Low-voltage transformer area topological structure identification method based on particle swarm optimization and related device

Abstract

The invention provides a low-voltage transformer area topological structure identification method based on a particle swarm algorithm and a related device. The method comprises the following steps: acquiring an electrical parameter set of a target low-voltage transformer area; determining a first particle swarm of the target low-voltage transformer 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 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 a particle swarm algorithm and the second fitness data to obtain a third particle swarm; and determining a target topological structure according to the particle with the highest fitness in the third particle swarm. The particle swarm algorithm and an error correction mechanism can be combined to perform global optimization search and dynamic correction on the topological structure of the target low-voltage transformer area so as to improve the accuracy of topological structure identification.

Description

Technical Field

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

[0002] In intelligent distribution automation systems, accurate identification of low-voltage substation topology is a crucial and fundamental step. Dynamic changes in low-voltage substation topology directly impact the accuracy of load distribution analysis, the efficiency of fault location, and the effectiveness of grid dispatch.

[0003] The current mainstream automatic identification methods each have their own limitations: the state estimation technology based on topological inference is highly dependent on the density of measurement points and the quality of collected data, and is prone to large errors when monitoring coverage is insufficient or data deviations exist; the network analysis method based on graph theory, although capable of structured topological analysis, has strict requirements on the integrity and accuracy of initial connection data, and is difficult to quickly adapt to the dynamic adjustment of the substation topology; and the clustering algorithm based on machine learning is often limited by the setting of initialization parameters and the constraints of local optimal solutions, resulting in certain deviations in the identification results, making it difficult to meet the needs of high-precision identification.

[0004] Therefore, how to improve the accuracy of identifying the topological structure of low-voltage substations needs to be solved urgently. Summary of the Invention

[0005] The embodiment of the present application provides a method and related devices for identifying the topological structure of a low-voltage substation based on a particle swarm algorithm. The global optimization search of the particle swarm algorithm is used to enhance the globality and accuracy of the identification, the fitness data is used to improve the assessment of the rationality of the topology, the error correction mechanism is used to dynamically detect and correct anomalies and misjudgments to ensure stability, and the iterative feedback is used to continuously improve the recognition process to adapt to the dynamically changing environment, thereby improving the accuracy of identifying the topological structure of the low-voltage substation.

[0006] In a first aspect, an embodiment of the present application provides a method for identifying a low-voltage substation topology structure based on a particle swarm algorithm, the method comprising: Obtain the electrical parameters of each node in the target low-voltage area to obtain an electrical parameter set; Determining a first particle group corresponding to the target low-pressure 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 the particle with the highest fitness in the third particle swarm as the global optimal particle; A target topological structure of the target low-pressure area is determined according to the global optimal particle.

[0007] In a second aspect, an embodiment of the present application provides a low-voltage substation 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: The acquisition module is used to acquire the electrical parameters of each node in the target low-voltage area to obtain an electrical parameter set; The determining module is configured to determine a first particle swarm corresponding to the target low-voltage area; and determine first fitness data of the first particle swarm according to the electrical parameter set; The updating module is configured to iteratively update the first particle swarm according to a preset particle swarm algorithm and the first fitness data to obtain a second particle swarm; The error correction module is used to detect and correct the second particle swarm according to a preset error correction mechanism to obtain second fitness data; The updating module is further configured to iteratively update the second particle swarm according to the particle swarm algorithm and the second fitness data to obtain a third particle swarm; The determination module is further configured to determine the particle with the highest fitness in the third particle swarm as the global optimal particle; and determine the target topology of the target low-pressure station area based on the global optimal particle.

[0008] 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 program comprises instructions for executing the steps of any method of the first aspect of the embodiment of the present application.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the above-mentioned computer-readable storage medium stores a computer program for electronic data exchange, wherein the above-mentioned computer program enables a computer to execute part or all of the steps described in any method of the first aspect of the embodiment of the present application.

[0010] In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to execute some or all of the steps described in any method of the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0011] 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 recognition, the topological rationality assessment can be improved with the help of fitness data, the error correction mechanism can be used to dynamically detect and correct anomalies and misjudgments to ensure stability, and the recognition process can be continuously self-improved through iterative feedback to adapt to the dynamically changing environment, thereby improving the accuracy of identifying the topological structure of the low-voltage substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0013] Figure 1 This is a system architecture diagram of a low-voltage substation topology structure identification system provided in an embodiment of the present application; Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application; Figure 3 This is an application scenario diagram of a topology structure recognition system provided by an embodiment of the present application; Figure 4 This is a flow chart of a method for identifying a low-voltage substation topology structure based on a particle swarm algorithm according to an embodiment of the present application; Figure 5 This is a schematic diagram of a process for determining a first particle group provided in an embodiment of the present application; Figure 6 This is a flow chart of an iterative update process of a particle swarm provided in an embodiment of the present application; Figure 7 This is a schematic diagram of a target topology structure provided by an embodiment of the present application; Figure 8 This is a functional module composition block diagram of a low-voltage substation topology structure identification device based on a particle swarm algorithm provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0015] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0016] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document indicates that the associated objects are in an "or" relationship. The "plurality" appearing in the embodiments of this application refers to two or more.

[0017] In the embodiments of the present application, "at least one item" or similar expressions refers to any combination of these items, including any combination of single items or plural items, and refers to one or more, and multiple refers to two or more. For example, at least one item (item) of a, b, or c can represent the following seven situations: 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.

[0018] The "connection" appearing in the embodiments of the present application refers to various connection methods such as direct connection or indirect connection to achieve communication between devices, and the embodiments of the present application do not impose any limitations on this.

[0019] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0020] In intelligent distribution automation systems, accurate identification of low-voltage substation topology is a crucial and fundamental step. Dynamic changes in low-voltage substation topology directly impact the accuracy of load distribution analysis, the efficiency of fault location, and the effectiveness of grid dispatch.

[0021] The current mainstream automatic identification methods each have their own limitations: the state estimation technology based on topological inference is highly dependent on the density of measurement points and the quality of collected data, and is prone to large errors when monitoring coverage is insufficient or data deviations exist; the network analysis method based on graph theory, although capable of structured topological analysis, has strict requirements on the integrity and accuracy of initial connection data, and is difficult to quickly adapt to the dynamic adjustment of the substation topology; and the clustering algorithm based on machine learning is often limited by the setting of initialization parameters and the constraints of local optimal solutions, resulting in certain deviations in the identification results, making it difficult to meet the needs of high-precision identification.

[0022] Therefore, how to improve the accuracy of identifying the topological structure of low-voltage substations needs to be solved urgently.

[0023] To solve the above problems, the embodiment of the present application provides a low-voltage substation topology structure identification method and related devices based on the particle swarm algorithm, which obtains the electrical parameters of each node in the target low-voltage substation to obtain an electrical parameter set; determines the first particle group corresponding to the target low-voltage substation; determines the first fitness data of the first particle group based on the electrical parameter set; iteratively updates the first particle group according to the preset particle swarm algorithm and the first fitness data to obtain a second particle group; detects and corrects the second particle group according to the preset error correction mechanism to obtain second fitness data; iteratively updates the second particle group according to the particle swarm algorithm and the second fitness data to obtain a third particle group; determines the particle with the highest fitness in the third particle group as the global optimal particle; and determines the target topology structure of the target low-voltage substation based on 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 topological rationality assessment, the error correction mechanism is used to dynamically detect and correct anomalies and misjudgments to ensure stability, and the iterative feedback allows the identification process to continuously improve itself to adapt to the dynamically changing environment, thereby improving the accuracy of the low-voltage substation topology structure identification.

[0024] For easier understanding, see Figure 1 , Figure 1 This is a system architecture diagram of a low-voltage substation topology structure identification system provided in an embodiment of the present application. The low-voltage substation topology structure identification system includes a data acquisition module, a data preprocessing module, a particle swarm topology identification module, an error correction mechanism module and a result output module.

[0025] The data acquisition module is responsible for collecting various raw data related to grid operation within the low-voltage substation and serves as the data source for the entire topology identification system. For example, the data acquisition module can collect electrical parameter data, such as voltage parameters (including voltage amplitude and phase), current parameters (current magnitude and direction), and power parameters (active power and reactive power) for each node, from various sensors deployed within the low-voltage substation, such as voltage transformers, current transformers, and power sensors. It also collects basic device information, such as node type (transformer node, branch box node, user node, etc.) and location coordinates.

[0026] The data preprocessing module is responsible for processing the raw data acquired by the data acquisition module, improving its quality to meet the requirements of the subsequent topology recognition algorithm. Firstly, it cleans the data to remove noise and outliers (such as obviously erroneous measurements or data errors due to equipment failure). Secondly, it normalizes and standardizes the data to unify its dimensions and value range, facilitating subsequent algorithm calculations. Furthermore, it may interpolate missing data, estimating missing values ​​based on existing data to ensure data integrity.

[0027] The particle swarm topology recognition module, based on the particle swarm algorithm (PSO), utilizes preprocessed data to perform preliminary identification of the low-voltage substation's topology. First, a list of node connection pairs is determined based on the total number of nodes, which in turn determines the length of the binary-coded vector. Multiple particles are randomly generated (each particle corresponds to a binary-coded vector, representing a possible topology) to form an initial particle swarm. The particle swarm's fitness data is then calculated based on the electrical parameter set, and the fitness is used to evaluate the quality of the topology represented by each particle. The particle swarm is then iteratively updated according to the PSO algorithm's rules, continuously adjusting the particle's speed and position to gradually converge toward a more optimal topology, resulting in preliminary topology recognition results.

[0028] The error correction mechanism module further verifies and corrects the topology obtained by the particle swarm topology identification module. The initially identified topology undergoes physical connection consistency testing (checking compliance with pre-set grid physical connection rules, such as the correct connection between transformers, branch boxes, and user nodes) and load distribution anomaly detection (analyzing the rationality of the load distribution of adjacent nodes and any abnormalities such as sudden load changes). This results in physical connection error and load distribution anomaly error values. Based on these error values, the particle error and swarm error values ​​are determined. Combined with a pre-set calculation formula and error penalty coefficient, the particle fitness is adjusted to reduce the fitness of topologies with large errors. This reduces the selection of these erroneous solutions in subsequent iterations or screening, enabling the system to search for more accurate topologies.

[0029] The result output module outputs the target topology, corrected by the error correction mechanism module, in user-interpretable graphical and data formats. Graphically, this module visualizes the location and connectivity of each node within the substation, distinguishing different topological areas with distinct colors and patterns. Data-wise, it provides a list of node connection pairs and detailed electrical parameters for each node. Furthermore, the output can be directly integrated with the distribution network automation system, providing accurate topological information support for dynamic topology management, fault diagnosis, and dispatch optimization.

[0030] It can be seen that the original data of the low-voltage substation is obtained through the data acquisition module, and after being cleaned and standardized by the data preprocessing module, the particle swarm topology recognition module preliminarily identifies the topology based on the algorithm, and then the unreasonable connections are 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; it can effectively avoid the defect of traditional algorithms that are prone to falling into local optimality, take into account the globality and accuracy in the identification process, and use the excellent characteristics of the particle swarm algorithm to improve the efficiency and stability of topology recognition, ensuring that efficient, fast and stable low-voltage substation topology structure recognition can be achieved in a dynamically changing and noisy data environment.

[0031] The following combination Figure 2 The electronic device in the embodiment of the present application is described. Figure 2 is a structural diagram of an electronic device provided in an embodiment of the present application, such as Figure 2 As shown, the electronic device includes one or more processors, a memory, a communication interface and one or more programs, and the processor is communicatively connected with the memory and the communication interface via an internal communication bus.

[0032] Among other things, the processor can be used to: Obtain the electrical parameters of each node in the target low-voltage area to obtain an electrical parameter set; Determine the first particle group corresponding to the target low-pressure area; determining first fitness data of a 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 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 group as the global optimal particle; The target topology of the target low-pressure area is determined based on the global optimal particles.

[0033] The one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for executing any step in the method embodiment.

[0034] The processor may 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. It may implement or execute the various exemplary logic blocks, units, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on. The communication unit may be a communication interface, a transceiver, a transceiver circuit, etc., and the storage unit may be a memory.

[0035] The memory may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM), which is used as an external cache memory. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM).

[0036] It is understood that the electronic device may include more or fewer structural elements than those in the above structural block diagram, for example, including a power module, physical buttons, Wi-Fi module, speaker, Bluetooth module, sensor, display module, etc., which are not limited here. It is understood that the electronic device may be equipped with Figure 1 The system architecture described.

[0037] For easier understanding, see Figure 3 , Figure 3 This is an application scenario diagram of a topology structure identification system provided by an embodiment of the present application, wherein the target low-voltage substation includes transformers, branch boxes, user nodes and other equipment, which are the objects of topology identification, and the electrical parameter set includes electrical data such as voltage, current, and power collected from the target low-voltage substation. The topology structure identification system can obtain the electrical parameter set of the target low-voltage substation through the data acquisition module, and 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, and then use the error correction mechanism module to correct the preliminary identified topology structure to obtain the target topology structure, and finally output the target topology structure to the target low-voltage substation in the form of graphics and data through the result output module.

[0038] After understanding the software and hardware architecture of this application, Figure 4 A method for identifying the low-voltage substation topology structure based on a particle swarm algorithm in an embodiment of the present application is described. Figure 4 This is a flow chart of a method for identifying a low-voltage substation topology structure based on a particle swarm algorithm provided in an embodiment of the present application, which specifically includes the following steps: Step S401: Acquire electrical parameters of each node in the target low-voltage substation to obtain an electrical parameter set.

[0039] Specifically, smart meters and sensors in the target low-voltage substation can be used to collect electrical parameters (such as voltage, current, and power) from various nodes (such as transformers, user meters, and branch boxes) to obtain an electrical parameter set. This electrical parameter data can be preprocessed to eliminate abnormal data. For example, missing values ​​can be filled using time series data, and normalization can be performed to ensure uniform data scaling, thereby enhancing subsequent data processing.

[0040] Step S402: determining a first particle group corresponding to the target low-pressure area.

[0041] For easier understanding, see Figure 5 , Figure 5 : This is a flow chart of determining a first particle group according to an embodiment of the present application, wherein the first particle group corresponding to the target low-pressure area is determined, and the specific steps include: A1. Obtain the total number of nodes corresponding to all nodes in the target low-voltage area; A2. Determine a node connection pair list according to the total number of nodes; the node connection pair list includes M connection pairs, where M is a positive integer; A3. Determine a vector length of a binary code vector according to the M connection pairs; the binary code vector includes M elements, each element including 0 or 1; A4. Randomly generate m particles according to the length of the vector; each particle corresponds to a binary code vector; m is an integer greater than 1; A5. Determine the first particle group based on the m particles.

[0042] In a specific embodiment, the total number of nodes corresponding to all nodes in the target low-voltage substation is first obtained. Based on the total number of nodes, all possible physical connection pairs between nodes are enumerated to obtain a node connection pair list. The node connection pair list includes M connection pairs excluding the node's own connection, where M is a positive integer. When the total number of nodes is N, M = N × (N-1) / 2. Then, based on the M connection pairs, the vector length of the binary encoding vector is determined. The binary encoding vector includes M elements, each of which is either 0 or 1. The vector length of the binary encoding vector for a particle is equal to the total number of possible connection pairs between any two nodes. Connection pairs are represented in an unordered form. For example, the connection between node i and node j is simply recorded as (ij), and (ji) is not repeated. For example, when N = 4 (e.g., nodes 1, 2, 3, and 4), the possible connection pairs are (1-2), (1-3), (1-4), (2-3), (2-4), and (3-4), for a total of 4 × 3 / 2 = 6 possible connection pairs, resulting in a vector length of 6. It should be noted that the kth bit in the binary encoding vector corresponds to the kth connection pair. A "1" indicates that the connection pair is electrically connected, and a "0" indicates that there is no electrical connection. For example, if the connection between nodes 1 and 2 forms the third connection pair, a "1" in the encoding vector indicates that the two are electrically connected. Each particle represents a possible node connection combination. The encoding method of the particle is based on the binary code of whether there is an electrical connection between the nodes. The length of the vector is equal to the number of possible connection pairs.

[0043] Next, m particles are randomly generated based on the vector length. Each particle corresponds to a binary code vector, where m is an integer greater than 1. The elements in the binary code vector corresponding to each particle can be generated as "0" or "1" using a preset random function to simulate different candidate topologies. In the initial stage of topology identification using the particle swarm algorithm, particles are randomly generated. During subsequent iterations, the particle positions (i.e., binary code vectors) are adjusted based on their own optimal positions and the global optimal position, gradually optimizing the candidate topologies. Finally, the generated m particles are defined as the first particle swarm, serving as the initial set of candidate topologies for the particle swarm algorithm's iterative optimization.

[0044] It can be seen that by converting the node connection relationship into binary code and randomly generating initial particles, the particle swarm algorithm is provided with an initial solution space suitable for topology recognition, ensuring the global search capability and algorithm versatility.

[0045] Step S403: determining first fitness data of the first particle swarm according to the electrical parameter set.

[0046] The electrical parameter set includes a voltage parameter set, a current parameter set, and a power parameter set. The first fitness data of the first particle swarm is determined according to the electrical parameter set. Specifically, the steps include: B1. Determine a first topological structure corresponding to a reference particle; the reference particle is any one of the m particles; B2. Performing rule verification on the first topology structure according to preset power grid rules to obtain a first score; B3. Determine a mean power deviation rate of all adjacent nodes of the first topology structure according to the power parameter set, and determine a second score according to the mean power deviation rate; B4. Determine a connection relationship corresponding to the first topological structure; B5. Determine a theoretical voltage parameter set and a theoretical current parameter set according to the connection relationship; B6. determining a first sum of squared errors based on the theoretical voltage parameter set and the voltage parameter set; B7. determining a second sum of squared errors based on the theoretical current parameter set and the current parameter set; B8. Normalize the first square error and the second square error respectively, and sum them to obtain a third square error sum; B9. Determine a third score according to the third sum of squared errors; B10. Perform weighted summation based on the first score, the second score, the third score, a preset first weight, a second weight, and a third weight to obtain the fitness corresponding to the reference particle in the first fitness data.

[0047] In a specific embodiment, the fitness of each particle in the first particle swarm is first determined based on the electrical parameter set to obtain first fitness data. A reference particle is any one of the m particles, and its corresponding binary code vector (a 0 / 1 combination) is directly mapped to the first candidate topology. Specifically, a connection pair corresponding to a "1" in the binary code vector indicates an actual connection between nodes. Then, based on preset grid electrical rules (such as "transformers must be directly connected to branch boxes," "in-phase nodes can be interconnected," and "closed loops are prohibited"), the first topology is checked to obtain a first score. For example, if a violation occurs, such as "transformers directly connected to user nodes," a 0.2 point deduction is made. If the rules are fully met, the full score is awarded, with a minimum score of 0 and a maximum score of 1. These are not specifically limited here.

[0048] Next, the power deviation rate (such as the ratio of the actual power difference to the theoretical distribution value) of all adjacent node pairs (directly connected nodes) in the first topology structure is calculated based on the power parameter set, and the average is taken. The smaller the average 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 range of the second score is 0-1 points. The calculation formula of the power deviation rate is: , , Indicates the node power parameter of any adjacent node pair.

[0049] Then, all actual connection relationships in the first topology are determined. Based on these connection relationships and circuit theory (e.g., Kirchhoff's laws and line impedance models), the theoretical voltage and theoretical current of each node in the first topology are calculated to form a theoretical voltage parameter set and a theoretical current parameter set. A first sum of squared errors between the theoretical voltage and the measured voltage are calculated based on the theoretical voltage parameter set and the voltage parameter set. A second sum of squared errors between the theoretical current and the measured current are calculated based on the theoretical current parameter set and the current parameter set. The first and second sums of squared errors are then normalized (to eliminate dimensional differences) and summed to obtain a third sum of squared errors, which comprehensively reflects the overall fitting effect of the electrical parameters. A third score is then determined based on the third sum of squared errors. A smaller third sum of squared errors indicates a closer fit between the first topology and the measured data, and a higher third score is assigned. The third score ranges from 0 to 1.

[0050] Finally, the first, second, and third weights can be set according to actual needs. A weighted sum is then taken based on the first score, second score, third score, first weight, second weight, and third weight to obtain the fitness corresponding to the reference particle in the first fitness data. All particles in the first particle swarm are processed according to the fitness calculation steps for the reference particle to obtain the first fitness data.

[0051] It can be seen that through multi-dimensional evaluation (conformity with physical rules, coordination of load distribution, and electrical data fitting) and weighted fusion, a comprehensive and scientific quantification of the topological structure is achieved, which provides a precise optimization guide for the particle swarm algorithm and ensures the accuracy of the recognition results.

[0052] Step S404 : iteratively updating the first particle swarm according to a preset particle swarm algorithm and the first fitness data to obtain a second particle swarm.

[0053] For easier understanding, see Figure 6 , Figure 6 : is a flow chart of an iterative update of a particle swarm provided in an embodiment of the present application, wherein the first particle swarm is iteratively updated according to the preset particle swarm algorithm and the first fitness data to obtain a second particle swarm, and the specific steps include: C1. Determine the fitness of each of the m particles according to the first fitness data to obtain m first fitnesses; C2. Determine 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; C3. Determine 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 among the m first fitnesses; C4. Determine m initial particle velocities corresponding to the first particle group; C5. 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.

[0054] In a specific embodiment, the fitness of each of the m particles is first extracted from the first fitness data, resulting in m first fitnesses, which serve as the initial basis for evaluating the quality of each candidate topology. Then, the initial optimal position of each particle (corresponding to the initial topology) is provisionally determined as its own optimal position, associated with the corresponding first fitness, 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 for the entire swarm, representing the optimal topology found by the current swarm. Next, initial particle velocities are randomly assigned to the m particles in the first swarm, resulting in m initial particle velocities. Finally, based on the particle swarm algorithm, the initial particle velocity, initial optimal position, and global optimal position of each particle are combined to iteratively adjust the particle velocity and position (i.e., optimize the topology) until convergence conditions are met (e.g., the global optimal fitness stabilizes), ultimately forming an optimized second swarm.

[0055] It can be seen that through the collaborative guidance of individual optimality and global optimality, the particle swarm gradually converges to a better topological structure, which improves the efficiency of topology recognition and the global optimization ability.

[0056] 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 specifically comprises the following steps: D1. Update the m initial particle velocities according to the velocity update formula corresponding to the particle swarm algorithm to obtain m first particle velocities; D2. determining m adjustment probabilities corresponding to the m first particle velocities according to a preset activation function; D3. Update the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions; D4. Determine m reference fitnesses corresponding to the m first particle positions; D5. Update the m first particle positions according to the m reference fitness values ​​to obtain m first optimal positions; D6. Determine the first optimal position with the highest fitness among the m first optimal positions as the first global optimal position; D7. Determine a reference second particle group according to the m first particle velocities, the m first optimal positions, and the first global optimal position; D8. 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 continued to be iteratively updated until the convergence condition is met.

[0057] In a specific embodiment, first, according to the velocity update formula corresponding to the particle swarm algorithm, the initial particle velocity, initial optimal position, and initial global optimal position of the particles are combined to calculate the m first particle velocities corresponding to the m particles. The velocity update formula is as follows:

[0058] in, Indicates that the i-th particle is Updated particle velocity after iterations; Indicates that the i-th particle is Updated particle velocity after iterations; Inertia weight, which is used to balance the global exploration and local development capabilities of particles (for example, a larger inertia weight enhances global search, while a smaller inertia weight enhances local optimization); 、 Represents the learning factor, which controls the weight of the particle learning to its own optimal position and the global optimal position respectively; 、 Represents a random number in the interval [0,1], which is used to increase the randomness of the search and prevent the algorithm from falling into a local optimum; Represents the current historical optimal position of the i-th particle, such as the initial optimal position; Indicates the current global optimal position of the particle swarm, such as the initial global optimal position of the first particle swarm; Indicates that the i-th particle is Updated particle positions after iterations.

[0059] Next, a preset activation function (such as a sigmoid function) is used to convert the first particle velocity into an adjustment probability, quantifying the possibility of adjusting the particle position, resulting in m adjustment probabilities. Based on the m adjustment probabilities, the initial optimal positions (i.e., binary encoding vectors) of the m particles are updated (e.g., by flipping the encoding bits from 0 to 1 or 1 to 0), generating m first particle positions, i.e., new candidate topologies. Next, m reference fitness values ​​corresponding to the m first particle positions are calculated, and the m first particle positions are updated based on the m reference fitness values, resulting in m first optimal positions. If a particle's reference fitness value is higher than its current fitness value, the particle's current position is updated as the first particle position. The first first optimal position is then selected from the m first optimal positions with the highest fitness value as the first global optimal position.

[0060] Finally, a reference second particle swarm is determined based on 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 iteratively updated until the convergence condition is met. The convergence condition can be that the change in fitness corresponding to the global optimal position for five consecutive iterations is less than 0.001, which is not specifically limited here.

[0061] It can be seen that the combination of individual and global optimal co-evolution enables the particle swarm to efficiently converge to a better topological structure, which not only ensures the globality of the search but also improves the recognition accuracy and efficiency.

[0062] The updating of the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions specifically comprises the following steps: E1. Determine a reference binary code 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 among the m adjustment probabilities; E2. Generate M random numbers based on the reference binary code vector; each random number corresponds to an element in the reference binary code vector; E3. If there is a random number among the M random numbers that is less than the reference adjustment probability, flip the value of the element corresponding to the random number to obtain an updated reference binary code vector; E4. Determine the first particle position corresponding to the reference initial optimal position among the m first particle positions according to the updated reference binary code vector.

[0063] In a specific embodiment, a reference binary code vector and a reference adjustment probability corresponding to a reference initial optimal position can be first 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, for the M elements of the reference binary code vector (each element corresponds to a node connection pair), M random numbers in the range [0, 1] are generated, with each random number corresponding one-to-one to an element in the code vector. Next, each random number is compared with the reference adjustment probability one by one. If any random number is less than the reference adjustment probability, indicating that the position requires adjustment, the value of the corresponding element is flipped (from 0 to 1 or from 1 to 0). If the random number is greater than or equal to the reference adjustment probability, the value of the element remains unchanged, ultimately obtaining an updated reference binary code vector. Finally, based on the updated reference binary code vector, the first particle position corresponding to the reference initial optimal position among the m first particle positions is determined. Repeating the update process for the reference initial optimal position for each of the m initial optimal positions yields m first particle positions.

[0064] It can be seen that the adaptive flipping of coding bits is achieved by comparing random numbers with adjustment probabilities, which not only ensures the randomness of particle position updates to expand the search space, but also preserves the effective connection of high-quality topological structures through probabilistic control, thereby improving the pertinence and efficiency of particle swarm optimization.

[0065] Step S405 : detecting and correcting the second particle swarm according to a preset error correction mechanism to obtain second fitness data.

[0066] The detecting and correcting of the second particle swarm according to the preset error correction mechanism to obtain the second fitness data specifically includes the following steps: F1. Determine the topological structure corresponding to each particle of the second particle group to obtain m second topological structures; F2. Performing a preset physical connection consistency check and load distribution anomaly check based on the m second topological structures to obtain m physical connection error values ​​and m load distribution anomaly error values; F3. Determine m particle error values ​​according to the m physical connection error values ​​and the m load distribution abnormality error values; each particle error value corresponds to a physical connection error value and a load distribution abnormality error value; F4. Determine the maximum value among the m particle error values ​​as the population error value; F5. Determine reference second fitness data corresponding to the second particle swarm; F6. 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.

[0067] In a specific embodiment, the binary code vector corresponding to each particle in the second particle swarm is first extracted and converted into a specific node connection relationship, resulting in m second topological structures, which are used as detection targets for the error correction mechanism. Then, based on the physical connection rules of the low-voltage substation (such as "transformers must be connected to users through branch boxes" and "loops are prohibited"), each second topological structure is tested for physical connection consistency. The number or degree of rule violations is calculated, resulting in m physical connection error values. A larger physical connection error value indicates a lower physical plausibility.

[0068] Next, load distribution anomaly detection is performed based on the m adjacent node pairs of the second topology structure and the power time series data of each node. The relevant Pearson coefficient of the power curve of each adjacent node pair is calculated, and the coefficient below the threshold (such as 0.6) is marked as abnormal. The number of anomalies is counted and the load distribution anomaly error value is calculated (such as the number of anomalies / the total number of adjacent node pairs), and m load distribution anomaly error values ​​are output.

[0069] Then, m particle error values ​​are determined based on 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. The particle error value is the average of the physical connection error value and the load distribution anomaly error value. The maximum value of the m particle error values ​​is then used as the population error value, and the reference second fitness data corresponding to the second particle population 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. Among them, the calculation formula corresponding to the error correction mechanism is as follows:

[0070] in, 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 the error penalty coefficient, which ranges from [0,1] and is used to control the impact of the error on fitness; represents the particle error value corresponding to the i-th particle; Indicates the population error value corresponding to the current particle swarm.

[0071] It can be seen that by detecting errors based on physical rules and load characteristics and dynamically correcting the fitness through error correction mechanisms, the physical irrationality of the topological structure is eliminated, the coordination of the load distribution is strengthened, and the accuracy of the particle swarm algorithm in screening high-quality topologies is improved.

[0072] Step S406: iteratively update the second particle swarm according to the particle swarm algorithm and the second fitness data to obtain a third particle swarm.

[0073] Specifically, starting from the second particle swarm, using the particle swarm algorithm, combined with the second fitness data corrected by the error correction mechanism, repeatedly perform speed update, position adjustment, fitness evaluation, individual optimal and global optimal update operations until the convergence condition is met, and the third particle swarm is obtained.

[0074] Step S407: determining the particle with the highest fitness in the third particle swarm as the global optimal particle.

[0075] Specifically, the particle with the highest fitness is selected from the third particle group and is used as the global optimal particle.

[0076] Step S408: determining a target topological structure of the target low-pressure area according to the global optimal particle.

[0077] Specifically, the binary coding vector corresponding to the global optimal particle is parsed: 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 substation, where the element "1" indicates that the corresponding node pair is physically connected, and the element "0" indicates that the corresponding node pair is not physically connected. Finally, the target topology structure of the target low-voltage substation is determined based on the parsing results. The target topology structure obtained after error correction can be output in the form of graphics and data to support the distribution network automation system to achieve dynamic topology management, fault diagnosis and scheduling optimization.

[0078] For easier understanding, see Figure 7 , Figure 7 This is a structural diagram of a target topology structure provided by an embodiment of the present application, wherein each dot represents a different grid node in the target low-voltage substation, wherein solid dots represent nodes corresponding to known information (such as line outlets), and dashed dots represent nodes corresponding to unknown information to be identified, and the solid lines between the nodes represent the actual connection relationship of the electrical lines. The first topology area includes nodes 1, 2, 5, and 6, and the second topology area includes nodes 3, 4, 7, 8, and 9, wherein the error correction area also includes node 2, indicating that node 2 has irrationality (such as incorrect association, non-compliance with physical rules, etc.), and needs to be triggered by the error correction mechanism to improve the accuracy and rationality of the entire target topology structure identification.

[0079] The above mainly introduces the solution of the embodiment of the present application from the perspective of the execution process of the method side. It is understandable that, in order to realize the above functions, the electronic device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0080] The embodiment of the present application can divide the functional units of the electronic device according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0081] In the case of dividing each functional module into corresponding functional modules, Figure 8 This is a functional module block diagram of a low-voltage area topology structure identification device based on a particle swarm algorithm provided in an embodiment of the present application. The low-voltage area topology structure identification device 800 based on a particle swarm algorithm includes an acquisition module 810, a determination module 820, an update module 830, and an error correction module 840, wherein: The acquisition module 810 is used to acquire electrical parameters of each node in the target low-voltage area to obtain an electrical parameter set; The determining module 820 is configured to determine a first particle swarm corresponding to the target low-voltage area; and determine first fitness data of the first particle swarm based on the electrical parameter set. The updating module 830 is configured to iteratively update the first particle swarm according to a preset particle swarm algorithm and the first fitness data to obtain a second particle swarm; The error correction module 840 is used to detect and correct the second particle swarm according to a preset error correction mechanism to obtain second fitness data; The updating module 830 is further configured to iteratively update the second particle swarm according to the particle swarm algorithm and the second fitness data to obtain a third particle swarm; The determination module 820 is further configured to determine the particle with the highest fitness in the third particle swarm as the global optimal particle; and determine the target topology of the target low-pressure station area based on the global optimal particle.

[0082] Optionally, in determining the first particle swarm corresponding to the target low-pressure area, the determining module 820 is specifically configured to: Obtain the total number of nodes corresponding to all nodes in the target low-voltage area; Determine a node connection pair list according to the total number of nodes; the node connection pair list includes M connection pairs, where M is a positive integer; Determine a vector length of a binary coded vector according to the M connection pairs; the binary coded vector includes M elements, each element includes 0 or 1; m particles are randomly generated according to the length of the vector; each particle corresponds to a binary code vector; m is an integer greater than 1; The first particle group is determined based on the m particles.

[0083] Optionally, the electrical parameter set includes a voltage parameter set, a current parameter set, and a power parameter set. In determining the first fitness data of the first particle swarm according to the electrical parameter set, the determination module 820 is further specifically configured to: Determine a first topological structure corresponding to a reference particle; the reference particle is any one of the m particles; Performing rule verification on the first topology structure according to preset power grid rules to obtain a first score; Determine a mean power deviation rate of all adjacent nodes of the first topology structure according to the power parameter set, and determine a second score according to the mean power deviation rate; Determining a connection relationship corresponding to the first topological structure; Determining a theoretical voltage parameter set and a theoretical current parameter set according to the connection relationship; determining a first sum of squared errors according to the theoretical voltage parameter set and the voltage parameter set; determining a second sum of squared errors according to the theoretical current parameter set and the current parameter set; Normalizing the first square error and the second square error respectively and summing them to obtain a third square error; determining a third score according to the third sum of squared errors; A fitness corresponding to the reference particle in the first fitness data is obtained by performing a weighted summation based on the first score, the second score, the third score, a preset first weight, a second weight, and a third weight.

[0084] Optionally, in the aspect of iteratively updating the first particle swarm according to the preset particle swarm algorithm and the first fitness data to obtain the second particle swarm, the updating module 830 is specifically configured to: determining the fitness of each of the m particles according to the first fitness data to obtain m first fitnesses; 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 fitness; Determine 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 among the m first fitnesses; Determining m initial particle velocities corresponding to the first particle group; 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.

[0085] Optionally, in the aspect of 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, the updating module 830 is further specifically configured to: The m initial particle velocities are updated according to the velocity update 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; The m initial optimal positions are updated 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 fitness values ​​to obtain m first optimal positions; Determine the first optimal position with the highest fitness among the m first optimal positions as the first global optimal position; determining a reference second particle group 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 until the convergence condition is met.

[0086] Optionally, in updating the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions, the updating module 830 is further specifically configured to: Determine a reference binary code 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 among the m adjustment probabilities; Generate M random numbers based on the reference binary code vector; each random number corresponds to an element in the reference binary code vector; If there is a random number among the M random numbers that is less than the reference adjustment probability, flip the value of the element corresponding to the random number to obtain an updated reference binary code vector; The first particle position corresponding to the reference initial optimal position among the m first particle positions is determined according to the updated reference binary code vector.

[0087] Optionally, in the aspect of detecting and correcting the second particle swarm according to a preset error correction mechanism to obtain the second fitness data, the error correction module 840 is specifically configured to: Determine a topological structure corresponding to each particle of the second particle group to obtain m second topological structures; Performing a preset physical connection consistency check and load distribution anomaly check according to the m second topology structures to obtain m physical connection error values ​​and m load distribution anomaly error values; determining m particle error values ​​according to the m physical connection error values ​​and the m load distribution abnormality error values; each particle error value corresponds to a physical connection error value and a load distribution abnormality error value; Determine the maximum value among the m particle error values ​​as the population error value; Determining reference second fitness data corresponding to the second particle swarm; 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.

[0088] It can be seen that the global optimization search of the particle swarm algorithm is used to enhance the globality and accuracy of recognition, the fitness data is used to improve the topological rationality assessment, the error correction mechanism is used to dynamically detect and correct anomalies and misjudgments to ensure stability, and the iterative feedback is used to enable the recognition process to continuously improve itself to adapt to the dynamically changing environment, thereby improving the accuracy of identifying the topological structure of the low-voltage substation area.

[0089] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above. The low-voltage substation topology structure identification device 800 based on the particle swarm algorithm can be used to execute the above method embodiment of this application, which will not be repeated here.

[0090] An 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 enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0091] The present application also provides a computer program product comprising a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may comprise an electronic device.

[0092] It should be noted that, for the above-mentioned various embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. Those skilled in the art should know that this application is not limited by the order of the actions described, because some steps in the embodiments of the present application can be performed in other orders or simultaneously. In addition, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions, steps, modules or units involved are not necessarily required by the embodiments of the present application.

[0093] In the above embodiments, the embodiments of the present application have different focuses on the description of each embodiment. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0094] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0095] The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, removable hard disk, CD-ROM, or any other form of storage medium 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 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 storage medium can also exist as discrete components in the terminal device or the management device.

[0096] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part via software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. This computer program product comprises one or more computer instructions. When these computer program instructions are loaded and executed on a computer, they fully or partially produce 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 device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0097] The modules / units included in the various devices and products described in the above embodiments may be software modules / units, hardware modules / units, or partly software modules / units and partly hardware modules / units. For example, for various devices and products applied to or integrated into a chip, the modules / units included therein may all be implemented in the form of hardware such as circuits, or at least part of the modules / units may be implemented in the form of software programs, which run on a processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated into a chip module, the modules / units included therein may all be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as a chip, circuit module, etc.) or different components of the chip module, or at least part of the modules / units may be It is implemented in the form of a software program, which runs on the processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal equipment, or at least some modules / units can be implemented in the form of a software program, which runs on the processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits.

[0098] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only a specific implementation method of the embodiments of the present application and is not intended to limit the scope of protection of the embodiments of the present application. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the scope of protection of the embodiments of the present application.

Claims

1. A method for identifying low-voltage substation topology based on particle swarm optimization, characterized in that: The method comprises: Obtain the electrical parameters of each node in the target low-voltage area to obtain an electrical parameter set; Determining a first particle group corresponding to the target low-pressure 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 the particle with the highest fitness in the third particle swarm as the global optimal particle; A target topological structure of the target low-pressure area is determined according to the global optimal particle.

2. The method according to claim 1, wherein The determining of the first particle group corresponding to the target low-pressure area includes: Obtain the total number of nodes corresponding to all nodes in the target low-voltage area; Determine a node connection pair list according to the total number of nodes; the node connection pair list includes M connection pairs, where M is a positive integer; Determine a vector length of a binary coded vector according to the M connection pairs; the binary coded vector includes M elements, each element includes 0 or 1; m particles are randomly generated according to the length of the vector; each particle corresponds to a binary code vector; m is an integer greater than 1; The first particle group is determined based on the m particles.

3. The method according to claim 2, wherein The electrical parameter set includes a voltage parameter set, a current parameter set, and a power parameter set. Determining the first fitness data of the first particle swarm according to the electrical parameter set includes: Determine a first topological structure corresponding to a reference particle; the reference particle is any one of the m particles; Performing rule verification on the first topology structure according to preset power grid rules to obtain a first score; Determine a mean power deviation rate of all adjacent nodes of the first topology structure according to the power parameter set, and determine a second score according to the mean power deviation rate; Determining a connection relationship corresponding to the first topological structure; Determining a theoretical voltage parameter set and a theoretical current parameter set according to the connection relationship; determining a first sum of squared errors according to the theoretical voltage parameter set and the voltage parameter set; determining a second sum of squared errors according to the theoretical current parameter set and the current parameter set; Normalizing the first square error and the second square error respectively and summing them to obtain a third square error; determining a third score according to the third sum of squared errors; A fitness corresponding to the reference particle in the first fitness data is obtained by performing a weighted summation based on the first score, the second score, the third score, a preset first weight, a second weight, and a third weight.

4. The method according to claim 2, wherein The iterative updating of the first particle swarm according to the preset particle swarm algorithm and the first fitness data to obtain a second particle swarm includes: determining the fitness of each of the m particles according to the first fitness data to obtain m first fitnesses; 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 fitness; Determine 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 among the m first fitnesses; Determining m initial particle velocities corresponding to the first particle group; 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.

5. The method according to claim 4, 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 includes: The m initial particle velocities are updated according to the velocity update 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; The m initial optimal positions are updated 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 fitness values ​​to obtain m first optimal positions; Determine the first optimal position with the highest fitness among the m first optimal positions as the first global optimal position; determining a reference second particle group 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 until the convergence condition is met.

6. The method according to claim 5, wherein The updating of the m initial optimal positions according to the m adjustment probabilities to obtain m first particle positions includes: Determine a reference binary code 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 among the m adjustment probabilities; Generate M random numbers based on the reference binary code vector; each random number corresponds to an element in the reference binary code vector; If there is a random number among the M random numbers that is less than the reference adjustment probability, flip the value of the element corresponding to the random number to obtain an updated reference binary code vector; The first particle position corresponding to the reference initial optimal position among the m first particle positions is determined according to the updated reference binary code vector.

7. The method according to any one of claims 2 to 6, wherein: The detecting and correcting the second particle swarm according to a preset error correction mechanism to obtain second fitness data includes: Determine a topological structure corresponding to each particle of the second particle group to obtain m second topological structures; Performing a preset physical connection consistency check and load distribution anomaly check according to the m second topology structures to obtain m physical connection error values ​​and m load distribution anomaly error values; determining m particle error values ​​according to the m physical connection error values ​​and the m load distribution abnormality error values; each particle error value corresponds to a physical connection error value and a load distribution abnormality error value; Determine the maximum value among the m particle error values ​​as the population error value; Determining reference second fitness data corresponding to the second particle swarm; 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.

8. A low voltage substation topology structure identification device based on particle swarm algorithm, characterized in that: The device includes an acquisition module, a determination module, an update module, and an error correction module, wherein: The acquisition module is used to acquire the electrical parameters of each node in the target low-voltage area to obtain an electrical parameter set; The determining module is configured to determine a first particle swarm corresponding to the target low-voltage area; and determine first fitness data of the first particle swarm according to the electrical parameter set; The updating module is configured to iteratively update the first particle swarm according to a preset particle swarm algorithm and the first fitness data to obtain a second particle swarm; The error correction module is used to detect and correct the second particle swarm according to a preset error correction mechanism to obtain second fitness data; The updating module is further configured to iteratively update the second particle swarm according to the particle swarm algorithm and the second fitness data to obtain a third particle swarm; The determination module is further configured to determine the particle with the highest fitness in the third particle swarm as the global optimal particle; and determine the target topology of the target low-pressure station area based on the global optimal particle.

9. An electronic device, characterized in that: include: 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, wherein the programs include instructions for executing the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images