Power grid equipment topology dynamic scheduling method and system

Abstract

The invention relates to the technical field of power system monitoring and intelligent scheduling, and discloses a power grid equipment topology dynamic scheduling method and system.The system firstly obtains operation data and spatial data of power grid equipment, and performs data fusion on differences among multi-source heterogeneous data based on the operation data and the spatial data; and then, dynamically adjusting / optimizing the initial power grid topological structure of the power grid equipment through the fusion data after the data fusion processing, and generating a target topological structure. And on the basis, fault prediction or monitoring is performed on nodes or edges of the target topological structure by adopting fusion data. According to the invention, through the multi-source data fusion and dynamic topology reconstruction technology, real-time monitoring, data transmission and scheduling optimization of the power grid state are realized. The technical problem that in the prior art, adaptability of an emergency plan to a complex external environment is not considered, and how to optimize scheduling efficiency in a multi-device cooperation scene is not considered, so that power grid equipment is difficult to schedule in the multi-device cooperation scene is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system monitoring and intelligent dispatching, and in particular to a method and system for dynamic dispatching of power grid equipment topology. Background Art

[0002] With the expansion of power systems and the rapid development of smart grids, the demand for intelligent monitoring, dispatch optimization, and real-time operation of power grid equipment has increased significantly. The operational stability of key equipment, such as substation main equipment and power cables, directly impacts the overall safety and economic viability of the power grid. Traditional monitoring and dispatch methods, often based on a single data source, struggle to address the demands of multi-source heterogeneous data integration and complex power grid scenarios. These methods suffer from issues such as poor data compatibility, insufficient dynamic topology updates, and limited dispatch intelligence.

[0003] Currently, existing technology (patent application number: CN202411380162) provides a substation main equipment self-test system based on multi-source heterogeneous data fusion technology. This system collects data through multi-source sensors in an intelligent monitoring and management system, and dynamically adjusts data weights using an adaptive fusion algorithm to ensure processing accuracy and robustness. A fault identification module based on a graph neural network dynamically identifies faults and generates repair suggestions, while a multi-scale prediction module generates emergency plans to quickly respond to emergencies. However, this method does not consider the adaptability of emergency plans to complex external environments or how to optimize scheduling efficiency in multi-device collaborative scenarios, making it difficult to schedule power grid equipment in these scenarios. Summary of the Invention

[0004] The present invention provides a method and system for dynamic scheduling of power grid equipment topology, which solves the technical problem that the existing technology does not consider the adaptability of emergency plans to complex external environments, and how to optimize scheduling efficiency in multi-device collaborative scenarios, resulting in difficulty in scheduling power grid equipment in multi-device collaborative scenarios.

[0005] A first aspect of the present invention provides a method for dynamic scheduling of power grid equipment topology, comprising:

[0006] Acquiring operation data and spatial data of power grid equipment, and performing data fusion processing on the operation data and the spatial data;

[0007] The fused data after data fusion processing is used to optimize the initial power grid topology to generate the target topology;

[0008] Based on the fused data, fault detection is performed on the nodes or edges of the target topology structure, and an optimal emergency plan for the topology structure of the power grid equipment is constructed according to the fault information of the faulty nodes and faulty edges corresponding to the detection results.

[0009] Optionally, the step of acquiring operation data and spatial data of power grid equipment and performing data fusion processing on the operation data and the spatial data includes:

[0010] Acquire real-time and historical operating data from grid sensors of power grid equipment and spatial data from geographic information systems;

[0011] The real-time operation data, the historical operation data and the spatial data are sequentially subjected to data cleaning, missing value filling, time alignment and standardization preprocessing;

[0012] Extract the features of pre-processed real-time operation data, historical operation data and spatial data, and perform data fusion processing.

[0013] Optionally, the step of optimizing the initial power grid topology structure using the fused data after data fusion processing to generate the target topology structure includes:

[0014] Analyze the fused data after data fusion processing, and determine the initial power grid topology according to the analysis results;

[0015] Based on the device status data in the fused data, updating the node status of the initial power grid topology structure;

[0016] Based on the line state data in the fused data, updating the edge state of the initial power grid topology structure;

[0017] Combine the updated node and edge states to generate an updated topology;

[0018] Calculating a node importance index of each node of the updated topology structure;

[0019] The updated topology structure is optimized according to the node importance index of each node to generate a target topology structure.

[0020] Optionally, the step of performing fault detection on nodes or edges of the target topology structure based on the fused data, and constructing an optimal emergency plan for the power grid equipment topology structure according to fault information of the faulty nodes and faulty edges corresponding to the detection results includes:

[0021] Inputting the fused data into a preset deep learning model;

[0022] Calculating the predicted output value of the fused data by the time series prediction method of the deep learning model;

[0023] Determining the pre-failure nodes and pre-failure edges of the target topology structure according to the predicted output value;

[0024] Determining an optimal scheduling solution for a topology of power grid equipment based on the load information of the pre-fault node and the transferable line information of the pre-fault edge;

[0025] Based on the fused data, real-time fault detection is performed on the nodes or edges of the target topology structure, and the optimal emergency plan for the power grid equipment topology structure is determined according to the fault information of the faulty nodes and faulty edges corresponding to the real-time fault detection results.

[0026] Optionally, the step of determining an optimal scheduling solution for the topology of power grid equipment based on the load information of the pre-failure node and the transferable line information of the pre-failure edge includes:

[0027] generating a plurality of grid equipment topology scheduling schemes according to the load information of the pre-fault node or the transferable line information of the pre-fault edge;

[0028] constructing an objective function with minimizing the sum of grid stability, resource utilization, and operation efficiency of the grid equipment as a target condition;

[0029] Based on the preset constraints, the objective function is optimized and solved, and the optimal stability, optimal resource utilization and optimal operating efficiency of the power grid are determined according to the optimal solution, and the optimal scheduling plan for the topology structure of the power grid equipment is determined.

[0030] Optionally, the step of performing real-time fault detection on nodes or edges of the target topology structure based on the fused data, and determining an optimal emergency plan for the topology structure of power grid equipment according to fault information of the faulty nodes and faulty edges corresponding to the real-time fault detection results, includes:

[0031] Performing real-time fault detection on nodes or edges of the target topology structure based on the real-time operation data and historical operation data of the fused data;

[0032] Determine the fault nodes and fault edges of the target topology structure according to the real-time fault detection result;

[0033] An optimal emergency plan for the topology of the power grid equipment is determined based on the backup power supply, required transfer load, and switchable paths corresponding to the fault node or the fault edge.

[0034] A second aspect of the present invention provides a power grid equipment topology dynamic scheduling system, comprising:

[0035] An acquisition module is used to acquire operation data and spatial data of power grid equipment, and perform data fusion processing on the operation data and the spatial data;

[0036] An optimization module is used to optimize the initial power grid topology using the fused data after data fusion processing to generate a target topology;

[0037] The emergency plan module is used to perform fault detection on the nodes or edges of the target topology structure based on the fused data, and to construct an optimal emergency plan for the topology structure of the power grid equipment according to the fault information of the faulty nodes and faulty edges corresponding to the detection results.

[0038] A third aspect of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method for dynamic scheduling of power grid equipment topology as described in any one of the above items.

[0039] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the method for dynamic scheduling of power grid device topology as described in any one of the above items.

[0040] A fifth aspect of the present invention provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the power grid equipment topology dynamic scheduling method as described in any one of the above items.

[0041] It can be seen from the above technical solutions that the present invention has the following advantages:

[0042] In the present invention, the system first obtains the operating data and spatial data of the power grid equipment, and performs data fusion on the differences between multi-source heterogeneous data based on the operating data and spatial data. Subsequently, the initial power grid topology structure of the power grid equipment is dynamically adjusted / optimized by the fused data after data fusion processing to generate a target topology structure. On this basis, the fused data is used to predict or monitor the nodes or edges of the target topology structure, and the fault nodes and fault edges are determined by the prediction or monitoring results. The optimal emergency plan for the topology structure of the power grid equipment is constructed based on the fault information of the fault nodes and fault edges, and scheduling is performed according to the optimal emergency plan for the topology structure of the power grid equipment. The present invention realizes real-time monitoring, data transmission and scheduling optimization of the power grid status through multi-source data fusion and dynamic topology reconstruction technology. It solves the technical problem that the existing technology does not consider the adaptability of the emergency plan to the complex external environment, and how to optimize the scheduling efficiency in the multi-device collaborative scenario, resulting in difficulty in scheduling the power grid equipment in the multi-device collaborative scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 A flowchart of a method for dynamic scheduling of power grid equipment topology provided in accordance with the first embodiment of the present invention;

[0045] Figure 2 A flowchart of a method for dynamic scheduling of power grid equipment topology provided in the second embodiment of the present invention;

[0046] Figure 3 A schematic diagram of the steps of a power grid equipment topology dynamic scheduling system provided in the second embodiment of the present invention;

[0047] Figure 4 This is a structural block diagram of another power grid equipment topology dynamic scheduling system provided in the third embodiment of the present invention;

[0048] Figure 5 This is a structural block diagram of a computer device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0049] An embodiment of the present invention provides a method and system for dynamic scheduling of power grid equipment topology, which is used to solve the technical problem that the existing technology does not consider the adaptability of emergency plans to complex external environments, and how to optimize scheduling efficiency in multi-device collaborative scenarios, resulting in difficulty in scheduling power grid equipment in multi-device collaborative scenarios.

[0050] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below 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 making creative work are within the scope of protection of the present invention.

[0051] See also Figure 1 , Figure 1 This is a flowchart of the steps of a method for dynamic scheduling of power grid equipment topology provided in Example 1 of the present invention.

[0052] The present invention provides a method for dynamic scheduling of power grid equipment topology, comprising:

[0053] Step 101: Acquire operation data and spatial data of power grid equipment, and perform data fusion processing on the operation data and spatial data.

[0054] The operating data of power grid equipment refers to the data collected by power grid sensors, which covers data such as the equipment operating status and load distribution of power grid equipment. The operating data contains real-time operating data and historical operating data.

[0055] The spatial data of power grid equipment refers to the data in the GIS system (geographic information system) specifically used to manage and analyze geographic information related to power grid equipment.

[0056] Data fusion processing refers to the processing operation of fusing the historical operation data, real-time operation data and spatial data of power grid equipment.

[0057] It is worth mentioning that the operating data of power grid equipment usually includes data such as voltage, current, and power, while the spatial data of power grid equipment usually includes information such as the geographical location and topological structure of the power grid equipment. There are differences between multi-source heterogeneous data sources, so data fusion processing of multi-source heterogeneous data is required.

[0058] In an embodiment of the present invention, the grid sensors collect operating data such as the equipment operating status and load distribution of the grid equipment and data on geographic information related to the grid equipment in the GIS system, wherein the operating data includes historical operating data in the historical database and real-time operating data collected in real time.

[0059] Step 102: Optimize the initial power grid topology using the fused data after data fusion processing to generate a target topology.

[0060] Fusion data refers to the data obtained by multi-source heterogeneous fusion of the operation data and spatial data of power grid equipment.

[0061] The initial grid topology structure refers to the initial grid topology structure constructed by obtaining information from fused data (historical operation data of grid sensors, real-time operation data, and spatial data of the GIS system).

[0062] The target topology refers to the topology with the latest connection relationship between devices and edges as nodes and edges.

[0063] In the embodiment of the present invention, the fused data after data fusion processing is used to obtain status changes of devices and edges, topology optimization, etc., so as to update and optimize the initial power grid topology to obtain the latest target topology.

[0064] Step 103: Based on the fused data, perform fault detection on the nodes or edges of the target topology structure, and build an optimal emergency plan for the power grid equipment topology structure according to the fault information of the faulty nodes and faulty edges corresponding to the detection results.

[0065] Node refers to the equipment in the power grid as a node.

[0066] Edge refers to the power grid lines as edges.

[0067] A faulty node refers to a device that has a fault, is overloaded, or has a voltage fluctuation exceeding a threshold.

[0068] The fault side refers to the line where the fault occurs.

[0069] Fault information refers to load information of load overload, voltage information of voltage fluctuation exceeding a threshold, etc.

[0070] It is worth mentioning that when predicting the nodes or edges of the target topology structure, it is also possible to predict the predicted load information that will be overloaded at the next moment and the predicted voltage information that the voltage fluctuation exceeds the threshold. If the nodes or edges of the target topology structure are detected in real time, it is possible to detect equipment with faults, overloads, or voltage fluctuations exceeding the threshold, as well as faulty lines.

[0071] In this embodiment of the present invention, when information such as predicted load information indicating an impending load overload or predicted voltage information indicating a voltage fluctuation exceeding a threshold is detected at the next moment, the optimal scheduling plan for the grid equipment topology is selected from multiple scheduling plans based on the predicted load information and voltage information. When a faulty device, load overload, or voltage fluctuation exceeding a threshold, or a faulty line, is detected in real time, the optimal emergency plan for the grid equipment topology is determined based on the detected information.

[0072] In the present invention, the system first obtains the operating data and spatial data of the power grid equipment, and performs data fusion on the differences between multi-source heterogeneous data based on the operating data and spatial data. Subsequently, the initial power grid topology structure of the power grid equipment is dynamically adjusted / optimized by the fused data after data fusion processing to generate a target topology structure. On this basis, the fused data is used to predict or monitor the nodes or edges of the target topology structure, and the fault nodes and fault edges are determined by the prediction or monitoring results. The optimal emergency plan for the topology structure of the power grid equipment is constructed based on the fault information of the fault nodes and fault edges, and scheduling is performed according to the optimal emergency plan for the topology structure of the power grid equipment. The present invention realizes real-time monitoring, data transmission and scheduling optimization of the power grid status through multi-source data fusion and dynamic topology reconstruction technology. It solves the technical problem that the existing technology does not consider the adaptability of the emergency plan to the complex external environment, and how to optimize the scheduling efficiency in the multi-device collaborative scenario, which makes it difficult to schedule the power grid equipment in the multi-device collaborative scenario.

[0073] See also Figure 2 , Figure 2 This is a flowchart of the steps of a method for dynamic scheduling of power grid equipment topology provided in Example 2 of the present invention.

[0074] The present invention provides a method for dynamic scheduling of power grid equipment topology, comprising:

[0075] Step 201: Acquire real-time operation data and historical operation data of power grid sensors of power grid equipment and spatial data of a geographic information system.

[0076] Real-time operation data refers to real-time voltage, real-time current, real-time temperature, real-time frequency, real-time power and other equipment real-time operation status data and real-time load distribution data.

[0077] Historical operation data refers to historical equipment operating status data such as historical voltage, historical current, historical temperature, historical frequency, and historical power, as well as historical load distribution data.

[0078] In the embodiment of the present invention, the real-time operation status data of the power grid equipment, the historical operation status data of the equipment, the real-time load distribution data, the historical load distribution data and the spatial data of the GIS system are obtained.

[0079] Step 202: perform data cleaning, missing value filling, time alignment and standardization preprocessing on the real-time operation data, historical operation data and spatial data in sequence.

[0080] Data cleaning refers to the process of reviewing and verifying data. The purpose is to delete duplicate information, correct existing errors, and maintain data consistency and integrity, thereby improving data quality and providing a reliable foundation for subsequent data analysis and mining.

[0081] Missing value filling refers to an important step in data preprocessing, which aims to deal with missing data in the dataset to improve data quality and the accuracy of analysis results.

[0082] It is worth mentioning that the main purpose of data cleaning is to remove or correct erroneous, inconsistent or redundant data, including: outlier detection and processing (such as abnormal data caused by sudden changes in current or voltage or sensor failure), processing of inconsistent formats (such as inconsistent time formats, units, and encoding methods of different data sources), and deduplication of duplicate data (such as historical databases and real-time monitoring data may contain duplicate records). Missing value completion focuses on filling in missing data to ensure data integrity. Data cleaning is not just missing value processing, it also includes outlier removal, data format standardization, duplicate value removal, etc. Missing value completion is part of data cleaning, but it is particularly important in scenarios such as power grid dispatching that rely on high-quality data. It is necessary to ensure that missing data can be reasonably completed to reduce the impact on subsequent models.

[0083] Time alignment refers to adjusting different time series data to the same time base so that they are comparable in the time dimension.

[0084] Standardization preprocessing refers to a technical method that converts data according to specific rules so that it has a specific mean and standard deviation, or is within a specific range of values. It plays an important role in data processing and analysis.

[0085] Data normalization formula, used to convert data from different sources into comparable dimensions:

[0086]

[0087] In the formula, x is the original data, is the data mean, is the standard deviation of the data.

[0088] Time alignment (based on interpolation method):

[0089]

[0090] Where, is the known data value at time t-1, is the known data value at time t+1.

[0091] In an embodiment of the present invention, the differences between heterogeneous data sources are resolved by sequentially performing data cleaning, missing value filling, time alignment and standardization preprocessing on real-time operation data, historical operation data and spatial data.

[0092] Step 203: extract features of the pre-processed real-time operation data, historical operation data, and spatial data, and perform data fusion processing.

[0093] In the embodiment of the present invention, feature extraction is performed according to the time series of the pre-processed real-time operation data, historical operation data and spatial data, and data fusion processing is performed on the extracted features.

[0094] Specifically, time series feature extraction (predicting the next state based on the long short-term memory network LSTM):

[0095]

[0096] Where, is the hidden state at the current time step t, representing the LSTM's memory information at the current time step. It is used to store information from previous time steps and pass it to future time steps. f is the activation function. is the hidden state weight matrix, which is used to calculate the hidden state of the previous time step Perform linear transformation to capture long-term dependency information. Is the input weight matrix, used to input the current time step Mapping is performed to learn the characteristics of the input data. is the bias vector.

[0097] Spatial topological feature fusion (based on graph neural network GNN):

[0098]

[0099] Where, is the activation function, W is the weight matrix, is the node feature of the lth layer, A is the topological adjacency matrix, and b is the bias vector.

[0100] Calculate feature fusion weights and dynamically assign weights to data sources:

[0101]

[0102] Where, is the weight of the i-th data source, is the quality indicator of the i-th data source (such as timeliness, reliability, etc.), Represents the quality index of all n data sources Perform summation, where j traverses all data sources from 1 to n and calculates the sum of all data source metrics. The fusion result is calculated as , is the data of the i-th data source.

[0103]

[0104] It is worth mentioning that the weight distribution mechanism adjusts the fusion weight based on the real-time reliability of the data source to ensure the accuracy and real-time performance of the fusion results. A spatial feature representation method based on graph neural networks is designed to effectively integrate topological relationships and real-time status.

[0105] Step 204: Optimize the initial power grid topology using the fused data after data fusion processing to generate a target topology.

[0106] Furthermore, step 204 may include the following sub-steps:

[0107] S11. Analyze the fused data after the data fusion processing, and determine the initial power grid topology according to the analysis result.

[0108] The analysis result refers to the result of analyzing the connection relationship between the devices and lines of the fused data.

[0109] In this embodiment of the present invention, the fused dataset, including equipment operating status, load distribution, and GIS spatial information, is read. The topological information in the data is parsed, and the connection relationships between nodes (devices) and edges (lines) are extracted. Based on the basic topology of the power grid, an initial graph model (i.e., the initial power grid topology) is constructed. Attributes (such as voltage, load, and operating status) are assigned to each node and edge.

[0110] S12. Based on the device status data in the fused data, update the node status of the initial power grid topology.

[0111] Equipment status data refers to various data on the operating status of power grid equipment.

[0112] Node status refers to the operating status and attribute characteristics of the node (device) itself.

[0113] In the embodiment of the present invention, node attributes of the initial power grid topology are dynamically updated based on the device status data in the fused data, such as load changes, device failures, and the like.

[0114] S13. Based on the line status data in the fused data, update the edge status of the initial power grid topology structure.

[0115] Line status data refers to various data on the operating conditions of the power grid's transmission and distribution lines.

[0116] Edge status refers to the characteristics and operating conditions of line connections.

[0117] In an embodiment of the present invention, the connectivity of the edges of the initial power grid topology is adjusted according to the line status information in the fused data, such as disconnection, path reconstruction, etc.

[0118] S14. Combine the updated node states and edge states to generate an updated topology structure.

[0119] In an embodiment of the present invention, during a dynamic topology update process, the topology of the power grid is updated according to situations such as the addition or removal of devices, line status changes, and topology optimization.

[0120] It is worth mentioning that the dynamic topology is constructed based on the graph theory model, with devices and lines as nodes and edges, and their connection relationships are updated in real time. The topological structure of the power grid is represented as , where V is the node set (representing devices) and G is the edge set (representing line connections between devices). Update the topology connection based on the device status:

[0121]

[0122] Where, Indicates the status of node v (e.g., "active" indicates normal operation, and "faulty" indicates faulty operation).

[0123] Combined with real-time data, it dynamically detects topological changes in the power grid, such as the removal of faulty nodes and the connection of new equipment, and updates the topology of the power grid.

[0124] S15. Calculate the node importance index of each node of the updated topology structure.

[0125] Node importance index refers to the index used to measure the criticality of nodes in the topology structure, such as load centrality.

[0126] In the embodiment of the present invention, the node importance index (such as load centrality) of each node in the updated topology structure is calculated and used to adjust the topology structure and ensure load balancing.

[0127] Formula for calculating node importance indicators (such as load centrality):

[0128]

[0129] Where, is the load from node u to node v, is the degree of node v.

[0130] S16. Optimize and update the topology structure according to the node importance index of each node to generate a target topology structure.

[0131] In this embodiment of the present invention, reinforcement learning is used to optimize the topology adjustment strategy. The node importance index of each node is optimized to update the topology structure and obtain the target topology. This improves the efficiency and accuracy of topology reconstruction and ensures high efficiency in complex scenarios. A dynamic topology update method driven by real-time data is proposed to ensure that the topology structure always accurately reflects the operating status of the power grid. A rapid topology adjustment algorithm has been developed to effectively shorten the topology response time caused by load fluctuations or equipment failures.

[0132] It is worth mentioning that during the dynamic topology update process, the topology of the power grid is updated based on the addition or removal of devices, line status changes, topology optimization, etc. The specific implementation process is as follows:

[0133] T1. Equipment status monitoring: Obtain the real-time status of each device from the fused data (for example, equipment operating status and fault detection information in sensor data).

[0134] Fault detection: When a device or line fails, it is marked as a faulty node or faulty edge in real time, and the node's status attributes (such as "faulty" or "normal") are updated.

[0135] T2. Line Status Update: Using GIS data or real-time sensor data, the connection status of each line is checked. If a line experiences a fault (e.g., a disconnection or outage), the edge is deleted and possible alternative routes are recalculated. Based on changes in load distribution, the line's load attributes are dynamically adjusted, assessing load centrality and edge transmission capacity. Based on the calculated load changes, the line's transmission capacity weight is dynamically updated.

[0136] T3. Device Addition and Removal: When a new device is added to the grid (such as a new substation or generator), relevant information about the new device (such as device type, capacity, and location) is obtained from the fused data. The new device is then added to the topology as a node, and corresponding edges are created based on the lines it connects to. When a device is removed, the corresponding node and related connected edges are deleted, and the overall topology structure is recalculated.

[0137] T4. Topology Optimization: Optimize the grid topology by calculating metrics such as load centrality and connectivity of nodes and edges. Nodes with high load centrality may become critical nodes, and their connectivity must be high.

[0138] When faulty nodes or lines are removed, the system will calculate a new optimal path or load transfer plan based on a dynamic topology reconstruction algorithm to ensure efficient operation and stability of the power grid.

[0139] T5. Real-time Update: When equipment or line status changes, the topology is dynamically updated using real-time data. Algorithms such as graph neural networks are used for status assessment and topology optimization, ensuring rapid topology response. Whenever the topology changes, the new topological state is immediately fed back to the dispatching system for adjustment of dispatch strategies and load distribution.

[0140] Step 205: Based on the fused data, perform fault detection on the nodes or edges of the target topology structure, and construct an optimal emergency plan for the power grid equipment topology structure according to the fault information of the faulty nodes and faulty edges corresponding to the detection results.

[0141] Furthermore, step 205 may include the following sub-steps:

[0142] S21. Input the fused data into a preset deep learning model.

[0143] Deep learning models refer to machine learning models based on artificial neural networks, which can automatically learn features and patterns from large amounts of data to achieve various tasks such as image recognition, speech recognition, natural language processing, etc.

[0144] In an embodiment of the present invention, the fused data is input into a preset deep learning model, and the deep learning model is combined with the real-time operation data and historical operation data of the fused data to quickly predict the power grid status and generate scheduling plans such as load transfer and line switching.

[0145] S22. Calculate the predicted output value of the fused data using the time series prediction method of the deep learning model.

[0146] In an embodiment of the present invention, the predicted output value of the fusion data is calculated by the time series prediction method of the deep learning model. The calculation formula of the time series prediction method based on deep learning is:

[0147]

[0148]

[0149] Where, Input features for time step t, is the hidden state at the current moment t, W and b are weight and bias vectors respectively, is the output prediction value.

[0150] S23. Determine the pre-failure nodes and pre-failure edges of the target topology structure according to the predicted output values.

[0151] A pre-failure node refers to a device that is predicted to fail or has an upcoming load peak.

[0152] A pre-fault edge refers to a line that is predicted to be overloaded.

[0153] In the embodiment of the present invention, the equipment or line that is about to fail or has a load peak or is about to be overloaded can be determined based on the predicted output value, thereby obtaining the pre-failure nodes or pre-failure edges of the target topology structure.

[0154] S24. Determine an optimal dispatching scheme for the topology of the power grid equipment based on the load information of the pre-fault node and the transferable line information of the pre-fault edge.

[0155] The transferable line information refers to the information of the switchable line of the pre-fault line.

[0156] In an embodiment of the present invention, when the prediction result indicates that a certain device's load peak is about to arrive, a first optimization scheduling scheme can be constructed to pre-adjust load distribution and reduce the pressure on high-load nodes. When the prediction result predicts that a certain line is about to overload, a second optimization scheduling scheme can be constructed to execute line switching in advance to optimize power flow. When the prediction result predicts that a certain device is about to fail, a third optimization scheduling scheme can be constructed to activate backup equipment to reduce the impact of the failure. When the prediction result indicates that a trend of topology adjustment is discovered, a fourth optimization scheduling scheme can be constructed to optimize scheduling in advance and adapt to topology changes. Based on the load information of the predicted failure node and the transferable line information of the predicted failure edge, the optimal scheduling scheme for the power grid device topology is selected.

[0157] Furthermore, S24 may include the following sub-steps:

[0158] S241. Generate multiple grid equipment topology scheduling schemes based on load information of pre-fault nodes or transferable line information of pre-fault edges.

[0159] In an embodiment of the present invention, when the prediction result indicates that a certain device's load peak is about to arrive, a first optimization scheduling scheme can be constructed to pre-adjust load distribution and reduce the pressure on high-load nodes; when the prediction result predicts that a certain line is about to be overloaded, a second optimization scheduling scheme can be constructed to execute line switching in advance and optimize power flow; when the prediction result predicts that a certain device is about to fail, a third optimization scheduling scheme can be constructed to start backup equipment and reduce the impact of the failure; when the prediction result indicates that a topology adjustment trend is discovered, a fourth optimization scheduling scheme can be constructed to optimize scheduling in advance and adapt to topology changes. Based on the above multiple prediction results, multiple grid device topology scheduling schemes can be constructed.

[0160] S242. Construct an objective function with minimizing the sum of grid stability, resource utilization, and operation efficiency of grid equipment as the target condition.

[0161] Grid stability refers to the ability of the power system to maintain synchronous operation, voltage and frequency within the allowable range, and ensure power quality and power supply reliability after being disturbed.

[0162] Resource utilization refers to an important indicator for measuring the operating efficiency and benefits of power grid equipment. It reflects the degree to which the equipment effectively utilizes its own resources during actual operation.

[0163] Operational efficiency refers to a comprehensive indicator used to measure the extent to which power grid equipment effectively utilizes electrical energy and exerts its own performance in the process of transmitting electrical energy from the power generation end to the power consumption end.

[0164] In the embodiment of the present invention, the optimal dispatching scheme is generated by comprehensively considering the stability of the power grid, resource utilization and operation efficiency. This is achieved through multi-objective optimization:

[0165]

[0166] Where, is the system stability index, To improve the efficiency of scheduling execution, is the resource utilization rate, 、 、 is the weight coefficient.

[0167] It is worth mentioning that a real-time intelligent reasoning model based on deep learning was proposed, which can generate scheduling solutions applicable to multiple scenarios.

[0168] S243. Based on the preset constraints, the objective function is optimized and solved, and the optimal stability, optimal resource utilization and optimal operating efficiency of the power grid are determined according to the optimal solution, and the optimal scheduling plan for the topology of the power grid equipment is determined.

[0169] In this embodiment of the present invention, the objective function is optimized and solved according to preset constraints to obtain the optimal solution, determine the optimal grid stability, optimal resource utilization, and optimal operating efficiency, and determine the optimal scheduling plan for the grid equipment topology. This invention establishes an adaptive scheduling optimization mechanism to ensure that the scheduling strategy can be dynamically adjusted based on actual execution results.

[0170] S25. Based on the fused data, real-time fault detection is performed on the nodes or edges of the target topology structure, and the optimal emergency plan for the power grid equipment topology structure is determined according to the fault information of the faulty nodes and faulty edges corresponding to the real-time fault detection results.

[0171] In this embodiment of the present invention, real-time fault detection is achieved by fusion data to monitor equipment status in real time and quickly identify faulty nodes and lines. The optimal emergency plan for the power grid equipment topology is determined based on the fault information of the faulty nodes and faulty edges corresponding to the real-time fault detection results.

[0172] Furthermore, S25 may include the following sub-steps:

[0173] S251 . Based on the real-time operation data and historical operation data of the fused data, perform real-time fault detection on nodes or edges of the target topology structure.

[0174] In the embodiment of the present invention, the real-time operation data and historical operation data in the fusion data are used to monitor the device status in real time, and the nodes or edges of the target topology structure are detected in real time to quickly identify the faulty nodes and faulty edges. The fault monitoring formula based on data anomalies is:

[0175]

[0176] Where, is the actual status value of the device, is the predicted state value, is the standard deviation of the state value, Indicates that node v has failed.

[0177] S252: Determine the faulty nodes and faulty edges of the target topology structure according to the real-time fault detection result.

[0178] In the embodiment of the present invention, the calculation result of the fault monitoring formula of the data anomaly can be used to know that a certain node or a certain edge has a fault, and the faulty node and the faulty edge can be obtained.

[0179] S253. Determine the optimal emergency plan for the topology of the power grid equipment based on the backup power source corresponding to the fault node or fault edge, the required transfer load, and the switchable path.

[0180] Backup power refers to a pre-prepared backup power source (such as a backup generator, uninterruptible power supply (UPS), battery pack, etc.) that starts working to ensure the continued normal operation of related equipment or systems, taking over the power supply task of the failed node and providing power to the affected part or the entire system.

[0181] Load transfer (load that needs to be transferred) refers to the redistribution of the load carried by the faulty node to other normally operating power supply lines, equipment or areas to ensure a continuous and reliable power supply when a node in the power grid fails (such as a short circuit, open circuit, component damage, etc.), resulting in the power supply of the node and its related areas being affected.

[0182] A switchable path refers to the process of switching the transmission path that originally passed through the faulty node to another available path to ensure the normal transmission of information or energy when a node fails.

[0183] In this embodiment of the present invention, based on the dynamic topology and intelligent reasoning results, an emergency plan is automatically generated, including backup power activation, load transfer (i.e., required load transfer), and path switching. The optimal recovery path is calculated using the shortest path algorithm:

[0184]

[0185] Where, is the set of all available paths, is the weight of the edge in the path.

[0186] According to the above calculation method, the optimal emergency plan for the topological structure of the power grid equipment can be obtained.

[0187] It is worth mentioning that see Figure 3 As shown in the figure, the present invention can be composed of a system architecture consisting of a data acquisition module, a data fusion module, a dynamic topology module, an intelligent reasoning module, and a scheduling execution module. Each module achieves efficient collaboration through a unified interface, ensuring seamless integration of data flow and task flow. Adjust the model parameters according to the system execution effect:

[0188]

[0189] Where, are model parameters, is the learning rate, is the loss function.

[0190] A collaborative optimization mechanism between modules is designed to improve the overall system performance by adjusting the parameters and interaction methods of each module through feedback. The overall system performance optimization and the collaborative optimization goals between modules are:

[0191]

[0192] Where, is the data fusion time, is the topology reconstruction time, is the fault response time, 、 、 is the weight coefficient.

[0193] It is worth mentioning that in smart grids, this invention achieves real-time monitoring of grid status, data transmission, and scheduling optimization through multi-source data fusion and dynamic topology reconstruction technology. Sensors collect data from each node of the grid in real time, including voltage, load, topology status, and fault information. Through multi-source heterogeneous data fusion technology, sensor data, GIS information, and historical operation data are integrated into a unified dynamic state model and sent to the central control system. When the system starts, based on deep learning and graph neural network algorithms, model parameters such as feature weights, learning rate, and maximum number of iterations are initialized to establish a dynamic topology model. Through real-time data fusion and intelligent analysis, it not only operates efficiently in various grid operation scenarios (such as equipment failures, load fluctuations, extreme conditions, etc.), but also significantly improves the real-time performance of grid topology updates, the intelligence of scheduling plans, and the stability and reliability of system operation.

[0194] During real-time operation, the system leverages fused data to drive topology updates, quickly identifying equipment failures and load changes. The dynamic topology reconstruction module analyzes grid connections using graph theory and verifies this with historical operational data. It then optimizes topology adjustment strategies through reinforcement learning, ensuring the topology remains synchronized with actual operating conditions. The central control system monitors grid status in real time and dynamically adjusts algorithm parameters based on feedback, enhancing the system's adaptability and responsiveness.

[0195] When an abnormal situation is detected, the intelligent reasoning model of this invention automatically generates an emergency response plan, including fault information transmission, load transfer strategies, and the activation of backup paths, to ensure that fault information is quickly transmitted to the control center and promptly processed. By optimizing the scheduling algorithm, the system can accurately predict grid load changes and dynamically adjust the allocation of power resources based on real-time data, optimizing load scheduling, reducing energy waste, and significantly improving the operational efficiency and overall stability of the grid.

[0196] In this invention, by combining multi-source data fusion with dynamic topology reconstruction technology, the limitations of traditional power grid dispatching systems are broken through, and the intelligence, real-time performance, accuracy and stability of the system are comprehensively improved, which helps to improve the efficiency and safety of power grid operation. Specific advantages include:

[0197] 1. Multi-source heterogeneous data fusion: Integrate data from multiple sources such as sensors and GIS systems to solve the information island problem caused by differences in data formats and types in traditional technologies, ensure data integrity and consistency, and provide accurate and comprehensive decision-making basis for power grid dispatching.

[0198] 2. Dynamic topology reconstruction: Introducing a real-time data-driven topology reconstruction method overcomes the limitations of traditional static models in reflecting changes in device status. It quickly updates the topology in situations such as device failures and load fluctuations, significantly improving system response speed and adaptability.

[0199] 3. Improve stability and reliability: By real-time monitoring and analysis of equipment status, dynamically optimize the topology structure, avoid operational risks caused by information lag or misjudgment of equipment status, and ensure the stability and reliability of the power grid in complex environments.

[0200] 4. Intelligent scheduling and recovery: Combining deep learning and intelligent reasoning models, it automatically generates startup and recovery plans based on real-time data, optimizes scheduling efficiency, quickly responds to anomalies or failures, and reduces manual intervention.

[0201] 5. Enhanced fault recovery capabilities: Dynamic topology reconstruction and intelligent scheduling methods can quickly generate emergency plans, adjust the grid structure in real time, shorten power outages, reduce losses, and ensure the security and continuity of power supply.

[0202] 6. Adaptability to multiple scenarios: Through adaptive learning algorithms and multi-source data fusion analysis, it can cope with various scenarios such as normal operation, load fluctuations, equipment failures and extreme environments, demonstrating excellent adaptability and flexibility.

[0203] The present invention is significantly superior to traditional technologies in terms of real-time performance, intelligence and reliability, and comprehensively improves the efficiency and safety of modern power grid dispatching.

[0204] See also Figure 4 , Figure 4 This is a structural block diagram of a power grid equipment topology dynamic scheduling system provided in Example 3 of the present invention.

[0205] The present invention provides a power grid equipment topology dynamic scheduling system, comprising:

[0206] An acquisition module 401 is used to acquire operation data and spatial data of power grid equipment and perform data fusion processing on the operation data and spatial data;

[0207] An optimization module 402 is configured to optimize the initial power grid topology using the fused data after data fusion processing to generate a target topology;

[0208] The emergency plan module 403 is used to perform fault detection on nodes or edges of the target topology structure based on the fused data, and to construct an optimal emergency plan for the power grid equipment topology structure according to the fault information of the faulty nodes and faulty edges corresponding to the detection results.

[0209] Furthermore, the acquisition module 401 includes:

[0210] An acquisition submodule is used to acquire real-time operation data and historical operation data of power grid sensors of power grid equipment and spatial data of geographic information systems;

[0211] The preprocessing submodule is used to perform data cleaning, missing value filling, time alignment and standardization preprocessing on real-time operation data, historical operation data and spatial data in sequence;

[0212] The data fusion submodule is used to extract the features of pre-processed real-time operation data, historical operation data and spatial data, and perform data fusion processing.

[0213] Furthermore, the optimization module 402 includes:

[0214] The parsing submodule is used to parse the fused data after data fusion processing and determine the initial power grid topology according to the parsing results;

[0215] The node status update submodule is used to update the node status of the initial power grid topology structure based on the device status data in the fused data;

[0216] An edge state update submodule is used to update the edge state of the initial power grid topology based on the line state data in the fused data;

[0217] The combining submodule is used to combine the updated node status and edge status to generate an updated topology structure;

[0218] The calculation submodule is used to calculate the node importance index of each node in the updated topology structure;

[0219] The optimization submodule is used to optimize and update the topology structure according to the node importance index of each node and generate the target topology structure.

[0220] Furthermore, the emergency plan module 403 includes:

[0221] Input submodule, used to input fused data into the preset deep learning model;

[0222] The prediction submodule is used to calculate the predicted output value of the fused data using the time series prediction method of the deep learning model;

[0223] A pre-fault submodule is used to determine the pre-fault nodes and pre-fault edges of the target topology structure according to the predicted output value;

[0224] The optimal scheduling scheme submodule is used to determine the optimal scheduling scheme for the topology of the power grid equipment based on the load information of the pre-fault node and the transferable line information of the pre-fault edge;

[0225] The optimal emergency plan submodule is used to perform real-time fault detection on the nodes or edges of the target topology structure based on the fused data, and determine the optimal emergency plan for the power grid equipment topology structure according to the fault information of the fault nodes and fault edges corresponding to the real-time fault detection results.

[0226] Furthermore, the optimal scheduling solution submodule includes:

[0227] A scheduling scheme submodule is used to generate multiple grid equipment topology scheduling schemes based on the load information of the pre-fault node or the transferable line information of the pre-fault edge;

[0228] An objective function submodule is used to construct an objective function based on the objective condition of minimizing the sum of grid stability, resource utilization, and operation efficiency of grid equipment;

[0229] The submodule of the optimal dispatching scheme for the topology structure of power grid equipment is used to find the optimal solution for the objective function based on preset constraints, determine the optimal stability, optimal resource utilization and optimal operating efficiency of the power grid according to the optimal solution, and determine the optimal dispatching scheme for the topology structure of power grid equipment.

[0230] Furthermore, the optimal emergency plan submodule includes:

[0231] The fault detection submodule is used to perform real-time fault detection on nodes or edges of the target topology based on the real-time operation data and historical operation data of the fused data;

[0232] The detection result submodule is used to determine the faulty nodes and faulty edges of the target topology structure based on the real-time fault detection results;

[0233] The optimal emergency plan submodule for the topology of power grid equipment is used to determine the optimal emergency plan for the topology of power grid equipment based on the backup power supply, required transfer load and switchable path corresponding to the fault node or fault edge.

[0234] See also Figure 5 , Figure 5 This is a structural block diagram of a computer device provided in Example 4 of the present invention.

[0235] An electronic device according to an embodiment of the present invention includes: a memory 501 and a processor 502, wherein the memory 501 stores a computer program; when the computer program is executed by the processor 502, the processor 502 executes the power grid equipment topology dynamic scheduling method as described in any of the above embodiments.

[0236] Memory 501 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Memory 501 has storage space 503 for program code 513 for executing any of the method steps described above. For example, storage space 503 for program code may include individual program codes 513 for implementing various steps in the method described above. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. The program codes may be compressed, for example, in a suitable format. When executed by a processing device, these codes cause the processing device to execute the various steps in the method described above. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. The program codes may be compressed, for example, in a suitable format. When these codes are executed by a computing and processing device, they cause the computing and processing device to execute the various steps of the method for dynamic scheduling of power grid device topologies described above.

[0237] The fifth embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for dynamic scheduling of power grid device topology as described in any of the above embodiments is implemented.

[0238] Embodiment 6 of the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the power grid equipment topology dynamic scheduling method as described in any of the above embodiments.

[0239] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0240] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely 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 an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0241] The units described 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 to achieve the purpose of this embodiment according to actual needs.

[0242] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, 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.

[0243] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0244] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for dynamic scheduling of power grid equipment topology, characterized in that: include: Acquiring operation data and spatial data of power grid equipment, and performing data fusion processing on the operation data and the spatial data; The fused data after data fusion processing is used to optimize the initial power grid topology to generate the target topology; Based on the fused data, fault detection is performed on the nodes or edges of the target topology structure, and an optimal emergency plan for the topology structure of the power grid equipment is constructed according to the fault information of the faulty nodes and faulty edges corresponding to the detection results.

2. The method for dynamic scheduling of power grid equipment topology according to claim 1, characterized in that: The step of acquiring the operation data and spatial data of the power grid equipment and performing data fusion processing on the operation data and the spatial data includes: Acquire real-time and historical operating data from grid sensors of power grid equipment and spatial data from geographic information systems; The real-time operation data, the historical operation data and the spatial data are sequentially subjected to data cleaning, missing value filling, time alignment and standardization preprocessing; Extract the features of pre-processed real-time operation data, historical operation data and spatial data, and perform data fusion processing.

3. The method for dynamic scheduling of power grid equipment topology according to claim 1, characterized in that: The step of optimizing the initial power grid topology structure using the fused data after data fusion processing to generate the target topology structure includes: Analyze the fused data after data fusion processing, and determine the initial power grid topology according to the analysis results; Based on the device status data in the fused data, updating the node status of the initial power grid topology structure; Based on the line state data in the fused data, updating the edge state of the initial power grid topology structure; Combine the updated node and edge states to generate an updated topology; Calculating a node importance index of each node of the updated topology structure; The updated topology structure is optimized according to the node importance index of each node to generate a target topology structure.

4. The method for dynamic scheduling of power grid equipment topology according to claim 2, characterized in that: The step of performing fault detection on nodes or edges of the target topology structure based on the fused data, and constructing an optimal emergency plan for the topology structure of power grid equipment according to fault information of the faulty nodes and faulty edges corresponding to the detection results, includes: Inputting the fused data into a preset deep learning model; Calculating the predicted output value of the fused data by the time series prediction method of the deep learning model; Determining the pre-failure nodes and pre-failure edges of the target topology structure according to the predicted output value; Determining an optimal scheduling solution for a topology of power grid equipment based on the load information of the pre-fault node and the transferable line information of the pre-fault edge; Based on the fused data, real-time fault detection is performed on the nodes or edges of the target topology structure, and the optimal emergency plan for the power grid equipment topology structure is determined according to the fault information of the faulty nodes and faulty edges corresponding to the real-time fault detection results.

5. The method for dynamic scheduling of power grid equipment topology according to claim 4, characterized in that: The step of determining an optimal scheduling solution for the topology of power grid equipment based on the load information of the pre-failure node and the transferable line information of the pre-failure edge includes: generating a plurality of grid equipment topology scheduling schemes according to the load information of the pre-fault node or the transferable line information of the pre-fault edge; constructing an objective function with minimizing the sum of grid stability, resource utilization, and operation efficiency of the grid equipment as a target condition; Based on the preset constraints, the objective function is optimized and solved, and the optimal stability, optimal resource utilization and optimal operating efficiency of the power grid are determined according to the optimal solution, and the optimal scheduling plan for the topology structure of the power grid equipment is determined.

6. The method for dynamic scheduling of power grid equipment topology according to claim 4, characterized in that: The step of performing real-time fault detection on nodes or edges of the target topology structure based on the fused data, and determining an optimal emergency plan for the topology structure of power grid equipment according to fault information of the faulty nodes and faulty edges corresponding to the real-time fault detection results, includes: Performing real-time fault detection on nodes or edges of the target topology structure based on the real-time operation data and historical operation data of the fused data; Determine the fault nodes and fault edges of the target topology structure according to the real-time fault detection result; An optimal emergency plan for the topology of the power grid equipment is determined based on the backup power supply, required transfer load, and switchable paths corresponding to the fault node or the fault edge.

7. A power grid equipment topology dynamic scheduling system, characterized in that: include: An acquisition module is used to acquire operation data and spatial data of power grid equipment, and perform data fusion processing on the operation data and the spatial data; An optimization module is used to optimize the initial power grid topology using the fused data after data fusion processing to generate a target topology; The emergency plan module is used to perform fault detection on the nodes or edges of the target topology structure based on the fused data, and to construct an optimal emergency plan for the topology structure of the power grid equipment according to the fault information of the faulty nodes and faulty edges corresponding to the detection results.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method for dynamic scheduling of power grid device topology according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method for dynamic scheduling of power grid device topology according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer is caused to execute the method for dynamic scheduling of power grid device topology according to any one of claims 1 to 6.

Images