A method, system, device and medium for constructing area topology

Abstract

The present invention belongs to the field of electric power technology. In order to solve the problem of inaccurate construction of existing substation topology, a substation topology construction method, system, equipment and medium are proposed. By obtaining voltage data and current data at electrical connections, by path tracking, by minimizing the deviation between the calculated association metric and the expected topology structure as the optimization target, the optimization target is solved by a gradient descent optimization algorithm, the optimal association metric is determined, and according to the determined optimal association degree, the subordinate relationship between the electrical connection points is determined to construct a substation topology diagram. The method of the present invention can accurately identify and verify the actual connection status in the power grid, including temporary or newly formed connections that are difficult to detect, and the constructed topology structure is more accurate. Accurate topology information can improve the economy and environmental friendliness of the entire power grid.

Description

Technical Field

[0001] The present invention belongs to the field of electric power technology, and in particular relates to a method, system, equipment and medium for constructing a substation topology. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In the management of power systems, it is crucial to accurately understand the topological relationship of the substation, which involves the stability, efficiency and operation and maintenance cost control of the power grid. The substation topology refers to the connection relationship between various electrical equipment (such as transformers, circuit breakers, transmission lines, etc.) in the power system. This information helps grid operators optimize the load distribution of current, reduce energy losses, improve the response speed of the system, and ensure the reliability of power supply.

[0004] Traditionally, the identification and updating of substation topology mainly rely on manual operations by ground staff and periodic system inspections. This process is not only time-consuming and costly, but also susceptible to human errors and difficult to reflect the dynamic changes of the system in real time. For example, after extreme weather events or emergencies, the actual operating status of the power grid may change rapidly, and traditional methods cannot provide timely and accurate topology information updates, which may lead to wrong decisions and insufficient system response.

[0005] As power systems become more intelligent, the requirements for topology management are also increasing. Real-time, automated topology recognition technology has become a necessity for grid modernization, especially with the introduction of distributed energy and renewable energy integration, as grid structures become more complex and dynamic. Therefore, developing a method that can accurately identify and update substation topology relationships in real time is of great significance for improving the operating efficiency and reliability of the grid.

[0006] According to the inventors, the prior art has the following technical problems: some substations are unable to detect temporary or newly formed connections in the power grid in a timely manner due to power outages and reconnections for maintenance, users' unauthorized changes in lines or overlapping power supply ranges, resulting in inaccurate topological structures of the constructed substations, which may result in potential problems caused by this being missed, increasing the risk of power grid operation. Summary of the invention

[0007] In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides a method, system, device and medium for constructing a substation topology, which can accurately identify and verify the actual connection status in the power grid, including imperceptible temporary or newly formed connections, and the constructed topology structure is more accurate.

[0008] To achieve the above object, the first aspect of the present invention provides a method for constructing a station area topology, comprising:

[0009] Acquire power data at the electrical connection points in the substation to be constructed and perform preprocessing; wherein the power data includes voltage data and current data;

[0010] Perform dynamic path tracking on the preprocessed power data, and calculate the correlation metrics between different electrical connection points based on the dynamic path tracking results;

[0011] Taking minimizing the deviation between the calculated association metric and the expected topological structure as the optimization goal, the optimal association metric is obtained by optimizing the solution through the gradient descent optimization algorithm;

[0012] Based on the optimal correlation metric and the power data difference between the corresponding electrical connection points, the subordinate relationship between different electrical connection points is determined, and all electrical connection points are traversed until the substation topology structure corresponding to the substation to be constructed is constructed.

[0013] A second aspect of the present invention provides a system for constructing a station area topology, comprising:

[0014] An acquisition module is used to acquire power data at the electrical connection points in the substation to be constructed and perform preprocessing; wherein the power data includes voltage data and current data;

[0015] A calculation module, used for performing dynamic path tracking on the pre-processed power data, and calculating the correlation metrics between different electrical connection points according to the dynamic path tracking results;

[0016] The update module takes minimizing the deviation between the calculated association metric and the expected topological structure as the optimization goal, and optimizes and solves it through the gradient descent optimization algorithm to obtain the optimal association metric;

[0017] The construction module is used to determine the subordinate relationship between different electrical connection points based on the optimal association metric and the power data difference between the corresponding electrical connection points, and traverse all electrical connection points until the substation topology structure corresponding to the substation to be constructed is constructed.

[0018] The third aspect of the present invention provides a computer device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, a method for constructing a station area topology is executed.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, a method for constructing a station area topology is executed.

[0020] One or more of the above technical solutions have the following beneficial effects:

[0021] In the present invention, by acquiring the voltage data and current data at the electrical connection, through path tracking, by minimizing the deviation between the calculated association metric and the expected topological structure as the optimization target, the optimization target is solved by the gradient descent optimization algorithm, the optimal association metric is determined, and according to the determined optimal association degree, the subordinate relationship between the electrical connection points is determined to construct the substation area topological structure diagram. The method of the present invention can accurately identify and verify the actual connection status in the power grid, including temporary or newly formed connections that are difficult to detect. The constructed topological structure is more accurate, and accurate topological information supports the implementation of more efficient demand response strategies and the integration of renewable energy, thereby improving the economy and environmental friendliness of the entire power grid; accurate topological information can also help quickly locate the problem and shorten the recovery time. The automated topological identification method can also update the power grid status in real time and provide necessary data support for fault recovery.

[0022] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0024] Figure 1 This is a flow chart of a method for constructing a topology of a substation in Embodiment 1 of the present invention;

[0025] Figure 2 This is a topological connection diagram of the station area in Example 1 of the present invention. DETAILED DESCRIPTION

[0026] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0027] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0028] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0029] Embodiment 1

[0030] This embodiment discloses a method for constructing a station area topology, including:

[0031] Step 1: Obtain power data at the electrical connection points in the substation to be constructed and perform preprocessing; wherein the power data includes voltage data and current data;

[0032] Step 2: Perform dynamic path tracking on the preprocessed power data, and calculate the correlation metrics between different electrical connection points based on the dynamic path tracking results;

[0033] Step 3: Taking minimizing the deviation between the calculated association metric and the expected topological structure as the optimization goal, the optimization is solved by the gradient descent optimization algorithm to obtain the optimal association metric;

[0034] Step 4: Based on the updated association metric and the power data difference between the corresponding electrical connection points, determine the subordinate relationship between different electrical connection points, and traverse all electrical connection points until the substation topology structure corresponding to the substation to be constructed is constructed.

[0035] This embodiment can accurately identify and verify the actual connection status in the power grid, including imperceptible temporary or newly formed connections, by acquiring voltage data and current data at the electrical connection point, through path tracking, and by minimizing the deviation between the calculated association metric and the expected topological structure as the optimization goal, solving the optimization goal through a gradient descent optimization algorithm, determining the optimal association metric, and determining the subordinate relationship between the electrical connection points based on the determined optimal association degree, and constructing a substation topological structure diagram. The topological structure constructed by the method of the present invention is more accurate, making the power grid operation more stable and reliable, reducing the risk of unexpected power outages and equipment failures, and in addition, accurate topological information also supports the implementation of more efficient demand response strategies and the integration of renewable energy, thereby improving the economy and environmental friendliness of the entire power grid; it can help quickly locate the problem and shorten the recovery time, and the automated topology recognition system can also update the power grid status in real time, providing necessary data support for fault recovery.

[0036] Combine the following Figure 1 A method for constructing a substation topology proposed in this embodiment is described in detail, specifically including:

[0037] Step 1: Obtain power data at the electrical connection points in the substation to be constructed and perform preprocessing; wherein the power data includes voltage data and current data.

[0038] Utilize the existing power line structure to build a high-speed power line communication (HPLC) network, install communication equipment in the substation, including repeaters and receivers, to ensure that every electrical connection point in the entire substation is within the network coverage, and use sensors installed at each electrical connection point in the substation to monitor in real time the current and voltage data changes before and after the circuit breaker is operated.

[0039] The acquired current and voltage data are preprocessed, including preliminary cleaning and verification, specifically removing noise, correcting bias and filling missing values. The cleaned current and voltage data are mapped into high-dimensional space to reveal the complex patterns and features hidden in the data and convert them into a form more suitable for analysis.

[0040] The high-dimensional space mapping formula is:

[0041] (1)

[0042] in, It is the current data and voltage data mapped into the high-dimensional space. is the cleaned current data, is the voltage data after cleaning, and They are the current adjustment parameter and the voltage adjustment parameter, which are used to adjust the influence of the quadratic terms of current and voltage. It is a parameter that adjusts the nonlinear effect of the product of current and voltage to ensure that the mapped data can reveal the intrinsic relationship between current and voltage to the greatest extent.

[0043] Among them, the initial parameters , and It can be determined empirically or through simple exploratory data analysis (EDA). In this embodiment, the initial value can be selected as: , A random value in the range [0.1, 1.0], A random value in the range [0.01, 0.1].

[0044] Use optimization algorithms (such as gradient descent method, genetic algorithm, etc.) to optimize the parameters. The specific steps are as follows:

[0045] Define a loss function, such as mean square error (MSE), to evaluate the effect of the mapped data. Minimize the loss function through the optimization algorithm and gradually adjust , and The value of is used to find the parameter combination that achieves the best mapping effect.

[0046] Through the above optimization method, the parameter ranges are determined as follows:

[0047] Current adjustment parameters : Generally in the range [0.1, 2.0]. Lower values ​​are suitable for smaller current changes, while higher values ​​are suitable for larger current changes.

[0048] Voltage adjustment parameters : Generally in the range [0.1, 2.0]. Similarly, lower values ​​are suitable for smaller voltage changes, and higher values ​​are suitable for larger voltage changes.

[0049] Nonlinear tuning parameters : Generally in the range [0.01, 1.0]. Lower values ​​are suitable for situations where the relationship between current and voltage is more linear, while higher values ​​are suitable for situations where the relationship between the two is complex and more nonlinear.

[0050] Step 2: Perform dynamic path tracking on the preprocessed power data, and calculate the correlation metrics between different electrical connection points based on the dynamic path tracking results.

[0051] In order to capture the changes in current and voltage over time and understand the dynamic changes in the power grid, data in high-dimensional space are used for dynamic path tracing, which can identify potential connections between electrical connection points because connected electrical connection points will show similar or related change patterns.

[0052] Dynamic path tracking is achieved by integrating the path, and the specific formula is:

[0053] (2)

[0054] in, represents the dynamic path integral from time 0 to t, which is used to track the path described by the current and voltage changes. is to apply the mapping function to time The current and voltage represent the high-dimensional eigenvalues ​​after mapping. , and Respectively, in time At the moment of , the absolute value of current and the absolute value of voltage in the high-dimensional space.

[0055] The dynamic change trajectory of current and voltage from the initial state to the current state is depicted through path integration, which helps to identify new or temporary connection states formed due to small changes in the power network.

[0056] In order to determine whether there is a connection between electrical connection points and the type of connection, such as direct connection, indirect connection or no connection, it is necessary to compare the path differences between different electrical connection points and calculate the association metric between the electrical connection points.

[0057] The calculation method of the association measure is:

[0058] (3)

[0059] in, represents the association metric between the ith electrical connection point and the jth electrical connection point, used to evaluate whether the two electrical connection points are connected; is the dynamic path integral of the ith electrical connection point, is the dynamic path integral of the jth electrical connection point; The function is used to provide a smooth but sensitive measure of variance. is a parameter that adjusts the effect of voltage difference and is used to control the sensitivity of voltage difference to the correlation metric. and are the voltage values ​​of the i-th electrical connection point and the j-th electrical connection point respectively.

[0060] Step 3: Taking minimizing the deviation between the calculated association metric and the expected topological structure as the optimization goal, the optimization solution is performed through the gradient descent optimization algorithm to obtain the optimal association metric.

[0061] An optimization problem is set to ultimately determine the most likely connection relationship between electrical connection points. The optimization goal is to minimize the deviation between the actual measured association metric and the expected topology. By adjusting the parameters in the optimization process, different high-speed power line communication network conditions and measurement errors can be adapted. In order to avoid ignoring potential connection relationships outside the expected topology during the optimization process, the consideration of potential connection relationships is introduced in the optimization goals and methods, so that the final optimization results can not only fit the expected topology, but also discover and adapt to the actual potential connection relationships. Regularization terms are introduced, and the confidence of the potential connection relationship is considered. A confidence index is introduced for each pair of electrical connection points. , weighted consideration is taken into account in the optimization objective, and the optimization objective formula is as follows:

[0062] (4)

[0063] in, is the indicator variable of whether the i-th electrical connection point and the j-th electrical connection point are connected in theory, that is, the expected topological structure, is the set of all electrical connection points, is an adjustment factor used to increase the model's tolerance to small-scale topological errors. is the regularization coefficient, which is used to control the influence of the regularization term. R(M) is the regularization term, and L2 regularization or L1 regularization can be selected.

[0064] Adding regularization terms to the optimization objective can better adapt to potential connection relationships and avoid over-reliance on expected topological structures. Initialization can be performed based on historical data and measurement results to reflect the potential connection relationship of each pair of electrical connection points.

[0065] In this embodiment, the confidence index of each pair of electrical connection points can be determined based on the following aspects:

[0066] Historical data: Analyze historical operation data and observe the connection status of each pair of electrical connection points. For example, count whether each pair of connection points has been connected multiple times in the past period of time. The more times it occurs, the higher the confidence level.

[0067] Measurement results: Based on real-time measurement data, determine the current connection status of each pair of electrical connection points. Infer the connection status by measuring parameters such as current, voltage, signal strength, etc.

[0068] Expert experience: Combined with the experts’ understanding and experience of grid operation, some connection relationships are given a higher degree of confidence. Expert opinions are usually based on a deep understanding and long-term observation of the grid topology.

[0069] Statistical models: Use statistical models such as Bayesian networks, Markov chains, etc. to analyze historical data and measurement results to infer the confidence level of each pair of electrical connection points.

[0070] The optimization objective formula Indicates the indicator variable In most cases, the indicator variable is a binary variable used to represent the connection status in the expected topology, namely: , indicating that there is a connection between the i-th electrical connection point and the j-th electrical connection point; , indicating that there is no connection between the i-th electrical connection point and the j-th electrical connection point. Therefore, In practical applications, it should always be non-negative (0 or 1). The absolute value is introduced in this formula to better handle a wide range of topological structures and measurement errors, ensuring the universality and robustness of the formula. In actual calculations, the absolute value operation does not change the properties of the binary indicator variable, but it provides a certain mathematical rigor and universality in the theoretical formula.

[0071] The choice of the optimization objective is based on the small topological changes and measurement errors often encountered in actual grid operation, which can accurately reconstruct the topology of the grid.

[0072] The optimization goal is to adjust the correlation metrics between the electrical connection points to make them as close as possible to the expected topology, while To adjust the tolerance for inconsistency.

[0073] The gradient descent algorithm is an iterative method that gradually adjusts parameters to minimize the given optimization objective.

[0074] From an initial guess of the association metric matrix Initially, the correlation between all pairs of electrical connection points is usually set to 0, indicating that there is no connection initially; then the gradient of the optimization target is calculated, that is, the direction and magnitude of the influence of each correlation metric on the optimization target.

[0075] For each pair of electrical connection points, the association metric is updated by computing the following gradient:

[0076] (5)

[0077] in, Represents the optimization goal about In each iteration, the gradient To adjust the current value.

[0078] (6)

[0079] in, and are the association measures before and after adjustment, is the learning rate, a positive number used to control the size of the update step. The adjustment is repeated until the update amount of the association metric is less than the first preset threshold, thereby minimizing the optimization objective to determine the most likely connection state between each electrical connection point, such as which electrical connection points are directly connected, which electrical connection points are indirectly connected, and the isolated parts or subnets that may exist in the power network, and reconstruct the topology of the entire power grid.

[0080] After the calculation of the correlation measure between the electrical connection points is completed, an optimal correlation measure containing all pairs of electrical connection points will be obtained. Each element value represents the connection possibility between a pair of electrical connection points, and the higher the value, the more likely it is that the two electrical connection points are directly connected.

[0081] In order to determine whether the electrical connection point belongs to this substation, a second preset threshold needs to be set based on the historical data of the power grid and the previous experimental analysis. , by comparing the optimal association metric and The size of , preliminarily determines which pairs of electrical connection points are strongly correlated, that is, the optimal correlation metric It indicates that the possibility that the i-th electrical connection point and the j-th electrical connection point are in the same station area is strong.

[0082] Step 4: Based on the updated association metric and the power data difference between the corresponding electrical connection points, determine the subordinate relationship between different electrical connection points, and traverse all electrical connection points until the substation topology structure corresponding to the substation to be constructed is constructed.

[0083] like Figure 2 As shown in the figure, after identifying the electrical connection points of this substation, it is necessary to determine the parent-child relationship between the electrical connection points to ensure that the position and role of each electrical connection point are correctly defined in the topology. Finally, by traversing all electrical connection points and using the traversal algorithm to systematically check and verify each electrical connection point and its connection, a complete and accurate substation topology diagram is constructed.

[0084] In the parent-child relationship determination algorithm, the current difference between each pair of electrical connection points is calculated and voltage difference , the difference will be used to evaluate the possible power supply relationship between each pair of electrical connection points; by calculating the inverse tangent of the ratio of the current and voltage differences, an angle value can be obtained, which reflects the dependence of the current on the voltage, that is:

[0085] (7)

[0086] in, The angle expression representing the difference between the current and voltage between electrical connection points is used to preliminarily determine the possible power supply direction between electrical connection points. In order to give a more accurate judgment, an association metric is used to weight the angle value and determine the parent-child relationship between electrical connection points.

[0087] The formula for determining the parent-child relationship is:

[0088] (8)

[0089] in, is the weighted parent-child relationship score between the ith electrical connection point and the jth electrical connection point, which is used to determine the power supply relationship between the two electrical connection points. is a constant used to ensure the stability of calculation.

[0090] judge Is it greater than a third preset threshold? If so, it is considered that there is a parent-child relationship between the i-th electrical connection point and the j-th electrical connection point, with i being the parent and j being the child; otherwise, it is considered that there is no parent-child relationship between the pair of electrical connection points.

[0091] The parent-child relationship between electrical connection points is determined and confirmed by weighting the angle of the current and voltage difference with the logarithm of the correlation measure between the electrical connection points. This method is particularly suitable for complex power grid environments and can effectively distinguish between the main power supply electrical connection points and the slave electrical connection points.

[0092] All electrical connection points and the relationships between them are considered as a graph structure, where nodes represent entities in the power grid and edges represent electrical connections between nodes. When it is determined that there is a parent-child relationship between two electrical connection points, a directed edge will be connected between the two electrical connection points in the topology graph, with the direction of the edge pointing from the parent electrical connection point to the child electrical connection point.

[0093] Use graph search techniques, such as depth-first search or breadth-first search, to traverse the entire graph: starting from a known electrical connection point, usually the main transformer or power supply of the substation, expand outward, and gradually visit all electrical connection points directly or indirectly connected to it. In each step of the search, only when the parent-child relationship between two electrical connection points is confirmed and meets the physical characteristics of voltage and current, the two electrical connection points are considered connected, thereby gradually building a complete substation topology diagram.

[0094] This embodiment eliminates human errors and delays in traditional manual monitoring methods by automatically collecting current and voltage data using a high-speed power line communication network and sensors installed at each electrical connection point. Automated data collection and processing ensures the real-time and accuracy of data, thereby enabling instant response to changes in the state of the power grid.

[0095] In this embodiment, the automatically identified and constructed substation topology relationship helps to effectively manage and maintain the power grid, reducing the maintenance costs caused by incorrect connections or failures that are not discovered in time. Accurate topology information can guide more precise maintenance plans and resource allocation, further reducing operation and maintenance costs.

[0096] This embodiment scheme, through the method of dynamic path tracking and high-dimensional space mapping, can accurately identify and verify the actual connection status in the power grid, including imperceptible temporary or newly formed connections, so that the operation of the power grid is more stable and reliable, and the risk of unexpected power outages and equipment failures is reduced.

[0097] In this embodiment, through the automatically identified topology structure, the grid operator can optimize the load distribution of current and the transmission path of electric energy, effectively reduce line losses and improve energy efficiency. Accurate topology information also supports the implementation of more efficient demand response strategies and the integration of renewable energy, thereby improving the economy and environmental friendliness of the entire grid.

[0098] In this embodiment, when a fault or abnormal situation occurs, accurate topology information can help quickly locate the problem and shorten the recovery time. The automated topology identification system can also update the power grid status in real time and provide necessary data support for fault recovery.

[0099] Embodiment 2

[0100] The purpose of this embodiment is to provide a system for constructing a substation topology, including:

[0101] An acquisition module is used to acquire power data at the electrical connection points in the substation to be constructed and perform preprocessing; wherein the power data includes voltage data and current data;

[0102] A calculation module, used for performing dynamic path tracking on the pre-processed power data, and calculating the correlation metrics between different electrical connection points according to the dynamic path tracking results;

[0103] An updating module is used to minimize the deviation between the calculated association metric and the expected topological structure as the optimization goal, and to obtain the optimal association metric by optimizing the solution through a gradient descent optimization algorithm;

[0104] The construction module is used to determine the subordinate relationship between different electrical connection points based on the optimal association metric and the power data difference between the corresponding electrical connection points, and traverse all electrical connection points until the substation topology structure corresponding to the substation to be constructed is constructed.

[0105] Embodiment 3

[0106] The purpose of this embodiment is to provide a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the program.

[0107] Embodiment 4

[0108] The purpose of this embodiment is to provide a computer-readable storage medium.

[0109] A computer-readable storage medium stores a computer program, which executes the steps of the above method when executed by a processor.

[0110] The steps involved in the apparatuses of the above embodiments 2, 3 and 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0111] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0112] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for constructing a station area topology, characterized in that: include: Acquire power data at the electrical connection points in the substation to be constructed and perform preprocessing; wherein the power data includes voltage data and current data; Perform dynamic path tracking on the preprocessed power data, and calculate the correlation metrics between different electrical connection points based on the dynamic path tracking results; Taking minimizing the deviation between the calculated association metric and the expected topological structure as the optimization goal, the optimal association metric is obtained by optimizing the solution through the gradient descent optimization algorithm; specifically: For each pair of electrical connection points, the gradient of the association metric is calculated based on the corresponding association metric and the indicator variable of whether it is theoretically connected; According to the calculated association metric and the calculated gradient of the association metric, the association metric is updated to obtain an updated association metric; Repeatedly adjusting the updated association metric until the updated association metric is less than a first preset threshold, thereby obtaining an optimal association metric; Comparing the optimal correlation metric with a second preset threshold, and considering the electrical connection points corresponding to the optimal correlation metric greater than the second preset threshold as being located in the same station area; Based on the optimal correlation metric and the power data difference between the corresponding electrical connection points, the subordinate relationship between different electrical connection points is determined, and all electrical connection points are traversed until the substation topology structure corresponding to the substation to be constructed is constructed; Determine the current difference and voltage difference between each pair of electrical connection points; performing an inverse tangent calculation on the determined ratio of the current difference to the voltage difference to obtain an angular expression for representing the difference between the current and the voltage between the electrical connection points; Using the optimal association metric, the angle expression of the current and voltage differences between the electrical connection points represented by the weighted calculation is obtained to obtain the corresponding weighted parent-child relationship score; The electrical connection points corresponding to the weighted parent-child relationship scores that are greater than the third set threshold are regarded as having a parent-child relationship.

2. A method for constructing a substation topology according to claim 1, characterized in that: The preprocessing includes performing high-dimensional mapping processing on the acquired power data, specifically: ， in, It is the current data and voltage data mapped into the high-dimensional space. is the current data, is the voltage data, and are the current adjustment parameters and the voltage adjustment parameters respectively, It is a parameter that adjusts the nonlinear effect of the product of current and voltage.

3. A method for constructing a substation topology according to claim 1, characterized in that: Dynamic path tracking is performed on the preprocessed power data, and the correlation metrics between different electrical connection points are calculated based on the dynamic path tracking results, specifically: In the form of integral path, the dynamic change trajectory of power data from the initial state to the current state is described for dynamic path tracking; Based on the inverse tangent function, the differences in the dynamic change trajectories of power data between different electrical connection points are measured, and the correlation measurement between different electrical connection points is obtained.

4. A method for constructing a substation topology according to claim 1 or 3, characterized in that: The calculation of the correlation metric between different electrical connection points is as follows: ， in, represents the association measure between the ith electrical connection point and the jth electrical connection point, is a parameter that adjusts the effect of voltage difference and is used to control the sensitivity of voltage difference to the correlation metric. and are the voltage values ​​of the ith electrical connection point and the jth electrical connection point, respectively. is the dynamic path integral of the ith electrical connection point, is the dynamic path integral of the jth electrical connection point.

5. A substation topology construction system, using a substation topology construction method as claimed in claim 1, characterized in that: include: An acquisition module is used to acquire power data at the electrical connection points in the substation to be constructed and perform preprocessing; wherein the power data includes voltage data and current data; A calculation module, used for performing dynamic path tracking on the pre-processed power data, and calculating the correlation metrics between different electrical connection points according to the dynamic path tracking results; An updating module is used to minimize the deviation between the calculated association metric and the expected topological structure as the optimization goal, and to obtain the optimal association metric by optimizing the solution through a gradient descent optimization algorithm; The construction module is used to determine the subordinate relationship between different electrical connection points based on the optimal association metric and the power data difference between the corresponding electrical connection points, and traverse all electrical connection points until the substation topology structure corresponding to the substation to be constructed is constructed.

6. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, a method for constructing a substation topology as described in any one of claims 1 to 4 is executed.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for constructing a substation topology according to any one of claims 1 to 4 is executed.

Images