Power grid synchronous broadband forced oscillation detection and positioning method, system and medium

Abstract

The invention discloses a power grid synchronous broadband forced oscillation detection and positioning method and system and a medium, and the method comprises the steps: obtaining an oscillation data sequence of a power grid and a power system topological graph, and inputting the oscillation data sequence and the power system topological graph into a pre-trained multi-task graph sequence network, so as to obtain an oscillation source positioning detection result; comprising the following steps: performing information transmission on an oscillation data sequence through a convolutional layer, a pooling layer and an output feature obtained by a created embeddable sequence autoregression module and a topological graph of a power system through a constructed multi-task graph sequence network, and obtaining node features of each node through a gate control cycle unit GRU, and inputting a graph-level detection branch and a node-level detection branch to realize event type classification of the oscillation source and positioning of the oscillation source. The method aims at reducing interference of other information on broadband oscillation information, data are dynamically analyzed from the two dimensions of time and space, and broadband oscillation source positioning is rapidly and accurately achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power system, in particular to a power grid synchronous wide frequency forced oscillation detection and positioning method, system and medium. BACKGROUND

[0002] In modern power systems, the increasing integration of renewable energy, high-voltage direct current links and power electronic devices greatly increases the possibility of wide frequency oscillations, ranging from low frequency oscillations of a few hertz to high frequency oscillations of hundreds of hertz, thereby posing a major challenge to traditional stability analysis methods. Accurate detection and positioning of such oscillations is crucial for implementing targeted mitigation strategies to prevent equipment damage and large-scale system failures. At the same time, advances in wide-area monitoring technology, such as waveform measurement units, enable higher precision synchronization and significantly enhance monitoring capabilities in a wider frequency range and finer time resolution. However, the time-varying, nonlinear and dynamic characteristics of wide frequency oscillation propagation continue to hinder the effectiveness of real-time positioning work. To address the challenges of oscillation detection and positioning, existing methods can be broadly divided into three categories: physical-based, energy flow-based and data-driven methods. Physical-based methods use critical oscillation parameters to identify the source, however, a key limitation of this method is that they are difficult to accurately identify forced sources under resonance conditions, where the most severe oscillations may not occur near the actual source; secondly, to reduce the uncertainty of oscillation localization, energy flow-based methods are proposed, where dissipated energy flow is the most widely used method, however, under low damping conditions and high noise levels, this method still struggles with complex situations; considering the large amount of measurement data, data-driven methods have been developed, however, this method can cause information loss during inter-stage interaction. Other emerging methods, including graph convolutional neural networks and long short-term memory networks, have also been proposed to locate oscillations by integrating signal processing techniques with energy flow methods. Nevertheless, most methods require additional noise-resistant modules before positioning, thereby increasing the complexity of the model; secondly, purely physical and data-driven methods exhibit limited accuracy and real-time performance when dealing with high-speed dynamic oscillations; finally, traditional models usually assume that oscillations have been detected and only focus on positioning. Therefore, how to efficiently and accurately solve the problem of finding the source of complex wide frequency forced oscillations based on wide-area synchronous measurement data in modern power systems has become a key technical problem that needs to be solved. SUMMARY

[0003] The technical problems to be solved by the present application are: in view of the above problems of the prior art, a power grid synchronous wide frequency forced oscillation detection and positioning method, system and medium are provided, and the present application aims to efficiently and accurately solve the source finding problem of complex wide frequency forced oscillation in a modern power system based on wide area synchronous measurement data, reduce the interference of other information on wide frequency oscillation information, dynamically analyze data from two dimensions of time and space, and quickly and accurately realize wide frequency oscillation source positioning.

[0004] To solve the above technical problems, the technical scheme adopted by the present application is: A power grid synchronous wide frequency forced oscillation detection and positioning method, comprising the following steps: obtaining an oscillation data sequence of a power grid and a power system topology graph, the oscillation data sequence comprising voltage, frequency and frequency rate of change of the power grid, the nodes in the power system topology graph being generators or loads in the power grid, the edges being lines, and the oscillation characteristics of the nodes comprising voltage, frequency and frequency rate of change of the nodes; inputting the oscillation data sequence of the power grid and the power system topology graph into a pre-trained multi-task graph sequence network to obtain an oscillation source positioning detection result, comprising: S101, extracting key features from the oscillation data sequence through a convolution layer and a pooling layer ; S102, inputting the key features into an embeddable sequence autoregressive module, the embeddable sequence autoregressive module performing embedded feature filtering on the key features through a plurality of stacked ARMA(1,0) filters, and summing responses of the plurality of stacked ARMA(1,0) filters to obtain final output features ; ; S103, taking the output features and the power system topology graph as inputs of the multi-task graph sequence network, performing information transmission through the multi-task graph sequence network, and obtaining node features of each node through a gated recurrent unit (GRU) ; S104, inputting the node features of each node into a graph-level detection branch and a node-level detection branch respectively, realizing event type classification of the oscillation source through the graph-level detection branch, and realizing positioning of the oscillation source through the node-level detection branch.

[0005] Optionally, when the oscillation data sequence of the power grid and the power system topology graph are obtained, the voltage time sequence of the power grid is obtained, the voltage time sequence is filtered to eliminate the direct current component to extract the frequency of the power grid, and the frequency rate of change is calculated according to the frequency of the power grid and the following formula: ; wherein, ​and Sampling points and sampling points frequency, The sampling interval is... The voltage sampling frequency is used, and the obtained voltage, frequency, and rate of change of the power grid are normalized to form an oscillation data sequence.

[0006] Optionally, when acquiring the oscillation data sequence of the power grid and the power system topology map, the functional expression of the obtained power system topology map is: ; in, This is a power system topology diagram. For a set of nodes, It is an unordered set of edges. The oscillation characteristics of a node include its voltage, frequency, and rate of change of frequency, and the unordered edge set. Through the adjacency matrix This represents the line connection relationship between different nodes. The node and the first When nodes are directly connected by a line, the adjacency matrix The Middle Line number Column elements ;otherwise , indicating the first The node and the first The nodes have no direct connection.

[0007] Optionally, in step S101, key features are extracted from the oscillating data sequence through convolutional and pooling layers. The function expression for the convolution operation of the convolutional layer is: ; In the above formula, This is the output of the convolution operation. The number of types of oscillating data. for The first moment The input signal for the oscillation data; convolution kernel The offset time that is applied, and The first moment Input signal of oscillation data Time axis alignment; convolution kernel For the first Such oscillation data in The convolution kernel corresponding to each time step.

[0008] Optionally, in step S102, the... The final output feature is obtained by summing the responses of the stacked ARMA(1,0) filters. The function expression is: ; in, Let be the number of stacking levels of the ARMA(1,0) filter. For activation function, For the first The output characteristics of an ARMA(1,0) filter. For the first Input characteristics of an ARMA(1,0) filter. and Let be the trainable weight parameters of the k-th ARMA(1,0) filter. As a key feature, The normalized Laplace matrix is ​​symmetric; the ARMA(1,0) filter is approximated using a first-order recursive method as shown in the following equation: ; ; in, and These represent the output characteristics and the oscillation characteristics of the input nodes of the ARMA(1,0) filter, respectively. and For coefficients, For symmetric normalized Laplace matrix The intermediate coefficients related to the eigenvalues, and These are the symmetric normalized Laplace matrices. Maximum and minimum eigenvalues It is an identity matrix.

[0009] Optionally, in step S103, the output features will be... The power system topology graph is used as input to the multi-task graph sequence network. Information is transmitted through the multi-task graph sequence network, and the node characteristics of each node are obtained through the gated cyclic unit (GRU). At that time, the functional expression for information transmission in the multi-task graph sequence network is: ; in, and The first The output characteristics and the oscillation characteristics of the input nodes during the next transmission. For activation function, Adjacency matrix and an identity matrix adjacency matrix to represent an unordered edge set in a power system topology graph adjacency matrix, to represent a diagonal node degree matrix to represent a diagonal node degree matrix and are the node feature matrix and trainable parameter matrix at the first passing, respectively, and the node features of each node are obtained through a gated recurrent unit (GRU) The functional expression of the node features is as follows: ; ; wherein, is a softmax function, is a normalized adjacency matrix, is an activation function, is the output of the gated recurrent unit (GRU) layer, and are trainable parameter matrices.

[0010] Optionally, the functional expression of the loss function used by the multi-task graph sequence network during training is as follows: ; ; ; ; wherein, is the loss function used by the multi-task graph sequence network during training, is the positioning detection result of the oscillation source of the node-level detection branch, is the model parameter of the multi-task graph sequence network, and are the weight hyperparameters of the node-level detection branch and the graph-level detection branch learned by the softplus function, respectively, is a weighted binary cross-entropy loss function considering the node mask loss, is a cross-entropy loss for the graph-level detection branch to perform a graph classification task, is the mask of the first node, and the mask is an indicator of whether the node is valid, is the weight of the first node, is the total number of measurement nodes, is the number of generator nodes, is a cross-entropy loss function, and The detection result and the true value of the graph classification task performed by the graph-level detection branch, respectively.

[0011] The application also provides a power grid synchronous wide frequency forced oscillation detection and positioning system, comprising a microprocessor and a memory connected with each other, wherein the microprocessor is programmed or configured to execute the power grid synchronous wide frequency forced oscillation detection and positioning method.

[0012] The application also provides a computer readable storage medium, wherein a computer program or instructions are stored in the computer readable storage medium, and the computer program or instructions are programmed or configured to execute the power grid synchronous wide frequency forced oscillation detection and positioning method by a processor.

[0013] The application also provides a computer program product, comprising a computer program or instructions, which are programmed or configured to execute the power grid synchronous wide frequency forced oscillation detection and positioning method by a processor.

[0014] Compared with the prior art, the application mainly has the following beneficial effects: the power grid synchronous wide frequency forced oscillation detection and positioning method can make full use of the combination of the autoregressive moving average model and the multi-task graph sequence network and the multi-task mechanism, can effectively reduce the interference of other information on the wide frequency oscillation information, can efficiently and accurately solve the source finding problem of complex wide frequency forced oscillation in a modern power system based on wide-area synchronous measurement data, can reduce the interference of other information on the wide frequency oscillation information, can dynamically analyze the data from the time and space dimensions, and can quickly and accurately realize the wide frequency oscillation source positioning. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 FIG. 1 is a basic flowchart of the method of the embodiment of the application.

[0016] Figure 2 FIG. 4 is the original frequency data of the generator based on the IEEE 39-node system in the embodiment of the application.

[0017] Figure 3 FIG. 6 is the frequency data of the generator after normalization processing based on the IEEE 39-node system in the embodiment of the application.

[0018] Figure 4 FIG. 8 is a network structure diagram of the sequence autoregressive module that can be embedded in the embodiment of the application.

[0019] Figure 5 FIG. 10 is a signal spectrum diagram comparison of the input and output of the sequence autoregressive module that can be embedded in the embodiment of the application. DETAILED DESCRIPTION

[0020] To enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings in the embodiments of the present invention.

[0021] like Figure 1 As shown, the method for detecting and locating synchronous broadband forced oscillations in a power grid in this embodiment includes the following steps: acquiring the oscillation data sequence and power system topology map of the power grid, wherein the oscillation data sequence includes the voltage, frequency, and frequency change rate of the power grid, and the nodes in the power system topology map are generators or loads in the power grid, the edges are lines, and the oscillation characteristics of the nodes include the voltage, frequency, and frequency change rate of the nodes; inputting the oscillation data sequence and power system topology map of the power grid into a pre-trained multi-task graph sequence network to obtain the oscillation source location detection result, including: S101 extracts key features from the oscillating data sequence through convolutional and pooling layers. ; S102, key features Input can be embedded into a sequence autoregressive module, the embedded sequence autoregressive module through Stacked ARMA(1,0) filters for key features Perform embedded feature filtering and... The final output feature is obtained by summing the responses of the stacked ARMA(1,0) filters. ; S103 will output features The power system topology graph is used as input to the multi-task graph sequence network. Information is transmitted through the multi-task graph sequence network, and the node characteristics of each node are obtained through the gated cyclic unit (GRU). ; S104, The node characteristics of each node. Input graph-level detection branch and node-level detection branch respectively. Use graph-level detection branch to classify the event type of the oscillation source and use node-level detection branch to locate the oscillation source.

[0022] In this embodiment, acquiring the oscillation data sequence of the power grid and the power system topology map includes acquiring the voltage time series of the power grid and collecting the oscillation data source of the synchronous motor excitation system, as well as the voltage of the injected broadband forced oscillation. The function expression in the time domain is as follows: ; In the above formula, , , and These represent the oscillation amplitude, damping coefficient, angular frequency, and initial phase, respectively. and angular frequency As two key parameters, once their values ​​are determined, they can uniquely define the oscillation characteristic curve; initial phase This determines the onset time of oscillation, a characteristic similar to the phase convergence phenomenon at the zero-crossing point of the power frequency; the acquired voltage The data contains wideband oscillation information and a large amount of redundant information. Therefore, the voltage time series can be filtered to eliminate the DC component and extract the grid frequency. As an optional implementation, to remove the long-term trend in the original data, this embodiment uses a zero-phase high-pass Butterworth filter to perform DC filtering on the original data, extracting and highlighting the frequency information of the wideband oscillation. In this embodiment, the frequency change rate is calculated based on the grid frequency and the following formula: ; in, and Sampling points and sampling points frequency, The sampling interval is... The sampling frequency of the voltage, where the sampling interval is typically... It can be set to 1 to 5, where , Indicates the number of sampling points. The sampling time interval is [not specified]. The obtained grid voltage [is then used]. ,frequency and frequency change rate After normalization, the resulting oscillating data sequence can be represented as a three-dimensional eigenvector: .

[0023] Figure 2 This embodiment uses the raw frequency data of the generator based on the IEEE 39-bus system. Figure 3 This embodiment presents the normalized frequency data of generators based on the IEEE 39-bus system. Figure 2 and Figure 3 Curve G30 represents an oscillating generator, while the other curves represent non-oscillating generators. (Comparison) Figure 2 and Figure 3 It can be seen that, Figure 2 The frequencies of each generator, including both oscillating and non-oscillating generators, are almost identical, making it difficult to distinguish subtle variations; however, as Figure 3 As shown, after data preprocessing through filtering and normalization, the frequency difference between the oscillating source generator and the non-oscillating source generator becomes larger, and the oscillation waveform becomes distinguishable, providing stronger nodal characteristics for broadband oscillation localization.

[0024] The functional expression for the power system topology obtained in this embodiment is: ; in, This is a power system topology diagram. For a set of nodes, It is an unordered set of edges. The oscillation characteristics of a node include its voltage, frequency, and rate of change of frequency, and the unordered edge set. Through the adjacency matrix This represents the line connection relationship between different nodes. The node and the first When nodes are directly connected by a line, the adjacency matrix The Middle Line number Column elements ;otherwise , indicating the first The node and the first The nodes have no direct connection.

[0025] In step S101 of this embodiment, key features are extracted from the oscillating data sequence through convolutional and pooling layers. The function expression for the convolution operation of the convolutional layer is: ; In the above formula, This is the output of the convolution operation. The number of types of oscillating data. for The first moment The input signal for the oscillation data; convolution kernel The offset time that is applied, and The first moment Input signal of oscillation data Time axis alignment; convolution kernel For the first Such oscillation data in The convolution kernel corresponding to each time step.

[0026] Considering the long duration of low-frequency oscillations and the short duration of high-frequency oscillations, this embodiment further constructs an embeddable sequence autoregressive module. The embeddable sequence autoregressive module is a neural network component specifically designed for processing spatiotemporal sequence data. Its core idea is to combine the classic autoregressive moving average model from signal processing with a graph neural network to extract features from broadband oscillation information. The embeddable sequence autoregressive module uses an autoregressive moving average model for embedded feature filtering to extract oscillation-related features and physical features, simultaneously capturing the short-term and long-term dynamic characteristics of oscillations, corresponding to the modes of high-frequency and low-frequency oscillations, respectively. Figure 4As shown, in this embodiment, a sequence autoregression module can be embedded through... Stacked ARMA(1,0) filters for key features Perform embedded feature filtering and... The final output feature is obtained by summing the responses of the stacked ARMA(1,0) filters. In step S102, for The final output feature is obtained by summing the responses of the stacked ARMA(1,0) filters. The function expression is: ; in, Let be the number of stacking levels of the ARMA(1,0) filter. For activation function, For the first The output characteristics of an ARMA(1,0) filter. For the first Input characteristics of an ARMA(1,0) filter. and Let be the trainable weight parameters of the k-th ARMA(1,0) filter. As a key feature, For a symmetric normalized Laplacian matrix, the above function expression can be structurally implemented using skip connection layers in a neural network.

[0027] ARMA(1,0) filter is an ARMA ( p , q One type of model, ARMA ( p , q The model can be approximated as: ; in, For ARMA ( p , q The transfer function of the model. These are characteristic roots. and These are the weighting coefficients. For order, and These are the orders of the moving average component and the autoregressive component, respectively. Transforming the above equation to the measurement domain, we obtain the domain expression: ; in, The output characteristics of the ARMA(1,0) filter are given. The oscillation characteristics of the nodes at the input of the ARMA(1,0) filter. For symmetric normalized Laplace matrix. ARMA( p , q The model will be based on the transfer function. In the symmetric normalized Laplace matrix Oscillation characteristics of nodes on the eigenvector basis Modulation is applied. The transfer function of the autoregressive moving average model is expressed as follows: ; In the above formula, This is the moving average portion, which can be used to control the zero point; This is the autoregressive part, which can be used to control the poles. and These are the orders of the moving average component and the autoregressive component, respectively. and The weighting coefficients are used. This autoregressive moving average model can adjust the gain at zeros and poles, and this structure can produce a filter-like effect. In this embodiment, the moving average and autoregressive moving average models have been incorporated into the power system topology structure. The autoregressive moving average model can model stochastic processes, corresponding to the propagation process of broadband oscillations. This gives the ARMA(1,0) filter both noise immunity, long-range dependency capture capability, and global graph structure awareness capability. By tracking measurement data and calculating poles, the oscillation frequency can be derived. With damping ratio The calculation formula is: ; ; In the above formula, and express The i For conjugate eigenvalues, The sampling time and eigenvalues ​​determine the stability and frequency selectivity of the power system. To avoid delays in oscillation localization, this embodiment employs a recursive calculation method for the ARMA(1,0) filter. Specifically, the ARMA(1,0) filter is approximated using a first-order recursion as shown in the following formula: ; ; in, and These represent the output characteristics and the oscillation characteristics of the input nodes of the ARMA(1,0) filter, respectively. and For coefficients, For symmetric normalized Laplace matrix The intermediate coefficients related to the eigenvalues, and are the symmetric normalized Laplacian matrices respectively. are the maximum and minimum eigenvalues, is the identity matrix. and can be simplified to fixed hyperparameters 1 and 0, so that the intermediate coefficients approximately equal the symmetric normalized Laplacian matrices ; the coefficients and have mathematical relations with the transfer function while following the ARMA(1, 0) model; and respectively represent the residual and pole of the rational function. The coefficients and Figure 5 are optimized as trainable parameters to adapt to different oscillation characteristics; at the same time, the autoregressive module iterates with the convolution layer and the pooling layer to form an embeddable sequence autoregressive module, which is convenient for dynamic feature extraction and solves the problem of multi-modal oscillation tracing. In addition, when applied to graph-based oscillation signals, the ARMA(1, 0) filter function can be regarded as a low-pass filter, and the embeddable sequence autoregressive module is constructed as a filter bank by stacking multiple ARMA(1, 0) filters to adapt to multiple oscillation modes to realize oscillation dynamic feature extraction. The input and output signals of the embeddable sequence autoregressive module in this embodiment are visualized, and the results are shown in Figure 5 , and it can be seen from the comparison of the input and output signal spectra in

[0028] In step S103 of this embodiment, the output features and the power system topology graph are taken as the input of the multi-task graph sequence network, and the information is transmitted through the multi-task graph sequence network, and the node features of each node are obtained through the gated recurrent unit GRU. ; wherein, and are the output features and the input node oscillation features at the time of transmission, is an activation function, is the sum of the adjacency matrix and the identity matrix , and the adjacency matrix is a set of unordered edges in the power system topology graph The adjacency matrix, for The degree matrix of the diagonal nodes, and The first The node feature matrix and trainable parameter matrix at each transmission are used. The purpose is to achieve symmetric normalization, thereby avoiding distortion of the feature vector scale.

[0029] In this embodiment, the gated recurrent unit (GRU) enhances the model's learning ability by selectively memorizing and forgetting information to model sequence measurement data. The GRU obtains the node features of each node. The function expression is: ; ; in, For the softmax function, The normalized adjacency matrix, For activation function, The output of the gated recurrent unit (GRU) layer. and is a trainable parameter matrix.

[0030] In this embodiment, the loss function used by the multi-task graph sequence network during training has the following expression: ; ; ; ; in, This is the loss function used during training of the multi-task graph sequence network. This is the location detection result of the oscillation source in the node-level detection branch. These are the model parameters for a multi-task graph sequence network. and These are the weight hyperparameters for the node-level and graph-level detection branches learned by the softplus function, respectively. To consider the weighted binary cross-entropy loss function that takes into account node mask loss, The cross-entropy loss is used for graph classification tasks in the graph-level detection branch. For the first The mask of each node, which serves as a flag indicating whether a node is valid. For the first The weight of each node, This represents the total number of measurement nodes. the number of generator nodes, the cross-entropy loss function, and respectively, are the detection results and true values of the graph-level detection branch performing the graph classification task. The loss function (multi-task loss function) in this embodiment includes a weighted binary cross-entropy loss function , a cross-entropy loss and a regularization term The weights of each loss are not fixed hyperparameters, but are dynamically adaptive and are automatically learned and updated during the neural network training process. The dynamic updating of weights and parameters is achieved through the multi-task loss function, and the loss values of the two sub-branches are calculated separately according to their respective performances, ensuring that the balance between tasks is maintained during the optimization process and avoiding the dominance of a single task in the training process. The multi-task loss function in this embodiment introduces a loss weighting mechanism and a node-level loss mask technique to focus the learning process on effective samples. The calculation of the loss weighting mechanism assigns greater weights to classes with smaller sample sizes, thereby achieving lower loss penalties. The calculation of the node-level loss mask technique ensures that only effective nodes participate in loss calculation during the training process. The main advantage of this masking mechanism is that it ensures that only effective nodes participate in backpropagation and parameter optimization when calculating the loss function, and it prevents noise interference from irrelevant nodes and avoids the impact of unlabeled nodes on gradient updates. This embodiment achieves subgraph recognition and subnode recognition by introducing a trainable parameter and weight system. Each branch is designed to support a specific learning goal, with the graph-level detection branch focusing on event type classification and the node-level detection branch working to solve the problem of locating synchronous wideband oscillation sources. Information is transmitted through the multi-task graph sequence network to obtain the node features of each node, and the node with the maximum prediction value is the synchronous wideband oscillation source.

[0031] In order to verify the performance of the multi-task graph sequence network (MGSNet) in the power grid synchronous broadband forced oscillation detection and positioning method of the embodiment, the IEEE 39-node system is taken as an experimental object in the embodiment, and an ablation experiment is designed for the multi-task graph sequence network. The "node-graph convolution network" represents that each node is modeled as an independent graph. The "masked graph convolution network-gated recurrent unit model" and the "sequence graph sequence network" are both single-task frameworks, and correspond to the gated recurrent unit architecture with the added mask mechanism and the architecture integrated with the embeddable sequence autoregressive module, respectively. In the embodiment, the IEEE 39-node system is selected to compare three latest existing methods with the method proposed in the embodiment. Six performance indicators are summarized: accuracy, F1 value, precision, area under the curve (AUC), event detection capability and single-sample calculation time. During the test, 40 dB noise level is superimposed on the original voltage and frequency oscillation measurement data, and the results are shown in Table 1.

[0032] Table 1 Comparison of different existing methods based on IEEE 39-node system

[0033] In Table 1, "-" indicates that the method does not have event type detection capability. As can be seen from Table 1, the accuracy, precision, area under the curve (AUC) and F1 value of the multi-task graph sequence network proposed in the method of the embodiment are better than those of the models adopted by other methods, and the average running time on the single task is only 11.2 ms, which shows the real-time positioning capability of the method.

[0034] In addition, based on the IEEE 39-node system, experiments are further conducted on the multi-task graph sequence network proposed in the method of the embodiment to analyze the positioning of oscillations with different noise levels using different methods, and the results are shown in Table 2.

[0035] Table 2 Oscillation source positioning experiment results of different methods and noise levels based on IEEE 39-node system

[0036] Table 2 is a comparison of F1 value and TOP-1 accuracy of different methods and noise levels based on IEEE 39-node system. The F1 value is obtained by coordinating the precision and recall, and can be used as a comprehensive evaluation index of positioning quality. The TOP-1 accuracy directly reflects the correctness of the highest confidence prediction. As can be seen from Table 2, the effectiveness and superiority of the multi-task graph sequence network proposed in the method of the embodiment in the broadband oscillation positioning task under different noise levels all exceed those of the models of other methods, achieving the most advanced performance and realizing the best balance between oscillation sources and non-oscillation sources.

[0037] In summary, the method of the embodiment realizes end-to-end processing from original measurement data to event detection and source positioning through a multi-task graph sequence network (MGSNet), without additional preprocessing modules, simplifying the process and improving real-time performance; the method introduces an embeddable sequence autoregressive (SA) block combined with the implementation of the autoregressive moving average model in the graph domain, which can effectively filter out noise and extract key oscillation features, and still maintain high accuracy under a noise level of 20-60 dB; the method simultaneously performs event type classification and oscillation source positioning through multi-task learning, and introduces a customized loss function and a mask mechanism, which significantly improves the discrimination ability and generalization performance of the model; the method is constructed based on a graph convolutional network (GCN), which effectively fuses spatiotemporal features and topological information by combining a gated recurrent unit (GRU) and an embeddable sequence autoregressive block, improving the modeling ability of oscillation propagation in complex power grids; the method realizes autoregressive moving average filtering through recursive approximation, and has good engineering applicability with a single-sample processing time of only 11.2 ms (3 seconds of data) by combining a lightweight graph neural network structure. The method of the embodiment can fully capture the time and space information of the node electrical parameters of the power grid, construct a sequence-based autoregressive module and an autoregressive moving average model, and simultaneously capture short-term and long-term dynamic characteristics, extract and integrate oscillation-related features and physical features to realize noise suppression and significant feature enhancement. The autoregressive moving average model is embedded in the sequence autoregressive module, which has the structure of embedding and pluggability, and the autoregressive module and the convolutional layer and the pooling layer iteratively run synchronously to form an embeddable sequence autoregressive module, which facilitates dynamic feature extraction and solves the problem of multi-modal oscillation tracing. The multi-task mechanism realizes simultaneous processing of oscillation detection and positioning tasks, and the improved multi-task loss function minimizes the objective function value and adaptively balances the performance to realize oscillation tracing. The method of the embodiment can effectively reduce the interference of other information on wideband oscillation information, effectively solve the problem of multi-task wideband oscillation positioning, realize rapid and accurate positioning of wideband oscillation sources, and has important engineering practical significance.

[0038] The embodiment also provides a power grid synchronous wideband forced oscillation detection and positioning system, which comprises a microprocessor and a memory connected to each other, and the microprocessor is programmed or configured to execute the power grid synchronous wideband forced oscillation detection and positioning method.

[0039] The embodiment also provides a computer readable storage medium, which stores a computer program or instructions programmed or configured to execute the power grid synchronous wideband forced oscillation detection and positioning method by a processor.

[0040] The embodiments also provide a computer program product comprising computer programs or instructions programmed or configured to perform the method of power grid synchronization broadband forced oscillation detection and positioning by a processor.

[0041] Those skilled in the art should understand that the technical solutions provided by the present application can be in the form of a method, a system, or a computer program product. Therefore, the present application can be in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer usable program code. The present application is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows 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 apparatus to produce a machine, so that the instructions that are executed by the processor of the computer or other programmable data processing apparatus generate an apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus with a means for performing the functions specified in the flowchart Figure 1 one or more flows and / or blocks Figure 1 an apparatus with a means for performing the functions specified in the flowchart Figure 1 one or more flows and / or blocks Figure 1 an apparatus with a means for performing the functions specified in the flowchart

[0042] The above description is only the preferred embodiments of the present application, and the protection scope of the present application is not limited to the above-described embodiments. Any technical solutions falling within the concept of the present application shall be considered as falling within the protection scope of the present application. It should be noted that, for those skilled in the art, some improvements and refinements without departing from the principles of the present application shall also be considered as falling within the protection scope of the present application.

Claims

1. A method for detecting and locating broadband forced oscillations in a power grid, characterized in that, The process includes the following steps: acquiring an oscillation data sequence of the power grid and a power system topology map, wherein the oscillation data sequence includes the voltage, frequency, and rate of change of the power grid, and the nodes in the power system topology map are generators or loads in the power grid, the edges are lines, and the oscillation characteristics of the nodes include the voltage, frequency, and rate of change of the nodes. The oscillation data sequence of the power grid and the power system topology map are input into a pre-trained multi-task graph sequence network to obtain oscillation source localization and detection results, including: S101 extracts key features from the oscillating data sequence through convolutional and pooling layers. ; S102, key features Input can be embedded into a sequence autoregressive module, the embedded sequence autoregressive module through Stacked ARMA(1,0) filters for key features Perform embedded feature filtering and... The final output feature is obtained by summing the responses of the stacked ARMA(1,0) filters. ; S103 will output features The power system topology graph is used as input to the multi-task graph sequence network. Information is transmitted through the multi-task graph sequence network, and the node characteristics of each node are obtained through the gated cyclic unit (GRU). ; S104, The node characteristics of each node. Input graph-level detection branch and node-level detection branch respectively. Use graph-level detection branch to classify the event type of the oscillation source and use node-level detection branch to locate the oscillation source.

2. The method for detecting and locating broadband forced oscillations in power grids according to claim 1, characterized in that, The process of acquiring the oscillation data sequence and power system topology map of the power grid includes acquiring the voltage time series of the power grid, filtering the voltage time series to eliminate the DC component to extract the frequency of the power grid, and calculating the frequency change rate based on the frequency of the power grid and the following formula: ； in, and Sampling points and sampling points frequency, The sampling interval is... The voltage sampling frequency is used, and the obtained voltage, frequency, and rate of change of the power grid are normalized to form an oscillation data sequence.

3. The method for detecting and locating broadband forced oscillations in power grids according to claim 1, characterized in that, When acquiring the oscillation data sequence of the power grid and the power system topology map, the functional expression of the obtained power system topology map is: ； in, This is a power system topology diagram. For a set of nodes, It is an unordered set of edges. The oscillation characteristics of a node include its voltage, frequency, and rate of change of frequency, and the unordered edge set. Through the adjacency matrix This represents the line connection relationship between different nodes. The node and the first When nodes are directly connected by a line, the adjacency matrix The Middle Line number Column elements ;otherwise , indicating the first The node and the first The nodes have no direct connection.

4. The method for detecting and locating broadband forced oscillations in power grids according to claim 1, characterized in that, In step S101, key features are extracted from the oscillating data sequence through convolutional and pooling layers. The function expression for the convolution operation of the convolutional layer is: ； In the above formula, This is the output of the convolution operation. The number of types of oscillating data. for The first moment The input signal for the oscillation data; convolution kernel The offset time that is applied, and The first moment Input signal of oscillation data Time axis alignment; convolution kernel For the first Such oscillation data in The convolution kernel corresponding to each time step.

5. The method for detecting and locating broadband forced oscillations in power grids according to claim 1, characterized in that, In step S102, for The final output feature is obtained by summing the responses of the stacked ARMA(1,0) filters. The function expression is: ； in, Let be the number of stacking levels of the ARMA(1,0) filter. For activation function, For the first The output characteristics of an ARMA(1,0) filter. For the first Input characteristics of an ARMA(1,0) filter. and For the first Trainable weight parameters of an ARMA(1,0) filter. As a key feature, The normalized Laplace matrix is ​​symmetric; the ARMA(1,0) filter is approximated using a first-order recursive method as shown in the following equation: ； ； in, and These represent the output characteristics and the oscillation characteristics of the input nodes of the ARMA(1,0) filter, respectively. and For coefficients, For symmetric normalized Laplace matrix The intermediate coefficients related to the eigenvalues, and These are the symmetric normalized Laplace matrices. Maximum and minimum eigenvalues It is an identity matrix.

6. The method for detecting and locating broadband forced oscillations in power grids according to claim 1, characterized in that, In step S103, the output features will be... The power system topology graph is used as input to the multi-task graph sequence network. Information is transmitted through the multi-task graph sequence network, and the node characteristics of each node are obtained through the gated cyclic unit (GRU). At that time, the functional expression for information transmission in the multi-task graph sequence network is: ； in, and The first The output characteristics and the oscillation characteristics of the input nodes during the next transmission. For activation function, Adjacency matrix and identity matrix The sum of adjacency matrices To represent the unordered set of edges in a power system topology graph The adjacency matrix, for The degree matrix of the diagonal nodes, and The first The node feature matrix and trainable parameter matrix are obtained during each transmission, and the node features of each node are obtained through a gated recurrent unit (GRU). The function expression is: ； ； in, For the softmax function, The normalized adjacency matrix, For activation function, The output of the gated recurrent unit (GRU) layer. and is a trainable parameter matrix.

7. The method for detecting and locating broadband forced oscillations in power grids according to claim 1, characterized in that, The loss function used during training of the multi-task graph sequence network is expressed as follows: ； ； ； ； in, This is the loss function used during training of the multi-task graph sequence network. This is the location detection result of the oscillation source in the node-level detection branch. These are the model parameters for a multi-task graph sequence network. and These are the weight hyperparameters for the node-level and graph-level detection branches learned by the softplus function, respectively. To consider the weighted binary cross-entropy loss function that takes into account node mask loss, The cross-entropy loss is used for graph classification tasks in the graph-level detection branch. For the first The mask of each node, which serves as a flag indicating whether a node is valid. For the first The weight of each node, This represents the total number of measurement nodes. This represents the number of generator nodes. Let cross-entropy be the loss function. and These are the detection results and ground truth values ​​for the graph classification task performed by the graph-level detection branch.

8. A power grid synchronous broadband forced oscillation detection and positioning system, comprising a microprocessor and a memory interconnected, characterized in that, The microprocessor is programmed or configured to execute the power grid synchronization broadband forced oscillation detection and location method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute the power grid synchronization broadband forced oscillation detection and location method according to any one of claims 1 to 7 via a processor.

10. A computer program product, comprising a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute the power grid synchronization broadband forced oscillation detection and location method according to any one of claims 1 to 7 via a processor.

Images