Reactive power optimization method and device of power system, storage medium and electronic equipment

Abstract

The application discloses a reactive power optimization method and device of a power system, a storage medium and an electronic device. It relates to the technical field of data processing, the field of power engineering and other related technical fields. The method comprises the following steps: acquiring historical power grid operation data corresponding to a plurality of power grid nodes in a power system; determining a target power grid node from the plurality of power grid nodes of the power system according to the historical power grid operation data; determining a capacitive reactive power compensation capacity and an inductive reactive power compensation capacity corresponding to the target power grid node through a target neural network model and the historical power grid operation data corresponding to the target power grid node; and performing optimization processing on the power system according to the capacitive reactive power compensation capacity and the inductive reactive power compensation capacity. Through the application, the problem that the optimization of the power system through the reactive voltage sensitivity corresponding to a single power grid node in the related art leads to a relatively poor reactive power optimization effect of the power system is solved.

Description

Technical Field

[0001] This application relates to the fields of data processing technology, power engineering, and other related technical fields. Specifically, it relates to a reactive power optimization method and apparatus, storage medium, and electronic equipment for a power system. Background Technology

[0002] In the operation of power systems, hierarchical and regional reactive power balancing is a crucial means to ensure grid voltage quality and reduce power system losses. A reasonable reactive power optimization method is always a vital prerequisite for solving reactive power voltage problems in power systems. While traditional reactive power optimization methods are easy to implement, they only consider the impact of reactive power fluctuations at a single node on the voltage of the power system, neglecting the impact on the voltage of other nodes. In reality, changing the reactive power of a node in the power system will also change the reactive power voltage of other nodes. Therefore, this method ignores the overall grid structure, resulting in poor optimization performance.

[0003] There is currently no effective solution to the problem that optimizing the power system by using the reactive power voltage sensitivity of a single grid node in related technologies results in poor reactive power optimization. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, storage medium, and electronic device for reactive power optimization of a power system, in order to solve the problem that the reactive power optimization effect of the power system is relatively poor when optimizing the power system by using the reactive voltage sensitivity of a single grid node in related technologies.

[0005] To achieve the above objectives, according to one aspect of this application, a reactive power optimization method for a power system is provided. The method includes: acquiring historical grid operation data corresponding to multiple grid nodes in the power system, wherein the historical grid operation data includes at least: fault information, operating parameters, and reactive power exchange power corresponding to the multiple grid nodes in the power system; determining a target grid node from the multiple grid nodes in the power system based on the historical grid operation data; determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node through a target neural network model and the historical grid operation data corresponding to the target grid node; and optimizing the power system based on the capacitive reactive power compensation capacity and the inductive reactive power compensation capacity.

[0006] Further, determining the target grid node from multiple grid nodes of the power system based on the historical grid operation data includes: fitting the historical grid operation data to obtain the power flow equations corresponding to the multiple grid nodes of the power system; calculating the target reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the power flow equations; and determining the target grid node from the multiple grid nodes of the power system based on the target reactive voltage sensitivity.

[0007] Further, the calculation based on the power flow equation to obtain the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system includes: constructing a node admittance matrix corresponding to the power system based on the admittance values ​​between the multiple grid nodes of the power system; calculating a target matrix based on the node admittance matrix and the power flow equation; calculating a first reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the target matrix; and calculating the target reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the first reactive voltage sensitivity.

[0008] Further, the calculation based on the first reactive voltage sensitivity to obtain the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system includes: determining the voltage change value of the power system based on the first reactive voltage sensitivity; and calculating the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the voltage change value and the first reactive voltage sensitivity.

[0009] Further, determining the target grid node from multiple grid nodes of the power system based on the target reactive voltage sensitivity includes: sorting the target reactive voltage sensitivities to obtain a reactive voltage sensitivity list; obtaining a second reactive voltage sensitivity from the reactive voltage sensitivity list, wherein the order of the second reactive voltage sensitivity in the reactive voltage sensitivity list is less than the order of the remaining reactive voltage sensitivities in the reactive voltage sensitivity list; and determining the grid node corresponding to the second reactive voltage sensitivity as the target grid node.

[0010] Further, determining the capacitive and inductive reactive power compensation capacities corresponding to the target grid node using the target neural network model and the historical grid operation data corresponding to the target grid node includes: obtaining the target parameters corresponding to the target grid node, wherein the target parameters include at least: the power factor, operating voltage, operating frequency, and load type corresponding to the target grid node; normalizing the historical grid operation data corresponding to the target grid node to obtain processed historical grid operation data; and processing the processed historical grid operation data and the target parameters using the target neural network model to obtain the capacitive and inductive reactive power compensation capacities corresponding to the target grid node.

[0011] Furthermore, before determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node through the target neural network model and the historical power grid operation data corresponding to the target power grid node, the method further includes: acquiring a training dataset, wherein the training dataset includes at least: sample historical power grid operation data and sample parameters corresponding to multiple sample power grid nodes, as well as the actual capacitive reactive power compensation capacity and actual inductive reactive power compensation capacity corresponding to each sample power grid node; training the initial neural network model based on the training dataset to obtain the target neural network model.

[0012] To achieve the above objectives, according to another aspect of this application, a reactive power optimization device for a power system is provided. The device includes: a first acquisition unit, configured to acquire historical grid operation data corresponding to multiple grid nodes in the power system, wherein the historical grid operation data includes at least: fault information, operating parameters, and reactive power exchange power corresponding to the multiple grid nodes in the power system; a first determination unit, configured to determine a target grid node from the multiple grid nodes in the power system based on the historical grid operation data; a second determination unit, configured to determine the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node using a target neural network model and the historical grid operation data corresponding to the target grid node; and a processing unit, configured to perform optimization processing on the power system based on the capacitive reactive power compensation capacity and the inductive reactive power compensation capacity.

[0013] Further, the first determining unit includes: a fitting module, used to fit the historical power grid operation data to obtain the power flow equations corresponding to multiple power grid nodes of the power system; a calculation module, used to calculate the target reactive voltage sensitivity corresponding to multiple power grid nodes of the power system based on the power flow equations; and a determining module, used to determine the target power grid node from the multiple power grid nodes of the power system based on the target reactive voltage sensitivity.

[0014] Furthermore, the calculation module includes: a construction submodule, used to construct a node admittance matrix corresponding to the power system based on the admittance values ​​between multiple grid nodes of the power system; a first calculation submodule, used to calculate a target matrix based on the node admittance matrix and the power flow equation; a second calculation submodule, used to calculate a first reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the target matrix; and a third calculation submodule, used to calculate a target reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the first reactive voltage sensitivity.

[0015] Furthermore, the third calculation submodule includes: a determination submodule, used to determine the voltage change value of the power system based on the first reactive voltage sensitivity; and a calculation submodule, used to calculate the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the voltage change value and the first reactive voltage sensitivity.

[0016] Further, the determining module includes: a sorting submodule, used to sort the target reactive voltage sensitivity to obtain a reactive voltage sensitivity list; an acquisition submodule, used to acquire a second reactive voltage sensitivity in the reactive voltage sensitivity list, wherein the order of the second reactive voltage sensitivity in the reactive voltage sensitivity list is less than the order of the remaining reactive voltage sensitivities in the reactive voltage sensitivity list; and a determining submodule, used to determine the grid node corresponding to the second reactive voltage sensitivity as the target grid node.

[0017] Further, the second determining unit includes: an acquisition module, used to acquire target parameters corresponding to the target grid node, wherein the target parameters include at least: the power factor, operating voltage, operating frequency, and load type corresponding to the target grid node; a first processing module, used to normalize the historical grid operation data corresponding to the target grid node to obtain processed historical grid operation data; and a second processing module, used to process the processed historical grid operation data and the target parameters through the target neural network model to obtain the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node.

[0018] Furthermore, the device further includes: a second acquisition unit, configured to acquire a training dataset before determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node through the target neural network model and the historical power grid operation data corresponding to the target power grid node, wherein the training dataset includes at least: sample historical power grid operation data and sample parameters corresponding to multiple sample power grid nodes, as well as the actual capacitive reactive power compensation capacity and actual inductive reactive power compensation capacity corresponding to each sample power grid node; and a training unit, configured to train the initial neural network model based on the training dataset to obtain the target neural network model.

[0019] To achieve the above objectives, according to one aspect of this application, a computer-readable storage medium is provided, the storage medium storing a program, wherein, when the program is executed, the device where the storage medium is located is controlled to perform the reactive power optimization method of the power system described in any one of the above claims.

[0020] To achieve the above objectives, according to another aspect of this application, an electronic device is also provided, comprising one or more processors and a memory, the memory being used to store the reactive power optimization method for the power system implemented by the one or more processors as described in any of the above claims.

[0021] This application employs the following steps: acquiring historical grid operation data corresponding to multiple grid nodes in a power system, wherein the historical grid operation data includes at least: fault information, operating parameters, and reactive power exchange power corresponding to the multiple grid nodes in the power system; determining a target grid node from the multiple grid nodes based on the historical grid operation data; determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node using a target neural network model and the historical grid operation data corresponding to the target grid node; and optimizing the power system based on the capacitive and inductive reactive power compensation capacities. This application solves the problem in related technologies where optimizing the power system based on the reactive power voltage sensitivity of a single grid node results in poor reactive power optimization effects. In this scheme, by acquiring historical grid operation data such as fault information, operating parameters, and reactive power exchange power corresponding to multiple grid nodes in the power system, a target grid node is determined from the multiple grid nodes in the power system. Then, using a target neural network model and the historical grid operation data corresponding to the target grid node, the capacitive and inductive reactive power compensation capacities corresponding to that node are calculated, and the power system is optimized based on the reactive power compensation capacities. By considering historical grid operation data of multiple nodes in the power system, the impact of reactive power variation at a given node on reactive power variation at other nodes in the grid system can be accurately calculated. This allows for the comprehensive determination of the target grid nodes in the power system, thereby obtaining the optimization range of the power system. This avoids the problems of inaccurate optimization results caused by traditional methods that only evaluate the voltage impact of reactive power variation at a single node. By comprehensively considering the overall grid, the optimization effect of the power system is improved. Attached Figure Description

[0022] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0023] Figure 1 This is a flowchart of a reactive power optimization method for a power system provided according to an embodiment of this application;

[0024] Figure 2 This is a schematic diagram of a reactive power optimization method for a power system provided according to an embodiment of this application;

[0025] Figure 3 This is a schematic diagram of a reactive power optimization device for a power system according to an embodiment of this application;

[0026] Figure 4 This is a schematic diagram of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0027] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are information and data authorized by the user or fully authorized by all parties. For example, this system has an interface with relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving consent information from the aforementioned user or organization.

[0031] The present invention will now be described in conjunction with preferred implementation steps. Figure 1 This is a flowchart of a reactive power optimization method for a power system according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0032] Step S101: Obtain historical grid operation data corresponding to multiple grid nodes in the power system. The historical grid operation data includes at least: fault information, operating parameters and reactive power exchange power corresponding to multiple grid nodes in the power system.

[0033] Optionally, historical grid operation data corresponding to multiple grid nodes in the power system can be obtained through grid companies, power research institutions, and power market operators, and the obtained data can be organized into a unified format for easy analysis.

[0034] It should be noted that the fault information includes: fault type, time of occurrence, scope of impact, and handling measures; operating parameters include: voltage, current, frequency, and load; and reactive power exchange refers to the reactive power exchange between grid nodes.

[0035] Step S102: Based on historical power grid operation data, determine the target power grid node from multiple power grid nodes in the power system.

[0036] Optionally, the power flow equations for each node are obtained by fitting historical power grid operation data of multiple power grid nodes in the power system. The power flow equations are then expressed and calculated in polar coordinates to obtain the reactive power voltage sensitivity of each power grid node. Based on the reactive power voltage sensitivity, the impact of reactive power fluctuations of the power grid node on reactive power fluctuations of other nodes in the power grid system is comprehensively considered to determine the target power grid node.

[0037] Step S103: Determine the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node by using the target neural network model and the historical power grid operation data corresponding to the target power grid node.

[0038] Optionally, the reactive power compensation configuration optimization neural network model (i.e., the target neural network model) is used to calculate the optimized results of the capacitive reactive power compensation capacity (i.e., the capacitive reactive power compensation capacity) for the target grid node when it operates in the maximum load grid operation mode, and the optimized results of the inductive reactive power compensation capacity (i.e., the inductive reactive power compensation capacity) when it operates in the load operation mode.

[0039] Step S104: Optimize the power system based on the capacitive reactive power compensation capacity and the inductive reactive power compensation capacity.

[0040] Optionally, a comprehensive analysis of the power system is conducted, including load characteristics, voltage levels, and line losses. The reactive power demand in the power system is determined, and it is assessed whether the existing reactive power compensation capacity meets this demand. Based on the assessment, the reactive power compensation objectives of the power system (e.g., improving voltage levels, reducing line losses, and increasing transmission capacity) and the optimal installation locations of compensation devices (e.g., static synchronizing compensators or dynamic voltage regulators) are determined to achieve the best compensation effect. The power system is then optimized using the compensation devices based on capacitive and inductive reactive power compensation capacities.

[0041] It should be noted that reactive power compensation capacity in power systems is mainly used to improve system voltage stability, reduce line losses, and enhance system transmission capacity. Capacitive reactive power compensation and inductive reactive power compensation are two common reactive power compensation methods. Capacitive reactive power compensation is typically used to increase system voltage levels and is suitable for areas with heavy loads; inductive reactive power compensation is used to reduce line losses and enhance system transmission capacity and is suitable for long-distance transmission lines.

[0042] In summary, by acquiring historical grid operation data such as fault information, operating parameters, and reactive power exchange power corresponding to multiple grid nodes in the power system, a target grid node is identified among these nodes. Using a target neural network model and the historical grid operation data corresponding to the target node, the capacitive and inductive reactive power compensation capacities corresponding to that node are calculated. The power system is then optimized based on these reactive power compensation capacities. By considering the historical grid operation data of multiple nodes in the power system, the impact of reactive power fluctuations at that node on the reactive power fluctuations of other nodes in the grid system can be accurately calculated. This allows for the comprehensive determination of the target grid node and the determination of the optimization range for the power system. This approach avoids the inaccurate optimization results caused by traditional methods that only assess the voltage impact of reactive power fluctuations at a single node. By comprehensively considering the overall grid structure, the optimization effect of the power system is improved.

[0043] Optionally, in the reactive power optimization method for a power system provided in this application embodiment, determining the target grid node from multiple grid nodes of the power system based on historical grid operation data includes: fitting the historical grid operation data to obtain the power flow equations corresponding to the multiple grid nodes of the power system; calculating the target reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the power flow equations; and determining the target grid node from the multiple grid nodes of the power system based on the target reactive voltage sensitivity.

[0044] In an optional embodiment, firstly, historical power flow equations for each power grid node are obtained by fitting historical power grid operation data of multiple power grid nodes, and these equations are represented in polar coordinates. Then, considering the impact of reactive power fluctuations at individual power grid nodes on the power system, and combining this with the power flow equations, the combined reactive power and voltage sensitivity (i.e., the target reactive power and voltage sensitivity) for multiple power grid nodes is calculated. Finally, based on the combined reactive power and voltage sensitivity, the target reactive power compensation node (i.e., the target power grid node) is determined among the multiple power grid nodes.

[0045] It should be noted that the polar coordinate expression of the power flow equations for multiple grid nodes is as follows:

[0046]

[0047] Where P represents the active power of the power system; Q represents the reactive power of the power system; U represents the voltage amplitude of the power system; θ represents the voltage phase angle of the power system; ΔP = [ΔP1, ΔP2, ..., ΔPn] represents the active power imbalance vector; ΔQ = [ΔQ1, ΔQ2, ..., ΔQn] represents the reactive power imbalance vector; Δθ = [Δθ1, Δθ2, ..., Δθn] represents the voltage phase angle vector; ΔU / U = [ΔU1 / U1, ΔU2 / U2, ..., ΔUn / Un] represents the amplitude correction vector; and J represents the Jacobian matrix.

[0048] By representing the power flow equations of multiple grid nodes in polar coordinates, the relative relationships and power flow directions between multiple grid nodes are more clearly shown, improving the efficiency of power balance and load flow calculation and analysis.

[0049] Optionally, in the reactive power optimization method for power systems provided in this application embodiment, the calculation based on the power flow equation to obtain the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system includes: constructing a node admittance matrix corresponding to the power system based on the admittance values ​​between multiple grid nodes of the power system; calculating a target matrix based on the node admittance matrix and the power flow equation; calculating a first reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the target matrix; and calculating the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the first reactive voltage sensitivity.

[0050] In an optional embodiment, the Jacobian matrix J can be expressed as follows:

[0051]

[0052] Where P represents the active power of the power system; Q represents the reactive power of the power system; U represents the voltage amplitude of the power system; and θ represents the voltage phase angle of the power system. and This corresponds to the real part of the node voltage in the power system. and The imaginary part of the node voltage in the corresponding power system; submatrix H corresponds to Submatrix N corresponds to U Submatrix J corresponds to Submatrix L corresponds to U

[0053] Since the voltage amplitude at each node of a power system is related to reactive power, and the voltage phase angle is related to active power, in matrix J, submatrix U and The values ​​are relatively small and can be ignored. Furthermore, this application's embodiments only discuss the relationship between reactive power and voltage; therefore, the subarray... This can also be omitted. Therefore, the polar coordinate expression of the power flow equations for multiple grid nodes in a power system can be simplified to ΔQ = LΔU / U.

[0054] It should be noted that matrix L can be represented by the nodal admittance matrix, as shown in the following expression:

[0055]

[0056] in, For voltage matrix, Let be the nodal admittance matrix.

[0057] It's important to note that the node admittance matrix is ​​a crucial concept in power system analysis, used to describe the electrical connections between nodes in the system. It's a core data structure in power system analyses such as power flow calculations and short-circuit calculations. The node admittance matrix is ​​derived from the system's impedance parameters, and its elements represent the admittance values ​​between nodes. Specifically, Bji in the node admittance matrix represents the admittance value between grid node i and grid node j, i.e., the current transfer ratio between the two nodes. Bii represents the self-admittance of grid node i, i.e., the ratio of the injected current to the voltage at that node. The node admittance matrix is ​​typically used to solve the system's nodal voltage equations, thereby obtaining the voltage magnitude and phase angle at each node.

[0058] Therefore, by calculating the nodal admittance matrix and the power flow equations, the target matrix can be obtained. Then, by calculating the target matrix, the first reactive voltage sensitivity corresponding to multiple grid nodes in the power system can be obtained, as expressed below:

[0059]

[0060] Among them, S F i represents the impact of reactive power transformation at multiple nodes in the power system on voltage. The larger the value, the weaker the voltage stability at that node. ΔUi represents the voltage amplitude change at node i in the power system. ΔQi represents the reactive power change at node i in the power system.

[0061] It should be noted that while the first reactive voltage sensitivity reflects the impact of reactive power transformation on voltage at a given node, it neglects the overall grid structure and does not consider the influence of reactive power transformation at that node on the voltages of other nodes. Therefore, the target reactive voltage sensitivity can be obtained by comprehensively considering the first reactive voltage sensitivities of multiple grid nodes.

[0062] By using the power flow equations and node admittance matrix corresponding to each power grid node, the first reactive voltage sensitivity of that node can be obtained quickly and accurately, which helps to determine the target reactive voltage sensitivity of multiple power grid nodes.

[0063] Optionally, in the reactive power optimization method for power systems provided in this application embodiment, calculating the target reactive power voltage sensitivity corresponding to multiple grid nodes of the power system based on the first reactive power voltage sensitivity includes: determining the voltage change value of the power system based on the first reactive power voltage sensitivity; and calculating the target reactive power voltage sensitivity corresponding to multiple grid nodes of the power system based on the voltage change value and the first reactive power voltage sensitivity.

[0064] In an optional embodiment, when the first reactive voltage sensitivity of a certain grid node in the power system is changed, the reactive voltages of the other nodes will change accordingly. For a power grid in a certain region, if the reactive power of node i is changed while keeping the reactive power of the other nodes constant, the polar coordinate expression of the power flow equations for different grid nodes can be expressed as follows:

[0065]

[0066] Where Ui represents the voltage amplitude at node i in the power system; ΔQi represents the reactive power change at node i in the power system; Let be the nodal admittance matrix.

[0067] Therefore, when the reactive power of node i is changed, the voltage change value of the entire power system will also change accordingly. By calculating the voltage change value and the first reactive voltage sensitivity corresponding to multiple grid nodes, the target reactive voltage sensitivity of the power system can be obtained, as shown in the following expression:

[0068]

[0069] Where Svi represents the combined reactive and voltage sensitivity, Bji represents the admittance value between grid node i and grid node j, and Ui represents the voltage amplitude of node i in the power system.

[0070] It should be noted that the reactive power and voltage comprehensive sensitivity Svi fully considers the overall nature of the power grid and interprets the mutual influence between nodes within the region. That is, in an n-node system, the greater the first reactive power and voltage sensitivity of node i, the better the compensation effect after installing reactive power compensation equipment at that node, the more obvious the improvement effect on the power system voltage, and the greater the benefits to the operation of the power grid.

[0071] By taking into account the interactions between nodes in a power system, the compensated system can operate in a better state.

[0072] Optionally, in the reactive power optimization method for power systems provided in this application embodiment, determining the target grid node from multiple grid nodes of the power system based on the target reactive voltage sensitivity includes: sorting the target reactive voltage sensitivities to obtain a reactive voltage sensitivity list; obtaining the second reactive voltage sensitivity in the reactive voltage sensitivity list, wherein the order of the second reactive voltage sensitivity in the reactive voltage sensitivity list is less than the order of the remaining reactive voltage sensitivities in the reactive voltage sensitivity list; and determining the grid node corresponding to the second reactive voltage sensitivity as the target grid node.

[0073] In an optional embodiment, the target reactive voltage sensitivities corresponding to multiple grid nodes are sorted in descending order to obtain a reactive voltage sensitivities list. The maximum value in the reactive voltage sensitivities list is determined as the second reactive voltage sensibility, and the grid node corresponding to the second reactive voltage sensibility is determined as the target grid node.

[0074] By sorting the target reactive voltage sensitivity of multiple grid nodes in descending order, the second reactive voltage sensitivity can be quickly determined, thereby accurately identifying the target grid node.

[0075] Optionally, in the reactive power optimization method for power systems provided in this application embodiment, determining the capacitive and inductive reactive power compensation capacities corresponding to the target grid node through the target neural network model and the historical grid operation data corresponding to the target grid node includes: obtaining the target parameters corresponding to the target grid node, wherein the target parameters include at least: the power factor, operating voltage, operating frequency, and load type corresponding to the target grid node; normalizing the historical grid operation data corresponding to the target grid node to obtain the processed historical grid operation data; and processing the processed historical grid operation data and target parameters through the target neural network model to obtain the capacitive and inductive reactive power compensation capacities corresponding to the target grid node.

[0076] In an optional embodiment, the historical power grid operation data corresponding to the target power grid node is normalized to remove outlier data, resulting in processed historical power grid operation data. Then, a reactive power compensation configuration optimization neural network structure (i.e., the target neural network model) is used to calculate the processed historical power grid operation data and the target parameters corresponding to the target power grid node. This yields the capacitive and inductive reactive power compensation capacities corresponding to the target power grid node, with the following calculation relationship expressions:

[0077]

[0078] Where B represents the bias of the output node in the reactive power compensation configuration optimization neural network structure, and H... W x represents the input of the x-th node in the hidden layer.

[0079] It should be noted that H W The expression for x is as follows:

[0080]

[0081] Where Wx represents the coefficient of the x-th inequality constraint; Wy represents the coefficient of the y-th inequality constraint; K is the investment cost per unit capacity capacitor; Qi is the capacitive reactive power compensation capacity at node i; b is the constant value of the inequality constraint; and Ui represents the voltage amplitude at node i in the power system.

[0082] It's important to note that the bias of the output node in the target neural network model is a crucial parameter. It controls the activation state of neurons and enhances the network's fitting ability. In the target neural network model, the output of a neuron is obtained by summing the products of all inputs multiplied by their corresponding weights. This weighted sum, plus the bias value, is the neuron's final output. The bias can be understood as providing a baseline activation level for the neuron, allowing it to have a non-zero output even without any input signal. Its purpose is to remove the limitations of linear models, enabling the target neural network model to fit more complex nonlinear relationships, thereby increasing the model's flexibility and expressive power.

[0083] By using the target neural network model, the capacitive and inductive reactive power compensation capacities corresponding to the target power grid nodes can be calculated quickly and accurately, thereby improving the optimization effect of the power system.

[0084] Optionally, in the reactive power optimization method for power systems provided in this application embodiment, before determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node through the target neural network model and the historical power grid operation data corresponding to the target power grid node, the method further includes: obtaining a training dataset, wherein the training dataset includes at least: sample historical power grid operation data and sample parameters corresponding to multiple sample power grid nodes, as well as the actual capacitive reactive power compensation capacity and actual inductive reactive power compensation capacity corresponding to each sample power grid node; and training the initial neural network model based on the training dataset to obtain the target neural network model.

[0085] In an optional embodiment, firstly, using time as the filtering unit, the historical power grid operation data and sample parameters corresponding to multiple sample power grid nodes at different time stages, as well as the actual capacitive reactive power compensation capacity and actual inductive reactive power compensation capacity corresponding to each sample power grid node, are divided into stages to generate training datasets, test datasets, and validation datasets. Then, hyperparameters and constraints are configured for the input layer, output layer, and hidden layer of the initial neural network model: upper and lower limits for transformer taps and reactive power compensation capacity are set; thresholds for transformer taps and reactive power compensation capacity are set; thresholds for the number of faults are set; thresholds for power grid operating costs and unit capacity capacitor investment are set; thresholds for power system network losses under different operating modes and thresholds for the number of iterations are set. Finally, the initial neural network model is trained based on the training dataset to obtain the target neural network model.

[0086] By training the dataset and configuring hyperparameters on the initial neural network model, the target neural network model can be obtained quickly and accurately.

[0087] It should be noted that, Figure 2 This is a schematic diagram of a reactive power optimization method for a power system provided according to an embodiment of this application. For example... Figure 2 As shown, historical power grid operation data such as fault information, operating parameters, and reactive power exchange power corresponding to multiple power grid nodes in the power system are obtained, and the historical power grid operation data are fitted to obtain the power flow equations corresponding to multiple power grid nodes.

[0088] Then, the target matrix is ​​calculated based on the node admittance matrix and power flow equations corresponding to multiple grid nodes in the power system. The target matrix is ​​then used to calculate the first reactive voltage sensitivity corresponding to multiple grid nodes in the power system. Taking into account the impact of reactive power transformation at this node on the remaining nodes in the power system, the target reactive voltage sensitivity corresponding to multiple grid nodes in the power system is determined. Simultaneously, the target reactive voltage sensitivities are sorted in descending order, and the maximum value in the reactive voltage sensitivity list is selected as the second reactive voltage sensitivity. The grid node corresponding to the second reactive voltage sensitivity is then determined as the target grid node.

[0089] Finally, the target parameters and historical grid operation data corresponding to the target grid nodes are processed using a target neural network model to obtain the capacitive and inductive reactive power compensation capacities corresponding to the target grid nodes. Based on these capacitive and inductive reactive power compensation capacities, the power system is optimized.

[0090] The reactive power optimization method for power systems provided in this application acquires historical grid operation data corresponding to multiple grid nodes in the power system. This historical grid operation data includes at least: fault information, operating parameters, and reactive power exchange power corresponding to the multiple grid nodes in the power system. Based on the historical grid operation data, a target grid node is determined from the multiple grid nodes in the power system. Using a target neural network model and the historical grid operation data corresponding to the target grid node, the capacitive and inductive reactive power compensation capacities corresponding to the target grid node are determined. Based on the capacitive and inductive reactive power compensation capacities, the power system is optimized. This solves the problem in related technologies where optimizing the power system based on the reactive power voltage sensitivity of a single grid node leads to poor reactive power optimization results. In summary, this solution acquires historical grid operation data such as fault information, operating parameters, and reactive power exchange power corresponding to multiple grid nodes in the power system to determine a target grid node. Then, using a target neural network model and the historical grid operation data corresponding to the target grid node, the capacitive and inductive reactive power compensation capacities corresponding to that node are calculated, and the power system is optimized based on the reactive power compensation capacities. By considering historical grid operation data of multiple nodes in the power system, the impact of reactive power variation at a given node on reactive power variation at other nodes in the grid system can be accurately calculated. This allows for the comprehensive determination of the target grid node in the power system, thus obtaining the optimization range of the power system. This avoids the problems of inaccurate optimization results caused by traditional methods that only evaluate the voltage impact of reactive power variation at a single node. By comprehensively considering the overall grid, the optimization effect of the power system is improved.

[0091] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0092] This application also provides a reactive power optimization device for a power system. It should be noted that the reactive power optimization device for a power system provided in this application can be used to execute the reactive power optimization method for a power system provided in this application. The reactive power optimization device for a power system provided in this application is described below.

[0093] Figure 3 This is a schematic diagram of a reactive power optimization device for a power system according to an embodiment of this application. Figure 3 As shown, the device includes: a first acquisition unit 301, a first determination unit 302, a second determination unit 303, and a processing unit 304.

[0094] The first acquisition unit 301 is used to acquire historical power grid operation data corresponding to multiple power grid nodes in the power system. The historical power grid operation data includes at least: fault information, operating parameters and reactive power exchange power corresponding to multiple power grid nodes in the power system.

[0095] The first determining unit 302 is used to determine the target power grid node from multiple power grid nodes in the power system based on historical power grid operation data;

[0096] The second determining unit 303 is used to determine the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node by using the target neural network model and the historical power grid operation data corresponding to the target power grid node.

[0097] The processing unit 304 is used to optimize the power system based on the capacitive reactive power compensation capacity and the inductive reactive power compensation capacity.

[0098] The reactive power optimization device for a power system provided in this application embodiment includes a first acquisition unit 301 that acquires historical grid operation data corresponding to multiple grid nodes in the power system. The historical grid operation data includes at least: fault information, operating parameters, and reactive power exchange power corresponding to the multiple grid nodes in the power system. A first determination unit 302 determines a target grid node from the multiple grid nodes in the power system based on the historical grid operation data. A second determination unit 303 determines the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node using a target neural network model and the historical grid operation data corresponding to the target grid node. A processing unit 304 optimizes the power system based on the capacitive and inductive reactive power compensation capacities. This solves the problem in related technologies where optimizing the power system based on the reactive power voltage sensitivity of a single grid node leads to poor reactive power optimization results. In this solution, the target grid node is determined from the multiple grid nodes in the power system by acquiring historical grid operation data such as fault information, operating parameters, and reactive power exchange power corresponding to multiple grid nodes in the power system. By utilizing the target neural network model and historical grid operation data corresponding to the target grid node, the capacitive and inductive reactive power compensation capacities corresponding to that node are calculated. The power system is then optimized based on these reactive power compensation capacities. By considering historical grid operation data from multiple nodes in the power system, the impact of reactive power fluctuations at that node on the reactive power fluctuations of other nodes in the grid system can be accurately calculated. This comprehensively determines the target grid node of the power system, thereby obtaining the optimization range for the power system. This avoids the inaccurate optimization results caused by traditional methods that only evaluate the voltage impact of reactive power fluctuations at a single node. By comprehensively considering the overall grid structure, the optimization effect of the power system is improved.

[0099] Optionally, in the reactive power optimization device for a power system provided in this application embodiment, the first determining unit includes: a fitting module, used to fit based on historical power grid operation data to obtain power flow equations corresponding to multiple power grid nodes of the power system; a calculation module, used to calculate based on the power flow equations to obtain target reactive voltage sensitivity corresponding to multiple power grid nodes of the power system; and a determining module, used to determine the target power grid node from the multiple power grid nodes of the power system based on the target reactive voltage sensitivity.

[0100] Optionally, in the reactive power optimization device for a power system provided in this application embodiment, the calculation module includes: a construction submodule, used to construct a node admittance matrix corresponding to the power system based on the admittance values ​​between multiple grid nodes of the power system; a first calculation submodule, used to calculate a target matrix based on the node admittance matrix and the power flow equation; a second calculation submodule, used to calculate a first reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the target matrix; and a third calculation submodule, used to calculate a target reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the first reactive voltage sensitivity.

[0101] Optionally, in the reactive power optimization device for a power system provided in this application embodiment, the third calculation submodule includes: a determination submodule, used to determine the voltage change value of the power system based on the first reactive power voltage sensitivity; and a calculation submodule, used to calculate based on the voltage change value and the first reactive power voltage sensitivity to obtain the target reactive power voltage sensitivity corresponding to multiple grid nodes of the power system.

[0102] Optionally, in the reactive power optimization device for a power system provided in this application embodiment, the determining module includes: a sorting submodule, used to sort the target reactive voltage sensitivity to obtain a reactive voltage sensitivity list; an acquisition submodule, used to acquire the second reactive voltage sensitivity in the reactive voltage sensitivity list, wherein the order of the second reactive voltage sensitivity in the reactive voltage sensitivity list is less than the order of the remaining reactive voltage sensitivities in the reactive voltage sensitivity list; and a determining submodule, used to determine the grid node corresponding to the second reactive voltage sensitivity as the target grid node.

[0103] Optionally, in the reactive power optimization device for a power system provided in this application embodiment, the second determining unit includes: an acquisition module, used to acquire target parameters corresponding to the target grid node, wherein the target parameters include at least: the power factor, operating voltage, operating frequency, and load type corresponding to the target grid node; a first processing module, used to normalize the historical grid operation data corresponding to the target grid node to obtain processed historical grid operation data; and a second processing module, used to process the processed historical grid operation data and target parameters through a target neural network model to obtain the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node.

[0104] Optionally, in the reactive power optimization device for a power system provided in this application embodiment, the device further includes: a second acquisition unit, used to acquire a training dataset before determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node through the target neural network model and the historical power grid operation data corresponding to the target power grid node, wherein the training dataset includes at least: sample historical power grid operation data and sample parameters corresponding to multiple sample power grid nodes, as well as the actual capacitive reactive power compensation capacity and actual inductive reactive power compensation capacity corresponding to each sample power grid node; and a training unit, used to train the initial neural network model based on the training dataset to obtain the target neural network model.

[0105] The reactive power optimization device for the power system includes a processor and a memory. The first acquisition unit 301, the first determination unit 302, the second determination unit 303, the processing unit 304, etc., mentioned above are all stored in the memory as program units. The processor executes the program units stored in the memory to achieve efficient reactive power optimization of the power system.

[0106] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and efficient reactive power optimization of the power system can be achieved by adjusting kernel parameters.

[0107] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0108] This invention provides a computer-readable storage medium storing a program that, when executed by a processor, implements a reactive power optimization method for a power system.

[0109] This invention provides a processor for running a program, wherein the program executes a reactive power optimization method for a power system.

[0110] like Figure 4 As shown, this embodiment of the invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring historical grid operation data corresponding to multiple grid nodes in a power system, wherein the historical grid operation data includes at least: fault information, operating parameters, and reactive power exchange power corresponding to the multiple grid nodes in the power system; determining a target grid node from the multiple grid nodes in the power system based on the historical grid operation data; determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node through a target neural network model and the historical grid operation data corresponding to the target grid node; and optimizing the power system based on the capacitive reactive power compensation capacity and inductive reactive power compensation capacity.

[0111] Optionally, determining the target grid node from multiple grid nodes of the power system based on historical grid operation data includes: fitting the historical grid operation data to obtain the power flow equations corresponding to the multiple grid nodes of the power system; calculating the target reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the power flow equations; and determining the target grid node from the multiple grid nodes of the power system based on the target reactive voltage sensitivity.

[0112] Optionally, the calculation based on the power flow equations to obtain the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system includes: constructing a node admittance matrix corresponding to the power system based on the admittance values ​​between the multiple grid nodes of the power system; calculating the target matrix based on the node admittance matrix and the power flow equations; calculating the first reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the target matrix; and calculating the target reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the first reactive voltage sensitivity.

[0113] Optionally, the calculation based on the first reactive voltage sensitivity to obtain the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system includes: determining the voltage change value of the power system based on the first reactive voltage sensitivity; and calculating the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the voltage change value and the first reactive voltage sensitivity.

[0114] Optionally, determining the target grid node from multiple grid nodes in the power system based on the target reactive voltage sensitivity includes: sorting the target reactive voltage sensitivities to obtain a reactive voltage sensitivity list; obtaining the second reactive voltage sensitivity in the reactive voltage sensitivity list, wherein the order of the second reactive voltage sensitivity in the reactive voltage sensitivity list is less than the order of the remaining reactive voltage sensitivities in the reactive voltage sensitivity list; and determining the grid node corresponding to the second reactive voltage sensitivity as the target grid node.

[0115] Optionally, determining the capacitive and inductive reactive power compensation capacities corresponding to the target grid node using the target neural network model and historical grid operation data of the target grid node includes: obtaining the target parameters corresponding to the target grid node, wherein the target parameters include at least the power factor, operating voltage, operating frequency, and load type of the target grid node; normalizing the historical grid operation data corresponding to the target grid node to obtain processed historical grid operation data; and processing the processed historical grid operation data and target parameters using the target neural network model to obtain the capacitive and inductive reactive power compensation capacities corresponding to the target grid node.

[0116] Optionally, before determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node through the target neural network model and the historical power grid operation data corresponding to the target power grid node, the method further includes: acquiring a training dataset, wherein the training dataset includes at least: sample historical power grid operation data and sample parameters corresponding to multiple sample power grid nodes, as well as the actual capacitive reactive power compensation capacity and actual inductive reactive power compensation capacity corresponding to each sample power grid node; and training the initial neural network model based on the training dataset to obtain the target neural network model.

[0117] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0118] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program with the following method steps: acquiring historical grid operation data corresponding to multiple grid nodes in a power system, wherein the historical grid operation data includes at least: fault information, operating parameters, and reactive power exchange power corresponding to the multiple grid nodes in the power system; determining a target grid node from the multiple grid nodes in the power system based on the historical grid operation data; determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node through a target neural network model and the historical grid operation data corresponding to the target grid node; and optimizing the power system based on the capacitive reactive power compensation capacity and inductive reactive power compensation capacity.

[0119] Optionally, determining the target grid node from multiple grid nodes of the power system based on historical grid operation data includes: fitting the historical grid operation data to obtain the power flow equations corresponding to the multiple grid nodes of the power system; calculating the target reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the power flow equations; and determining the target grid node from the multiple grid nodes of the power system based on the target reactive voltage sensitivity.

[0120] Optionally, the calculation based on the power flow equations to obtain the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system includes: constructing a node admittance matrix corresponding to the power system based on the admittance values ​​between the multiple grid nodes of the power system; calculating the target matrix based on the node admittance matrix and the power flow equations; calculating the first reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the target matrix; and calculating the target reactive voltage sensitivity corresponding to the multiple grid nodes of the power system based on the first reactive voltage sensitivity.

[0121] Optionally, the calculation based on the first reactive voltage sensitivity to obtain the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system includes: determining the voltage change value of the power system based on the first reactive voltage sensitivity; and calculating the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system based on the voltage change value and the first reactive voltage sensitivity.

[0122] Optionally, determining the target grid node from multiple grid nodes in the power system based on the target reactive voltage sensitivity includes: sorting the target reactive voltage sensitivities to obtain a reactive voltage sensitivity list; obtaining the second reactive voltage sensitivity in the reactive voltage sensitivity list, wherein the order of the second reactive voltage sensitivity in the reactive voltage sensitivity list is less than the order of the remaining reactive voltage sensitivities in the reactive voltage sensitivity list; and determining the grid node corresponding to the second reactive voltage sensitivity as the target grid node.

[0123] Optionally, determining the capacitive and inductive reactive power compensation capacities corresponding to the target grid node using the target neural network model and historical grid operation data of the target grid node includes: obtaining the target parameters corresponding to the target grid node, wherein the target parameters include at least the power factor, operating voltage, operating frequency, and load type of the target grid node; normalizing the historical grid operation data corresponding to the target grid node to obtain processed historical grid operation data; and processing the processed historical grid operation data and target parameters using the target neural network model to obtain the capacitive and inductive reactive power compensation capacities corresponding to the target grid node.

[0124] Optionally, before determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node through the target neural network model and the historical power grid operation data corresponding to the target power grid node, the method further includes: acquiring a training dataset, wherein the training dataset includes at least: sample historical power grid operation data and sample parameters corresponding to multiple sample power grid nodes, as well as the actual capacitive reactive power compensation capacity and actual inductive reactive power compensation capacity corresponding to each sample power grid node; and training the initial neural network model based on the training dataset to obtain the target neural network model.

[0125] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0127] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0128] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0129] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0130] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0131] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0132] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0133] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A reactive power optimization method for a power system, characterized in that, include: The historical power grid operation data corresponding to multiple power grid nodes in the power system is obtained, wherein the historical power grid operation data includes at least: fault information, operating parameters and reactive power exchange power corresponding to the multiple power grid nodes in the power system; Based on the historical power grid operation data, the target power grid node is determined from multiple power grid nodes in the power system; The capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node are determined by using the target neural network model and the historical power grid operation data corresponding to the target power grid node. Based on the capacitive reactive power compensation capacity and the inductive reactive power compensation capacity, the power system is optimized. The determination of the target power grid node from multiple power grid nodes in the power system based on the historical power grid operation data includes: By fitting the historical power grid operation data, the power flow equations corresponding to multiple power grid nodes of the power system are obtained. The target reactive voltage sensitivity of multiple grid nodes in the power system is obtained by calculation based on the power flow equation. Based on the target reactive voltage sensitivity, the target grid node is determined from multiple grid nodes of the power system; Determining the target grid node from multiple grid nodes of the power system based on the target reactive voltage sensitivity includes: The target reactive voltage sensitivities are sorted to obtain a reactive voltage sensitivities list; Obtain the second reactive voltage sensitivity from the reactive voltage sensitivity list, wherein the order of the second reactive voltage sensitivity in the reactive voltage sensitivity list is less than the order of the remaining reactive voltage sensitivities in the reactive voltage sensitivity list. The grid node corresponding to the second reactive voltage sensitivity is determined as the target grid node; Specifically, determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node using the target neural network model and the historical grid operation data corresponding to the target grid node includes: Obtain the target parameters corresponding to the target power grid node, wherein the target parameters include at least: the power factor, operating voltage, operating frequency and load type corresponding to the target power grid node; The historical power grid operation data corresponding to the target power grid node is normalized to obtain the processed historical power grid operation data. The target neural network model is used to process the processed historical power grid operation data and the target parameters to obtain the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node.

2. The method according to claim 1, characterized in that, Based on the power flow equations, the target reactive voltage sensitivities corresponding to multiple grid nodes of the power system are calculated, including: Based on the admittance values ​​among multiple power grid nodes of the power system, a node admittance matrix corresponding to the power system is constructed. The target matrix is ​​obtained by calculating based on the node admittance matrix and the power flow equation. The first reactive voltage sensitivity corresponding to multiple grid nodes of the power system is obtained by calculation based on the target matrix. Based on the first reactive voltage sensitivity, the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system is obtained.

3. The method according to claim 2, characterized in that, Based on the first reactive voltage sensitivity, the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system is calculated as follows: Based on the first reactive voltage sensitivity, the voltage change value of the power system is determined; Based on the voltage change value and the first reactive voltage sensitivity, the target reactive voltage sensitivity corresponding to multiple grid nodes of the power system is obtained.

4. The method according to claim 1, characterized in that, Before determining the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target grid node using the target neural network model and the historical grid operation data corresponding to the target grid node, the method further includes: Obtain a training dataset, wherein the training dataset includes at least: sample historical power grid operation data and sample parameters corresponding to multiple sample power grid nodes, as well as the actual capacitive reactive power compensation capacity and the actual inductive reactive power compensation capacity corresponding to each sample power grid node; The initial neural network model is trained based on the training dataset to obtain the target neural network model.

5. A reactive power optimization device for a power system, characterized in that, include: The first acquisition unit is used to acquire historical power grid operation data corresponding to multiple power grid nodes in the power system, wherein the historical power grid operation data includes at least: fault information, operating parameters and reactive power exchange power corresponding to the multiple power grid nodes in the power system; The first determining unit is used to determine the target power grid node from multiple power grid nodes of the power system based on the historical power grid operation data. The second determining unit is used to determine the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node by using the target neural network model and the historical power grid operation data corresponding to the target power grid node. The processing unit is used to optimize the power system based on the capacitive reactive power compensation capacity and the inductive reactive power compensation capacity. The first determining unit includes: a fitting module, used to fit the historical power grid operation data to obtain the power flow equations corresponding to multiple power grid nodes of the power system; a calculation module, used to calculate the target reactive voltage sensitivity corresponding to multiple power grid nodes of the power system based on the power flow equations; and a determining module, used to determine the target power grid node from the multiple power grid nodes of the power system based on the target reactive voltage sensitivity. The determining module includes: a sorting submodule, used to sort the target reactive voltage sensitivity to obtain a reactive voltage sensitivity list; an acquisition submodule, used to acquire the second reactive voltage sensitivity in the reactive voltage sensitivity list, wherein the order of the second reactive voltage sensitivity in the reactive voltage sensitivity list is less than the order of the remaining reactive voltage sensitivities in the reactive voltage sensitivity list; and a determining submodule, used to determine the grid node corresponding to the second reactive voltage sensitivity as the target grid node. The second determining unit includes: an acquisition module for acquiring target parameters corresponding to the target power grid node, wherein the target parameters include at least: the power factor, operating voltage, operating frequency, and load type corresponding to the target power grid node; a first processing module for normalizing the historical power grid operation data corresponding to the target power grid node to obtain processed historical power grid operation data; and a second processing module for processing the processed historical power grid operation data and the target parameters through the target neural network model to obtain the capacitive reactive power compensation capacity and inductive reactive power compensation capacity corresponding to the target power grid node.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, the storage medium controls the device to perform the reactive power optimization method for the power system according to any one of claims 1 to 4.

7. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the reactive power optimization method for the power system according to any one of claims 1 to 4.

Images