Power grid broadband oscillation tracing method and system based on modal dynamic modulation graph network

Abstract

The invention discloses a power grid broadband oscillation tracing method and system based on a modal dynamic modulation graph network, and the method comprises the steps: inputting an oscillation data sequence of a power grid and a power system graph into the modal dynamic modulation graph network to obtain an oscillation source positioning result based on the power system graph; the processing of each stage of modal dynamic modulation graph module in the modal dynamic modulation graph network comprises the following steps of: modulating an oscillation data sequence through a modal modulator and then performing characteristic modal decomposition; key features are extracted through a convolution layer and a pooling layer; dynamic modulation is carried out based on a Prony dynamic modulator, and feature blocks are segmented; key features are extracted through a convolution layer and a pooling layer; extracting node features through a graph network; and realizing power grid broadband oscillation traceability by using a classifier according to node features. 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 invention relates to a broadband oscillation source locating technology in the field of electric power systems, and in particular to a method and system for tracing broadband oscillations of a power grid based on a modal dynamic modulation graph network. Background Art

[0002] With the high proportion of power electronic equipment and distributed energy penetration, the low-frequency oscillations observed in traditional power systems have gradually turned to broadband oscillations. Accurately locating these oscillation sources is of great significance for ensuring the stability and safety of power grid operation. However, broadband oscillations often have regional, highly random and multi-source characteristics, and the power grid acquisition information also contains a large amount of redundant information, which greatly increases the difficulty of accurately locating broadband oscillation sources. Existing signal processing methods such as continuous wavelet transform and fast Fourier transform are not suitable for non-stationary signals. They often have problems such as modal aliasing and slow calculation speed, and cannot extract oscillation components from the acquired information in a timely and accurate manner. In terms of oscillation source location methods, the current mainstream location method involves energy flow analysis. However, this method faces many challenges such as system structure, measurement resolution and noise interference. The high-resolution data collection capability of the waveform measurement unit provides potential for broadband oscillation source location. However, the introduction of high-frequency data analysis and the dynamic characteristics of broadband oscillation sources make the application of this method more complicated. Inspired by graph neural networks, methods based on graph neural networks can be effectively used for fault location prediction. Nevertheless, the above methods mainly focus on low-frequency oscillations or major fault monitoring, and still ignore the time-varying and broadband characteristics of oscillations. Summary of the invention

[0003] Technical problem to be solved by the present invention: In view of the above-mentioned problems in the prior art, a method and system for tracing the source of broadband oscillations in a power grid based on a modal dynamic modulation diagram network is provided. The present invention aims to reduce the interference of other information on broadband oscillation information, dynamically analyze data from two dimensions of time and space, and quickly and accurately locate the source of broadband oscillations.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for tracing the source of broadband oscillations of a power grid based on a modal dynamic modulation graph network comprises the following steps: obtaining an oscillation data sequence and a power system diagram of a power grid, wherein nodes in the power system diagram are generators or loads in the power grid and edges are lines; inputting the oscillation data sequence and the power system diagram of the power grid into the modal dynamic modulation graph network to obtain an oscillation source positioning result based on the power system diagram, wherein the modal dynamic modulation graph network comprises a multi-level modal dynamic modulation graph module, and the modal dynamic modulation graph module processes the input oscillation data sequence and the power system diagram of the power grid, comprising: S1, modulating the oscillation data sequence through a modal modulator and then performing characteristic mode decomposition to remove redundant and mixed mode information; S2, extract key features from the oscillation data after removing redundant and mixed modal information through convolution layers and pooling layers; S3, dynamically modulate the key features of the broadband oscillation information based on the Prony dynamic modulator to calculate the broadband oscillation frequency and determine the frequency window size, and divide the broadband oscillation information into feature blocks according to the frequency window size; S4, extract key features from the dynamically modulated feature blocks through convolution layers and pooling layers; S5, take the key features of the feature blocks and the power system diagram as inputs of the graph network, and transfer information through the graph network to obtain the node features of each node; S6, use the classifier to realize oscillation tracing according to the node features of each node finally output by the graph network.

[0005] Optionally, the oscillation data in the oscillation data sequence includes voltage ,frequency and the frequency change rate RoCoF, the voltage ,frequency The interval scaled by normalization The calculation function expression of the frequency change rate RoCoF is: , In the above formula, is the frequency change rate RoCoF at time t, and are the normalized frequencies at time t+1 and time t respectively , is the time interval; the functional expression of the power system diagram is ,in is a node set, is the edge set, is the node characteristic, and the node characteristic includes the voltage of the node ,frequency and the frequency change rate RoCoF, the voltage ,frequency The interval scaled by normalization In the edge set is encoded as an adjacency matrix , is the number of nodes, the adjacency matrix Any of Line Elements of a column , if the node and Between is an edge set The elements in ,otherwise .

[0006] Optionally, in step S1, when the oscillation data sequence is modulated by a modal modulator and then subjected to characteristic modal decomposition to remove redundant and mixed modal information, the function expression of the input signal used by the modal modulator is: , In the above formula, is the input signal used by the modal modulator, is the number of internal periodic oscillation control signal components, is the amplitude of the i-th internal periodic oscillation control signal component, For the A composite signal of the internal periodic oscillation control signal components, For time, For the The index of the internal periodic oscillation control signal component, is the time interval between adjacent disturbances of the internal periodic oscillation; For the An offset parameter of an internal periodic oscillation control signal component, used to simulate the irregular characteristics of the oscillation component; is the number of external random disturbance signal components, For the The amplitude of the external random disturbance signal component, For the A composite signal of external random disturbance signal components, For the The index of the external random disturbance signal component, is the time interval between adjacent disturbances of external random disturbances, is the number of harmonic interference signal components, For the The amplitude of the harmonic interference signal component, For the The frequency of the harmonic interference signal component, For the The phase of the harmonic interference signal component, is noise; the composite signal is a signal composed of oscillation and redundant information, and the function expression of the composite signal is: , , , , , In the above formula, is the output signal of the modal modulator, is the number of modes, For the The amplitude of the first mode, For the The damping factor of the first mode, For the The angular frequency of the order mode, is an imaginary unit, For time, For the The eigenvalues ​​of the order modes, and is a real number; and in step S1, when the oscillation data sequence is modulated by the modal modulator and then the characteristic modal decomposition is performed to remove redundant and mixed modal information, the characteristic modal decomposition to remove redundant and mixed modal information refers to inputting the input signal of the modal modulator into the adaptive finite impulse response filter FIR for filtering to achieve the removal of redundant and mixed modal information.

[0007] Optionally, when extracting key features through the convolution layer and the pooling layer, the function expression of the convolution operation performed by the convolution layer is: , In the above formula, is the output of the convolution operation, is the number of types of oscillatory data, for The moment The input signal of the oscillating data is is the convolution kernel The offset time is Align the time axis, For the Oscillation data in The convolution kernel corresponding to the moment.

[0008] Optionally, in step S3, when the key features of the broadband oscillation information are dynamically modulated based on the Prony dynamic modulator to calculate the broadband oscillation frequency and determine the frequency window size, the function expression for determining the frequency window size is: , In the above formula, is the frequency window size, is the total time step of the modulator output timing signal, corresponding to the data points in the discrete time series, the number is the angular frequency corresponding to the modulator output timing signal, The frequency of the modulator output timing signal.

[0009] Optionally, in step S5, the key features of the feature block and the power system diagram are used as inputs of the graph network, and information is transmitted through the graph network to obtain node features of each node, including: S5.1, the key features of the feature block and the power system diagram are used as the input of the graph network, and information is transmitted through the graph network to obtain the node features of each node, and the function expression of the graph network for information transmission is: , In the above formula, and They are the first and The output of the layer, is the activation function, the matrix ,matrix ,in Edge Set The encoded adjacency matrix is is the identity matrix, For the matrix The upper diagonal matrix of ; S5.2, the original input of the graph network is superimposed on the output of the last layer of the graph network through the residual block according to the following formula to generate the final output of the graph network: , In the above formula, is the final output of the graph network, is the output of the last layer of the graph network, It is the information passing operation of the last layer of the graph network; S5.3, the final output of the graph network is used to obtain the node features of each node using a gated recurrent unit GRU, and the function expression of the gated recurrent unit GRU is: , In the above formula, and Respectively Step and The hidden state of the step, For the Step update door, For the The candidate hidden state of the step, Represents element-wise multiplication.

[0010] Optionally, in step S6, when a classifier is used to realize oscillation tracing according to the node features of each node finally output by the graph network, the classifier used is a multi-layer perceptron, and the multi-layer perceptron introduces a class weight parameter shown in the following formula so that the weight of the positive sample is inversely proportional to the number of the positive sample to balance the training loss: , In the above formula, is the class weight parameter, is the number of positive samples.

[0011] In addition, the present invention also provides a power grid broadband oscillation tracing system based on a modal dynamic modulation graph network, comprising an interconnected microprocessor and a memory, wherein the microprocessor is programmed or configured to execute the power grid broadband oscillation tracing method based on a modal dynamic modulation graph network.

[0012] In addition, the present invention also provides a computer-readable storage medium, which stores a computer program or instruction, and the computer program or instruction is programmed or configured to execute the power grid broadband oscillation tracing method based on the modal dynamic modulation diagram network through a processor.

[0013] In addition, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the power grid broadband oscillation tracing method based on the modal dynamic modulation diagram network through a processor.

[0014] Compared with the prior art, the present invention mainly has the following advantages: the method of the present invention can fully capture the time and space information of the electrical parameters of the power grid nodes, dynamically analyze and segment the data within different broadband oscillation ranges, and through the constructed modal dynamic modulation graph network, it can dynamically and quickly and accurately locate the broadband oscillation source with finer granularity, thereby effectively reducing the interference of other information on the broadband oscillation information, and quickly and accurately locating the broadband oscillation source. It has important engineering practice significance and solves the problem of broadband oscillation positioning of the power grid under the new power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the basic flow of the method of the embodiment of the present invention.

[0016] Figure 2 Schematic diagram of the network structure of the modal dynamic modulation graph network in an embodiment of the present invention.

[0017] Figure 3It is the original frequency data of the generator based on the IEEE 9-node system in the embodiment of the present invention.

[0018] Figure 4 It is the frequency data after normalization processing of the generator based on the IEEE 9-bus system in the embodiment of the present invention.

[0019] Figure 5 It is a schematic diagram of the oscillation positioning result in the embodiment of the present invention.

[0020] Figure 6 It is the accuracy evaluation result of each power system model component in the embodiment of the present invention.

[0021] Figure 7 The figure is a comparison of the running time of five different algorithms based on the IEEE 9-node system in the embodiment of the present invention. DETAILED DESCRIPTION

[0022] The method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation graph network of the present invention aims to make full use of characteristic mode decomposition and window dynamic modulation of a Prony modulator, effectively reduce the interference of other information on broadband oscillation information, dynamically analyze data from two dimensions of time and space, and quickly and accurately locate the broadband oscillation source. In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0023] like Figure 1 and Figure 2As shown, this embodiment provides a method for tracing the source of broadband oscillations in a power grid based on a modal dynamic modulation graph network, comprising the following steps: obtaining an oscillation data sequence and a power system diagram of the power grid, wherein the nodes in the power system diagram are generators or loads in the power grid and the edges are lines; inputting the oscillation data sequence and the power system diagram of the power grid into the modal dynamic modulation graph network to obtain an oscillation source positioning result based on the power system diagram, wherein the modal dynamic modulation graph network includes a multi-level modal dynamic modulation graph module, and the processing of the input oscillation data sequence and the power system diagram of the power grid by the modal dynamic modulation graph module includes: S1, modulating the oscillation data sequence through a modal modulator and then performing characteristic mode decomposition to remove redundancy and mixing modal information; S2, extract key features from the oscillation data after removing redundant and mixed modal information through convolution layers and pooling layers; S3, dynamically modulate the key features of the broadband oscillation information based on the Prony dynamic modulator to calculate the broadband oscillation frequency and determine the frequency window size, and divide the broadband oscillation information into feature blocks according to the frequency window size; S4, extract key features from the dynamically modulated feature blocks through convolution layers and pooling layers; S5, use the key features of the feature blocks and the power system diagram as inputs to the graph network, and transfer information through the graph network to obtain the node features of each node; S6, use the classifier to realize oscillation tracing according to the node features of each node finally output by the graph network.

[0024] When acquiring the oscillation data sequence of the power grid, it includes collecting the voltage of the power grid And count as time series The collected voltage data contains broadband oscillation information and a large amount of redundant information. Combined with the data set information, the original data is DC filtered to extract the frequency , and the oscillation characteristics (including voltage and frequency As an optional implementation, in order to remove the long-term trend in the original data, a high-pass Butterworth filter is used to perform DC filtering on the original data, extract and highlight the frequency information of the broadband oscillation, and convert the oscillation characteristics (including voltage and frequency ) is normalized, Figure 3 is the original frequency data of the generator based on the IEEE 9-bus system in this embodiment, Figure 4 is the frequency data of the generator after normalization based on the IEEE 9-bus system in this embodiment, Figure 3 The frequency of each generator is almost the same, and it is difficult to distinguish slight changes; however, Figure 4 As shown, by filtering, the oscillation waveform becomes distinguishable, providing stronger node features for broadband oscillation localization.

[0025] To enhance the feature set and capture the frequency variation of voltage data, the rate of change of frequency (RoCoF) is introduced as an additional feature. Specifically, the oscillation data in the oscillation data sequence in this embodiment includes voltage ,frequency and the frequency change rate RoCoF, the voltage ,frequency The interval scaled by normalization The calculation function expression of the frequency change rate RoCoF is: , In the above formula, is the frequency change rate RoCoF at time t, and are the normalized frequencies at time t+1 and time t respectively , is the time interval; the functional expression of the power system diagram is ,in is a set of nodes, which are generators or loads in a predefined power system topology. is the edge set, corresponding to the busbars connecting these nodes, is the node characteristic, and the node characteristic includes the voltage of the node ,frequency and the frequency change rate RoCoF, the voltage ,frequency The interval scaled by normalization In the edge set is encoded as an adjacency matrix , is the number of nodes, the adjacency matrix Any of Line Elements of a column , if the node and Between is an edge set The elements in , that is, it is an edge of the power system topology; otherwise , that is, it is not an edge of the power system topology.

[0026] In this embodiment, the oscillation data sequence of the power grid and the power system diagram are input into the modal dynamic modulation graph network to obtain the oscillation source positioning result based on the power system diagram. In view of the rich and complex information in the collected data, an embeddable modal dynamic modulation graph network is constructed, and automatic feature learning is achieved through end-to-end training, multi-modal adaptive decomposition, and dynamic adjustment of window lengths in different frequency bands. With stronger adaptability and scalability, the multi-modal information in the collected data is decomposed, the interference of redundant information is reduced, the key features of broadband oscillation information are extracted, and the dynamic scaling of the frequency window size is achieved, so that the broadband oscillation source positioning task can be completed more accurately and efficiently.

[0027] In step S1 of this embodiment, when the oscillation data sequence is modulated by a modal modulator and then subjected to characteristic modal decomposition to remove redundant and mixed modal information, the function expression of the input signal used by the modal modulator is: , In the above formula, is the input signal used by the modal modulator, is the number of internal periodic oscillation control signal components, is the amplitude of the i-th internal periodic oscillation control signal component, For the A composite signal of the internal periodic oscillation control signal components, For time, For the The index of the internal periodic oscillation control signal component, is the time interval between adjacent disturbances of the internal periodic oscillation; For the An offset parameter of an internal periodic oscillation control signal component, used to simulate the irregular characteristics of the oscillation component; is the number of external random disturbance signal components, For the The amplitude of the external random disturbance signal component, For the A composite signal of external random disturbance signal components, For the The index of the external random disturbance signal component, is the time interval between adjacent disturbances of external random disturbances, is the number of harmonic interference signal components, For the The amplitude of the harmonic interference signal component, For the The frequency of the harmonic interference signal component, For the The phase of the harmonic interference signal component, The right side of the function expression of the input signal used by the above modal modulator consists of four parts. The first part represents the periodic oscillation inside the power system, such as the periodic fluctuation of system frequency and voltage caused by overreaction of the control system, load change of the unit or mechanical failure. The offset parameter It is set to 1%~2% of the fluctuation period; the second part represents the random disturbance from the outside in the power system, such as the impact of external electromagnetic interference on the measuring instrument or control system; the third part represents the harmonic interference caused by nonlinear elements in the power system such as transformers and rectifiers; the fourth part is noise. The composite signal is a signal composed of oscillation and redundant information, and the function expression is: , , , , , In the above formula, is the output signal of the modal modulator, is the number of modes, For the The amplitude of the first mode, For the The damping factor of the first mode, For the The angular frequency of the order mode, is an imaginary unit, For time, For the The eigenvalues ​​of the order modes, and is a real number.

[0028] Characteristic mode decomposition can extract decomposition modes through adaptive finite impulse response (FIR) filter. Since adaptive finite impulse response (FIR) filter is not limited by filter shape, bandwidth and center frequency, redundant and mixed modes can be removed in the mode selection process. After iteration, the set target can be continuously approached to obtain the required filtered signal, making the mode decomposition more thorough. Therefore, in step S1 of this embodiment, when the oscillation data sequence is modulated by the mode modulator and then the characteristic mode decomposition is performed to remove redundant and mixed mode information, the characteristic mode decomposition to remove redundant and mixed mode information refers to inputting the input signal of the mode modulator into the adaptive finite impulse response filter FIR for filtering to achieve the removal of redundant and mixed mode information. The output signal after characteristic mode decomposition is still a time series data containing voltage, frequency, and frequency change rate, but the output at this time only contains specific modes, which realizes the decomposition of mixed modes and the elimination of redundant modes in the collected data.

[0029] When extracting key features through convolutional layers and pooling layers, the function expression of the convolution operation of the convolutional layer is: , in, After the convolution operation The output signal at the time, , , respectively The convolution kernel of voltage, frequency and frequency change rate RoCoF at the moment, for The voltage at the moment, for The frequency change rate RoCoF at the moment; Time index, is the index of the convolution kernel, that is, the process of translating the input signal. Extending to multi-channel convolution, the function expression of the convolution layer for convolution operation is: , In the above formula, is the output of the convolution operation, is the number of types of oscillatory data, for The moment The input signal of the oscillating data is is the convolution kernel The offset time is Align the time axis, For the Oscillation data in The convolution kernel corresponding to the moment. The convolution pooling layer extracts the key features of the input voltage, frequency, and frequency change rate, and performs weighted summation and dimensionality reduction to improve the computational efficiency of the model. The output at this time is no longer a signal of the original granularity, but it still contains the time series data of the key features of voltage, frequency, and frequency change rate, with sufficient oscillation information to ensure the subsequent Prony dynamic modulation processing of the oscillation information.

[0030] The results of the convolution and pooling operations are input to a Prony-based dynamic modulator. The Prony algorithm is suitable for identifying oscillation modes, attenuation rates, and frequency components, and is widely used in signal processing in power systems. The oscillation modes in the broadband oscillation information after modal modulation are clearer. The output results after the aforementioned modal modulation are used to analyze and calculate the frequencies of these oscillation modes. Frequency windows of different sizes are divided for oscillation modes of different frequencies, and each oscillation mode is analyzed with an appropriate granularity to better adapt to the characteristics of different modes in broadband oscillations, improve frequency resolution, and thus more effectively identify and locate broadband oscillation sources. In step S3 of this embodiment, when the key features of the broadband oscillation information are dynamically modulated based on the Prony dynamic modulator to calculate the broadband oscillation frequency and determine the frequency window size, the function expression for determining the frequency window size is: , In the above formula, is the frequency window size, is the total time step of the modulator output timing signal, corresponding to the data points in the discrete time series, is the angular frequency corresponding to the modulator output timing signal, is the frequency of the modulator output timing signal. Then, the dynamic modulator The input time series Split into dynamic blocks , where each block contains The dynamic modulator calculates the broadband oscillation frequency, determines the frequency window size, and divides the data into manageable segments. This segmentation enables the graph convolutional neural network (GCN) and gated recurrent unit (GRU) to adjust the data analysis granularity of broadband oscillations in the time dimension, enabling the model to effectively solve the task of locating the source of broadband oscillations.

[0031] The modal dynamic modulation graph network includes a multi-level modal dynamic modulation graph module, through which the fused modal decomposition and the modal dynamic modulator are superimposed in multiple layers, and the graph topology information is fused to form a modal dynamic modulation graph network, which aggregates the spatial dependencies and interactions within the power grid. In step S5 of this embodiment, the key features of the feature block and the power system diagram are used as inputs of the graph network, and information is transmitted through the graph network to obtain the node features of each node, including: S5.1, the key features of the feature block and the power system diagram are used as the input of the graph network, and information is transmitted through the graph network to obtain the node features of each node, and the function expression of the graph network for information transmission is: , In the above formula, and They are the first and The output of the layer, is the activation function, the matrix ,matrix ,in Edge Set The encoded adjacency matrix is is the identity matrix, For the matrix The upper diagonal matrix of ; S5.2, the original input of the graph network is superimposed on the output of the last layer of the graph network through the residual block according to the following formula to generate the final output of the graph network: , In the above formula, is the final output of the graph network, is the output of the last layer of the graph network, It is the information passing operation of the last layer of the graph network; S5.3, the final output of the graph network is used to obtain the node features of each node using the gated recurrent unit GRU, and the final output of the graph network is As input, the dynamic modulator dynamically adjusts the frequency window size w, allowing the gated recurrent unit GRU to divide the data into smaller blocks and process the data at a finer granularity, so that the gated recurrent unit GRU can effectively capture the time dependency and mode in each block, and learn from the sequential characteristics of the time series to improve its performance in processing broadband oscillations. In this embodiment, the function expression of the gated recurrent unit GRU is: , In the above formula, and Respectively Step and The hidden state of the step, For the Step update door, For the The candidate hidden state of the step, This process enables GRU to exploit the spatial relationships identified by GNN and the temporal dynamics inherent in time series data, thereby improving the overall modeling performance. After finally obtaining the node features of each node, it is superimposed on the power system diagram to obtain the result as follows: Figure 5 shown.

[0032] In step S6, when a classifier is used to realize oscillation tracing according to the node features of each node finally output by the graph network, the adopted classifier can be selected according to actual needs. For example, as an optional implementation, the classifier adopted in this embodiment is a multi-layer perceptron (MLP), and the multi-layer perceptron introduces a class weight parameter shown in the following formula so that the weight of the positive sample is inversely proportional to its number to balance the training loss: , In the above formula, is the class weight parameter, is the number of positive samples. By setting the class weight parameter , which makes the weight of positive samples inversely proportional to their number. When the number of positive samples is small (i.e. smaller), class weight parameter The larger the value of is, the higher the weight is given to positive samples. When the number of positive samples is large, the weight value is small, making the impact of positive and negative samples more balanced. In multi-layer perceptron (MLP), the problem of data imbalance may have a significant impact on the training and performance of the model. The class weight parameter is introduced These problems can be effectively alleviated. This setting can reduce the impact of data imbalance problems on the model, effectively utilize the spatial information from the graph network GCN and the temporal insights captured by the gated recurrent unit GRU, and produce more robust broadband oscillation source positioning results. In this embodiment, the graph network uses the voltage difference and frequency characteristics between the nodes of the power system to automatically learn, where the input time series voltage data is divided into feature blocks with frequency windows of different sizes after modal dynamic modulation, which can improve the positioning accuracy of the graph network. These data correspond to the nodes to which they belong at the same time, and then the multi-layer perceptron (MLP) is used to classify and determine whether nodes 1, 2, 3, ..., n are oscillation sources, and the final output is the node number corresponding to the oscillation source.

[0033] In order to better understand the contribution of each component in the broadband oscillation tracing method based on the modal dynamic modulation graph network in this embodiment, an ablation experiment is conducted on this model to add these components incrementally to illustrate their respective contributions to the model performance. The accuracy evaluation results of the four power system model components are shown in the figure. Figure 6 As shown, "FMD" represents the modal modulator, "Prony" represents the Prony dynamic modulator, "GCN" represents the link in step S5.1 that uses the graph network for information transmission, "Residual" represents the residual block used in step S5.2, and "GRU" represents the gated recurrent unit GRU used in step S5.3. Figure 6From the ablation experiment results, it can be seen that the complete solution consisting of "FMD+Prony+GCN+Residual+GRU" (the method in this embodiment) has an accuracy of 91.3% in the IEEE 9-node system, and each functional component has played a certain effect.

[0034] In order to verify the performance superiority of the power grid broadband oscillation source tracing method based on the modal dynamic modulation graph network in this embodiment, this embodiment selects 8 latest existing methods (including 4 traditional models and 4 machine learning models) based on the IEEE 9-node system to conduct comparative experiments with the method proposed in this embodiment. The data results are shown in Table 1. The machine learning model is compared again, with the single task running time as the measurement indicator. The comparison results are shown in Table 1. Figure 7 shown.

[0035] Table 1 Comparison of different existing methods based on IEEE 9-bus system

[0036] As shown in Table 1 and Figure 7 As shown in the figure, the accuracy, area under the curve (AUC), and F1 value of the modal dynamic modulation graph network proposed by the method of this embodiment are better than the models adopted by other methods. The positioning accuracy and precision in the IEEE 9-node system reach [25%, 38%] and [30%, 90%] respectively; and on a single task, the average running time is 10ms, which is better than the models adopted by other methods, showing its real-time positioning capability. In addition, the modal dynamic modulation graph network proposed by the method of this embodiment is further experimented based on the IEEE 9-node system, and the method is used to locate and analyze the oscillation conditions of different frequencies. Table 2 shows the experimental results of locating oscillation sources of different frequencies based on the IEEE 9-node system.

[0037] Table 2 Experimental results of locating different frequency oscillation sources based on IEEE 9-node system

[0038] As shown in Table 2, the modal dynamic modulation graph network proposed by the method of this embodiment is more effective and superior than the models of other methods in the broadband oscillation positioning task, achieving the most advanced performance.

[0039] The method for tracing the source of broadband oscillations in a power grid based on a modal dynamic modulation graph network in this embodiment can fully capture the temporal and spatial information of electrical parameters of power grid nodes, construct an adaptive scaling mechanism based on characteristic mode decomposition and Prony modulator, and realize dynamic scaling of the window size of key features of oscillation information, so as to effectively cope with oscillations in different frequency bands and multiple modes, and dynamically realize precise positioning of broadband oscillation sources with finer granularity; the modal dynamic modulator is an embeddable neural network layer, which is easy to call, plug and unplug and stack, and has strong portability. The method in this embodiment can effectively reduce the interference of other information on broadband oscillation information, effectively solve the problem of wide broadband range and difficult window selection, effectively solve the problem of locating multi-modal broadband oscillations, and realize fast and accurate positioning of broadband oscillation sources, which has important engineering practice significance.

[0040] In addition, this embodiment also provides a power grid broadband oscillation tracing system based on a modal dynamic modulation graph network, comprising an interconnected microprocessor and a memory, wherein the microprocessor is programmed or configured to execute the power grid broadband oscillation tracing method based on a modal dynamic modulation graph network.

[0041] In addition, this embodiment also provides a computer-readable storage medium, which stores a computer program or instruction, and the computer program or instruction is programmed or configured to execute the power grid broadband oscillation tracing method based on the modal dynamic modulation diagram network through a processor.

[0042] In addition, this embodiment also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the power grid broadband oscillation tracing method based on the modal dynamic modulation diagram network through a processor.

[0043] Those skilled in the art should understand that the technical solutions provided by the embodiments of the present application may be in the form of methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, 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 process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0044] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for tracing the source of broadband oscillations in a power grid based on a modal dynamic modulation graph network, characterized in that: The method comprises the following steps: obtaining an oscillation data sequence of a power grid and a power system diagram, wherein the nodes in the power system diagram are generators or loads in the power grid and the edges are lines; The oscillation data sequence of the power grid and the power system diagram are input into the modal dynamic modulation diagram network to obtain the oscillation source positioning result based on the power system diagram. The modal dynamic modulation diagram network includes a multi-level modal dynamic modulation diagram module. The modal dynamic modulation diagram module processes the input oscillation data sequence of the power grid and the power system diagram, including: S1, modulating the oscillation data sequence through a modal modulator and then performing characteristic mode decomposition to remove redundant and mixed mode information; S2, extract key features from the oscillation data after removing redundant and mixed modal information through convolution layers and pooling layers; S3, dynamically modulate the key features of the broadband oscillation information based on the Prony dynamic modulator to calculate the broadband oscillation frequency and determine the frequency window size, and divide the broadband oscillation information into feature blocks according to the frequency window size; S4, extract key features from the dynamically modulated feature blocks through convolution layers and pooling layers; S5, take the key features of the feature blocks and the power system diagram as inputs of the graph network, and transfer information through the graph network to obtain the node features of each node; S6, use the classifier to realize oscillation tracing according to the node features of each node finally output by the graph network.

2. The method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation graph network according to claim 1 is characterized in that: The oscillation data in the oscillation data sequence includes voltage ,frequency and the frequency change rate RoCoF, the voltage ,frequency The interval scaled by normalization The calculation function expression of the frequency change rate RoCoF is: ， In the above formula, is the frequency change rate RoCoF at time t, and are the normalized frequencies at time t+1 and time t respectively , is the time interval; the functional expression of the power system diagram is ,in is a node set, is the edge set, is the node characteristic, and the node characteristic includes the voltage of the node ,frequency and the frequency change rate RoCoF, the voltage ,frequency The interval scaled by normalization In the edge set is encoded as an adjacency matrix , is the number of nodes, the adjacency matrix Any of Line Elements of a column , if the node and Between is an edge set The elements in ,otherwise .

3. The method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation graph network according to claim 1 is characterized in that: In step S1, when the oscillation data sequence is modulated by a modal modulator and then subjected to characteristic modal decomposition to remove redundant and mixed modal information, the function expression of the input signal used by the modal modulator is: ， In the above formula, is the input signal used by the modal modulator, is the number of internal periodic oscillation control signal components, is the amplitude of the i-th internal periodic oscillation control signal component, For the A composite signal of the internal periodic oscillation control signal components, For time, For the The index of the internal periodic oscillation control signal component, is the time interval between adjacent disturbances of the internal periodic oscillation; For the An offset parameter of an internal periodic oscillation control signal component, used to simulate the irregular characteristics of the oscillation component; is the number of external random disturbance signal components, For the The amplitude of the external random disturbance signal component, For the A composite signal of external random disturbance signal components, For the The index of the external random disturbance signal component, is the time interval between adjacent disturbances of external random disturbances, is the number of harmonic interference signal components, For the The amplitude of the harmonic interference signal component, For the The frequency of the harmonic interference signal component, For the The phase of the harmonic interference signal component, is noise; the composite signal is a signal composed of oscillation and redundant information, and the function expression of the composite signal is: ， ， ， ， ， In the above formula, is the output signal of the modal modulator, is the number of modes, For the The amplitude of the first mode, For the The damping factor of the first mode, For the The angular frequency of the first mode, is an imaginary unit, For time, For the The eigenvalues ​​of the order modes, and is a real number; and in step S1, when the oscillation data sequence is modulated by the modal modulator and then the characteristic modal decomposition is performed to remove redundant and mixed modal information, the characteristic modal decomposition to remove redundant and mixed modal information refers to inputting the input signal of the modal modulator into the adaptive finite impulse response filter FIR for filtering to achieve the removal of redundant and mixed modal information.

4. The method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation graph network according to claim 1 is characterized in that: When extracting key features through the convolution layer and the pooling layer, the function expression of the convolution operation performed by the convolution layer is: ， In the above formula, is the output of the convolution operation, is the number of types of oscillatory data, for The moment The input signal of the oscillating data is is the convolution kernel The offset time is Align the time axis, For the Oscillation data in The convolution kernel corresponding to the moment.

5. The method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation graph network according to claim 1 is characterized in that: In step S3, when the key features of the broadband oscillation information are dynamically modulated based on the Prony dynamic modulator to calculate the broadband oscillation frequency and determine the frequency window size, the function expression for determining the frequency window size is: ， In the above formula, is the frequency window size, is the total time step of the modulator output timing signal, corresponding to the data points in the discrete time series, is the angular frequency corresponding to the modulator output timing signal, The frequency of the modulator output timing signal.

6. The method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation graph network according to claim 1, characterized in that: In step S5, the key features of the feature block and the power system diagram are used as inputs of the graph network, and information is transmitted through the graph network to obtain the node features of each node, including: S5.1, the key features of the feature block and the power system diagram are used as the input of the graph network, and information is transmitted through the graph network to obtain the node features of each node, and the function expression of the graph network for information transmission is: ， In the above formula, and They are the graph networks and The output of the layer, is the activation function, the matrix ,matrix ,in Edge Set The encoded adjacency matrix is is the identity matrix, For the matrix The upper diagonal matrix of ; S5.2, the original input of the graph network is superimposed on the output of the last layer of the graph network through the residual block according to the following formula to generate the final output of the graph network: ， In the above formula, is the final output of the graph network, is the output of the last layer of the graph network, It is the information passing operation of the last layer of the graph network; S5.3, the final output of the graph network is used to obtain the node features of each node using a gated recurrent unit GRU, and the function expression of the gated recurrent unit GRU is: ， In the above formula, and Respectively Step and The hidden state of the step, For the Step update door, For the The candidate hidden state of the step, Represents element-wise multiplication.

7. The method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation graph network according to claim 1, characterized in that: In step S6, when a classifier is used to realize oscillation tracing according to the node features of each node finally output by the graph network, the classifier used is a multi-layer perceptron, and the multi-layer perceptron introduces a class weight parameter shown in the following formula so that the weight of the positive sample is inversely proportional to the number of the positive sample to balance the training loss: ， In the above formula, is the class weight parameter, is the number of positive samples.

8. A power grid broadband oscillation source tracing system based on a modal dynamic modulation graph network, comprising a microprocessor and a memory connected to each other, characterized in that: The microprocessor is programmed or configured to execute the method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation diagram network as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program or instruction stored therein, characterized in that: The computer program or instruction is programmed or configured to execute the method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation diagram network as described in any one of claims 1 to 7 through a processor.

10. A computer program product comprising a computer program or instructions, characterized in that The computer program or instruction is programmed or configured to execute the method for tracing the source of broadband oscillation of a power grid based on a modal dynamic modulation diagram network as described in any one of claims 1 to 7 through a processor.

Images