program 42 can be stored in a computer-readable storage medium. When executed by the processor 40, the computer program 42 can implement the steps of the various method embodiments described above. The computer program 42 includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0083] The computer-readable storage medium can be an internal storage unit of the terminal in any of the foregoing embodiments, such as the terminal's hard disk or memory. The computer-readable storage medium can also be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of the terminal. The computer-readable storage medium is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0084] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0085] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0086] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0087] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0088] In the embodiments provided by this invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0089] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0091] If an integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0092] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A distribution network topology identification method based on neural networks, characterized in that, include: The system obtains the first topology of the target distribution network at the previous moment and the SCADA measurement information at the current moment; wherein, the SCADA measurement information includes: node power, node voltage amplitude and switching quantity; Based on the first topology and the switching quantity, determine the second topology of the target distribution network; Based on the node power and the node voltage amplitude, the second topology of the target distribution network is modified to obtain the third topology; The step of modifying the second topology of the target distribution network based on the node power and the node voltage amplitude to obtain the third topology includes: The second topology is divided according to the preset key nodes, resulting in multiple branches to be corrected; Based on the node power and the node voltage amplitude, power flow calculation is performed on the second topology to obtain the calculated voltage and power values ​​of each node in each branch to be corrected. For each branch to be corrected, a first similarity matrix of the branch to be corrected is determined based on the calculated power value and the node power. Based on the first similarity matrix, voltage calculation value, and power calculation value of each branch to be corrected, the topology change information of the branch to be corrected is determined, the second topology is corrected, and the third topology is obtained.

2. The distribution network topology identification method based on neural networks according to claim 1, characterized in that, Based on the first similarity matrix, calculated voltage, and calculated power for each branch to be corrected, the topology change information of the branch to be corrected is determined, including: If the mean of each element in the first similarity matrix is ​​less than a preset threshold, the branch to be corrected remains unchanged. If the mean of each element in the first similarity matrix is ​​greater than or equal to a preset threshold, then the topology change information of the branch to be corrected is determined based on the calculated node voltage and power values ​​of each node in the branch to be corrected.

3. The distribution network topology identification method based on neural networks according to claim 2, characterized in that, Based on the calculated voltage and power values ​​of each node in the branch to be corrected, the topology change information of the branch to be corrected is determined, including: Obtain the adjacent nodes in the branch to be corrected; The impedance matrix corresponding to the adjacent nodes is determined based on the difference between the calculated voltage values ​​of the adjacent nodes. Based on the impedance matrix corresponding to the adjacent nodes, determine the topology change information of the branch to be corrected; Based on the difference in voltage calculations between adjacent nodes, determine the impedance matrix corresponding to the adjacent nodes, including: in, U 1 represents the calculated voltage value of the first node among two adjacent nodes. U 2 represents the calculated voltage value of the second node out of two adjacent nodes. P 1 represents the difference in calculated active power between the first node and the critical node. P 2 represents the difference in calculated active power between the second node and the critical node. Q 1 represents the difference in calculated reactive power between the first node and the critical node. Q 2 represents the difference in calculated reactive power between the second node and the critical node. R 1 represents the resistance between the first node and the critical node. R 2 represents the resistance between the second node and the critical node. X 1 represents the reactance between the first node and the critical node. X 2 represents the reactance between the second node and the critical node. λ 1 and λ 2 is a random number between [0, 1]. m 1 represents the active power value of the first node in the first similarity matrix. m 2 represents the active power value of the second node in the first similarity matrix. n 1 represents the reactive power value of the first node in the first similarity matrix. n 2 represents the reactive power value of the second node in the first similarity matrix.

4. The distribution network topology identification method based on neural networks according to claim 2, characterized in that, Based on the calculated voltage and power values ​​of each node in the branch to be corrected, the topology change information of the branch to be corrected is determined, including: Obtain the adjacent nodes in the branch to be corrected; The impedance matrix corresponding to the adjacent nodes is determined based on the difference between the calculated voltage values ​​of the adjacent nodes. Based on the impedance matrix, determine the correction value of the voltage calculation value in the branch to be corrected, and then proceed to the step of determining the impedance matrix corresponding to the adjacent node based on the difference of the voltage calculation values ​​of the adjacent node. If the difference between the corrected voltage calculation value before this iteration and the corrected voltage calculation value before the previous iteration is less than a preset difference, then the topology change information of the branch to be corrected is determined based on the impedance matrix corresponding to this iteration.

5. The distribution network topology identification method based on neural networks according to claim 2, characterized in that, Based on the calculated voltage and power values ​​of each node in the branch to be corrected, the topology change information of the branch to be corrected is determined, including: The calculated voltage and power values ​​of each node of the branch to be corrected, as well as the first similarity matrix, are input into a pre-established neural network to determine the topology change information of the branch to be corrected.

6. The distribution network topology identification method based on neural networks according to claim 1, characterized in that, For each branch to be corrected, a first similarity matrix is ​​determined based on the calculated power value and the node power, including: Calculate the power deviation matrix based on the calculated power value and the node power; The power deviation matrix is ​​normalized to obtain the first similarity matrix.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the neural network-based distribution network topology identification method as described in any one of claims 1 to 6.

8. A topology identification system, characterized in that, include: SCADA measurement equipment and the electronic equipment as described in claim 7 above.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the neural network-based distribution network topology identification method as described in any one of claims 1 to 6.

Images