Low-voltage transformer area topology structure identification method based on particle swarm algorithm and related device

Abstract

The application provides a low-voltage area topology structure identification method based on a particle swarm algorithm and a related device. The method comprises: obtaining an electrical parameter set of a target low-voltage area; determining a first particle swarm of the target low-voltage area; determining first fitness data of the first particle swarm according to the electrical parameter set; iteratively updating the first particle swarm according to the particle swarm algorithm and the first fitness data to obtain a second particle swarm; detecting and correcting the second particle swarm according to an error correction mechanism to obtain second fitness data; iteratively updating the second particle swarm according to the particle swarm algorithm and the second fitness data to obtain a third particle swarm; and determining the target topology structure according to a particle with the highest fitness in the third particle swarm. The particle swarm algorithm and the error correction mechanism can be combined to globally optimize and search and dynamically correct the topology structure of the target low-voltage area, thereby improving the accuracy of topology structure identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution automation, and in particular to a low-voltage transformer area topology structure identification method based on a particle swarm algorithm and related devices. BACKGROUND

[0002] In an intelligent power distribution automation system, accurate identification of the topology structure of a low-voltage transformer area is a crucial basic link. Dynamic changes in the topology structure of a low-voltage transformer area are directly related to the accuracy of load distribution analysis, the efficiency of fault location, and the scientific nature of power grid dispatching.

[0003] Current mainstream automatic identification methods have limitations: state estimation techniques based on topology inference are highly dependent on the density of measurement points and the quality of collected data, and when there is insufficient monitoring coverage or data bias, large errors can occur; network analysis methods based on graph theory can achieve structured topology analysis, but are strict in terms of the completeness and accuracy of initial connection data, and are difficult to quickly adapt to dynamic adjustments in transformer area topology; and clustering algorithms based on machine learning are often limited by the setting of initialization parameters and the constraint of local optimal solutions, resulting in certain deviations in the identification results and making it difficult to meet high-precision identification requirements.

[0004] Therefore, how to improve the accuracy of identifying the topology structure of a low-voltage transformer area needs to be addressed. SUMMARY

[0005] Embodiments of the present application provide a low-voltage transformer area topology structure identification method based on a particle swarm algorithm and related devices, which enhances the global nature and precision of identification through global optimization search of the particle swarm algorithm, improves topology rationality evaluation with fitness data, dynamically detects and corrects abnormalities and misjudgments with a correction mechanism to ensure stability, and continuously improves the identification process through iterative feedback to adapt to dynamic changes in the environment, thereby improving the accuracy of identifying the topology structure of a low-voltage transformer area.

[0006] In a first aspect, embodiments of the present application provide a low-voltage transformer area topology structure identification method based on a particle swarm algorithm, which includes:

[0007] Obtaining electrical parameters of each node in a target low-voltage transformer area to obtain a set of electrical parameters;

[0008] Determining a first particle swarm corresponding to the target low-voltage transformer area;

[0009] Determining first fitness data of the first particle swarm according to the set of electrical parameters;

[0010] Iteratively updating the first particle swarm according to a preset particle swarm algorithm and the first fitness data to obtain a second particle swarm;

[0011] detect and correct the second particle group according to a preset error correction mechanism, to obtain second fitness data;

[0012] iteratively update the second particle group according to the particle swarm algorithm and the second fitness data, to obtain a third particle group;

[0013] determine a particle with the highest fitness in the third particle group as a global optimal particle;

[0014] determine a target topology structure of the target low-voltage transformer area according to the global optimal particle.

[0015] In a second aspect, an embodiment of the present application provides a low-voltage transformer area topology structure identification device based on a particle swarm algorithm, the device comprising an acquisition module, a determination module, an update module, and an error correction module, wherein:

[0016] The acquisition module is configured to acquire electrical parameters of each node in a target low-voltage transformer area, to obtain an electrical parameter set.

[0017] The determination module is configured to determine a first particle group corresponding to the target low-voltage transformer area, and determine first fitness data of the first particle group according to the electrical parameter set.

[0018] The update module is configured to iteratively update the first particle group according to a preset particle swarm algorithm and the first fitness data, to obtain a second particle group.

[0019] The error correction module is configured to detect and correct the second particle group according to a preset error correction mechanism, to obtain second fitness data.

[0020] The update module is further configured to iteratively update the second particle group according to the particle swarm algorithm and the second fitness data, to obtain a third particle group.

[0021] The determination module is further configured to determine a particle with the highest fitness in the third particle group as a global optimal particle, and determine a target topology structure of the target low-voltage transformer area according to the global optimal particle.

[0022] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs comprise instructions for executing steps in any method of the first aspect of the embodiments of the present application.

[0023] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to perform some or all of the steps described in any of the methods of the first aspect of the embodiments of the present application.

[0024] In a fifth aspect, an embodiment of the present application provides a computer program product, which comprises a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps described in any of the methods of the first aspect of the embodiments of the present application. The computer program product can be a software installation package.

[0025] By implementing the embodiments of the present application, the global optimization search of the particle swarm algorithm can be used to enhance the globality and accuracy of identification, the fitness data can be used to improve the topological rationality evaluation, the error correction mechanism can be used to dynamically detect and correct the abnormality and misjudgment to ensure stability, and the iterative feedback can be used to continuously self-improve the identification process to adapt to the dynamic change environment, thereby improving the accuracy of identifying the topology structure of the low-voltage transformer area. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0027] Figure 1 is a system architecture diagram of a topology structure identification system of a low-voltage transformer area provided by an embodiment of the present application;

[0028] Figure 2 is a structural schematic diagram of an electronic device provided by an embodiment of the present application;

[0029] Figure 3 is an application scenario diagram of a topology structure identification system provided by an embodiment of the present application;

[0030] Figure 4 is a flowchart of a low-voltage transformer area topology structure identification method based on a particle swarm algorithm provided by an embodiment of the present application;

[0031] Figure 5 is a flowchart of determining a first particle swarm provided by an embodiment of the present application;

[0032] Figure 6 is a flowchart of iterative updating of a particle swarm provided by an embodiment of the present application;

[0033] Figure 7 is a structural schematic diagram of a target topology provided by an embodiment of the present application;

[0034] Figure 8 is a function module composition block diagram of a low-voltage transformer area topology identification device based on a particle swarm algorithm provided by an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0036] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish different objects, not to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product, or device.

[0037] It should be understood that the term "and / or" herein is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in this paper represents that the front and rear associated objects are a "or" relationship. The "multiple" in the embodiments of the present application means two or more than two.

[0038] The "at least one" or similar expressions in the embodiments of the present application means any combination of these items, including any combination of single item or multiple items, means one or more, and multiple means two or more than two. For example, at least one of a, b or c can mean the following seven cases: a, b, c, a and b, a and c, b and c, a, b and c. Among them, each of a, b and c can be an element or a set containing one or more elements.

[0039] The "connection" appearing in the embodiments of the present application means direct connection or indirect connection and various connection modes to realize communication between devices, which is not limited by the embodiments of the present application.

[0040] Reference to“an embodiment” herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase“in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all directed to the same embodiment, nor are they necessarily all mutually exclusive or alternative embodiments.

[0041] In the intelligent power distribution automation system, the accurate identification of the low-voltage transformer area topology structure is a crucial basic link. The dynamic change of the low-voltage transformer area topology structure is directly related to the accuracy of load distribution analysis, the efficiency of fault location, and the scientificity of power grid dispatching.

[0042] The current mainstream automatic identification methods have limitations: the state estimation technology based on topology inference is highly dependent on the layout density of the measurement points and the quality of the collected data, and when the monitoring coverage is insufficient or the data is biased, large errors are prone to occur; the network analysis method based on graph theory can realize structured topology analysis, but it is strict in the integrity and accuracy of the initial connection data, and it is difficult to quickly adapt to the dynamic adjustment of the transformer area topology; and the clustering algorithm based on machine learning is often limited by the setting of the initialization parameters and the constraint of the local optimal solution, resulting in certain deviation in the identification result, which is difficult to meet the high-precision identification demand.

[0043] Therefore, how to improve the accuracy of identifying the low-voltage transformer area topology structure needs to be solved urgently.

[0044] To solve the above problems, the embodiments of the present application provide a low-voltage transformer area topology structure identification method and related device based on a particle swarm algorithm, obtain the electrical parameters of each node in the target low-voltage transformer area to obtain an electrical parameter set; determine a first particle swarm corresponding to the target low-voltage transformer area; determine the first fitness data of the first particle swarm according to the electrical parameter set; iteratively update the first particle swarm according to the preset particle swarm algorithm and the first fitness data to obtain a second particle swarm; detect and correct the second particle swarm according to the preset error correction mechanism to obtain second fitness data; iteratively update the second particle swarm according to the particle swarm algorithm and the second fitness data to obtain a third particle swarm; determine the particle with the highest fitness in the third particle swarm as the global optimal particle; and determine the target topology structure of the target low-voltage transformer area according to the global optimal particle. The global optimization search of the particle swarm algorithm enhances the globality and accuracy of the identification, the fitness data is used to improve the topology rationality evaluation, the error correction mechanism is used to dynamically detect and correct the abnormality and misjudgment to ensure the stability, and the iterative feedback is used to continuously improve the identification process to adapt to the dynamic change environment, thereby improving the accuracy of identifying the low-voltage transformer area topology structure.

[0045] For ease of understanding, please refer to Figure 1 , Figure 1 is a system architecture diagram of a low-voltage area topology identification system provided by an embodiment of the application. The low-voltage area topology identification system comprises a data acquisition module, a data preprocessing module, a particle swarm topology identification module, an error correction mechanism module, and a result output module.

[0046] The data acquisition module is responsible for collecting various types of raw data related to power grid operation in the low-voltage area, and is the data source basis of the entire topology identification system. For example, the data acquisition module can collect electrical parameter data such as voltage parameter sets (including voltage amplitude, phase, etc.), current parameter sets (current size, direction, etc.), and power parameter sets (active power, reactive power, etc.) through various sensors such as voltage transformers, current transformers, and power sensors deployed in the low-voltage area. In addition, it can also collect device basic information such as node type (transformer node, branch box node, user node, etc.) and location coordinates.

[0047] The data preprocessing module is responsible for processing the raw data obtained by the data acquisition module to improve data quality and meet the needs of subsequent topology identification algorithms. On the one hand, data cleaning is performed to remove noise and outliers (such as obviously incorrect measurement values and incorrect data due to device failure) in the data. On the other hand, normalization and standardization operations are performed on the data to unify the dimension and value range of the data, facilitating subsequent algorithm calculations. In addition, interpolation processing of missing data may also be performed to estimate missing values based on existing data to ensure data integrity.

[0048] The particle swarm topology identification module can use the preprocessed data to preliminarily identify the topology structure of the low-voltage area based on the particle swarm algorithm. First, the node connection pair list is determined according to the total number of nodes, and the vector length of the binary coding vector is determined, and a plurality of particles (each particle corresponds to a binary coding vector representing a possible topology structure) are randomly generated to form an initial particle swarm. Then, the fitness data of the particle swarm is calculated based on the electrical parameter set, and the advantages and disadvantages of the topology structure represented by each particle are evaluated through fitness. Next, the particle swarm is iteratively updated according to the rules of the particle swarm algorithm, and the speed and position of the particles are constantly adjusted to gradually converge the particle swarm to a better topology structure, and a preliminary topology identification result is obtained.

[0049] The error correction mechanism module can further check and correct the topological structure obtained by the particle swarm topological identification module. The topological structure preliminarily identified is subjected to physical connection consistency detection (checking whether it conforms to the preset physical connection rules of the power grid, such as whether the connection relationship of the transformer and the branch box, the user node is correct, etc.) and load distribution anomaly detection (analyzing whether the load distribution of the adjacent nodes is reasonable, whether there is a load mutation or other abnormal conditions), to obtain a physical connection error value and a load distribution anomaly error value. According to the error value, the particle error value and the population error value are determined, and then the fitness of the particle is adjusted by combining the preset calculation formula and the error penalty coefficient, so as to reduce the fitness of the topological structure with large error, thereby reducing the selection of these error schemes in subsequent iteration or screening, and prompting the system to search for a more accurate topological structure.

[0050] The result output module can output the target topological structure modified by the error correction mechanism module in the form of user-understandable graphics and data. In terms of graphics, the positions and connection relationships of the nodes in the transformer area are displayed in a visual manner, and different topological regions can be distinguished by different colors and patterns. In terms of data, the node connection pair list and detailed electrical parameters of each node are provided. In addition, the output result can be directly connected to the power distribution network automation system, providing accurate topological information support for dynamic topological management, fault diagnosis and dispatching optimization of the power distribution network.

[0051] It can be seen that the original data of the low-voltage transformer area is obtained by the data acquisition module, cleaned and standardized by the data preprocessing module, preliminarily identified by the particle swarm topological identification module based on the algorithm, and then the unreasonable connection is checked and corrected by the error correction mechanism module. Finally, the result output module outputs the accurate topology in the form of graphics and data. The traditional algorithm can effectively avoid the defect of being easily trapped in local optimum, and the globality and accuracy in the identification process are taken into account. The excellent characteristics of the particle swarm algorithm are used to improve the efficiency and stability of the topological identification, and the efficient, fast and stable low-voltage transformer area topological structure identification can still be realized in the dynamic change and noise data environment.

[0052] The following will be described in combination with Figure 2 The electronic device in the embodiment of the present application is described, Figure 2 is a structural schematic diagram of an electronic device provided by the embodiment of the present application, as Figure 2 shown, the electronic device includes one or more processors, memories, communication interfaces, and one or more programs, and the processor is in communication connection with the memory and the communication interface through an internal communication bus.

[0053] The processor can be configured to:

[0054] Obtain the electrical parameters of each node in the target low-voltage transformer area to obtain an electrical parameter set;

[0055] determine a first particle swarm corresponding to the target low-voltage transformer area;

[0056] determine first fitness data of the first particle swarm according to the set of electrical parameters;

[0057] perform iterative updating on the first particle swarm according to the preset particle swarm algorithm and the first fitness data to obtain a second particle swarm;

[0058] detect and correct the second particle swarm according to the preset error correction mechanism to obtain second fitness data;

[0059] perform iterative updating on the second particle swarm according to the particle swarm algorithm and the second fitness data to obtain a third particle swarm;

[0060] determine a global optimal particle in the third particle swarm as a global optimal particle;

[0061] determine a target topology of the target low-voltage transformer area according to the global optimal particle.

[0062] The one or more programs stored in the memory are configured to be executed by the processor, and the one or more programs include instructions for performing any of the steps of the above method embodiments.

[0063] The processor can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The processor can implement or execute the various exemplary logical blocks, units and circuits described in combination with the disclosure. The processor can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc. The communication unit can be a communication interface, a transceiver, a transceiver circuit, etc., and the storage unit can be a memory.

[0064] The memory can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, a number of forms of random access memory (RAM) can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct Rambus RAM (DR RAM).

[0065] It can be understood that the electronic device can include more or less structural elements than those in the above structural block diagram, for example, including a power module, a physical key, a Wi-Fi module, a speaker, a Bluetooth module, a sensor, a display module, etc., which are not limited herein. It can be understood that the electronic device can be equipped with a system architecture as described above. Figure 1

[0066] For ease of understanding, please refer to Figure 3 , Figure 3 is an application scenario of a topology structure identification system provided by an embodiment of the present application, wherein the target low-voltage area includes transformers, branch boxes, user nodes and other equipment, and is the object of topology identification, and the electrical parameter set includes electrical data such as voltage, current and power collected from the target low-voltage area. The topology structure identification system can obtain the electrical parameter set of the target low-voltage area through the data acquisition module, then perform data preprocessing on the electrical parameter set through the data preprocessing module, and perform preliminary identification of the topology structure through the particle swarm topology identification module, then correct the preliminary identified topology structure through the error correction mechanism module to obtain the target topology structure, and finally output the target topology structure to the target low-voltage area in the form of graphics and data through the result output module.​

[0067] After understanding the software and hardware architecture of the present application, the following will be combined with the Figure 4 A low-voltage transformer area topology structure identification method based on a particle swarm algorithm is described in the embodiments of the present application, Figure 4 is a flowchart of a low-voltage transformer area topology structure identification method based on a particle swarm algorithm provided by the embodiments of the present application, and specifically includes the following steps:

[0068] Step S401: Obtain the electrical parameters of each node in the target low-voltage transformer area to obtain an electrical parameter set.

[0069] Specifically, the electrical parameters (such as voltage, current, power, etc.) of each node (such as a transformer, a user meter, a branch box, etc.) can be collected by the smart meter and sensor of the target low-voltage transformer area to obtain the electrical parameter set. The electrical parameters can be preprocessed to eliminate abnormal data, for example, time series can be used to fill in missing values, and normalization processing can be used to ensure uniform data scale, thereby enhancing the subsequent data processing effect.

[0070] Step S402: Determine a first particle swarm corresponding to the target low-voltage transformer area.

[0071] For ease of understanding, please refer to Figure 5 , Figure 5 is a flowchart of determining a first particle swarm provided by the embodiments of the present application, wherein the first particle swarm corresponding to the target low-voltage transformer area is determined, and the specific steps include:

[0072] A1: Obtain the total number of nodes corresponding to all nodes in the target low-voltage transformer area;

[0073] A2: Determine a node connection pair list according to the total number of nodes; the node connection pair list includes M connection pairs, and M is a positive integer;

[0074] A3: Determine the vector length of a binary coding vector according to the M connection pairs; the binary coding vector includes M elements, and each element includes 0 or 1;

[0075] A4: Randomly generate m particles according to the vector length; each particle corresponds to a binary coding vector; m is an integer greater than 1;

[0076] A5: Determine the first particle swarm according to the m particles.

[0077] In specific embodiments, first, the total number of nodes corresponding to all nodes in the target low-voltage area is obtained, and then all possible physical connection pairs between nodes are enumerated according to the total number of nodes to obtain a node connection pair list. The node connection pair list includes M connection pairs excluding the connection of the node itself, and M is a positive integer. When the total number of nodes is N, M = N × (N-1) / 2. Then, the vector length of the binary encoding vector is determined according to the M connection pairs, and the binary encoding vector includes M elements, each element including 0 or 1. The vector length of the binary encoding vector of the particle is equal to the total number of possible connection pairs between any two nodes, and the connection pairs are represented in an unordered form, such as the connection between node i and node j, which is only recorded as (i-j), and (j-i) is not recorded repeatedly. For example, when N = 4 (such as nodes 1, 2, 3, and 4), the possible connection pairs are (1-2), (1-3), (1-4), (2-3), (2-4), and (3-4), a total of 4 × 3 / 2 = 6, so the vector length is 6. It should be noted that the kth bit in the binary encoding vector corresponds to the kth connection pair, and if it is "1", it indicates that the connection pair exists, and if it is "0", it indicates that the connection pair does not exist. For example, if the connection between node 1 and node 2 is the third connection pair, then the third bit in the encoding vector is "1" to indicate that there is an electrical connection between the two nodes. Each particle represents a possible node connection combination scheme, and the encoding method of the particle is based on the binary encoding of whether there is an electrical connection relationship between the nodes, and the vector length is equal to the number of possible connection pairs.

[0078] Next, m particles are randomly generated according to the vector length, each particle corresponding to a binary encoding vector, and m is an integer greater than 1. The elements in the binary encoding vector corresponding to each particle can be generated as "0" or "1" by a predetermined random function to simulate different candidate topological structures. In the initial stage of the particle swarm algorithm topology identification, the particles are randomly generated, and in the subsequent iteration process, the position of the particle (i.e., the binary encoding vector) will be adjusted according to the optimal position of itself and the global optimal position, gradually optimizing the candidate topological structure. Finally, the m particles generated are defined as the first particle swarm, which is used as the initial candidate topological structure set for the iteration optimization of the particle swarm algorithm.

[0079] It can be seen that by converting the node connection relationship into binary encoding and randomly generating initial particles, an initial solution space suitable for topology identification is provided for the particle swarm algorithm, ensuring global search capability and algorithm versatility.

[0080] In step S403, first fitness data of the first particle swarm is determined according to the set of electrical parameters.

[0081] The set of electrical parameters includes a set of voltage parameters, a set of current parameters, and a set of power parameters. The first fitness data of the first particle swarm is determined according to the set of electrical parameters, and the specific steps include:

[0082] B1, determine a first topological structure corresponding to a reference particle; the reference particle is any one of the m particles;

[0083] B2, according to the preset power grid rule, the first topological structure is checked, and a first score is obtained;

[0084] B3, according to the power parameter set, the power deviation rate mean of all adjacent nodes of the first topological structure is determined, and a second score is determined according to the power deviation rate mean;

[0085] B4, determine the connection relationship corresponding to the first topological structure;

[0086] B5, according to the connection relationship, a theoretical voltage parameter set and a theoretical current parameter set are determined;

[0087] B6, according to the theoretical voltage parameter set and the voltage parameter set, a first error sum of squares is determined;

[0088] B7, according to the theoretical current parameter set and the current parameter set, a second error sum of squares is determined;

[0089] B8, the first error sum of squares and the second error sum of squares are normalized and summed respectively, and a third error sum of squares is obtained;

[0090] B9, according to the third error sum of squares, a third score is determined;

[0091] B10, according to the first score, the second score, the third score, the first weight, the second weight and the third weight, weighted sum is obtained, and the fitness of the reference particle in the first fitness data is obtained.

[0092] In specific embodiments, first, according to the electrical parameter set, the fitness corresponding to each particle in the first particle group is determined, and the first fitness data is obtained. Wherein, the reference particle is any one of the m particles, and its corresponding binary code vector (0 / 1 combination) is directly mapped to the first candidate topological structure, that is, the connection pair corresponding to "1" in the binary code vector represents that there is actual connection between nodes. Then, according to the preset power grid electrical rule (such as "transformer needs to be directly connected to branch box", "nodes in the same phase can be interconnected", "prohibition of forming closed loop circuit" and the like), the first topological structure is checked, and a first score is obtained. For example, if there is a rule violation connection of "transformer directly connected to user node", 0.2 points will be deducted; if it fully meets the rules, it will get full marks, wherein the minimum is 0 points, and the full marks are 1 point, which is not limited here.

[0093] Then, the power deviation rate (ratio of actual power difference to theoretically allocated value) of all adjacent node pairs (directly connected nodes) in the first topology structure is calculated based on the power parameter set, and the mean value thereof is taken. The smaller the mean value of the power deviation rate, the more coordinated the power distribution of the adjacent nodes, and the higher the second score. Conversely, the lower the second score. The value range of the second score is 0-1 points. The calculation formula of the power deviation rate is , , represents the node power parameter of any adjacent node pair.

[0094] Then, all existing connection relationships in the first topology structure are determined, and the theoretical voltage and the theoretical current of each node under the first topology structure are calculated according to the connection relationship and the circuit theory (such as Kirchhoff's law and line impedance model), to form a theoretical voltage parameter set and a theoretical current parameter set. Then, the first error sum of squares of the theoretical voltage and the measured voltage is calculated according to the theoretical voltage parameter set and the voltage parameter set. The second error sum of squares of the theoretical current and the measured current is calculated according to the theoretical current parameter set and the current parameter set. Then, the first error sum of squares and the second error sum of squares are normalized (to eliminate dimensional differences) and summed to obtain a third error sum of squares, which comprehensively reflects the overall fitting effect of the electrical parameters. Then, the third score is determined according to the third error sum of squares. The smaller the third error sum of squares, the more consistent the first topology structure is with the measured data, and the higher the third score. The value range of the third score is 0-1 points.

[0095] Finally, the first weight, the second weight and the third weight can be set according to actual needs, and the fitness of the reference particle corresponding to the first fitness data is obtained by weighted summation according to the first score, the second score, the third score, the first weight, the second weight and the third weight. All particles in the first particle swarm are processed according to the fitness calculation steps of the reference particle, so as to obtain the first fitness data.

[0096] It can be seen that through multi-dimensional evaluation (physical rule compliance, load distribution coordination, electrical data fitting degree) and weighted fusion, the overall scientific quantification of the topology structure is realized, the accurate optimization guidance is provided for the particle swarm algorithm, and the accuracy of the identification result is ensured.

[0097] Step S404: According to the preset particle swarm algorithm and the first fitness data, the first particle swarm is iteratively updated to obtain a second particle swarm.

[0098] For ease of understanding, please refer to Figure 6 , Figure 6is a flowchart of particle swarm iterative updating provided by an embodiment of the present application, wherein the first particle swarm is iteratively updated according to a preset particle swarm algorithm and the first fitness data to obtain a second particle swarm, and the specific steps include:

[0099] C1, determining the fitness of each particle in the m particles according to the first fitness data to obtain m first fitnesses;

[0100] C2, determining the initial optimal position of each particle in the m particles to obtain m initial optimal positions; each initial optimal position corresponds to a first fitness;

[0101] C3, determining an initial global optimal position according to the m first fitnesses; the initial global optimal position is the initial optimal position corresponding to the highest first fitness in the m first fitnesses;

[0102] C4, determining m initial particle velocities corresponding to the first particle swarm;

[0103] C5, iteratively updating the m initial particle velocities and the m initial optimal positions according to the particle swarm algorithm to obtain the second particle swarm.

[0104] In specific embodiments, first, the fitness corresponding to each particle in the m particles is extracted from the first fitness data to obtain m first fitnesses as an initial basis for evaluating the advantages and disadvantages of each candidate topology structure. Then, the initial optimal position (corresponding to the initial topology structure) of each particle is temporarily set as its own optimal position, and the corresponding first fitness is associated and recorded as the optimal solution currently found by the particle. The first fitnesses of all particles are compared, and the initial optimal position of the particle with the highest fitness is determined as the initial global optimal position of the entire population, representing the optimal topology structure currently found by the population. Next, the m particles in the first particle swarm are randomly assigned initial particle velocities to obtain m initial particle velocities. Finally, based on the particle swarm algorithm, the initial particle velocity, the initial optimal position, and the global optimal position of each particle are combined to iteratively adjust the velocity and position of the particle (i.e., optimize the topology structure) until the convergence condition (such as the global optimal fitness tends to be stable) is met, and finally an optimized second particle swarm is formed.

[0105] As can be seen, through the synergistic guidance of individual optimal and global optimal, the particle swarm gradually converges to a better topology structure, improving the efficiency of topology identification and global optimization ability.

[0106] wherein the m initial particle velocities and the m initial optimal positions are iteratively updated according to the particle swarm algorithm to obtain the second particle swarm, and the specific steps include:

[0107] D1. Update the velocities of the m initial particles according to the velocity update formula corresponding to the particle swarm algorithm to obtain the velocities of the m first particles;

[0108] D2. Determine the m adjustment probabilities corresponding to the m first particle velocities according to the preset activation function;

[0109] D3. Update the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions;

[0110] D4. Determine the m reference fitnesss corresponding to the m positions of the first particles;

[0111] D5. Update the positions of the m first particles based on the m reference fitness values ​​to obtain the m first optimal positions;

[0112] D6. Determine the first optimal position with the highest fitness among the m first optimal positions as the first global optimal position;

[0113] D7. Determine the reference second particle swarm based on the m first particle velocities, m first optimal positions, and the first global optimal position;

[0114] D8. If the first global optimal position satisfies the preset convergence condition, then the reference second particle group is determined as the second particle group; if the first global optimal position does not satisfy the convergence condition, then the reference second particle group continues to be iteratively updated until the convergence condition is satisfied.

[0115] In a specific embodiment, firstly, based on the velocity update formula corresponding to the particle swarm optimization algorithm, and combining the initial particle velocity, initial optimal position, and initial global optimal position of each particle, the velocities of the m first particles corresponding to the m particles are calculated. The velocity update formula is as follows:

[0116]

[0117] in, Indicates that the i-th particle is in The particle velocity updated after the next iteration; Indicates that the i-th particle is in The particle velocity updated after the next iteration; Inertial weight represents the balance between a particle's global exploration and local development capabilities (e.g., a larger inertial weight enhances global search, while a smaller inertial weight strengthens local optimization). , The learning factor represents the weights that control the particle's learning towards its own optimal position and the global optimal position, respectively. , represents a random number in the interval [0, 1], used to increase the randomness of the search, and avoid the algorithm falling into a local optimum; represents the current historical optimal position of the i-th particle, such as the initial optimal position; represents the current global optimal position of the particle swarm, such as the initial global optimal position of the first particle swarm; represents the particle position of the i-th particle after the j-th iteration; represents the particle position updated after the j-th iteration.

[0118] Next, the first particle velocity is converted into an adjustment probability by a preset activation function (such as a sigmoid function), which quantifies the adjustment possibility of the particle position, and m adjustment probabilities are obtained. Based on the m adjustment probabilities, the initial optimal position (i.e. the binary coded vector) of the m particles is updated (such as flipping the coded bits, 0 to 1 or 1 to 0), and m first particle positions, i.e. new candidate topological structures, are generated. Then, m reference fitnesses corresponding to the m first particle positions are calculated, and the m first particle positions are updated according to the m reference fitnesses, and m first optimal positions are obtained. Among them, if the reference fitness of a particle is higher than its current fitness, the current position of the particle is updated to the first particle position. Then, the first global optimal position with the highest fitness is selected from the m first optimal positions.

[0119] Finally, the reference second particle swarm is determined according to the m first particle velocities, the m first optimal positions, and the first global optimal position. If the first global optimal position meets the preset convergence condition, the reference second particle swarm is determined as the second particle swarm; if the first global optimal position does not meet the convergence condition, the reference second particle swarm is continuously iterated and updated until the convergence condition is met. Among them, the convergence condition can be that the change amount of the fitness corresponding to the global optimal position of the last 5 iterations is less than 0.001, which is not limited here.

[0120] It can be seen that the synergistic evolution of individual and global optimum enables the particle swarm to efficiently converge to a better topological structure, ensuring the global nature of the search and improving the recognition accuracy and efficiency.

[0121] Among them, the updating of the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions includes the following specific steps:

[0122] E1, determining a reference binary coded vector and a reference adjustment probability corresponding to a reference initial optimal position; the reference initial optimal position is any one of the m initial optimal positions; the reference adjustment probability is the adjustment probability corresponding to the reference initial optimal position in the m adjustment probabilities;

[0123] E2, generating M random numbers according to the reference binary encoding vector; each random number corresponds to an element in the reference binary encoding vector;

[0124] E3, if there is a random number less than the reference adjustment probability in the M random numbers, flipping the value of the element corresponding to the random number to obtain an updated reference binary encoding vector;

[0125] E4, determining the first particle position corresponding to the reference initial optimal position in the m first particle positions according to the updated reference binary encoding vector.

[0126] In specific embodiments, first, the reference binary encoding vector corresponding to the reference initial optimal position and the reference adjustment probability can be determined, the reference initial optimal position is any one of the m initial optimal positions, and the reference adjustment probability is the adjustment probability corresponding to the reference initial optimal position among the m adjustment probabilities. Then, M elements (each element corresponds to a node connection pair) of the reference binary encoding vector are generated, each random number corresponds to an element in the encoding vector. Next, each random number is compared with the reference adjustment probability: if there is a random number less than the reference adjustment probability, the value of the corresponding element is flipped (0 is flipped to 1 or 1 is flipped to 0); if the random number is greater than or equal to the reference adjustment probability, the value of the element is kept unchanged, and finally the updated reference binary encoding vector is obtained. Finally, the first particle position corresponding to the reference initial optimal position in the m first particle positions is determined according to the updated reference binary encoding vector. For the m initial optimal positions, the updating process of the reference initial optimal position is repeated to obtain the m first particle positions.

[0127] It can be seen that the adaptive flipping of the encoding bits is realized by comparing the random number with the adjustment probability, which not only ensures the randomness of the particle position updating to expand the search space, but also preserves the effective connection of the high-quality topological structure through probability control, improving the pertinence and efficiency of the particle swarm optimization.

[0128] Step S405, detecting and correcting the second particle swarm according to a preset error correction mechanism to obtain second fitness data.

[0129] The detecting and correcting the second particle swarm according to a preset error correction mechanism to obtain second fitness data includes the following steps:

[0130] F1, determining the topological structure corresponding to each particle of the second particle swarm to obtain m second topological structures;

[0131] F2, performing preset physical connection consistency detection and load distribution anomaly detection according to the m second topologies, to obtain m physical connection error values and m load distribution anomaly error values;

[0132] F3, determining m particle error values according to the m physical connection error values and the m load distribution anomaly error values; each particle error value corresponds to a physical connection error value and a load distribution anomaly error value;

[0133] F4, determining a maximum value in the m particle error values as a population error value;

[0134] F5, determining reference second fitness data corresponding to the second particle swarm;

[0135] F6, calculating the preset error penalty coefficient, the m particle error values, the population error value and the reference second fitness data according to a calculation formula corresponding to the error correction mechanism, to obtain the second fitness data.

[0136] In specific embodiments, first, the binary encoding vector corresponding to each particle in the second particle swarm is extracted, which is converted into a specific node connection relationship, to obtain m second topologies as detection objects of the error correction mechanism. Then, according to the physical connection rules of the low-voltage transformer area (such as “transformer needs to be connected to users through branch boxes”, “prohibition of forming a loop”, etc.), the physical connection consistency of each second topology is detected, the number or degree of violation of the rules is calculated, and m physical connection error values are obtained, wherein the larger the physical connection error value, the worse the physical rationality.

[0137] Next, according to the adjacent node pairs of the m second topologies and the node power time sequence data, load distribution anomaly detection is performed, the correlation Pearson coefficient of the power curve of each adjacent node pair is calculated, the coefficient lower than a threshold value (such as 0.6) is marked as abnormal, the number of abnormalities is counted and the load distribution anomaly error value (such as the number of abnormalities / total number of adjacent node pairs) is calculated, and m load distribution anomaly error values are output.

[0138] Then, according to the m physical connection error values and the m load distribution anomaly error values, m particle error values are determined, each particle error value corresponds to a physical connection error value and a load distribution anomaly error value, and the particle error value is the average of the physical connection error value and the load distribution anomaly error value. The maximum value in the m particle error values is taken as the population error value, and the reference second fitness data corresponding to the second particle swarm is calculated. Finally, the preset error penalty coefficient, the m particle error values, the population error value and the reference second fitness data are calculated according to the calculation formula corresponding to the error correction mechanism, to obtain the second fitness data. The calculation formula corresponding to the error correction mechanism is as follows:

[0139]

[0140] wherein, represents the fitness of the i-th particle in the second fitness data; represents the fitness of the i-th particle in the reference second fitness data; represents an error penalty coefficient, taking a value in the range of [0, 1], for controlling the influence strength of the error on the fitness; represents the particle error value corresponding to the i-th particle; represents the population error value corresponding to the current particle swarm.

[0141] It can be seen that, through the error detection of the physical rules and the load characteristics, and in combination with the error correction mechanism for dynamically correcting the fitness, the physical irrationality of the topological structure is eliminated, the coordination of the load distribution is strengthened, and the screening accuracy of the particle swarm algorithm for the high-quality topology is improved.

[0142] Step S406: iteratively updating the second particle swarm according to the particle swarm algorithm and the second fitness data, to obtain a third particle swarm.

[0143] Specifically, taking the second particle swarm as the starting point, using the particle swarm algorithm, in combination with the second fitness data corrected by the error correction mechanism, repeatedly performing the operations of velocity updating, position adjustment, fitness evaluation, individual optimal and global optimal updating, and the like, until the convergence condition is met, to obtain the third particle swarm.

[0144] Step S407: determining that the particle with the highest fitness in the third particle swarm is the global optimal particle.

[0145] Specifically, the particle with the highest fitness is selected from the third particle swarm, and the particle is taken as the global optimal particle.

[0146] Step S408: determining the target topological structure of the target low-voltage transformer area according to the global optimal particle.

[0147] Specifically, the binary coding vector corresponding to the global optimal particle is analyzed: the "1" or "0" of each element in the binary coding vector corresponds to the actual existence of the corresponding connection pair in the node connection pair list in the target low-voltage transformer area, wherein the element "1" indicates that the corresponding node pair has physical connection, and the element "0" indicates that the corresponding node pair has no physical connection. Finally, the target topological structure of the target low-voltage transformer area is determined according to the analysis result. The target topological structure obtained after error correction can be output in the form of graphics and data to support the power distribution automation system to realize dynamic topology management, fault diagnosis and dispatching optimization.

[0148] For ease of understanding, please refer to Figure 7 ,Figure 7 is a structural schematic diagram of a target topology provided by an embodiment of the present application, wherein each dot represents a different power grid node in a target low-voltage transformer area, wherein a solid dot represents a node corresponding to known information (such as a line outgoing end), a dashed dot represents a node corresponding to unknown information to be identified, and a solid line between each node represents an actual connection relationship of an electrical line. A first topology region includes nodes 1, 2, 5, and 6, and a second topology region includes nodes 3, 4, 7, 8, and 9, wherein the error correction correction region further includes node 2, indicating that the node 2 has irrationality (such as incorrect association, not in line with physical rules, etc.), and needs to be corrected by an error correction mechanism to improve the accuracy and rationality of the identification of the entire target topology.

[0149] The above describes the scheme of the embodiments of the present application mainly from the perspective of the execution process of the method. It can be understood that, in order to implement the above functions, the electronic device includes a hardware structure and / or a software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the unit and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0150] The embodiments of the present application can divide the functional units of the electronic device according to the above method examples, for example, each functional unit can be divided according to each function, or two or more functions can be integrated in one processing unit. The integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical function division. When actually implemented, there can be another division method.

[0151] In the case of dividing each functional module according to each function, Figure 8 is a functional module composition block diagram of a low-voltage transformer area topology structure identification device based on a particle swarm algorithm provided by an embodiment of the present application, the low-voltage transformer area topology structure identification device based on a particle swarm algorithm 800 includes an acquisition module 810, a determination module 820, an update module 830, and an error correction module 840, wherein:

[0152] The acquisition module 810 is configured to acquire the electrical parameters of each node in the target low-voltage transformer area to obtain an electrical parameter set.

[0153] The determination module 820 is configured to determine a first particle group corresponding to the target low-voltage transformer area; and determine first fitness data of the first particle group according to the electrical parameter set.

[0154] The update module 830 is configured to perform iterative update on the first particle group according to a preset particle swarm algorithm and the first fitness data, to obtain a second particle group.

[0155] The error correction module 840 is configured to perform detection and correction on the second particle group according to a preset error correction mechanism, to obtain second fitness data.

[0156] The update module 830 is further configured to perform iterative update on the second particle group according to the particle swarm algorithm and the second fitness data, to obtain a third particle group.

[0157] The determination module 820 is further configured to determine a global optimal particle as a particle with the highest fitness in the third particle group; and determine a target topology structure of the target low-voltage transformer area according to the global optimal particle.

[0158] Optionally, in the determination of the first particle group corresponding to the target low-voltage transformer area, the determination module 820 is specifically configured to:

[0159] acquire a total number of nodes corresponding to all nodes in the target low-voltage transformer area;

[0160] determine a node connection pair list according to the total number of nodes; the node connection pair list includes M connection pairs, and M is a positive integer;

[0161] determine a vector length of a binary coding vector according to the M connection pairs; the binary coding vector includes M elements, and each element includes 0 or 1;

[0162] randomly generate m particles according to the vector length; each particle corresponds to a binary coding vector; m is an integer greater than 1;

[0163] determine the first particle group according to the m particles.

[0164] Optionally, the electrical parameter set includes a voltage parameter set, a current parameter set and a power parameter set, and in the determination of the first fitness data of the first particle group according to the electrical parameter set, the determination module 820 is further configured to:

[0165] determine a first topology structure corresponding to a reference particle; the reference particle is any one of the m particles;

[0166] perform rule checking on the first topology structure according to a preset power grid rule, to obtain a first score;

[0167] determine a power deviation rate mean of all adjacent nodes of the first topology according to the power parameter set, and determine a second score value according to the power deviation rate mean;

[0168] determine a connection relationship corresponding to the first topology;

[0169] determine a theoretical voltage parameter set and a theoretical current parameter set according to the connection relationship;

[0170] determine a first error sum of squares according to the theoretical voltage parameter set and the voltage parameter set;

[0171] determine a second error sum of squares according to the theoretical current parameter set and the current parameter set;

[0172] normalize and sum the first error sum of squares and the second error sum of squares respectively to obtain a third error sum of squares;

[0173] determine a third score value according to the third error sum of squares;

[0174] perform weighted summation according to the first score value, the second score value, the third score value, a preset first weight, a second weight and a third weight to obtain an adaptability corresponding to the reference particle in the first adaptability data.

[0175] Optionally, in the aspect of iteratively updating the first particle swarm according to the preset particle swarm algorithm and the first adaptability data to obtain a second particle swarm, the updating module 830 is specifically configured to:

[0176] determine an adaptability of each particle in the m particles according to the first adaptability data to obtain m first adaptabilities;

[0177] determine an initial optimal position of each particle in the m particles to obtain m initial optimal positions; each initial optimal position corresponds to a first adaptability;

[0178] determine an initial global optimal position according to the m first adaptabilities; the initial global optimal position is an initial optimal position corresponding to a highest first adaptability in the m first adaptabilities;

[0179] determine m initial particle velocities corresponding to the first particle swarm;

[0180] iteratively update the m initial particle velocities and the m initial optimal positions according to the particle swarm algorithm to obtain the second particle swarm.

[0181] Optionally, in the aspect of updating the m initial particle velocities and the m initial optimal positions according to the particle swarm algorithm to obtain the second particle swarm, the updating module 830 is further configured to:

[0182] updating the m initial particle velocities according to a velocity updating formula corresponding to the particle swarm algorithm to obtain m first particle velocities;

[0183] determining m adjustment probabilities corresponding to the m first particle velocities according to a preset activation function;

[0184] updating the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions;

[0185] determining m reference fitnesses corresponding to the m first particle positions;

[0186] updating the m first particle positions according to the m reference fitnesses to obtain m first optimal positions;

[0187] determining a first optimal position with the highest fitness in the m first optimal positions as a first global optimal position;

[0188] determining a reference second particle swarm according to the m first particle velocities, the m first optimal positions, and the first global optimal position;

[0189] if the first global optimal position satisfies a preset convergence condition, determining the reference second particle swarm as the second particle swarm; if the first global optimal position does not satisfy the convergence condition, continuing to update the reference second particle swarm iteratively until the convergence condition is satisfied.

[0190] Optionally, in the aspect of updating the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions, the updating module 830 is further configured to:

[0191] determining a reference binary encoding vector and a reference adjustment probability corresponding to a reference initial optimal position; the reference initial optimal position is any one of the m initial optimal positions; the reference adjustment probability is an adjustment probability corresponding to the reference initial optimal position in the m adjustment probabilities;

[0192] generating M random numbers according to the reference binary encoding vector; each random number corresponds to an element in the reference binary encoding vector;

[0193] if there is a random number less than the reference adjustment probability in the M random numbers, flipping the value of the element corresponding to the random number to obtain an updated reference binary encoding vector.

[0194] determining a first particle position corresponding to the reference initial optimal position in the m first particle positions according to the updated reference binary encoding vector.

[0195] Optionally, in the aspect of detecting and correcting the second particle group according to the preset error correction mechanism to obtain the second fitness data, the error correction module 840 is specifically configured to:

[0196] determining a topological structure corresponding to each particle of the second particle group to obtain m second topological structures;

[0197] performing preset physical connection consistency detection and load distribution anomaly detection according to the m second topological structures to obtain m physical connection error values and m load distribution anomaly error values;

[0198] determining m particle error values according to the m physical connection error values and the m load distribution anomaly error values; each particle error value corresponds to a physical connection error value and a load distribution anomaly error value;

[0199] determining a maximum value in the m particle error values as a population error value;

[0200] determining reference second fitness data corresponding to the second particle group;

[0201] calculating a preset error penalty coefficient, the m particle error values, the population error value and the reference second fitness data according to a calculation formula corresponding to the error correction mechanism to obtain the second fitness data.

[0202] It can be seen that the global optimization search of the particle swarm algorithm enhances the globality and accuracy of identification, the fitness data is used to improve the topological rationality evaluation, the error correction mechanism is used to dynamically detect and correct abnormalities and misjudgments to ensure stability, and the iterative feedback is used to continuously improve the identification process to adapt to the dynamic change environment, thereby improving the accuracy of identifying the low-voltage transformer area topological structure.

[0203] It should be noted that the specific implementation of each operation can be implemented by the corresponding description of the above-mentioned method embodiment, and the low-voltage transformer area topological structure identification device 800 based on the particle swarm algorithm can be used to execute the method embodiment of the present application, and details are not repeated.

[0204] The embodiment of the present application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, and the computer program makes the computer execute part or all steps of any method recorded in the above-mentioned method embodiment, and the above-mentioned computer includes an electronic device.

[0205] The embodiment of the present application further provides a computer program product, which comprises a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any method described in the above method embodiments. The computer program product can be a software installation package, and the computer comprises an electronic device.

[0206] It should be noted that, for each of the above embodiments, in order to simply describe, each of the above embodiments is described as a series of action combinations. Those skilled in the art should know that the present application is not limited to the order of actions described, because some steps in the embodiment of the present application can be performed in other order or simultaneously. In addition, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions, steps, modules or units involved are not necessarily required in the embodiment of the present application.

[0207] In the above embodiments, the description of each embodiment of the present application has its own focus, and the part not described in detail in an embodiment can be referred to the related description of other embodiments.

[0208] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by a computer program instructing relevant hardware to complete, and the program can be stored in a computer readable storage medium. When the program is executed, the processes of each method embodiment described above can be included. The storage medium described above includes: ROM, random access memory (RAM), magnetic disk or optical disk and other various storage media that can store program codes.

[0209] The steps of the method or algorithm described in the embodiments of the present application can be implemented in the form of hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in RAM, flash memory, ROM, EPROM, electrically EPROM (EEPROM), register, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a terminal device or a management device. Of course, the processor and the storage medium can also exist as discrete components in the terminal device or the management device.

[0210] Those skilled in the art should be aware that, in one or more examples described above, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, the computer program instructions generate, in whole or in part, the processes or functions described in the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0211] The various modules / units included in the various devices and products described in the above embodiments can be software modules / units or hardware modules / units, or partially software modules / units and partially hardware modules / units. For example, for the various devices and products applied to or integrated into a chip, the various modules / units included therein can all be implemented in the form of hardware such as circuitry, or at least some of the modules / units can be implemented in the form of software programs running on a processor integrated in the chip, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuitry; for the various devices and products applied to or integrated into a chip module, the various modules / units included therein can all be implemented in the form of hardware such as circuitry, and different modules / units can be located in the same component (e.g., a chip, a circuit module, etc.) or different components of the chip module, or at least some of the modules / units can be implemented in the form of software programs running on a processor integrated in the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuitry; for the various devices and products applied to or integrated into a terminal device, the various modules / units included therein can all be implemented in the form of hardware such as circuitry, and different modules / units can be located in the same component (e.g., a chip, a circuit module, etc.) or different components of the terminal device, or at least some of the modules / units can be implemented in the form of software programs running on a processor integrated in the terminal device, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuitry.

[0212] The above detailed description of the specific embodiments of the present application has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the application to the precise form described, and many modifications, equivalents and alternatives shown. The detailed description is not intended to limit the scope of the present application. Instead, the scope of the present application is defined by the appended claims, reasonably construed in light of the prior art.

Claims

1. A low-voltage area topology identification method based on a particle swarm algorithm, characterized in that, The method comprises: acquiring electrical parameters of each node in a target low-voltage area to obtain an electrical parameter set; determining a first particle swarm corresponding to the target low-voltage area; determining first fitness data of the first particle swarm according to the electrical parameter set; iteratively updating the first particle swarm according to a preset particle swarm algorithm and the first fitness data to obtain a second particle swarm; detecting and correcting the second particle swarm according to a preset error correction mechanism to obtain second fitness data; iteratively updating the second particle swarm according to the particle swarm algorithm and the second fitness data to obtain a third particle swarm; determining a global optimal particle with the highest fitness in the third particle swarm as a global optimal particle; determining a target topology structure of the target low-voltage area according to the global optimal particle; wherein the determination of the first particle swarm corresponding to the target low-voltage area comprises: acquiring a total number of nodes corresponding to all nodes in the target low-voltage area; determining a node connection pair list according to the total number of nodes; the node connection pair list comprises M connection pairs, and M is a positive integer; determining a vector length of a binary coding vector according to the M connection pairs; the binary coding vector comprises M elements, and each element comprises 0 or 1; randomly generating m particles according to the vector length; each particle corresponds to a binary coding vector; m is an integer greater than 1; determining the first particle swarm according to the m particles; wherein the iteratively updating of the first particle swarm according to the preset particle swarm algorithm and the first fitness data to obtain the second particle swarm comprises: determining the fitness of each particle in the m particles according to the first fitness data to obtain m first fitnesses; determining an initial optimal position of each particle in the m particles to obtain m initial optimal positions; each initial optimal position corresponds to a first fitness; determining an initial global optimal position according to the m first fitnesses; the initial global optimal position is an initial optimal position corresponding to the highest first fitness in the m first fitnesses; determining m initial particle velocities corresponding to the first particle swarm; iteratively updating the m initial particle velocities and the m initial optimal positions according to the particle swarm algorithm to obtain the second particle swarm.

2. The method of claim 1, wherein, The electrical parameter set comprises a voltage parameter set, a current parameter set and a power parameter set, and the determination of the first fitness data of the first particle swarm according to the electrical parameter set comprises: determining a first topology structure corresponding to a reference particle; the reference particle is any one of the m particles; performing rule checking on the first topology structure according to a preset power grid rule to obtain a first score; determining a power deviation rate mean of all adjacent nodes of the first topology structure according to the power parameter set, and determining a second score according to the power deviation rate mean; determining a connection relationship corresponding to the first topology structure; determining a theoretical voltage parameter set and a theoretical current parameter set according to the connection relationship; determining a first error sum of squares according to the theoretical voltage parameter set and the voltage parameter set; determining a second error sum of squares according to the theoretical current parameter set and the current parameter set; normalizing and summing the first error sum of squares and the second error sum of squares respectively to obtain a third error sum of squares; determining a third score according to the third error sum of squares; performing weighted sum according to the first score, the second score, the third score, preset first weight, second weight and third weight to obtain the fitness corresponding to the reference particle in the first fitness data.

3. The method of claim 1, wherein, The iterative updating of the m initial particle velocities and the m initial optimal positions according to the particle swarm algorithm to obtain the second particle swarm comprises: updating the m initial particle velocities according to a velocity updating formula corresponding to the particle swarm algorithm to obtain m first particle velocities; determining m adjustment probabilities corresponding to the m first particle velocities according to a preset activation function; updating the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions; determining m reference fitnesses corresponding to the m first particle positions; updating the m first particle positions according to the m reference fitnesses to obtain m first optimal positions; determining a first global optimal position with the highest fitness in the m first optimal positions as the first global optimal position; determining a reference second particle swarm according to the m first particle velocities, the m first optimal positions and the first global optimal position; if the first global optimal position satisfies a preset convergence condition, determining the reference second particle swarm as the second particle swarm; if the first global optimal position does not satisfy the convergence condition, continuing to iteratively update the reference second particle swarm until the convergence condition is satisfied.

4. The method of claim 3, wherein, The updating of the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions comprises: determining a reference binary encoding vector and a reference adjustment probability corresponding to a reference initial optimal position; the reference initial optimal position is any one of the m initial optimal positions; the reference adjustment probability is an adjustment probability corresponding to the reference initial optimal position in the m adjustment probabilities; generating M random numbers according to the reference binary encoding vector; each random number corresponds to an element in the reference binary encoding vector; if there is a random number less than the reference adjustment probability in the M random numbers, flipping the value of the element corresponding to the random number to obtain an updated reference binary encoding vector; determining a first particle position corresponding to the reference initial optimal position in the m first particle positions according to the updated reference binary encoding vector.

5. The method according to any one of claims 1 to 4, characterized in that, The detection and correction of the second particle swarm according to a preset error correction mechanism to obtain second fitness data comprises: determining m second topological structures corresponding to each particle of the second particle swarm; performing preset physical connection consistency detection and load distribution anomaly detection according to the m second topological structures to obtain m physical connection error values and m load distribution anomaly error values; determine m particle error values according to the m physical connection error values and the m load distribution abnormal error values, each particle error value corresponding to a physical connection error value and a load distribution abnormal error value; determine a maximum value in the m particle error values as a population error value; determine reference second fitness data corresponding to the second particle group; calculate a preset error penalty coefficient, the m particle error values, the population error value and the reference second fitness data according to a calculation formula corresponding to the error correction mechanism to obtain the second fitness data.

6. A low voltage distribution area topology identification device based on particle swarm optimization algorithm, configured to perform the method according to any one of claims 1-5, characterized in that, The device comprises an acquisition module, a determination module, an update module and an error correction module, wherein: The acquisition module is configured to acquire electrical parameters of each node in a target low-voltage area to obtain an electrical parameter set. The determination module is configured to determine a first particle group corresponding to the target low-voltage area, and determine first fitness data of the first particle group according to the electrical parameter set. The update module is configured to perform iterative update on the first particle group according to a preset particle swarm algorithm and the first fitness data to obtain a second particle group. The error correction module is configured to detect and correct the second particle group according to a preset error correction mechanism to obtain second fitness data. The update module is further configured to perform iterative update on the second particle group according to the particle swarm algorithm and the second fitness data to obtain a third particle group. The determination module is further configured to determine a particle with the highest fitness in the third particle group as a global optimal particle, and determine a target topology structure of the target low-voltage area according to the global optimal particle.

7. An electronic device, comprising: It comprises: a processor, a memory, a communication interface and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, and the programs comprise instructions for performing steps in the method of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program comprises program instructions, which make the processor execute the method of any one of claims 1-5 when executed by the processor. The computer readable storage medium stores a computer program, and the computer program comprises program instructions, which make the processor execute the method of any one of claims 1-5 when executed by the processor.

Images