Method and apparatus for generating a critical parameter prediction model, and method and apparatus for generating a stable critical parameter

Abstract

A method and apparatus for generating a key parameter prediction model and stable key parameters are disclosed. The method for generating the key parameter prediction model includes: obtaining stable key parameters and stable time series based on transiently stable file samples; training an initialized key parameter prediction model using the stable time series as input and the stable key parameters as labels to obtain the final key parameter prediction model. The method and apparatus provided by this invention enable rapid response to real-time faults and changes in power grid operation modes, and real-time modification of key parameters, providing dispatchers with the latest and most reliable stable key parameters.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and more specifically, to a method and apparatus for generating a key parameter prediction model and generating stable key parameters. Background Technology

[0002] With the development of the power system, from traditional system and operation objectives to today's energy forms of clean energy, new energy, and integrated energy layout, from hybrid systems and controls of mechanical, electromagnetic, electronic, and power electronic components, and from simple power quality objectives to new energy efficiency objectives of integrated energy, the requirements for power construction, operation, and management are becoming increasingly higher, requiring high-precision supervision, accurate regulation, and effective protection technologies and methods.

[0003] With increasingly complex power systems and ever-higher operational and management requirements, relying solely on specialized technical experts is insufficient to grasp the intricate characteristics of power system operation. While some intelligent stability assessment technologies for large power grids exist, they all suffer from various problems: they only include end-to-end algorithms, resulting in poor interpretability and significant application difficulties; training samples cannot fully reflect real-world data under extreme boundary conditions, leading to poor performance under such conditions; and they lack versatility, requiring different structures to be redesigned for different scenarios. Summary of the Invention

[0004] In view of this, the present invention proposes a method and apparatus for generating a key parameter prediction model and generating stable key parameters, aiming to solve the above problems.

[0005] In a first aspect, embodiments of the present invention provide a method for generating a key parameter prediction model, the method comprising: obtaining stable key parameters and stable time series based on transiently stable file samples; training an initialized key parameter prediction model using the stable time series as input and the stable key parameters as labels to obtain a final key parameter prediction model; wherein the key parameter prediction model includes an input layer, a sequence processing layer and a parameter output layer, wherein the sequence processing layer includes a two-layer LSTM model.

[0006] Furthermore, the step of obtaining stable key parameters and stable time series based on the transient stability file samples includes: generating samples in the stable boundary state in batches by dynamically modifying the fault settings in the transient stability file samples, obtaining stable key parameter indicators in the stable boundary state, and obtaining the power grid characterization at each time point based on the key features of the transient stability file samples, and selecting the power grid characterization in the neighborhood time before and after the fault occurs and before and after the fault is cleared to form a stable time series.

[0007] Furthermore, the step of dynamically modifying the fault settings in the transiently stable file samples to generate samples in batches at the stable boundary state and obtaining the stability key parameter indicators at the stable boundary state includes: changing the severity of the fault by adjusting the fault duration, and performing a binary search on the fault duration using a binary search method. Each time, the fault duration of the transiently stable file sample is modified to the current binary search value and a new stability judgment is performed to determine whether the current state is unstable, thereby obtaining samples at the stable boundary state, and obtaining the stability key parameter indicators based on the samples at the stable boundary state.

[0008] Furthermore, the process of obtaining the power grid characterization at each time step based on the key features of the transient stability file samples includes: extracting key information step by step based on the key features of the transient stability samples, refining the feature vector, and obtaining the power grid characterization that can represent the key information of the power grid stability state at each time step.

[0009] Furthermore, the step of extracting key information from each key feature of the transient stable sample, refining the feature vector, and obtaining a power grid representation that can represent the key information of the power grid stability at each time step includes: vectorizing each key feature of the power grid in the transient stable sample to obtain a feature representation; aggregating the feature representations of the same branch to obtain a branch representation; and aggregating the representations of all branches of the entire power grid to obtain a power grid representation.

[0010] Furthermore, the parameter output layer includes an attention network and multiple fully connected layers.

[0011] Secondly, embodiments of the present invention also provide a method for generating stable key parameters, wherein the stable key parameters are key parameters used for stability discrimination and control in a power system. The method includes: determining the fault occurrence time and fault clearing time based on the power grid characterization at various times of real-time measurement or imaging system and obtaining a stable time series; inputting the stable time series into a key parameter prediction model to obtain the prediction result of the stable key parameters, wherein the key parameter prediction model is obtained using the methods provided in the above embodiments.

[0012] Thirdly, embodiments of the present invention also provide an apparatus for generating a key parameter prediction model, the apparatus comprising: a processing unit for obtaining stable key parameters and a stable time series based on transiently stable file samples; and a training unit for training an initialized key parameter prediction model using the stable time series as input and the stable key parameters as labels to obtain a final key parameter prediction model; wherein the key parameter prediction model includes an input layer, a sequence processing layer, and a parameter output layer, wherein the sequence processing layer includes a two-layer LSTM model.

[0013] Furthermore, the processing unit is also used to: generate samples in a stable boundary state in batches by dynamically modifying the fault settings in the transient stability file samples, obtain the key stability parameters in the stable boundary state, and obtain the power grid characterization at each time based on the key features of the transient stability file samples, and select the power grid characterization in the neighborhood time before and after the fault occurs and before and after the fault is cleared to form a stable time series.

[0014] Furthermore, the step of dynamically modifying the fault settings in the transiently stable file samples to generate samples in batches at the stable boundary state and obtaining the stability key parameter indicators at the stable boundary state includes: changing the severity of the fault by adjusting the fault duration, and performing a binary search on the fault duration using a binary search method. Each time, the fault duration of the transiently stable file sample is modified to the current binary search value and a new stability judgment is performed to determine whether the current state is unstable, thereby obtaining samples at the stable boundary state, and obtaining the stability key parameter indicators based on the samples at the stable boundary state.

[0015] Furthermore, the process of obtaining the power grid characterization at each time step based on the key features of the transient stability file samples includes: extracting key information step by step based on the key features of the transient stability samples, refining the feature vector, and obtaining the power grid characterization that can represent the key information of the power grid stability state at each time step.

[0016] Furthermore, the step of extracting key information from each key feature of the transient stable sample, refining the feature vector, and obtaining a power grid representation that can represent the key information of the power grid stability at each time step includes: vectorizing each key feature of the power grid in the transient stable sample to obtain a feature representation; aggregating the feature representations of the same branch to obtain a branch representation; and aggregating the representations of all branches of the entire power grid to obtain a power grid representation.

[0017] Furthermore, the parameter output layer includes an attention network and multiple fully connected layers.

[0018] Fourthly, embodiments of the present invention also provide an apparatus for generating stable key parameters, wherein the stable key parameters are key parameters used for stability discrimination and control in a power system. The apparatus includes: an acquisition unit, used to determine the fault occurrence time and fault clearing time based on the power grid characterization at various times of real-time measurement or imaging system and acquire a stable time series; and a prediction unit, used to input the stable time series into a key parameter prediction model to obtain the prediction result of the stable key parameters, wherein the key parameter prediction model is obtained using the apparatus provided in the above embodiments.

[0019] Fifthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the methods provided in the above embodiments.

[0020] In a sixth aspect, embodiments of the present invention also provide an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the methods provided in the above embodiments.

[0021] The method and apparatus for generating a key parameter prediction model provided in this invention obtain stable key parameters and stable time series based on transient stable file samples, and use the stable time series as input and the stable key parameters as labels to train an initialized key parameter prediction model to obtain the final key parameter prediction model. This key parameter prediction model can quickly respond to real-time faults and changes in power grid operation mode and modify key parameters in real time, providing dispatchers with the latest and most reliable stable key parameters.

[0022] The method and apparatus for generating stable key parameters provided in this invention determine the fault occurrence time and fault clearing time based on the power grid characterization at various times using real-time measurement or imaging systems, obtain a stable time series, and input the stable time series into a key parameter prediction model to obtain the prediction results of stable key parameters. This enables rapid response to real-time faults and changes in power grid operation modes, and real-time modification of key parameters, providing dispatchers with the latest and most reliable stable key parameters. Furthermore, it provides an effective solution for ensuring the continuous, safe, and stable operation of my country's power grid, representing a significant improvement over the existing power grid operation status. Attached Figure Description

[0023] Figure 1 An exemplary flowchart of a method for generating a key parameter prediction model according to an embodiment of the present invention is shown;

[0024] Figure 2 A schematic diagram of a multi-level power grid representation according to an embodiment of the present invention is shown;

[0025] Figure 3 A schematic diagram of the structure of a key parameter prediction model according to an embodiment of the present invention is shown;

[0026] Figure 4 An exemplary flowchart of a method for generating stable key parameters according to an embodiment of the present invention is shown;

[0027] Figure 5 A schematic diagram of the structure of an apparatus for generating a key parameter prediction model according to an embodiment of the present invention is shown;

[0028] Figure 6 A schematic diagram of an apparatus for generating stable key parameters according to an embodiment of the present invention is shown. Detailed Implementation

[0029] Exemplary embodiments of the invention will now be described with reference to the accompanying drawings. However, the invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.

[0030] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.

[0031] Figure 1 An exemplary flowchart of a method for generating a key parameter prediction model according to an embodiment of the present invention is shown.

[0032] like Figure 1 As shown, the method includes:

[0033] Step S101: Based on the metastable file samples, obtain the key stable parameters and stable time series.

[0034] Further, step S101 includes:

[0035] By dynamically modifying the fault settings in the transient stability file samples, samples in the stable boundary state are generated in batches, and the key stability parameters under the stable boundary state are obtained. Based on the key features of the transient stability file samples, the power grid characterization at each time point is obtained, and the power grid characterizations in the neighborhood time before and after the fault occurs and before and after the fault is cleared are combined into a stable time series.

[0036] Furthermore, by dynamically modifying the fault settings in the transient stability file samples, samples in the stable boundary state are generated in batches, and the key stability parameters under the stable boundary state are obtained, including:

[0037] The severity of the fault is changed by adjusting the fault duration, and a binary search is used to search for the fault duration. Each time, the fault duration of the transiently stable file sample is modified to the current binary value and a new stability judgment is performed to determine whether it is currently unstable. Samples in the stable boundary state are obtained, and the key stability parameters are obtained based on the samples in the stable boundary state.

[0038] First, stable boundary samples are generated in batches from quasi-stable file samples. By modifying the content of the PSASP51 format file, the fault settings in the quasi-stable file samples, such as fault location and fault duration, are dynamically modified to generate samples in batches at the stable boundary state. The key parameters such as key thresholds and key coefficients of the key parameter prediction model at the stable boundary state are obtained, and these samples are organized into training samples.

[0039] The principle of generating samples in a stable boundary state is mainly to change the severity of the fault by adjusting the fault duration. Since the severity of the fault increases continuously with the increase of the fault duration, a binary search method can be used to perform a binary search on the fault duration. Each time, the fault duration of the sample is modified to the current binary value and the stability discrimination is run again to determine whether it is unstable. Finally, samples in a stable boundary state (currently stable, but will become unstable if the fault duration is increased a little more) are obtained, and the key stability parameters of the corresponding mechanism model in this state are obtained based on this state.

[0040] Furthermore, based on the key features of the transient stability file samples, the power grid characterization at each time point is obtained, including:

[0041] Based on the key features of transient stable samples, key information is extracted step by step, and feature vectors are refined to obtain a power grid representation that can represent the key information of the power grid stability at each time.

[0042] Furthermore, based on the key features of the transient stable samples, key information is extracted level by level, and the feature vectors are refined to obtain a power grid representation that can represent the key information of the power grid stability at each time point, including:

[0043] The key features of the power grid in the transient stable samples are vectorized to obtain feature representations;

[0044] The feature representations of the same branch are aggregated to obtain the branch representation;

[0045] The power grid characterization is obtained by aggregating the characterizations of all branches of the entire power grid.

[0046] Figure 2 A schematic diagram of a multi-level power grid representation according to an embodiment of the present invention is shown. Figure 2As shown, this embodiment of the invention uses a multi-level power grid representation structure to represent power grid information. The multi-level power grid representation employs a three-level representation method. The first level is a power grid characteristic-level representation, including voltage, frequency, power angle, etc. The second level is a branch-level representation, where each branch aggregates all its own and its related power grid characteristic quantities at both ends, merging to generate a branch-level representation. Subsequently, the information representations of multiple key branches are integrated to ultimately form the power grid representation. Specifically, the multi-level power grid representation is as follows:

[0047] Feature representation: The representation obtained by vectorizing key features of the power grid, such as voltage amplitude and voltage phase angle, represents the impact of a certain key feature at a certain moment;

[0048] Branch representation: A branch representation is formed by aggregating the feature representations of the same branch, representing the influence of the overall feature quantity of that branch at a certain moment;

[0049] Power grid characterization: The power grid characterization is formed by aggregating the characterizations of all key branches of the entire power grid, representing the impact of the overall characteristic quantity of the entire power grid at a certain moment.

[0050] Furthermore, power grid characteristics within the neighborhood before and after a fault occurs and before and after a fault is cleared are combined to form a stable time series, including:

[0051] The key node time series is used as the input of the key parameter prediction model. The key node time series consists of neighborhood sequences of multiple time nodes: first, the fault occurrence time and fault clearing time are determined, and then the power grid characterization data within Δt before and after the fault occurrence and within Δt before and after the fault clearing are extracted and integrated to form a new time series.

[0052] Step S102: Using stable time series as input and stable key parameters as labels, train the initial key parameter prediction model to obtain the final key parameter prediction model;

[0053] The key parameter prediction model includes an input layer, a sequence processing layer, and a parameter output layer. The sequence processing layer includes a two-layer LSTM model.

[0054] Furthermore, the parameter output layer includes an attention network and multiple fully connected layers.

[0055] Figure 3 A schematic diagram of the structure of a key parameter prediction model according to an embodiment of the present invention is shown. Figure 3As shown, this embodiment of the invention employs an improved LSTM as the key parameter time series long- and short-term information capture module for the parameter prediction model. LSTM is a deep learning model used to process sequential data, which can effectively capture both long-term time series feature correlations and short-term neighborhood feature correlations simultaneously. A two-layer LSTM model is used to process the previously generated power grid representation time series. Its hidden layer effectively captures long-term data correlations in the time series, while its output layer captures short-term neighborhood data correlations, ultimately feeding back to the next step of the model for key feature generation. This embodiment of the invention uses an attention mechanism network plus a multi-layer fully connected network as the parameter generation module of the parameter prediction model: first, an attention mechanism network is used to capture the key information from the LSTM hidden and output layers; then, a multi-layer fully connected network is used to map the key information to stable key parameters in the output, ultimately completing the key parameter generation.

[0056] For training the key parameter prediction model, Adam optimization can be used with a loss function of MSE and an exponential decay of the learning rate of 0.001 until the model converges. The epoch with the best performance on the validation set is taken as the final model parameters.

[0057] The above embodiments obtain stable key parameters and stable time series based on transient stable file samples, and use the stable time series as input and the stable key parameters as labels to train an initial key parameter prediction model, thus obtaining the final key parameter prediction model. This key parameter prediction model can quickly respond to real-time faults and changes in power grid operation mode and modify key parameters in real time, providing dispatchers with the latest and most reliable stable key parameters.

[0058] Figure 4 An exemplary flowchart of a method for generating stable key parameters according to an embodiment of the present invention is shown.

[0059] like Figure 4 As shown, this stability key parameter is a crucial parameter used for stability determination and control in power systems. The method includes:

[0060] Step S401: Based on the power grid characterization at various times of the real-time measurement or imaging system, determine the fault occurrence time and the fault clearing time and obtain a stable time series;

[0061] Step S402: Input the stable time series into the key parameter prediction model to obtain the prediction results of the stable key parameters. The key parameter prediction model is obtained by the method of generating the key parameter prediction model provided in the above embodiments.

[0062] The above embodiments, by using power grid characterization at various times based on real-time measurement or imaging systems, determine the time of fault occurrence and fault clearing, obtain a stable time series, and input the stable time series into a key parameter prediction model to obtain the prediction results of stable key parameters. This enables rapid response to real-time faults and changes in power grid operation modes, and real-time modification of key parameters, providing dispatchers with the latest and most reliable stable key parameters. Furthermore, it provides an effective solution for ensuring the continuous, safe, and stable operation of my country's power grid, representing a significant improvement over the existing power grid operation status.

[0063] Figure 5 A schematic diagram of an apparatus for generating a key parameter prediction model according to an embodiment of the present invention is shown.

[0064] like Figure 5 As shown, the device includes:

[0065] Processing unit 501 is used to obtain stable key parameters and stable time series based on the metastable file samples;

[0066] Training unit 502 is used to train an initial key parameter prediction model using a stable time series as input and stable key parameters as labels, to obtain the final key parameter prediction model.

[0067] The key parameter prediction model includes an input layer, a sequence processing layer, and a parameter output layer. The sequence processing layer includes a two-layer LSTM model.

[0068] Furthermore, the processing unit 501 is also used for:

[0069] By dynamically modifying the fault settings in the transient stability file samples, samples in the stable boundary state are generated in batches, and the key stability parameters under the stable boundary state are obtained. Based on the key features of the transient stability file samples, the power grid characterization at each time point is obtained, and the power grid characterizations in the neighborhood time before and after the fault occurs and before and after the fault is cleared are combined into a stable time series.

[0070] Furthermore, by dynamically modifying the fault settings in the transient stability file samples, samples in the stable boundary state are generated in batches, and the key stability parameters under the stable boundary state are obtained, including:

[0071] The severity of the fault is changed by adjusting the fault duration, and a binary search is used to search for the fault duration. Each time, the fault duration of the transiently stable file sample is modified to the current binary value and a new stability judgment is performed to determine whether it is currently unstable. Samples in the stable boundary state are obtained, and the key stability parameters are obtained based on the samples in the stable boundary state.

[0072] Furthermore, based on the key features of the transient stability file samples, the power grid characterization at each time point is obtained, including:

[0073] Based on the key features of transient stable samples, key information is extracted step by step, and feature vectors are refined to obtain a power grid representation that can represent the key information of the power grid stability at each time.

[0074] Furthermore, based on the key features of the transient stable samples, key information is extracted level by level, and the feature vectors are refined to obtain a power grid representation that can represent the key information of the power grid stability at each time point, including:

[0075] The key features of the power grid in the transient stable samples are vectorized to obtain feature representations;

[0076] The feature representations of the same branch are aggregated to obtain the branch representation;

[0077] The power grid characterization is obtained by aggregating the characterizations of all branches of the entire power grid.

[0078] Furthermore, the parameter output layer includes an attention network and multiple fully connected layers.

[0079] The above embodiments obtain stable key parameters and stable time series based on transient stable file samples, and use the stable time series as input and the stable key parameters as labels to train an initial key parameter prediction model, thus obtaining the final key parameter prediction model. This key parameter prediction model can quickly respond to real-time faults and changes in power grid operation mode and modify key parameters in real time, providing dispatchers with the latest and most reliable stable key parameters.

[0080] Figure 6 A schematic diagram of an apparatus for generating stable key parameters according to an embodiment of the present invention is shown.

[0081] like Figure 6 As shown, this stability key parameter is a crucial parameter used for stability determination and control in a power system. The device includes:

[0082] The acquisition unit 601 is used to determine the fault occurrence time and fault clearing time based on the power grid characterization at various times of the real-time measurement or imaging system and to acquire a stable time series.

[0083] The prediction unit 602 is used to input a stable time series into a key parameter prediction model to obtain the prediction results of stable key parameters. The key parameter prediction model is obtained using the apparatus for generating key parameter prediction models provided in the above embodiments.

[0084] The above embodiments, by using power grid characterization at various times based on real-time measurement or imaging systems, determine the time of fault occurrence and fault clearing, obtain a stable time series, and input the stable time series into a key parameter prediction model to obtain the prediction results of stable key parameters. This enables rapid response to real-time faults and changes in power grid operation modes, and real-time modification of key parameters, providing dispatchers with the latest and most reliable stable key parameters. Furthermore, it provides an effective solution for ensuring the continuous, safe, and stable operation of my country's power grid, representing a significant improvement over the existing power grid operation status.

[0085] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0086] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method for generating a key parameter prediction model or the method for generating stable key parameters provided in the above embodiments.

[0087] This invention also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the methods for generating key parameter prediction models or generating stable key parameters provided in the above embodiments.

[0088] The invention has been described with reference to a few embodiments. However, as will be known to those skilled in the art, and as defined in the appended claims, other embodiments besides those disclosed above fall equivalently within the scope of the invention.

[0089] Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the art, unless otherwise expressly defined herein. All references to “a / the / the [device, component, etc.]” ​​are openly interpreted as at least one instance of said device, component, etc., unless otherwise expressly stated. The steps of any method disclosed herein need not be performed in the exact order disclosed unless explicitly stated otherwise.

[0090] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0092] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0093] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for generating a key parameter prediction model, characterized in that, The method includes: Based on the samples of transiently stable files, the key parameters for stability and the stable time series are obtained; Using the stable time series as input and the stable key parameters as labels, an initial key parameter prediction model is trained to obtain the final key parameter prediction model. The key parameter prediction model includes an input layer, a sequence processing layer, and a parameter output layer, wherein the sequence processing layer includes a two-layer LSTM model. The process of obtaining stable key parameters and stable time series based on transiently stable file samples includes: By dynamically modifying the fault settings in the transient stability file samples, samples in the stable boundary state are generated in batches, and the key stability parameters under the stable boundary state are obtained. Based on the key features of the transient stability file samples, the power grid characterization at each time moment is obtained, and the power grid characterization in the neighborhood time before and after the fault occurs and before and after the fault is cleared is combined into a stable time series. The step of dynamically modifying the fault settings in the transient stability file samples to generate samples in batches at the stability boundary state and obtaining the key stability parameters at the stability boundary state includes: The severity of the fault is changed by adjusting the fault duration, and a binary search is used to search the fault duration. Each time, the fault duration of the temporarily stable file sample is modified to the current binary value and stability is re-judged to determine whether it is currently unstable. Samples in the stable boundary state are obtained, and the key stability parameters are obtained based on the samples in the stable boundary state. The power grid characterization at each time point, obtained based on key features of the transient stability file samples, includes: Based on the key features of transient stable samples, key information is extracted step by step, and feature vectors are refined to obtain a power grid representation that can represent the key information of the power grid stability at each time.

2. The method according to claim 1, characterized in that, The key information is extracted step by step from the key features of the transient stable samples, and the feature vectors are refined to obtain a power grid representation that can represent the key information of the power grid stability at each time point, including: The key features of the power grid in the transient stable samples are vectorized to obtain feature representations; The feature representations of the same branch are aggregated to obtain the branch representation; The power grid characterization is obtained by aggregating the characterizations of all branches of the entire power grid.

3. The method according to claim 1, characterized in that, The parameter output layer includes an attention network and multiple fully connected layers.

4. A method for generating stable key parameters, characterized in that, The stability key parameters are key parameters used for stability determination and control in power systems, and the method includes: Based on the power grid characterization at various moments of real-time measurement or imaging systems, the time of fault occurrence and fault clearance are determined and a stable time series is obtained. The stable time series is input into the key parameter prediction model to obtain the prediction results of the stable key parameters, wherein the key parameter prediction model is obtained by the method described in any one of claims 1-3.

5. An apparatus for generating a key parameter prediction model, characterized in that, The device includes: The processing unit is used to obtain stable key parameters and stable time series based on the transiently stable file samples; The training unit is used to train an initialized key parameter prediction model using the stable time series as input and the stable key parameters as labels, so as to obtain the final key parameter prediction model. The key parameter prediction model includes an input layer, a sequence processing layer, and a parameter output layer, wherein the sequence processing layer includes a two-layer LSTM model. The processing unit is further configured to: By dynamically modifying the fault settings in the transient stability file samples, samples in the stable boundary state are generated in batches, and the key stability parameters under the stable boundary state are obtained. Based on the key features of the transient stability file samples, the power grid characterization at each time moment is obtained, and the power grid characterization in the neighborhood time before and after the fault occurs and before and after the fault is cleared is combined into a stable time series. The step of dynamically modifying the fault settings in the transient stability file samples to generate samples in batches at the stability boundary state and obtaining the key stability parameters at the stability boundary state includes: The severity of the fault is changed by adjusting the fault duration, and a binary search is used to search the fault duration. Each time, the fault duration of the temporarily stable file sample is modified to the current binary value and stability is re-judged to determine whether it is currently unstable. Samples in the stable boundary state are obtained, and the key stability parameters are obtained based on the samples in the stable boundary state. The power grid characterization at each time point, obtained based on key features of the transient stability file samples, includes: Based on the key features of transient stable samples, key information is extracted step by step, and feature vectors are refined to obtain a power grid representation that can represent the key information of the power grid stability at each time.

6. The apparatus according to claim 5, characterized in that, The key information is extracted step by step from the key features of the transient stable samples, and the feature vectors are refined to obtain a power grid representation that can represent the key information of the power grid stability at each time point, including: The key features of the power grid in the transient stable samples are vectorized to obtain feature representations; The feature representations of the same branch are aggregated to obtain the branch representation; The power grid characterization is obtained by aggregating the characterizations of all branches of the entire power grid.

7. The apparatus according to claim 5, characterized in that, The parameter output layer includes an attention network and multiple fully connected layers.

8. An apparatus for generating stable key parameters, characterized in that, The stability key parameters are key parameters used for stability determination and control in power systems, and the device includes: The acquisition unit is used to determine the fault occurrence time and fault clearing time based on the power grid characterization at various moments of real-time measurement or imaging system and to acquire a stable time series. A prediction unit is used to input the stable time series into a key parameter prediction model to obtain the prediction results of the stable key parameters, wherein the key parameter prediction model is obtained using the apparatus described in any one of claims 5-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-3 or 4.

10. An electronic device, comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method according to any one of claims 1-3 or 4.

Images