Topology construction method of power distribution network system and related device

Abstract

The invention discloses a topology construction method of a power distribution network system and a related device. The topology construction method comprises the steps of collecting first power grid operation data of a target power distribution network system in a first preset time period; performing data preprocessing on the first power grid operation data to obtain second power grid operation data; topological nodes and node types corresponding to the target power distribution network system are determined according to the second power grid operation data, and n topological nodes and n node types are obtained; constructing a first topological graph according to the n topological nodes and the n node types; optimizing the first topological graph by adopting a preset particle swarm optimization algorithm to obtain a second topological graph; acquiring third power grid operation data of the target power distribution network system in a second preset time period; and updating the second topological graph according to the third power grid operation data to obtain a third topological graph. According to the embodiment of the invention, the response speed and accuracy of the topological graph to the state change of the power grid are improved.

Description

Technical Field

[0001] The present application relates to the technical field of power distribution networks, and in particular to a topology construction method and related devices for a power distribution network system. Background Art

[0002] As a key urban infrastructure, the distribution network serves as a bridge between the power grid and users. The distribution network topology directly reflects the grid's topological state and is essential graphical data for power system operation and management.

[0003] Traditional topology construction methods mostly use static layout algorithms, such as force-directed layout algorithms. Although they can better display the initial structure of the power grid, they often find it difficult to reflect these changes in a timely and effective manner when faced with frequent changes in the power grid's operating status, resulting in information lag and affecting decision-making efficiency.

[0004] Therefore, how to improve the response speed and accuracy of the topology map to changes in the power grid state. Summary of the Invention

[0005] The embodiments of the present application provide a topology construction method and related devices for a power distribution network system, which improve the response speed and accuracy of the topology map to changes in the power grid state.

[0006] In a first aspect, an embodiment of the present application provides a method for constructing a topology of a power distribution network system, the method comprising:

[0007] Collecting first grid operation data of a target distribution network system within a first preset time period; the first grid operation data includes at least one of the following: voltage and current data, power data, power generation and consumption data, and transaction data;

[0008] performing data preprocessing on the first power grid operation data to obtain second power grid operation data;

[0009] Determine the topological nodes and node types corresponding to the target distribution network system according to the second power grid operation data, and obtain n topological nodes and n node types; each topological node corresponds to a node type; n is an integer greater than 1;

[0010] Constructing a first topological graph according to the n topological nodes and the n node types;

[0011] Optimizing the first topology graph using a preset particle swarm optimization algorithm to obtain a second topology graph;

[0012] Collecting third power grid operation data of the target distribution network system within a second preset time period; the start time of the second preset time period is later than the end time of the first preset time period;

[0013] The second topology map is updated according to the third power grid operation data to obtain a third topology map.

[0014] In a second aspect, an embodiment of the present application provides a topology construction device for a distribution network system, the device comprising: a collection unit, a control unit, and a topology construction unit, wherein:

[0015] The collecting unit is configured to collect first grid operation data of the target distribution network system within a first preset time period; the first grid operation data includes at least one of the following: voltage and current data, power data, power generation and consumption data, and transaction data;

[0016] The control unit is configured to perform data preprocessing on the first power grid operation data to obtain second power grid operation data; determine the topological nodes and node types corresponding to the target distribution network system based on the second power grid operation data, and obtain n topological nodes and n node types; each topological node corresponds to a node type; n is an integer greater than 1;

[0017] The topology construction unit is configured to construct a first topology graph according to the n topology nodes and the n node types; and optimize the first topology graph using a preset particle swarm optimization algorithm to obtain a second topology graph;

[0018] The collecting unit is further configured to collect third power grid operation data of the target distribution network system within a second preset time period; the start time of the second preset time period is later than the end time of the first preset time period;

[0019] The topology construction unit is further configured to update the second topology map according to the third power grid operation data to obtain a third topology map.

[0020] In a third aspect, the present application provides an electronic device comprising: a processor and a memory, wherein the memory is used to store 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 includes instructions for executing the steps in the first aspect of the present application.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described in the first aspect of the present application.

[0022] In a fifth aspect, the present application provides 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 perform some or all of the steps described in the first aspect of the present application. The computer program product may be a software installation package.

[0023] The implementation of this application has the following beneficial effects:

[0024] It can be seen that the topology construction method of the distribution network system described in the present application includes: collecting first grid operation data of the target distribution network system within a first preset time period; performing data preprocessing on the first grid operation data to obtain second grid operation data; determining the topological nodes corresponding to the target distribution network system based on the second grid operation data to obtain n topological nodes and n node types; constructing a first topological graph based on the n topological nodes and n node types; optimizing the first topological graph using a preset particle swarm optimization algorithm to obtain a second topological graph; collecting third grid operation data of the target distribution network system within a second preset time period; updating the second topological graph based on the third grid operation data to obtain a third topological graph, and optimizing the first topological graph using a preset particle swarm optimization algorithm to obtain a second topological graph. The preset particle swarm optimization algorithm has powerful global search and local optimization capabilities, and can change the topological graph in a direction that is more in line with the efficient and stable operation of the power grid. Moreover, the algorithm can quickly search for a better solution in the solution space. When the power grid state changes, the topological graph can be adaptively optimized in a timely manner, thereby improving the response speed and accuracy of the topological graph to changes in the power grid state. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0026] Figure 1 This is a structural diagram of a power distribution network system provided by an embodiment of the present application;

[0027] Figure 2 This is a flowchart of a method for constructing a topology of a distribution network system provided in an embodiment of the present application;

[0028] Figure 3 is a schematic diagram of a reference topology provided in an embodiment of the present application;

[0029] Figure 4 is a schematic diagram of a first topological diagram provided in an embodiment of the present application;

[0030] Figure 5 This is a block diagram of the functional units of a topology construction device for a distribution network system provided in an embodiment of the present application;

[0031] Figure 6 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] 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.

[0033] 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.

[0034] 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.

[0035] The electronic devices described in the embodiments of the present application may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptops, video matrices, monitoring platforms, mobile Internet devices (MIDs) or wearable devices, etc. The above are only examples and not exhaustive, including but not limited to the above devices. Of course, the above electronic devices can also be servers, for example, cloud servers.

[0036] The following is an explanation of some professional terms involved in this application:

[0037] The distribution network is the user-facing component of the power system, primarily responsible for distributing electrical energy from the transmission system to individual users. It comprises multiple components, including distribution lines of various voltage levels (e.g., common 10kV and 35kV lines), distribution substations, switchgear, capacitor banks, user access equipment, and many other components.

[0038] A topology diagram of a distribution network system is a diagram that graphically represents the connections between various components in a distribution network (such as substations, lines, switches, and user access points). It is an abstract description of the physical structure and electrical connections of a distribution network. The nodes in a topology diagram represent components in the distribution network. For example, a substation can be represented by a node, and power generation equipment and load (user) access points are also represented by nodes. Branches represent the connection lines between components. For example, a transmission line between two substations or a distribution line between a substation and a user access point is represented by a branch. In graphics, nodes are usually represented by geometric shapes such as circles and squares, and branches are represented by line segments.

[0039] Dijkstra's algorithm is a greedy algorithm for computing the shortest path from a node to all other nodes in a graph. It is primarily used to solve the single-source shortest path problem with non-negatively weighted edges. Given a starting node, the algorithm finds the shortest path length from that starting node to all other nodes in the graph.

[0040] Particle Swarm Optimization (PSO): is an optimization algorithm based on swarm intelligence that simulates the foraging behavior of group organisms such as bird flocks or fish schools. In the solution space of the optimization problem, a group of particles (each particle represents a potential solution) searches for the optimal solution by continuously adjusting their positions. In this application, each particle represents a node in the distribution network system, the position of the particle corresponds to the position of the node in the distribution network system, and the speed of the particle corresponds to the change in the node position. By adjusting the position of the particles, the algorithm attempts to find a layout that optimizes certain performance indicators of the power grid (such as the distance between nodes, angle, connection efficiency, etc.).

[0041] See also Figure 1 , Figure 1 This is a structural diagram of a distribution network system provided in an embodiment of the present application. It can be seen that the distribution network system includes: a SCADA module (Supervisory Control And Data Acquisition, data acquisition and monitoring control system), a machine learning module, a user interaction module, a database module, and a control module, wherein:

[0042] The SCADA module collects various grid operation data in real time or periodically, including voltage and current data, power data, power generation and consumption data, and transaction data. For example, through sensors installed at substations, power plants, and user terminals, the SCADA module can obtain real-time values ​​of voltage and current at each node, as well as information such as the power generated by power generation equipment and the power consumption of users. This data is the foundation for building the distribution network topology.

[0043] The machine learning module is configured to determine the topological nodes and node types corresponding to the target distribution network system based on the second power grid operation data collected by the SCADA module and preprocessed (preprocessing can be completed by the control module). The machine learning module can utilize data mining and classification algorithms, such as clustering algorithms, to classify data points (representative nodes) with similar operating characteristics into different categories, thereby determining n topological nodes and n node types. For example, by analyzing data patterns such as node voltage and power, different types of nodes such as power station nodes, substation nodes, and load nodes can be distinguished.

[0044] During the topology construction process, the user interaction module allows users to participate in all aspects of topology construction and optimization. Users can use this module to set parameters such as the first preset time period and the second preset time period to determine the scope and timing of data collection. For example, users can specify data collection for a specific time period based on the grid maintenance plan or research purpose to obtain more targeted grid operation data for topology construction. At the same time, users can also provide some prior knowledge or constraints when the machine learning module performs topology node classification and topology optimization. For example, if a user knows that the grid structure in a certain area has a special connection method, they can inform the system through the user interaction module to make the topology construction more in line with the actual situation.

[0045] The database module is responsible for storing various data during the entire topology construction process.

[0046] The control module can formulate appropriate control strategies based on the constructed and updated topologies (such as the second and third topologies) and grid operation data. For example, if the topology indicates that lines in a certain area are overloaded, the control module can optimize grid operation by adjusting the output power of power generation equipment, switching lines, or adjusting loads. These control decisions based on accurate topologies enable more efficient utilization of grid resources and improve grid stability and reliability.

[0047] See also Figure 2 , Figure 2 This is a flowchart of a method for constructing a topology of a distribution network system provided in an embodiment of the present application, the method comprising:

[0048] S201. Collect first grid operation data of a target distribution network system within a first preset time period; the first grid operation data includes at least one of the following: voltage and current data, power data, power generation and consumption data, and transaction data.

[0049] In the embodiment of the present application, the first preset time period can be preset in advance or defaulted.

[0050] It should be explained that the structure of the target distribution network system mentioned in this application can be as follows: Figure 1 As shown in Figure 1, the SCADA module primarily consists of a remote terminal unit (RTU), a programmable logic controller (PLC), a communication network, and a monitoring center. RTUs and PLCs are typically installed at various equipment nodes in the distribution network (such as substations, switchyards, and energy storage stations). They collect data from local devices and execute control commands. The communication network transmits this data to the monitoring center, which processes, stores, and displays the collected data.

[0051] In a specific embodiment, the first power grid operation data of the target distribution network system within a first preset time period can be collected through the SCADA module in the target distribution network system. Specifically, the collection frequency can be set according to the importance and change characteristics of different data. For data with high real-time requirements and fast changes such as voltage and current, a higher collection frequency can be set, such as collecting once per second or once per minute; for some data that changes relatively slowly, such as the cumulative power generation of power generation equipment, trading power, etc., a lower collection frequency can be set, such as collecting once per hour. Data is collected through equipment such as voltage sensors, current sensors, and generator monitoring systems installed in locations such as substations and power grid lines to obtain the first power grid operation data.

[0052] S202: Preprocess the first power grid operation data to obtain second power grid operation data.

[0053] In an embodiment of the present application, data preprocessing may be performed on the first power grid operation data, for example, data cleaning, data standardization, data smoothing and other operations may be performed on the first power grid operation data, thereby obtaining the second power grid operation data.

[0054] Optionally, step S202, performing data preprocessing on the first power grid operation data to obtain second power grid operation data, includes:

[0055] A1. Obtaining a plurality of acquisition devices corresponding to the first power grid operation data;

[0056] A2. Determine a target accuracy parameter corresponding to each of the multiple acquisition devices to obtain multiple target accuracy parameters;

[0057] A3. Determine a target adjustment coefficient based on the multiple target accuracy parameters;

[0058] A4. Adjusting the first power grid operation data according to the target adjustment coefficient to obtain reference second power grid operation data;

[0059] A5. Process the reference second power grid operation data using a preset standardization method to obtain the second power grid operation data.

[0060] In the embodiment of the present application, the acquisition device may include at least one of the following: a voltage acquisition device, a current acquisition device, a power acquisition device, an electric energy meter, an electric power trading system, etc., which are not limited here.

[0061] In a specific embodiment, the collection device corresponding to the first power grid operation data can be obtained first to obtain multiple collection devices. Specifically, the first power grid operation data can include a collection device identifier, and the collection device identifier is used to indicate that a certain data is collected by a certain collection device. By extracting all the collection device identifiers from the first power grid operation data, and then determining the collection device corresponding to each of these collection device identifiers, multiple collection devices can be obtained.

[0062] Next, the target accuracy parameter corresponding to each of the multiple acquisition devices can be determined to obtain multiple target accuracy parameters; a target adjustment coefficient is determined based on the multiple target accuracy parameters, and the value range of the target adjustment coefficient can be -0.12 to 0.12; then, the first power grid operation data can be adjusted based on the target adjustment coefficient, and the specific calculation formula is:

[0063] Reference second grid operation data = first grid operation data * (1 + target adjustment coefficient);

[0064] The reference second power grid operation data can be obtained according to the above formula. Then, the reference second power grid operation data can be processed using a preset normalization method to obtain the second power grid operation data. For example, the preset normalization method can be a Z-Score normalization method. The calculation formula of the Z-Score normalization is:

[0065] Z = (x - μ) / σ;

[0066] Wherein, x represents any data in the reference second power grid operation data, μ represents the mean of the reference second power grid operation data, and σ represents the standard deviation of the reference second power grid operation data; the second power grid operation data can be obtained by calculating the reference second power grid operation data according to the above formula.

[0067] In this way, by determining the adjustment coefficient based on the acquisition device and its target accuracy parameters corresponding to the first power grid operation data, the data can be corrected for acquisition devices of different accuracy levels. This is because different acquisition devices vary in measurement accuracy due to factors such as their manufacturing process, technical level, and age. For example, a high-precision voltage transformer and a standard voltmeter may have varying degrees of error when measuring voltage. Determining the adjustment coefficient based on the device's accuracy parameters and adjusting the data can reduce data deviations caused by device accuracy issues, making the resulting second power grid operation data closer to the actual value.

[0068] Optionally, in step A2, determining a target accuracy parameter corresponding to each of the multiple acquisition devices to obtain multiple target accuracy parameters includes:

[0069] B1. Obtaining initial accuracy parameters of a target acquisition device; the target acquisition device is any acquisition device among the multiple acquisition devices;

[0070] B2. Determine the target ambient temperature corresponding to the target acquisition device;

[0071] B3. Determine the difference between the target ambient temperature and the preset temperature to obtain a target difference;

[0072] B4. determining a target deviation according to the target difference and the preset temperature;

[0073] B5. Determine a first adjustment factor corresponding to the target deviation;

[0074] B6. Obtaining the target usage time of the target acquisition device;

[0075] B7. Determine a target optimization factor corresponding to the target usage duration;

[0076] B8. Optimize the first adjustment factor according to the target optimization factor to obtain a second adjustment factor;

[0077] B9. Adjust the initial accuracy parameter according to the second adjustment factor to obtain a target accuracy parameter corresponding to the target acquisition device.

[0078] In the embodiment of the present application, the accuracy parameter can be one of the following: error margin, resolution, linearity, repeatability accuracy, etc., which are not limited here; the preset temperature can be preset or default, and the preset temperature represents the optimal operating temperature of the target acquisition device.

[0079] In a specific embodiment, the initial accuracy parameters of the target acquisition device can be obtained first. Specifically, the target device identification code of the target acquisition device can be obtained, and the corresponding technical manual can be queried from the Internet or database module based on the target device identification code to obtain the target technical manual, and the initial accuracy parameters can be obtained from the target technical manual; then, the target ambient temperature corresponding to the target acquisition device can be determined. Specifically, a temperature sensor can be provided in the target acquisition device, and the ambient temperature within a first preset time period can be collected by the temperature sensor according to a preset sampling frequency to obtain multiple ambient temperatures, and the average of these multiple ambient temperatures, that is, the target ambient temperature, is calculated; then, the preset temperature can be subtracted from the target ambient temperature to obtain the target difference.

[0080] Furthermore, the target deviation can be determined based on the target difference and the preset temperature. The calculation formula is as follows:

[0081] Target deviation = target difference / preset temperature * 100%;

[0082] According to the above formula, the target deviation can be obtained, and then the first adjustment factor corresponding to the target deviation can be determined. For example, the mapping relationship between the preset deviation and the influencing factor can be pre-stored, and the first adjustment factor corresponding to the target deviation can be determined based on the mapping relationship. The value range of the first adjustment factor can be -0.3 to 0.3; then, the target usage time of the target acquisition device can be obtained. Specifically, the factory time of the target acquisition device can be queried according to the above target device identification code, and then the current time can be obtained. The target usage time can be obtained by subtracting the factory time from the current time; then, the target optimization factor corresponding to the target usage time can be determined. For example, the mapping relationship between the preset usage time and the optimization factor can be pre-stored, and the target optimization factor corresponding to the target usage time can be determined based on the mapping relationship. The value range of the target optimization factor can be -0.2 to 0; then, the first adjustment factor can be optimized according to the target optimization factor. The calculation formula is as follows:

[0083] Second adjustment factor = first adjustment factor * (1 + target optimization factor);

[0084] The second adjustment factor can be obtained according to the above formula. Finally, the initial accuracy parameter can be adjusted according to the second adjustment factor. The calculation formula is as follows:

[0085] First target accuracy parameter = initial accuracy parameter * (1 + second adjustment factor);

[0086] According to the above formula, a first target accuracy parameter can be obtained, and the first target accuracy parameter is the target accuracy parameter corresponding to the target acquisition device.

[0087] In this way, by determining the difference between the target ambient temperature and the preset temperature (target difference) and further calculating the target deviation, the degree of influence of the ambient temperature on the equipment accuracy can be quantified. In addition, the first adjustment factor is optimized by the target optimization factor to obtain the second adjustment factor, so that the two important factors of temperature and equipment usage time are comprehensively considered in the adjustment process of the accuracy parameters. This comprehensive adjustment can more truly reflect the accuracy of the equipment in the actual operating environment and improve the accuracy of the target accuracy parameters.

[0088] Optionally, in step A3, determining a target adjustment coefficient according to the multiple target accuracy parameters includes:

[0089] C1. Determine a first weight corresponding to each of the multiple target accuracy parameters to obtain multiple first weights; the higher the target accuracy parameter, the greater the first weight;

[0090] C2. Determine the amount of data collected by each of the multiple collection devices based on the second power grid operation data to obtain multiple data amounts;

[0091] C3. Determine a first adjustment parameter corresponding to each of the multiple data amounts to obtain multiple first adjustment parameters;

[0092] C4. Adjust corresponding first weights among the plurality of first weights according to the plurality of first adjustment parameters to obtain a plurality of second weights;

[0093] C5. determining a target accuracy value according to the multiple second weights and the multiple target accuracy parameters;

[0094] C6. Determine a reference adjustment coefficient corresponding to the target accuracy value;

[0095] C7. Obtaining a normal accuracy range corresponding to the target distribution network system;

[0096] C8. When the target accuracy value is within the normal accuracy range, obtaining an intermediate accuracy value within the normal accuracy range;

[0097] C9. Determine the difference between the intermediate precision value and the target precision value to obtain a target precision difference;

[0098] C10. Determine a target fine-tuning factor corresponding to the target accuracy difference;

[0099] C11. Adjust the reference adjustment coefficient according to the target fine-tuning factor to obtain the target adjustment coefficient.

[0100] In an embodiment of the present application, a first weight corresponding to each of a plurality of target accuracy parameters can be determined to obtain a plurality of first weights. Specifically, a mapping relationship between preset target accuracy parameters and first weights can be pre-stored, and a plurality of first weights corresponding to the plurality of target accuracy parameters can be determined based on the mapping relationship. Then, the amount of data collected by each of a plurality of collection devices can be determined based on the second power grid operation data to obtain a plurality of data amounts. Specifically, a device identifier for each of the plurality of collection devices can be obtained to obtain a plurality of device identifiers, and the obtained plurality of device identifiers can be used to filter the second power grid operation data. This can be achieved by writing program code or using a database query tool. For example, if the data is stored in a database module, the "WHERE" clause of an SQL statement can be used to filter all data records corresponding to each device according to the plurality of device identifiers, thereby obtaining a plurality of data amounts.

[0101] Next, a first adjustment parameter corresponding to each of the multiple data amounts can be determined to obtain multiple first adjustment parameters. Specifically, a mapping relationship between preset data amounts and first adjustment parameters can be pre-stored, and multiple first adjustment parameters corresponding to the multiple data amounts can be determined based on the mapping relationship. Then, corresponding first weights among the multiple first weights can be adjusted according to the multiple first adjustment parameters. The specific calculation formula is as follows:

[0102] Second weight a3 = first weight a1 * (1 + first adjustment parameter a2);

[0103] Among them, the first weight a1 is any one of multiple first weights, and the first adjustment parameter a2 is the first adjustment parameter corresponding to the first weight a1; multiple second weights can be obtained by calculating according to the above formula; further, the target accuracy value can be obtained by weighted operation based on multiple second weights and multiple target accuracy parameters; then, the reference adjustment coefficient corresponding to the target accuracy value can be determined, for example, the mapping relationship between the preset accuracy value and the adjustment coefficient can be pre-stored, and the reference adjustment coefficient corresponding to the target accuracy value can be determined based on the mapping relationship; then, the normal accuracy range corresponding to the target distribution network system can be obtained, specifically, the maximum accuracy value and the minimum accuracy value among the multiple target accuracy parameters can be determined, and then, the normal accuracy range is obtained: the accuracy range between the minimum accuracy value and the maximum accuracy value, for example, assuming that the minimum accuracy value is 0.5% and the maximum accuracy value is 3%, the normal accuracy range is 0.5%~3%.

[0104] When the target accuracy value is within the normal accuracy range, it indicates that the error of the first power grid operation data is not large and is within an acceptable range. The middle accuracy value of the normal accuracy range can be obtained. For example, if the normal accuracy range is 0.5% to 3%, the middle accuracy value is 1.75%. Then, the target accuracy difference value can be obtained by subtracting the target accuracy value from the middle accuracy value. Further, the target fine-tuning factor corresponding to the target accuracy difference value can be determined. Specifically, a mapping relationship between a preset accuracy difference value and a fine-tuning factor can be pre-stored. Based on the mapping relationship, the target fine-tuning factor corresponding to the target accuracy difference value is determined. The value range of the target fine-tuning factor can be -0.25 to 0.25. Finally, the reference adjustment coefficient can be adjusted according to the target fine-tuning factor. The calculation formula is as follows:

[0105] Target adjustment coefficient = reference adjustment coefficient * (1 + target fine-tuning factor);

[0106] The target adjustment coefficient can be obtained according to the above formula.

[0107] When the target accuracy value is not within the normal accuracy range, it means that the error of the first power grid operation data is large and cannot be accepted. The power grid operation data needs to be re-acquired until its corresponding target accuracy value is within the normal accuracy range. The re-acquired power grid operation data will be used as the first power grid operation data.

[0108] In this way, the target accuracy value is determined by multiple second weights and multiple target accuracy parameters. This target accuracy value integrates the accuracy and data volume information of all acquisition devices and is an overall evaluation of the data acquisition accuracy of the entire distribution network system. It can more realistically reflect the data quality of the system and is more representative and authentic than methods that only consider the accuracy of a single device or simple average accuracy.

[0109] S203. Determine the topological nodes and node types corresponding to the target distribution network system according to the second power grid operation data, and obtain n topological nodes and n node types; each topological node corresponds to a node type; n is an integer greater than 1.

[0110] In the embodiment of the present application, the second power grid operation data can be analyzed to determine which topological nodes are included in the target distribution network system, thereby obtaining n topological nodes and n node types.

[0111] Optionally, step S203, determining the topological nodes and node types corresponding to the target distribution network system according to the second power grid operation data to obtain n topological nodes and n node types, includes:

[0112] S31. Determine the nodes included in the second power grid operation data to obtain the n topological nodes;

[0113] S32. Divide the second power grid operation data into n partial power grid operation data according to the n topological nodes; each topological node corresponds to one partial power grid operation data;

[0114] S33, extracting features from each portion of the n portions of grid operation data to construct n feature vectors;

[0115] S34. Input the n feature vectors into a preset machine learning model to obtain n node type labels; the node type labels include at least one of the following: a power node label, a load node label, an energy storage node label, and a network node label;

[0116] S35. Determine the n node types according to the n node type labels; each node type label corresponds to a node type.

[0117] In an embodiment of the present application, the preset machine learning model can be preset or defaulted in advance.

[0118] In a specific embodiment, the nodes included in the second power grid operation data can be determined to obtain n topological nodes. Specifically, it can be checked that the second power grid operation data may include a node identifier. The node identifier is used to indicate that a certain data is generated by a certain power grid device, and its value corresponds to a specific substation, bus, generator or load access point and other nodes. All node identifiers in the second power grid operation data are extracted, and these node identifiers are deduplicated to obtain n node identifiers. Based on these n node identifiers, n topological nodes can be determined; then, the second power grid operation data can be divided into n partial power grid operation data according to the n topological nodes. Specifically, the second power grid operation data can be distinguished according to the above-mentioned n node identifiers, and the data containing the same node identifier is the same part, thereby obtaining n partial power grid operation data.

[0119] Then, feature extraction is performed on each of the n parts of the grid operation data to construct n feature vectors. Specifically, it is possible to first determine which features of the node are helpful for node classification and obtain at least one feature, such as voltage level, power output, device type, geographic location and other attribute information. Then, the at least one feature can be extracted from the n parts of the grid operation data to obtain n feature data. These n feature data are combined in a certain order to construct a feature vector, so that each node has its corresponding unique feature vector, thereby obtaining n feature vectors. For example, assuming that a feature vector X is (x1, x2, x3, x4), where x1: can represent the voltage level of the node; x2: can represent the power output of the node; x3: can represent the device type of the node (for example, transformer, circuit breaker, generator); x4: can represent the geographic location of the node (for example, latitude and longitude coordinates), the feature vector X represents a point in the multidimensional feature space of a node, which captures the key features of the node, and these features can be used to distinguish different types of nodes.

[0120] By inputting these n feature vectors into the preset machine learning model respectively, n node type labels can be obtained; then, the n node types can be determined based on the n node type labels. For example, if a node type label is a power node label, then the node type of the node corresponding to the node type label is a power node.

[0121] In this way, by extracting features from n parts of power grid operation data and constructing feature vectors respectively, the most representative key information that best reflects the essential characteristics of the node can be extracted from the numerous power grid operation data. For example, by extracting statistical characteristics, frequency domain characteristics, and physical relationship-based characteristics of relevant parameters such as voltage, current, and power, complex data can be converted into a concise and information-rich feature vector form, providing strong data support for subsequent preset machine learning model recognition.

[0122] S204: Construct a first topology graph according to the n topology nodes and the n node types.

[0123] Optionally, step S204, constructing a first topology graph according to the n topological nodes and the n node types, includes:

[0124] S41, obtaining target network structure data of the target distribution network system;

[0125] S42, determining target connection relationship data between the n topological nodes according to the target network structure data;

[0126] S43, constructing a first adjacency matrix according to the target connection relationship data; the first adjacency matrix is ​​an n*n matrix;

[0127] S44. Connect the n topological nodes according to the first adjacency matrix and the n node types to obtain a reference topological graph; the reference topological graph includes the n topological nodes and m edges; m is an integer greater than 1;

[0128] S45. Determine the data transmission distances corresponding to the m edges to obtain m data transmission distances;

[0129] S46. Determine m weights according to the m data transmission distances; each data transmission distance corresponds to one weight;

[0130] S47, obtaining a node that meets a preset starting node condition among the n topological nodes to obtain a starting node;

[0131] S48. Determine the shortest data transmission distances between the starting node and n-1 nodes among the n topological nodes excluding the starting node according to the Dijkstra algorithm, and obtain n-1 shortest data transmission distances;

[0132] S49. Construct the first topology graph according to the n-1 shortest data transmission distances and the m weights.

[0133] In the embodiment of the present application, the preset starting node condition can be preset in advance or defaulted.

[0134] In a specific embodiment, the target network structure data of the target distribution network system can be obtained first. Specifically, the design document of the target distribution network system can be obtained from the database module, and the target network structure data can be obtained from the design document. Then, the target connection relationship data between the n topological nodes can be determined based on the target network structure data. Specifically, the network structure data between the n topological nodes, that is, the target connection relationship data, can be extracted from the target network structure data based on the above-mentioned n node identifiers. Then, a first adjacency matrix can be constructed based on the target connection relationship data. For example, assuming n=4, the target connection relationship data are as follows: node A (A indicates that the node is the first node) is connected to node B and node C; node B is connected to node A and node D; node C is connected to node A and node D; node D is connected to node B and node C; then the corresponding first adjacency matrix is:

[0135]

[0136] Among them, A represents the first adjacency matrix; A ij Indicates whether the i-th node is connected to the j-th node, A ij The following conditions are met:

[0137]

[0138] It should be explained that in the first adjacency matrix, when the i-th node connects to the j-th node, Aij may not be equal to 1, but equal to the weight of the edge ij; the first adjacency matrix in the embodiment of the present application can also be replaced by an adjacency list, and the two functions are the same. Then, the n topological nodes can be connected according to the first adjacency matrix, and the node types can be marked around the nodes, thereby obtaining a reference topology map. For details, please refer to Figure 3 , Figure 3 This is a schematic diagram of a reference topology provided by an embodiment of the present application. In the reference topology, the initial position of each node can be set to its corresponding geographic coordinates. An example is given below to illustrate:

[0139] Consider a small power grid with four nodes: A (source node), B (load node), C (network node), and D (storage node). The geographic locations of these nodes are as follows: Node A: longitude 115.0, latitude 39.0; Node B: longitude 115.5, latitude 39.2; Node C: longitude 115.3, latitude 38.8; Node D: longitude 115.1, latitude 39.1. When initializing the node positions, these geographic coordinates can be used directly as the initial positions of the nodes in the reference topology. For example, if a two-dimensional Cartesian coordinate system is used to represent these positions, the longitude and latitude can be converted to coordinates in that coordinate system (assuming the conversion has already been completed) and set as follows: Node A's position: (0, 0); Node B's position: (100, 50); Node C's position: (60, -30); Node D's position: (-20, 20).

[0140] In this example, the coordinates of each node represent their geographic location. These coordinates serve as the initial values ​​for node positions in the pre-defined particle swarm optimization algorithm. During the iterations of the pre-defined particle swarm optimization algorithm, these positions are adjusted based on optimization objectives (such as minimizing inter-node distances and balancing loads). By initializing node positions based on geographic location, the reference topology can more accurately reflect the physical layout of the power grid, which is of great significance for power grid planning, operation, and maintenance.

[0141] Then, the data transmission distances corresponding to the m edges can be determined to obtain m data transmission distances. Specifically, the signal transmission speed of the target distribution network system can be obtained (for example, in optical fiber communication, the speed of the optical signal is approximately the speed of light). The data transmission distance can be estimated by measuring the time delay of the signal transmitted from one node to another, thereby obtaining m data transmission distances. For example, assuming that the signal transmission speed is v and the measured time delay is t, then the data transmission distance d = v*t; then, m weights can be determined according to the m data transmission distances. Specifically, the mapping relationship between the preset data transmission distances and the weights can be pre-stored, and the m weights corresponding to the m data transmission distances can be determined based on the mapping relationship; then, the n topological nodes can be screened according to the preset starting node condition, and the node that meets the condition is the starting node; further, the Dijkstra algorithm can be used to calculate the weights. The method determines the shortest data transmission distance between the starting node and n-1 nodes other than the starting node among the n topological nodes, and obtains n-1 shortest data transmission distances. Since the Dijkstra algorithm is a common technology, the specific implementation steps are not repeated here; finally, the first topological graph can be constructed according to the n-1 shortest data transmission distances and m weights. Specifically, the above n nodes can be connected according to the n-1 shortest data transmission distances, and edges can be connected starting from the starting node, and corresponding edge weights can be assigned. For example, if the starting node is A, and the remaining nodes are B, C, D, etc., and it is known that the shortest data transmission distance from A to B is AB, the shortest data transmission distance from A to C is AC, and the shortest data transmission distance from A to D is ABD, then a topological graph can be drawn according to these shortest data transmission distances, and the corresponding weights can be marked on the edges, thereby obtaining the first topological graph. For details, please refer to Figure 4 , Figure 4 This is a schematic diagram of a first topology diagram provided in an embodiment of the present application.

[0142] It should be explained that the topological graphs in this application can all be undirected graphs, and the edges in the topological graphs have no direction.

[0143] In this way, by obtaining the target network structure data and constructing the first adjacency matrix, the connection relationship between each node in the distribution network system can be accurately represented, providing a basis for subsequent analysis and calculation. In addition, by determining the data transmission distance and weight and applying the Dijkstra algorithm to find the shortest data transmission distance, the data transmission path in the distribution network system can be optimized, the transmission efficiency can be improved and the transmission cost can be reduced.

[0144] S205 : Optimize the first topology graph using a preset particle swarm optimization algorithm to obtain a second topology graph.

[0145] Optionally, in step S205, optimizing the first topology graph using a preset particle swarm optimization algorithm to obtain a second topology graph includes:

[0146] S51, generating n particles according to the first topological graph, and initializing the initial position and initial velocity of each of the n particles; each particle corresponds to a topological node;

[0147] S52. Iteratively optimize the n particles according to a preset iterative formula. When the n particles meet a preset iterative condition, stop the iteration to obtain a global optimal solution at the time of stopping the iteration. The preset iterative formula is as follows:

[0148] v i (t+1)=v i (t)+c1*r1*(p i -x i (t))+c2*r2*(gx i (t));

[0149] x i (t+1)=x i (t)+v i (t+1);

[0150] Among them, v i is the velocity of the i-th particle at the t-th iteration, x i is the position of the i-th particle at the t-th iteration, pi is the individual optimal solution, g is the global optimal solution, c1 is the preset individual learning factor, c2 is the preset social learning factor, r1 and r2 are both random numbers between 0 and 1;

[0151] S53: Adjust the node positions in the first topology map according to the global optimal solution to obtain the second topology map.

[0152] In the embodiment of the present application, the preset particle swarm optimization algorithm can be preset or defaulted in advance, and the preset particle swarm optimization algorithm includes the following: standard particle swarm optimization algorithm, inertia weighted particle swarm optimization algorithm, adaptive particle swarm optimization algorithm, etc., which are not limited here.

[0153] In a specific embodiment, n particles are generated according to the first topological graph by a preset particle swarm optimization algorithm, and the initial position and initial velocity of each of the n particles are initialized. Specifically, the position of the particle in the multidimensional space directly corresponds to the position of the node in the target distribution network system. If the power grid is two-dimensional, then each particle will have two coordinates (X, Y) to represent the position of the node on the plane, and the velocity of the particle corresponds to the rate of change of the node position. In each iteration, the velocity of the particle is updated according to the rules of the preset particle swarm optimization algorithm, and then the position of the node is updated. For example, a preset velocity value range of the particle can be obtained, and then an initial velocity is randomly generated for each particle within the preset velocity value range.

[0154] Next, the n particles can be iteratively optimized according to a preset iterative formula. When the n particles meet the preset iterative conditions, the iteration is stopped to obtain the global optimal solution at the time of stopping the iteration. The preset iterative formula is as follows:

[0155] v i (t+1)=v i (t)+c1*r1*(p i -x i (t))+c2*r2*(gx i (t));

[0156] x i (t+1)=x i (t)+v i (t+1);

[0157] Among them, v i is the velocity of the i-th particle at the t-th iteration, x i is the position of the i-th particle at the t-th iteration, pi is the individual optimal solution, g is the global optimal solution, c1 is the preset individual learning factor, c2 is the preset social learning factor, r1 and r2 are both random numbers between 0 and 1;

[0158] It should be explained that the preset iteration condition may be that the particle swarm optimization algorithm has been iterated for a preset number of times, or when the improvement degree of the solution is lower than a preset threshold.

[0159] Finally, the node positions in the first topological graph can be adjusted according to the global optimal solution to obtain the second topological graph. Specifically, the position of each particle in the global optimal solution can be obtained first to obtain multiple particle positions, that is, multiple node optimal positions. Then, each node in the first topological graph is adjusted to the corresponding position in the multiple node optimal positions, thereby obtaining the second topological node.

[0160] In this way, by generating multiple particles, a broad search can be conducted across the entire solution space. Each particle represents a possible solution, and because their initial positions and velocities are randomly initialized, they can cover a variety of initial states. This is similar to how, in a distribution network optimization problem, different particles can explore solutions that achieve optimal system performance (such as minimizing network losses and stabilizing voltage) based on different node parameter combinations (such as voltage and phase angle), increasing the likelihood of finding a global optimal solution.

[0161] S206. Collect third power grid operation data of the target distribution network system within a second preset time period; the start time of the second preset time period is later than the end time of the first preset time period.

[0162] In the embodiment of the present application, the second preset time period can be preset in advance or defaulted.

[0163] In a specific embodiment, the third grid operation data of the target distribution network system within the second preset time period is collected. Specifically, the method for collecting the third grid operation data can be the same as the method for collecting the first grid operation data, which will not be repeated here.

[0164] S207: Update the second topology map according to the third power grid operation data to obtain a third topology map.

[0165] In an embodiment of the present application, the difference between the third power grid operation data and the first power grid operation data can be analyzed to obtain change data of the power grid status, and then the nodes in the second topology map can be adjusted according to the change data to obtain a third topology map. For example, assuming that the change data is that the power grid equipment corresponding to a certain node is damaged and another power grid equipment is added, then the node can be deleted from the second topology map, and according to the topology construction method of the distribution network system provided in an embodiment of the present application, the other power grid equipment can be added to the second topology map as a new node, thereby obtaining a third topology map.

[0166] Specifically, changes in the power grid status include but are not limited to the following situations:

[0167] Load changes: Increased or decreased demand for electricity, such as the startup or shutdown of large equipment in factories in industrial areas, or peaks and valleys in electricity consumption in residential areas. Power supply changes: The addition or withdrawal of renewable energy power generation equipment, such as the startup or shutdown of wind turbines, or output fluctuations of solar panels due to weather changes. Equipment failure: Failure of equipment in the power grid, such as transformers and circuit breakers, causes some parts of the power grid to fail to operate normally. Repair and maintenance: Planned repairs or maintenance of power grid equipment causes temporary disconnection of parts of the power grid. Natural disasters: Extreme weather such as storms and floods cause damage to power grid facilities, affecting the stability of the power grid and the continuity of power supply. Operational errors: Human operational errors, such as mistakenly closing a circuit breaker, causing power outages in parts of the power grid. Cyber ​​attacks or security incidents: Cyber ​​attacks on power grid control systems may cause abnormal operation of the power grid.

[0168] For example, consider a city's power grid. During peak evening hours, several large factories in an industrial zone simultaneously start nighttime production, leading to a sudden increase in grid load. This load increase can cause a change in the grid's state, requiring grid operators to recalculate and adjust the grid's node layout to ensure grid stability and power quality.

[0169] In this example, the change in grid status specifically refers to an increase in load, which requires the dynamic update mechanism in step S207 to recalculate the node layout within the affected area. This may involve adjusting the grid's power supply strategy, such as starting backup generators or redistributing power flow within the grid to cope with the increase in load. Through this dynamic update mechanism, the grid can more flexibly adapt to various changes, ensuring the reliability and efficiency of power supply.

[0170] The implementation of this application has the following beneficial effects:

[0171] It can be seen that the topology construction method of the distribution network system described in the present application includes: collecting first grid operation data of the target distribution network system within a first preset time period; performing data preprocessing on the first grid operation data to obtain second grid operation data; determining the topological nodes corresponding to the target distribution network system based on the second grid operation data to obtain n topological nodes and n node types; constructing a first topological graph based on the n topological nodes and n node types; optimizing the first topological graph using a preset particle swarm optimization algorithm to obtain a second topological graph; collecting third grid operation data of the target distribution network system within a second preset time period; updating the second topological graph based on the third grid operation data to obtain a third topological graph, and optimizing the first topological graph using a preset particle swarm optimization algorithm to obtain a second topological graph. The preset particle swarm optimization algorithm has powerful global search and local optimization capabilities, and can change the topological graph in a direction that is more in line with the efficient and stable operation of the power grid. Moreover, the algorithm can quickly search for a better solution in the solution space. When the power grid state changes, the topological graph can be adaptively optimized in a timely manner, thereby improving the response speed and accuracy of the topological graph to changes in the power grid state.

[0172] See also Figure 5 , Figure 5 This is a block diagram of the functional units of a topology construction device 500 of a distribution network system provided in an embodiment of the present application; the device 500 includes: a collection unit 501, a control unit 502, and a topology construction unit 503, wherein:

[0173] The collecting unit 501 is configured to collect first grid operation data of a target distribution network system within a first preset time period; the first grid operation data includes at least one of the following: voltage and current data, power data, power generation and consumption data, and transaction data;

[0174] The control unit 502 is configured to perform data preprocessing on the first power grid operation data to obtain second power grid operation data; determine the topological nodes and node types corresponding to the target distribution network system based on the second power grid operation data, and obtain n topological nodes and n node types; each topological node corresponds to a node type; n is an integer greater than 1;

[0175] The topology construction unit 503 is configured to construct a first topology graph according to the n topology nodes and the n node types; and optimize the first topology graph using a preset particle swarm optimization algorithm to obtain a second topology graph;

[0176] The collecting unit 501 is further configured to collect third power grid operation data of the target distribution network system within a second preset time period; the start time of the second preset time period is later than the end time of the first preset time period;

[0177] The topology construction unit 503 is further configured to update the second topology map according to the third power grid operation data to obtain a third topology map.

[0178] Optionally, in determining the topological nodes and node types corresponding to the target distribution network system according to the second power grid operation data, and obtaining n topological nodes and n node types, the control unit 502 is specifically configured to:

[0179] Determining nodes included in the second power grid operation data to obtain the n topological nodes;

[0180] dividing the second power grid operation data into n partial power grid operation data according to the n topological nodes; each topological node corresponds to one partial power grid operation data;

[0181] Performing feature extraction on each portion of the n portions of grid operation data to construct n feature vectors;

[0182] Inputting the n feature vectors into a preset machine learning model to obtain n node type labels; the node type labels include at least one of the following: a power node label, a load node label, an energy storage node label, and a network node label;

[0183] The n node types are determined according to the n node type labels; each node type label corresponds to a node type.

[0184] Optionally, in the aspect of constructing the first topology graph according to the n topological nodes and the n node types, the topology constructing unit 503 is specifically configured to:

[0185] Acquiring target network structure data of the target distribution network system;

[0186] Determining target connection relationship data between the n topological nodes according to the target network structure data;

[0187] Constructing a first adjacency matrix according to the target connection relationship data; the first adjacency matrix is ​​an n*n matrix;

[0188] Connecting the n topological nodes according to the first adjacency matrix and the n node types to obtain a reference topological graph; the reference topological graph includes the n topological nodes and m edges; m is an integer greater than 1;

[0189] Determine the data transmission distances corresponding to the m edges to obtain m data transmission distances;

[0190] Determine m weights according to the m data transmission distances; each data transmission distance corresponds to a weight;

[0191] Obtaining a node that meets a preset starting node condition among the n topological nodes to obtain a starting node;

[0192] Determine the shortest data transmission distance between the starting node and n-1 nodes among the n topological nodes excluding the starting node according to the Dijkstra algorithm, and obtain n-1 shortest data transmission distances;

[0193] The first topology graph is constructed according to the n-1 shortest data transmission distances and the m weights.

[0194] Optionally, in the aspect of optimizing the first topology graph by using a preset particle swarm optimization algorithm to obtain the second topology graph, the topology construction unit 503 is specifically configured to:

[0195] Generate n particles according to the first topological graph, and initialize the initial position and initial velocity of each of the n particles; each particle corresponds to a topological node;

[0196] The n particles are iteratively optimized according to a preset iterative formula. When the n particles meet a preset iterative condition, the iteration is stopped to obtain a global optimal solution at the time of stopping the iteration. The preset iterative formula is specifically as follows:

[0197] v i (t+1)=v i (t)+c1*r1*(p i -x i (t))+c2*r2*(gx i (t));

[0198] x i (t+1)=x i (t)+v i (t+1);

[0199] Among them, v i is the velocity of the i-th particle at the t-th iteration, x i is the position of the i-th particle at the t-th iteration, pi is the individual optimal solution, g is the global optimal solution, c1 is the preset individual learning factor, c2 is the preset social learning factor, r1 and r2 are both random numbers between 0 and 1;

[0200] The node positions in the first topology graph are adjusted according to the global optimal solution to obtain the second topology graph.

[0201] Optionally, in the aspect of performing data preprocessing on the first power grid operation data to obtain the second power grid operation data, the control unit 502 is specifically configured to:

[0202] Acquire a collection device corresponding to the first power grid operation data, and obtain a plurality of collection devices;

[0203] Determine a target accuracy parameter corresponding to each of the plurality of acquisition devices to obtain a plurality of target accuracy parameters;

[0204] determining a target adjustment coefficient according to the plurality of target accuracy parameters;

[0205] adjusting the first power grid operation data according to the target adjustment coefficient to obtain reference second power grid operation data;

[0206] The reference second power grid operation data is processed using a preset standardization method to obtain the second power grid operation data.

[0207] Optionally, in determining the target accuracy parameter corresponding to each of the multiple acquisition devices to obtain multiple target accuracy parameters, the control unit 502 is specifically configured to:

[0208] Acquire initial precision parameters of a target acquisition device; the target acquisition device is any acquisition device among the multiple acquisition devices;

[0209] Determining a target ambient temperature corresponding to the target acquisition device;

[0210] Determining a difference between the target ambient temperature and a preset temperature to obtain a target difference;

[0211] determining a target deviation according to the target difference and the preset temperature;

[0212] Determining a first adjustment factor corresponding to the target deviation;

[0213] Obtaining a target usage time of the target acquisition device;

[0214] Determine a target optimization factor corresponding to the target usage time;

[0215] Optimizing the first adjustment factor according to the target optimization factor to obtain a second adjustment factor;

[0216] The initial accuracy parameter is adjusted according to the second adjustment factor to obtain a target accuracy parameter corresponding to the target acquisition device.

[0217] Optionally, in determining the target adjustment coefficient according to the multiple target accuracy parameters, the control unit 502 is specifically configured to:

[0218] Determine a first weight corresponding to each of the plurality of target accuracy parameters to obtain a plurality of first weights; the higher the target accuracy parameter, the greater the first weight;

[0219] determining the amount of data collected by each of the plurality of collection devices according to the second power grid operation data, to obtain a plurality of data amounts;

[0220] Determining a first adjustment parameter corresponding to each of the multiple data amounts to obtain multiple first adjustment parameters;

[0221] Adjust corresponding first weights among the plurality of first weights according to the plurality of first adjustment parameters to obtain a plurality of second weights;

[0222] determining a target accuracy value according to the plurality of second weights and the plurality of target accuracy parameters;

[0223] Determining a reference adjustment coefficient corresponding to the target accuracy value;

[0224] Obtaining a normal accuracy range corresponding to the target distribution network system;

[0225] When the target accuracy value is within the normal accuracy range, obtaining an accuracy intermediate value within the normal accuracy range;

[0226] Determine the difference between the intermediate precision value and the target precision value to obtain a target precision difference;

[0227] Determining a target fine-tuning factor corresponding to the target accuracy difference;

[0228] The reference adjustment coefficient is adjusted according to the target fine-tuning factor to obtain the target adjustment coefficient.

[0229] In a specific implementation, the topology construction device 500 of the distribution network system described in the embodiment of the present application can also execute other implementation methods described in the topology construction method of the distribution network system provided in the above embodiment of the present application, which will not be repeated here.

[0230] See also Figure 6 , Figure 6 This is a structural diagram of an electronic device provided in an embodiment of the present application, which includes a processor, a memory, a communication interface and one or more programs. The processor, memory and communication interface are interconnected through a bus. The above one or more programs are stored in the above memory and are configured to be executed by the above processor. The one or more programs include instructions for executing other implementation methods described in the topology construction method of the distribution network system provided in the above embodiment of the present application, which will not be repeated here.

[0231] An embodiment of the present application also provides a computer storage medium, wherein the computer 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.

[0232] 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.

[0233] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0234] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0235] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0236] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0237] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0238] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0239] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for constructing a topology of a distribution network system, characterized in that: The method comprises: Collecting first power grid operation data of the target distribution network system within a first preset time period; the first power grid operation data includes at least one of the following: voltage and current data, power data, power generation and consumption data, and transaction data; performing data preprocessing on the first power grid operation data to obtain second power grid operation data; Determine the topological nodes and node types corresponding to the target distribution network system according to the second power grid operation data, and obtain n topological nodes and n node types; each topological node corresponds to a node type; n is an integer greater than 1; Constructing a first topological graph according to the n topological nodes and the n node types; Using a preset particle swarm optimization algorithm to optimize the first topology map to obtain a second topology map; Collecting third power grid operation data of the target distribution network system within a second preset time period; the start time of the second preset time period is later than the end time of the first preset time period; The second topology map is updated according to the third power grid operation data to obtain a third topology map.

2. The method according to claim 1, characterized in that The determining the topological nodes and node types corresponding to the target distribution network system according to the second power grid operation data to obtain n topological nodes and n node types includes: Determine the nodes included in the second power grid operation data to obtain the n topological nodes; Dividing the second power grid operation data into n partial power grid operation data according to the n topological nodes; each topological node corresponds to one partial power grid operation data; Extracting features from each portion of the n portions of grid operation data to construct n feature vectors; Input the n feature vectors into a preset machine learning model to obtain n node type labels; the node type labels include at least one of the following: a power node label, a load node label, an energy storage node label, and a network node label; The n node types are determined according to the n node type labels; each node type label corresponds to a node type.

3. The method according to claim 1, characterized in that The step of constructing a first topology graph according to the n topology nodes and the n node types includes: Acquiring target network structure data of the target distribution network system; Determine target connection relationship data between the n topological nodes according to the target network structure data; Constructing a first adjacency matrix according to the target connection relationship data; the first adjacency matrix is ​​an n*n matrix; Connecting the n topological nodes according to the first adjacency matrix and the n node types to obtain a reference topological graph; the reference topological graph includes the n topological nodes and m edges; m is an integer greater than 1; Determine the data transmission distances corresponding to the m edges, and obtain m data transmission distances; Determine m weights according to the m data transmission distances; each data transmission distance corresponds to a weight; Obtaining a node that meets a preset starting node condition among the n topological nodes to obtain a starting node; Determine the shortest data transmission distance between the starting node and n-1 nodes among the n topological nodes except the starting node according to the Dijkstra algorithm, and obtain n-1 shortest data transmission distances; The first topology graph is constructed according to the n-1 shortest data transmission distances and the m weights.

4. The method according to any one of claims 1 to 3, characterized in that: The step of optimizing the first topology map by using a preset particle swarm optimization algorithm to obtain a second topology map includes: Generate n particles according to the first topological graph, and initialize the initial position and initial velocity of each of the n particles; each particle corresponds to a topological node; The n particles are iteratively optimized according to a preset iterative formula. When the n particles meet a preset iterative condition, the iteration is stopped to obtain a global optimal solution at the time of stopping the iteration. The preset iterative formula is specifically as follows: v i (t+1)=v i (t)+c1*r1*(p i -x i (t))+c2*r2*(g-x i (t)); x i (t+1)=x i (t)+v i (t+1); Among them, v i is the velocity of the ith particle at the tth iteration, x i is the position of the ith particle at the tth iteration, pi is the individual optimal solution, g is the global optimal solution, c1 is the preset individual learning factor, c2 is the preset social learning factor, r1 and r2 are both random numbers between 0 and 1; The node positions in the first topological graph are adjusted according to the global optimal solution to obtain the second topological graph.

5. The method according to any one of claims 1 to 3, characterized in that: The performing data preprocessing on the first power grid operation data to obtain second power grid operation data includes: Acquire a collection device corresponding to the first power grid operation data to obtain a plurality of collection devices; Determine a target accuracy parameter corresponding to each of the multiple acquisition devices to obtain multiple target accuracy parameters; Determining a target adjustment coefficient according to the multiple target accuracy parameters; Adjusting the first power grid operation data according to the target adjustment coefficient to obtain reference second power grid operation data; The reference second power grid operation data is processed using a preset standardization method to obtain the second power grid operation data.

6. The method according to claim 5, characterized in that The step of determining a target accuracy parameter corresponding to each of the plurality of acquisition devices to obtain a plurality of target accuracy parameters includes: Acquire initial precision parameters of a target acquisition device; the target acquisition device is any acquisition device among the multiple acquisition devices; Determine the target ambient temperature corresponding to the target acquisition device; Determine the difference between the target ambient temperature and the preset temperature to obtain a target difference; Determining a target deviation according to the target difference and the preset temperature; Determining a first adjustment factor corresponding to the target deviation; Obtaining a target usage time of the target acquisition device; Determine a target optimization factor corresponding to the target usage time; Optimizing the first adjustment factor according to the target optimization factor to obtain a second adjustment factor; The initial accuracy parameter is adjusted according to the second adjustment factor to obtain a target accuracy parameter corresponding to the target acquisition device.

7. The method according to claim 5, characterized in that The determining of the target adjustment coefficient according to the multiple target accuracy parameters includes: Determine a first weight corresponding to each of the plurality of target precision parameters to obtain a plurality of first weights; the higher the target precision parameter, the greater the first weight; Determine the amount of data collected by each of the plurality of collection devices according to the second power grid operation data to obtain a plurality of data amounts; Determine a first adjustment parameter corresponding to each of the multiple data amounts to obtain multiple first adjustment parameters; Adjust corresponding first weights among the plurality of first weights according to the plurality of first adjustment parameters to obtain a plurality of second weights; Determine a target accuracy value according to the plurality of second weights and the plurality of target accuracy parameters; Determine a reference adjustment coefficient corresponding to the target accuracy value; Obtaining a normal accuracy range corresponding to the target power distribution network system; When the target accuracy value is within the normal accuracy range, obtaining an accuracy intermediate value within the normal accuracy range; Determine the difference between the intermediate precision value and the target precision value to obtain a target precision difference; Determine a target fine-tuning factor corresponding to the target accuracy difference; The reference adjustment coefficient is adjusted according to the target fine-tuning factor to obtain the target adjustment coefficient.

8. A topology construction device for a distribution network system, characterized in that: The device comprises: a collection unit, a control unit, and a topology construction unit, wherein: The acquisition unit is used to collect first power grid operation data of the target distribution network system within a first preset time period; the first power grid operation data includes at least one of the following: voltage and current data, power data, power generation and consumption data, and transaction data; The control unit is used to perform data preprocessing on the first power grid operation data to obtain second power grid operation data; determine the topological nodes and node types corresponding to the target distribution network system according to the second power grid operation data to obtain n topological nodes and n node types; each topological node corresponds to a node type; n is an integer greater than 1; The topology construction unit is used to construct a first topology graph according to the n topology nodes and the n node types; optimize the first topology graph using a preset particle swarm optimization algorithm to obtain a second topology graph; The acquisition unit is further used to collect third power grid operation data of the target distribution network system within a second preset time period; the start time of the second preset time period is later than the end time of the first preset time period; The topology construction unit is further used to update the second topology map according to the third power grid operation data to obtain a third topology map.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the program includes instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 7.

Images