Method and device for determining short-circuit ratio of new energy multi-station

Abstract

The invention provides a short circuit ratio determination method and device for a new energy multi-station, and the method comprises the steps: obtaining the graph structure data of a target power system, the target power system comprises a plurality of devices, and the plurality of devices comprise a new energy multi-station; nodes of the graph structure data represent feature data of equipment, and edges between the nodes represent feature data of lines; the characteristic data of the equipment comprises bus voltage, bus phase angle, active power injection of the bus and reactive power injection of the bus; the characteristic data of the line comprises line active power and line reactive power; determining the short-circuit ratio of the new energy multi-station according to the graph structure data and a short-circuit ratio evaluation model; the short-circuit ratio evaluation model is obtained by pre-training based on batch historical graph structure data and real short-circuit comparison graph convolutional network models of the new energy multiple stations corresponding to the batch historical graph structure data. The reliability of the short-circuit ratio of the new energy multi-station can be improved, and then the operation stability of a power system can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method and device for determining the short-circuit ratio of multiple renewable energy stations. Background Art

[0002] The short-circuit ratio of multiple renewable energy stations is a key indicator for measuring the voltage support strength of power systems. With the widespread integration of renewable energy generation, the grid structure has become more complex, and the short-circuit ratios of different renewable energy stations vary significantly. Therefore, real-time monitoring and control of the short-circuit ratio of multiple renewable energy stations is crucial for measuring the voltage strength of the system and for quantitatively assessing the scale of renewable energy integration.

[0003] Currently, the short-circuit ratio analysis metric is commonly used to evaluate short-circuit ratio. This metric is an analytical expression of a power flow analysis model and cannot characterize the dynamic control characteristics of the analysis system and renewable energy power generation equipment. In actual operation, the short-circuit ratio constraint for multiple renewable energy stations is incorporated into the renewable energy operating limit verification through offline calculations. This does not consider the impact of time-varying factors such as renewable energy output distribution and topological structure on the short-circuit ratio. As a result, under certain operating conditions, despite an increase in channel transmission limits, some renewable energy stations are restricted in output due to inaccurate offline short-circuit ratios obtained through monitoring. This limits renewable energy power generation and increases renewable energy curtailment. Summary of the Invention

[0004] In response to at least one problem in the prior art, the present application proposes a method and device for determining the short-circuit ratio of multiple renewable energy stations, thereby improving the reliability of the short-circuit ratio of multiple renewable energy stations and thereby improving the stability of power system operation.

[0005] In order to solve the above technical problems, this application provides the following technical solutions:

[0006] In a first aspect, the present application provides a method for determining the short-circuit ratio of multiple new energy stations, comprising:

[0007] Obtaining graph structure data of a target power system, the target power system including: a plurality of devices, the plurality of devices including: a new energy multi-station; nodes in the graph structure data represent characteristic data of corresponding devices, and edges between nodes represent characteristic data of corresponding lines; the characteristic data of the devices include: bus voltage, bus phase angle, bus active power injection, and bus reactive power injection; the characteristic data of the lines include: line active power and line reactive power;

[0008] Determining the short-circuit ratio of the new energy multi-station according to the graph structure data and a preset short-circuit ratio evaluation model;

[0009] Among them, the preset short-circuit ratio evaluation model is pre-trained based on the batch historical graph structure data and the real short-circuit ratio graph convolutional network model corresponding to each of the new energy multi-stations.

[0010] In one embodiment, obtaining graph structure data of the target power system includes:

[0011] Obtain the current steady-state characteristics and topology information of the target power system;

[0012] According to the steady-state characteristics and topology information, graph structure data of the target power system is obtained.

[0013] In one embodiment, the method for determining the short-circuit ratio of multiple new energy stations further includes:

[0014] Collecting a training set, the training set including: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations;

[0015] The training set is used to train a graph convolutional network model to obtain the short circuit ratio evaluation model.

[0016] In one embodiment, before acquiring the graph structure data of the target power system, the method further includes:

[0017] Collecting a verification set, the verification set includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations;

[0018] According to each historical graph structure data and the short circuit ratio evaluation model, a predicted short circuit ratio of the new energy multi-station corresponding to the historical graph structure data is obtained;

[0019] Perform mean square error processing on the predicted short circuit ratio and the actual short circuit ratio of multiple new energy stations corresponding to each historical graph structure data to obtain the mean square error value;

[0020] It is determined whether the mean square error value is less than a mean square error threshold; if so, it is determined that the short circuit ratio evaluation model has passed verification.

[0021] In one embodiment, the acquisition of a training set includes:

[0022] Obtain historical operating data, historical topology information, and actual short-circuit ratios of multiple renewable energy stations for the target power system under various operating scenarios. The same operating scenario corresponds to the same power generation, load, and topology, while different operating scenarios correspond to different power generation, load, and topology.

[0023] Normalize historical operation data under the same operation scenario;

[0024] Obtaining historical graph structure data for each operation scenario based on the normalized historical operation data and the historical topology information for that operation scenario;

[0025] The training set is composed of historical graph structure data under various operation scenarios and the actual short-circuit ratios of multiple new energy stations.

[0026] In a second aspect, the present application provides a short-circuit ratio determination device for multiple new energy stations, comprising:

[0027] An acquisition module is configured to acquire graph structure data of a target power system, the target power system comprising: a plurality of devices, the plurality of devices comprising: a new energy multi-station; nodes in the graph structure data represent characteristic data of corresponding devices, and edges between nodes represent characteristic data of corresponding lines; the characteristic data of the devices comprise: bus voltage, bus phase angle, bus active power injection, and bus reactive power injection; the characteristic data of the lines comprise: line active power and line reactive power;

[0028] a determination module, configured to determine the short-circuit ratio of the new energy multi-station according to the graph structure data and a preset short-circuit ratio evaluation model;

[0029] Among them, the preset short-circuit ratio evaluation model is pre-trained based on the batch historical graph structure data and the real short-circuit ratio graph convolutional network model corresponding to each of the new energy multi-stations.

[0030] In one embodiment, the acquisition module includes:

[0031] an acquisition unit, used to acquire the current steady-state characteristics and topology information of the target power system;

[0032] The obtaining unit is used to obtain the graph structure data of the target power system according to the steady-state characteristics and topology information.

[0033] In one embodiment, the short-circuit ratio determination device for multiple new energy stations further includes:

[0034] An acquisition module is used to acquire a training set, wherein the training set includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations;

[0035] A training module is used to apply the training set to train the graph convolutional network model to obtain the short circuit ratio evaluation model.

[0036] In one embodiment, the short-circuit ratio determination device for multiple new energy stations further includes:

[0037] A verification set acquisition module is used to acquire a verification set, wherein the verification set includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations;

[0038] A predicted short circuit ratio module is used to obtain the predicted short circuit ratio of the new energy multi-station corresponding to each historical graph structure data according to the short circuit ratio evaluation model;

[0039] A module for obtaining a mean square error value is used to perform mean square error processing on the predicted short circuit ratio and the actual short circuit ratio of the new energy multi-station corresponding to each historical graph structure data to obtain a mean square error value;

[0040] The verification module is used to determine whether the mean square error value is less than a mean square error threshold, and if so, determine that the short circuit ratio evaluation model is verified to be successful.

[0041] In one embodiment, the acquisition module includes:

[0042] A historical data acquisition unit is used to obtain historical operating data, historical topology information, and real short-circuit ratios of multiple renewable energy stations of the target power system under various operating scenarios. The power generation, load, and topology corresponding to the same operating scenario are the same, while the power generation, load, and topology corresponding to different operating scenarios may be different.

[0043] Normalization unit, used to normalize historical operation data under the same operation scenario;

[0044] Obtaining a historical graph structure data unit, for obtaining historical graph structure data for each operation scenario based on the normalized historical operation data and the historical topology information for that operation scenario;

[0045] The combination unit is used to combine the historical graph structure data under various operation scenarios and the actual short-circuit ratio of multiple new energy stations into the training set.

[0046] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for determining the short-circuit ratio of multiple new energy stations is implemented.

[0047] In a fourth aspect, the present application provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the method for determining the short-circuit ratio of multiple new energy stations.

[0048] It can be seen from the above technical solution that the present application provides a method and device for determining the short-circuit ratio of a new energy multi-station. The method includes: obtaining graph structure data of a target power system, the target power system includes: multiple devices, the multiple devices include: new energy multi-station; the nodes in the graph structure data represent the characteristic data of the corresponding devices, and the edges between the nodes represent the characteristic data of the corresponding lines; the characteristic data of the devices include: bus voltage, bus phase angle, bus active power injection and bus reactive power injection; the characteristic data of the lines include: line active power and line reactive power; according to the graph structure data and a preset short-circuit ratio evaluation model, the short-circuit ratio of the new energy multi-station is determined; wherein the preset short-circuit ratio evaluation model is based on A graph convolutional network model pre-trained on batch historical graph data and its corresponding real short-circuit ratios for multiple renewable energy stations can be used to consider the impact of renewable energy output and topology on the short-circuit ratios of renewable energy stations, improving the reliability of the short-circuit ratios and, consequently, enhancing the stability of power system operation. Specifically, the short-circuit ratios of renewable energy stations can be monitored and controlled in real time, intuitively and effectively measuring the voltage intensity of renewable energy stations connected to the power system, quantitatively assessing the scale of renewable energy integration, and improving grid stability. The short-circuit ratio evaluation model can be derived by considering the characteristics of busbars, lines, and topological connections to describe changes in power system topology. The effectiveness of the proposed method was verified by running 40,000 sets of sample data on a 109-node system. Results show that compared with traditional data-driven methods, this scheme has significant performance advantages under topology change scenarios and can meet the application requirements of complex and variable real-world power grid operation scenarios. Graph network-related technologies can be applied to large-scale power grids to improve the interpretability of graph networks for power system-related problems. Combining analytical methods based on power system physical patterns with graph networks can further improve model performance and generalization. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0050] Figure 1 This is a first flow chart of a method for determining the short-circuit ratio of multiple new energy stations in an embodiment of the present application;

[0051] Figure 2 This is a second flow chart of the method for determining the short-circuit ratio of multiple new energy stations in an embodiment of the present application;

[0052] Figure 3 It is the network topology diagram of the 109-node system;

[0053] Figure 4 1 is a comparative diagram of the curves of training and test loss versus the number of training rounds for the dataset MRSCR1 in the application example of this application;

[0054] Figure 5 Schematic diagram of the structure of the short-circuit ratio determination device for multiple new energy stations in an embodiment of the present application;

[0055] Figure 6 It is a schematic block diagram of the system structure of the electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0057] In recent years, the proportion of renewable energy generation equipment, represented by wind power and photovoltaics, in the power system has continued to increase, and access methods have become more diverse. In some areas, new energy sources have been integrated into weak grids. This process is prone to broadband oscillations and transient overvoltages, seriously impacting the power quality and stability of the grid. Common methods for determining the short-circuit ratio (SCR) of multiple renewable energy stations include: the aggregate short-circuit ratio (ASCR) for initial subsynchronous oscillation risk, online monitoring of wind farm gSCR, and assessment methods for the grid connection strength of a single wind farm, including the composite short-circuit ratio (CSCR), weighted short-circuit ratio (WSCR), and equivalent short-circuit ratio (ESCR). These methods only consider network characteristics and not the power electronics themselves, and have considerable engineering practical value. However, the generalized short-circuit ratio (gSCR) is a complex modal calculation method, with limited engineering practicality. This conflict exists between the accuracy and practicality of the SCR metric. Some researchers have further proposed the multiple renewable energy station short-circuit ratio (MRSCR) and, through extensive simulations, have determined the critical SCR threshold.

[0058] However, at present, the short-circuit ratio constraints of multiple stations are incorporated into the verification of new energy operation limits through offline calculation, without considering the impact of new energy distribution and topology on the short-circuit ratio. In order to solve the problems existing in the prior art and realize online calculation, this application considers introducing a new graph neural network framework and proposes a method and device for determining the short-circuit ratio of multiple new energy stations. It can determine the online short-circuit ratio of multiple new energy stations based on message passing GCNConv, and can use power system analysis software to perform data analysis on the basis of ensuring accuracy, and consider the impact of new energy output and topology changes on the short-circuit ratio of multiple new energy stations. It can process the graph structure data of the power system, and through the message passing mechanism, efficiently aggregate and disseminate the information of nodes and edges, thereby improving the efficiency of real-time online calculation of the short-circuit ratio of multiple new energy stations.

[0059] The details are described in detail through the following embodiments.

[0060] In order to improve the reliability of the short-circuit ratio of multiple renewable energy stations and thus improve the stability of power system operation, this embodiment provides a method for determining the short-circuit ratio of multiple renewable energy stations, wherein the execution subject is a short-circuit ratio determination device for multiple renewable energy stations. The short-circuit ratio determination device for multiple renewable energy stations includes but is not limited to a server, such as Figure 1 As shown, the method specifically includes the following contents:

[0061] Step 100: Obtain graph structure data of the target power system, wherein the target power system includes: multiple devices, and the multiple devices include: multiple new energy stations; the nodes in the graph structure data represent the characteristic data of the corresponding devices, and the edges between the nodes represent the characteristic data of the corresponding lines; the characteristic data of the devices include: bus voltage, bus phase angle, bus active power injection and bus reactive power injection; the characteristic data of the lines include: line active power and line reactive power.

[0062] Specifically, the target power system may include multiple devices, such as generators, transformers, circuit breakers, and new energy multi-stations.

[0063] Step 200: Determine the short circuit ratio of the new energy multi-station based on the graph structure data and a preset short circuit ratio evaluation model; wherein the preset short circuit ratio evaluation model is pre-trained based on a real short circuit ratio graph convolutional network model of batch historical graph structure data and their respective corresponding new energy multi-stations.

[0064] Specifically, the graph structure data can be input into a preset short-circuit ratio evaluation model, and the output result of the preset short-circuit ratio evaluation model can be determined as the short-circuit ratio of the new energy multi-station; the graph convolutional network model can be a GCNConv model. The short-circuit ratio of the new energy multi-station can represent the short-circuit ratio of each new energy station in the new energy multi-station, and the actual short-circuit ratio of the new energy multi-station can represent the actual short-circuit ratio of each new energy station in the new energy multi-station.

[0065] From the above description, it can be seen that the method for determining the short-circuit ratio of multiple new energy stations provided in this embodiment, the graph structure data of the target power system can reflect the new energy distribution and topology structure of the target power system, and can consider the impact of the new energy distribution and topology structure on the short-circuit ratio, which can improve the reliability of the short-circuit ratio of multiple new energy stations, and thus improve the stability of the power system operation.

[0066] To improve the reliability of graph structure data, in one embodiment, step 100 includes:

[0067] Step 101: Obtain current steady-state characteristics and topology information of the target power system.

[0068] Specifically, the topology information of the power system may represent the connection mode and organizational structure between various devices in the power system.

[0069] Step 102: Obtain graph structure data of the target power system according to the steady-state characteristics and topology information.

[0070] In order to improve the reliability of the short circuit ratio evaluation model training, and then apply the reliable short circuit ratio evaluation model to improve the accuracy of the short circuit ratio determination, such as Figure 2 As shown, in one embodiment, before step 100, the method further includes:

[0071] Step 001: Collect a training set, which includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations.

[0072] Step 002: Apply the training set to train the graph convolutional network model to obtain the short circuit ratio evaluation model.

[0073] In order to further improve the reliability of the short-circuit ratio evaluation model, in one embodiment, before obtaining the graph structure data of the target power system, the method further includes:

[0074] Step 003: Collect a verification set, which includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations.

[0075] Step 004: According to each historical graph structure data and the short-circuit ratio evaluation model, the predicted short-circuit ratio of the new energy multi-station corresponding to the historical graph structure data is obtained.

[0076] Step 005: Perform mean square error processing on the predicted short circuit ratio and the actual short circuit ratio of the new energy multi-station corresponding to each historical graph structure data to obtain a mean square error value.

[0077] Specifically, the mean square error value can be determined according to the following formula:

[0078]

[0079] Among them, n is the number of samples, that is, the total number of historical graph structure data, y i is the true short-circuit ratio corresponding to the i-th sample, The predicted short circuit ratio corresponding to the i-th sample.

[0080] Step 006: Determine whether the mean square error value is less than a mean square error threshold; if so, determine that the short circuit ratio evaluation model has passed verification.

[0081] Specifically, if the mean square error value is greater than the mean square error threshold, the short circuit ratio evaluation model may continue to be trained until the short circuit ratio evaluation model passes verification.

[0082] In order to improve the reliability of the training set and thus improve the reliability of the short circuit ratio evaluation model training, in one embodiment, step 001 includes:

[0083] Step 011: Obtain historical operating data, historical topology information, and actual short-circuit ratios of multiple new energy stations of the target power system under various operating scenarios. The power generation, load, and topology corresponding to the same operating scenario are the same, while the power generation, load, and topology corresponding to different operating scenarios are different.

[0084] Step 012: Normalize the historical operation data under the same operation scenario.

[0085] Step 013: Obtain historical graph structure data for each operation scenario based on the normalized historical operation data and the historical topology information for that operation scenario.

[0086] Step 014: The historical graph structure data under each operation scenario and the actual short-circuit ratio of multiple new energy stations are used to form the training set.

[0087] To further illustrate this solution, this application provides an application example of a method for determining the short-circuit ratio of multiple new energy stations, which is described in detail as follows:

[0088] Step 1: Sample generation: A training sample set is established based on historical steady-state data from the power system's operation history and derived simulation data. To enhance the model's applicability to diverse operating scenarios, the derived simulation data includes power generation and load levels that fluctuate within a certain range. The training set includes a variety of power generation and load distribution and topology combinations.

[0089] During sample generation, the sample input characteristics must be determined in advance. This application example uses steady-state data as sample characteristics for power system transient stability assessment. The selected steady-state characteristics are shown in Table 1. The subscripts v and e represent the vertex or edge of the graph where the feature resides, respectively. The topological information of each sample is represented by an adjacency matrix.

[0090] Table 1

[0091] Input characteristics meaning <![CDATA[P v ]]> Active power injection into the bus <![CDATA[Q v ]]> Reactive power injection into busbars V Bus voltage θ Bus phase angle <![CDATA[P e ]]> Line active power <![CDATA[Q e ]]> Line reactive power

[0092] Each node feature in the graph structure data is a four-dimensional vector [P v , Q v ,V,θ,]. The lines in the power system are modeled as edges in the graph structure data, and the feature vector of each edge is a two-dimensional vector [P e , Q e ]. In order to avoid the problem of large numerical differences between features leading to convergence difficulties, Z-score normalization is used to normalize the bus and line feature data collected during the sample generation phase:

[0093]

[0094] in, is feature X i The mean of It's X i After normalizing the features and combining them with the topological information represented by the adjacency matrix, they form graph data representing each operation scenario.

[0095] Step 2: Graph-structured data processing. This stage reconstructs the long vector data obtained in the sample generation phase into graph-structured data for use as input to the GCNConv message passing model. Each busbar in the power system is modeled as a node in the graph-structured data, and the node's characteristics are the corresponding busbar's characteristics. For some busbars connected to both generators and loads, power is injected to obtain their combined values.

[0096] Step 3: Offline training, which primarily involves building the model structure and training model parameters. A new energy multi-station short-circuit ratio training model based on GCNConv is defined. It includes two GCN convolutional layers. By defining methods for initialization, parameter reset, forward propagation, and message passing, it implements convolution operations on graph-structured data. It executes a message passing mechanism by calling the propagate method, aggregating neighbor information to each node to update node features.

[0097] The processed graph dataset is split into training and test sets in a ratio of 8:2. The training set is used to determine the various hyperparameters and weights of GCNConv, while the test set is used to evaluate the performance of the trained GCNConv model.

[0098] After model construction is complete, the graph data training set obtained during the graph data processing phase is fed into the GCNConv model for offline model training. During training, the GCNConv model's predictions are compared with the sample labels, a loss function is calculated, and the model's internal weights and bias parameters are updated via a backpropagation algorithm. The loss function used in training is the mean squared error (MSE), and these loss values ​​are output for each batch and epoch.

[0099] Taking a 109-node system as an example, 20 different working modes and topologies are considered. The network topology diagram of 109 nodes is as follows: Figure 3 The input features are 156 edges of 109 nodes. The output features are the short-circuit ratios of the six renewable energy multi-site stations, namely the short-circuit ratios of the six wind turbine nodes 96, 97, 104, 105, 106, and 107.

[0100] To ensure a relatively even distribution of total power generation and load levels considered in the samples, the power generation and load levels for each dataset were categorized and randomly varied during sample generation: the total power system power generation and load levels were uniformly varied between 80% and 120%. 2025 samples were generated for each pattern, providing a total of 40,500 sample sets to validate the model's performance. The GCNConv model was implemented using the PyTorch Geometric framework. The Adam optimizer was used with an initial learning rate of 0.01 after hyperparameter optimization, and the learning rate was reduced to 90% after 10 iterations. The batch size was set to 32, and the number of epochs was 200. Figure 4 This is a comparison diagram of the training and test loss curves of the MRSCR1 dataset as the number of training rounds changes. Figure 4 Curve A in the figure shows the curve of training loss changing with the number of training rounds, and curve B shows the curve of test loss changing with the number of training rounds.

[0101] In order to evaluate the performance of the GCNConv model in calculating the short-circuit ratio of renewable energy multi-substations under different topologies and operating modes, the mean square error (MSE) was selected to comprehensively evaluate the performance of various models:

[0102]

[0103] Where n is the number of samples, y i is the true value of the i-th sample, The predicted value of the i-th sample.

[0104] First, the short-circuit ratio of multiple stations of new energy is calculated using the least squares fitting algorithm for comparison; the MSE calculated by the least squares fitting algorithm is smaller than the MSE calculated by the GCNConv model, but it can only be applied to one topology and cannot be applied to other topologies.

[0105] Next, we selected three common data-driven methods for comparison: random forest (RF), XGBoost (XGBoost), and deep neural network (DNN). RF and XGB each had 100 trees. The DNN was structured as a 4-layer fully connected network, with 512, 256, 128, and 64 neurons in each layer. ReLU was selected as the activation function, and Adam was chosen as the optimizer. The initial learning rate was 0.001, and the learning rate decay was set to 90% of the original rate every 10 epochs. The DNN was implemented using the PyTorch framework. The RF, XGBoost, DNN, and GCNConv models were trained on the dataset. Table 2 shows the performance metrics of different models on different test sets.

[0106] Table 2

[0107]

[0108]

[0109] GCNConv's overall accuracy is higher than that of RF, XGB, and DNN. This fully demonstrates the GCNConv model's advantage in considering datasets with topological variations. In this application example, the GCNConv model effectively processes graph-structured data of power system topologies and enables online, real-time calculation of short-circuit ratios of multiple renewable energy stations.

[0110] Step 4: In the GCNConv online application phase, the current node data, edge data, and topology information are used to construct graph structure data, which is then input into the trained GCNConv model to output the short-circuit ratio of the new energy station. The trained GCNConv model is equivalent to the above-mentioned short-circuit ratio evaluation model.

[0111] From the software level, in order to improve the reliability of the short-circuit ratio of the new energy multi-station and thus improve the stability of the power system operation, the present application provides an embodiment of a short-circuit ratio determination device for a new energy multi-station for realizing all or part of the content of the short-circuit ratio determination method of the new energy multi-station, see Figure 5 The short-circuit ratio determination device for new energy multi-stations specifically includes the following contents:

[0112] Acquisition module 01 is used to acquire graph structure data of a target power system, wherein the target power system includes: multiple devices, including: a new energy multi-station; nodes in the graph structure data represent characteristic data of corresponding devices, and edges between nodes represent characteristic data of corresponding lines; the characteristic data of the devices include: bus voltage, bus phase angle, bus active power injection, and bus reactive power injection; the characteristic data of the lines include: line active power and line reactive power;

[0113] Determination module 02 is used to determine the short circuit ratio of the new energy multi-station based on the graph structure data and a preset short circuit ratio evaluation model; wherein the preset short circuit ratio evaluation model is pre-trained based on a real short circuit ratio graph convolutional network model of batch historical graph structure data and their corresponding new energy multi-stations.

[0114] In one embodiment, the acquisition module includes:

[0115] an acquisition unit, used to acquire the current steady-state characteristics and topology information of the target power system;

[0116] The obtaining unit is used to obtain the graph structure data of the target power system according to the steady-state characteristics and topology information.

[0117] In one embodiment, the short-circuit ratio determination device for multiple new energy stations further includes:

[0118] An acquisition module is used to acquire a training set, wherein the training set includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations;

[0119] A training module is used to apply the training set to train the graph convolutional network model to obtain the short circuit ratio evaluation model.

[0120] In one embodiment, the short-circuit ratio determination device for multiple new energy stations further includes:

[0121] A verification set acquisition module is used to acquire a verification set, wherein the verification set includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations;

[0122] A predicted short circuit ratio module is used to obtain the predicted short circuit ratio of the new energy multi-station corresponding to each historical graph structure data according to the short circuit ratio evaluation model;

[0123] A module for obtaining a mean square error value is used to perform mean square error processing on the predicted short circuit ratio and the actual short circuit ratio of the new energy multi-station corresponding to each historical graph structure data to obtain a mean square error value;

[0124] The verification module is used to determine whether the mean square error value is less than a mean square error threshold, and if so, determine that the short circuit ratio evaluation model is verified to be successful.

[0125] In one embodiment, the acquisition module includes:

[0126] A historical data acquisition unit is used to obtain historical operating data, historical topology information, and real short-circuit ratios of multiple renewable energy stations of the target power system under various operating scenarios. The power generation, load, and topology corresponding to the same operating scenario are the same, while the power generation, load, and topology corresponding to different operating scenarios may be different.

[0127] Normalization unit, used to normalize historical operation data under the same operation scenario;

[0128] Obtaining a historical graph structure data unit, for obtaining historical graph structure data for each operation scenario based on the normalized historical operation data and the historical topology information for that operation scenario;

[0129] The combination unit is used to combine the historical graph structure data under various operation scenarios and the actual short-circuit ratio of multiple new energy stations into the training set.

[0130] The embodiment of the short-circuit ratio determination device for new energy multi-stations provided in this specification can be specifically used to execute the processing flow of the embodiment of the short-circuit ratio determination method for new energy multi-stations mentioned above. Its functions will not be repeated here, and reference can be made to the detailed description of the embodiment of the short-circuit ratio determination method for new energy multi-stations mentioned above.

[0131] Figure 6 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 6 As shown, the electronic device includes: a memory 601, a processor 602, and a computer program stored in the memory 601 and executable on the processor 602. When the processor 602 executes the computer program, the following method is implemented:

[0132] Obtaining graph structure data of a target power system, the target power system including: a plurality of devices, the plurality of devices including: a new energy multi-station; nodes in the graph structure data represent characteristic data of corresponding devices, and edges between nodes represent characteristic data of corresponding lines; the characteristic data of the devices include: bus voltage, bus phase angle, bus active power injection, and bus reactive power injection; the characteristic data of the lines include: line active power and line reactive power;

[0133] Determining the short-circuit ratio of the new energy multi-station according to the graph structure data and a preset short-circuit ratio evaluation model;

[0134] Among them, the preset short-circuit ratio evaluation model is pre-trained based on the batch historical graph structure data and the real short-circuit ratio graph convolutional network model corresponding to each of the new energy multi-stations.

[0135] This embodiment discloses a computer program product, which includes a computer program. When the computer program is executed by a processor, the following method is implemented:

[0136] Obtaining graph structure data of a target power system, the target power system including: a plurality of devices, the plurality of devices including: a new energy multi-station; nodes in the graph structure data represent characteristic data of corresponding devices, and edges between nodes represent characteristic data of corresponding lines; the characteristic data of the devices include: bus voltage, bus phase angle, bus active power injection, and bus reactive power injection; the characteristic data of the lines include: line active power and line reactive power;

[0137] Determining the short-circuit ratio of the new energy multi-station according to the graph structure data and a preset short-circuit ratio evaluation model;

[0138] Among them, the preset short-circuit ratio evaluation model is pre-trained based on the batch historical graph structure data and the real short-circuit ratio graph convolutional network model corresponding to each of the new energy multi-stations.

[0139] This embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the following method is implemented:

[0140] Obtaining graph structure data of a target power system, the target power system including: a plurality of devices, the plurality of devices including: a new energy multi-station; nodes in the graph structure data represent characteristic data of corresponding devices, and edges between nodes represent characteristic data of corresponding lines; the characteristic data of the devices include: bus voltage, bus phase angle, bus active power injection, and bus reactive power injection; the characteristic data of the lines include: line active power and line reactive power;

[0141] Determining the short-circuit ratio of the new energy multi-station according to the graph structure data and a preset short-circuit ratio evaluation model;

[0142] Among them, the preset short-circuit ratio evaluation model is pre-trained based on the batch historical graph structure data and the real short-circuit ratio graph convolutional network model corresponding to each of the new energy multi-stations.

[0143] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts 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, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0145] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0147] Throughout this specification, reference to terms such as "one embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0148] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for determining the short-circuit ratio of multiple renewable energy stations, characterized in that: include: Acquire graph structure data of a target power system, the target power system comprising: a plurality of devices, the plurality of devices comprising: a new energy multi-station; nodes in the graph structure data represent characteristic data of corresponding devices, and edges between nodes represent characteristic data of corresponding lines; the characteristic data of the devices comprise: bus voltage, bus phase angle, active power injection of the bus, and reactive power injection of the bus; the characteristic data of the lines comprise: line active power and line reactive power; Determining the short-circuit ratio of the new energy multi-station according to the graph structure data and a preset short-circuit ratio evaluation model; Among them, the preset short-circuit ratio evaluation model is pre-trained based on the batch historical graph structure data and the real short-circuit ratio graph convolutional network model corresponding to each of the new energy multi-stations.

2. The short-circuit ratio determination method for multiple renewable energy stations according to claim 1, characterized in that: The obtaining of graph structure data of the target power system comprises: Obtain the current steady-state characteristics and topology information of the target power system; According to the steady-state characteristics and topology information, graph structure data of the target power system is obtained.

3. The short-circuit ratio determination method of new energy multi-station according to claim 1 is characterized in that: Also includes: Collecting a training set, the training set includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations; The training set is used to train the graph convolutional network model to obtain the short circuit ratio evaluation model.

4. The short-circuit ratio determination method for multiple new energy stations according to claim 3 is characterized in that: Before acquiring the graph structure data of the target power system, the method further includes: Collecting a verification set, the verification set includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations; According to each historical graph structure data and the short-circuit ratio evaluation model, a predicted short-circuit ratio of the new energy multi-station corresponding to the historical graph structure data is obtained; Perform mean square error processing on the predicted short circuit ratio and the actual short circuit ratio of the new energy multi-station corresponding to each historical graph structure data to obtain the mean square error value; It is determined whether the mean square error value is less than a mean square error threshold value, and if so, it is determined that the short circuit ratio evaluation model is verified to be passed.

5. The short-circuit ratio determination method for multiple new energy stations according to claim 3 is characterized in that: The acquisition training set includes: Obtaining historical operation data, historical topology information, and real short-circuit ratios of multiple renewable energy stations of the target power system under various operation scenarios; the power generation, load, and topology corresponding to the same operation scenario are the same, while the power generation, load, and topology corresponding to different operation scenarios are different; Normalize the historical operation data under the same operation scenario; According to the normalized historical operation data and the historical topology information in each operation scenario, the historical graph structure data in the operation scenario is obtained; The training set is composed of the historical graph structure data under various operation scenarios and the actual short-circuit ratio of multiple new energy stations.

6. A short-circuit ratio determination device for multiple renewable energy stations, characterized in that: include: An acquisition module is used to acquire graph structure data of a target power system, wherein the target power system includes: a plurality of devices, wherein the plurality of devices include: a new energy multi-station; the nodes in the graph structure data represent characteristic data of corresponding devices, and the edges between the nodes represent characteristic data of corresponding lines; the characteristic data of the devices include: bus voltage, bus phase angle, active power injection of the bus, and reactive power injection of the bus; the characteristic data of the lines include: line active power and line reactive power; A determination module, used to determine the short circuit ratio of the new energy multi-station according to the graph structure data and a preset short circuit ratio evaluation model; Among them, the preset short-circuit ratio evaluation model is pre-trained based on the batch historical graph structure data and the real short-circuit ratio graph convolutional network model corresponding to each of the new energy multi-stations.

7. The short-circuit ratio determination device for new energy multi-station according to claim 6, characterized in that: The acquisition module comprises: An acquisition unit, used to acquire current steady-state characteristics and topology information of the target power system; The obtaining unit is used to obtain the graph structure data of the target power system according to the steady-state characteristics and topology information.

8. The short-circuit ratio determination device for new energy multi-stations according to claim 6, characterized in that: Also includes: A collection module, used for collecting a training set, wherein the training set includes: batch historical graph structure data and their corresponding real short-circuit ratios of multiple new energy stations; A training module is used to apply the training set to train the graph convolutional network model to obtain the short circuit ratio evaluation model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the short-circuit ratio determination method for new energy multi-stations described in any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by the processor, the short-circuit ratio determination method of the new energy multi-station according to any one of claims 1 to 5 is implemented.

Images