Power grid stability evaluation method, device, equipment, storage medium and product

Abstract

The invention relates to a power grid stability evaluation method and device, equipment, a storage medium and a product. The method comprises the steps of determining operation parameters and at least one preset operation fault type according to a preset operation mode of a power grid, and constructing a to-be-analyzed sample according to fault parameters and operation parameters corresponding to the at least one preset operation fault type; performing stability prediction on the power grid based on the to-be-analyzed sample through a pre-trained stability prediction model to obtain a system-level stability index and an equipment-level stability index; performing stability judgment on the power grid based on the system-level stability index to obtain a first judgment result, and performing stability judgment on the power grid based on the equipment-level stability index to obtain a second judgment result; determining a target analysis mode for the power grid according to the first judgment result and the second judgment result; stability evaluation is performed on the power grid by using the target analysis mode to obtain the stability evaluation result of the power grid, so that the stability evaluation accuracy can be effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of power grid operation status analysis, and in particular to a power grid stability assessment method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] Stability refers to the ability of each synchronous generator to maintain synchronous operation and smoothly transition to a new stable state or return to the original stable state after the power system is subjected to a large disturbance (such as short circuit fault, generator tripping, sudden change in load, removal or input of important components, etc.). Stability is not only related to the stable operation of the power system, but also a key indicator to ensure the continuity and reliability of power supply. It has important guiding significance for the planning, design, operation and maintenance of the power system.

[0003] The data-driven stability assessment algorithm can use machine learning models to directly predict the stability of the system or generator level under preset faults based on the steady-state or dynamic information of the power grid, so as to evaluate and analyze the stability of the power grid.

[0004] However, when faced with operating scenarios that are significantly different from known scenarios, the reliability of system-level or generator-level stability predicted directly through prediction models is likely to be significantly reduced, and various prediction indicators themselves are difficult to support self-testing of the credibility of the results, resulting in reduced accuracy of stability assessment and analysis of the power grid based on prediction results. Summary of the invention

[0005] Based on this, it is necessary to provide a power grid stability assessment method, device, computer equipment, computer-readable storage medium and computer program product that can improve the assessment accuracy in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for evaluating power grid stability, comprising:

[0007] Determine operating parameters and at least one preset operating fault type according to a preset operating mode of the power grid, and construct a sample to be analyzed of the power grid according to the fault parameters corresponding to the at least one preset operating fault type and the operating parameters;

[0008] By using a pre-trained stability prediction model, stability prediction is performed on the power grid based on the sample to be analyzed to obtain a system-level stability index of the power grid and a device-level stability index of the power equipment running in the power grid;

[0009] Performing stability determination on the power grid based on the system-level stability index to obtain a first determination result of the power grid, and performing stability determination on the power grid based on the device-level stability index to obtain a second determination result of the power grid;

[0010] Determining a target analysis method for the power grid according to the first determination result and the second determination result;

[0011] The target analysis method is used to perform stability assessment on the power grid to obtain a stability assessment result of the power grid.

[0012] In one embodiment, determining a target analysis method for the power grid according to the first determination result and the second determination result includes:

[0013] When the first determination result and the second determination result are consistent, evaluating the stability of the power grid based on the system-level stability index and the device-level stability index;

[0014] When the first determination result and the second determination result are inconsistent, the power grid is simulated in the time domain based on the sample to be analyzed to obtain stability simulation parameters of the power grid, and the stability of the power grid is evaluated based on the stability simulation parameters.

[0015] In one of the embodiments, the system-level stability index includes a system stability state parameter and a system stability level parameter;

[0016] The performing stability determination on the power grid based on the system-level stability index to obtain a first determination result of the power grid includes:

[0017] Performing system-level parameter determination on the system stable state parameter and the system stable level parameter to obtain a third determination result;

[0018] A system-level instability state of the power grid is determined based on the third determination result, and a first determination result of the power grid is determined based on the system-level instability state.

[0019] In one of the embodiments, the equipment-level stability index includes a dominant instability state parameter and a disturbance severity parameter of the operating power equipment;

[0020] The performing stability determination on the power grid based on the device-level stability index to obtain a second determination result of the power grid includes:

[0021] Performing device-level parameter determination on each of the dominant instability state parameters and the disturbance severity parameter to obtain a fourth determination result;

[0022] A device-level instability state of the power grid is determined based on the fourth determination result, and a second determination result of the power grid is determined based on the device-level instability state.

[0023] In one embodiment, the determining of operating parameters and at least one preset operating fault type according to a preset operating mode of the power grid, and constructing a sample to be analyzed of the power grid according to the fault parameters corresponding to the at least one preset operating fault type and the operating parameters, includes:

[0024] Obtain the topology of the power grid;

[0025] Determining a preset operation mode of the power grid, and determining operation parameters corresponding to each system node in the topological structure according to the preset operation mode;

[0026] Determine at least one preset operation fault type corresponding to the preset operation mode, and determine the fault parameters corresponding to each of the system nodes in the topological structure according to the operation parameters and the preset operation fault type;

[0027] Based on the topological structure, the operating parameters corresponding to each of the system nodes and the fault parameters corresponding to each of the system nodes, an adjacency matrix and a node feature matrix based on a graph structure are constructed, and samples to be analyzed are obtained according to the adjacency matrix and the node feature matrix.

[0028] In one embodiment, the stability prediction model is pre-trained to predict the stability of the power grid based on the sample to be analyzed, and the system-level stability index of the power grid and the device-level stability index of the power equipment running in the power grid are obtained, including:

[0029] Inputting the sample to be analyzed into a pre-trained stability prediction model;

[0030] By using the system-level stability prediction sub-model of the stability prediction model, a system-level stability prediction is performed on the power grid based on the sample to be analyzed to obtain a system-level stability index of the power grid;

[0031] By using the device-level stability prediction sub-model of the stability prediction model, device-level stability prediction is performed for each operating power device in the power grid based on the samples to be analyzed, so as to obtain the device-level stability index of each operating power device in the power grid.

[0032] In a second aspect, the present application also provides a power grid stability assessment device, comprising:

[0033] A sample construction module, used to determine operating parameters and at least one preset operating fault type according to a preset operating mode of the power grid, and to construct a sample to be analyzed of the power grid according to the fault parameters corresponding to the at least one preset operating fault type and the operating parameters;

[0034] An indicator prediction module, used to perform stability prediction on the power grid based on the sample to be analyzed by using a pre-trained stability prediction model, and obtain a system-level stability indicator of the power grid and a device-level stability indicator of the power equipment running in the power grid;

[0035] An indicator determination module, configured to perform stability determination on the power grid based on the system-level stability indicator to obtain a first determination result of the power grid, and perform stability determination on the power grid based on the device-level stability indicator to obtain a second determination result of the power grid;

[0036] A method determination module, configured to determine a target analysis method for the power grid according to the first determination result and the second determination result;

[0037] The stability assessment module is used to perform stability assessment on the power grid using the target analysis method to obtain a stability assessment result of the power grid.

[0038] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the steps of the above-described method when executed by a processor.

[0040] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0041] The above-mentioned power grid stability assessment method, device, computer equipment, computer-readable storage medium and computer program product determine the operating parameters and at least one preset operating fault type according to the preset operating mode of the power grid, and construct a sample to be analyzed of the power grid according to the fault parameters and operating parameters corresponding to the at least one preset operating fault type; through the pre-trained stability prediction model, the stability prediction of the power grid is performed based on the sample to be analyzed, and the system-level stability index of the power grid and the equipment-level stability index of the power equipment running in the power grid are obtained, and the preliminary assessment results can be quickly given. Moreover, with the introduction of the system-level stability index and the equipment-level stability index, the stability assessment can comprehensively cover the overall performance of the power grid and the operating status of key equipment. state; then, based on the system-level stability index, the stability of the power grid is judged to obtain a first judgment result of the power grid, and based on the device-level stability index, the stability of the power grid is judged to obtain a second judgment result of the power grid; according to the first judgment result and the second judgment result, a target analysis method for the power grid is determined; the stability of the power grid is evaluated by using the target analysis method to obtain a stability evaluation result of the power grid; by using the pre-trained stability prediction model to predict the stable state of the power grid at the system level and the device level respectively, and combining the time domain simulation at the system level and the device level for the inconsistent results of the stability judgment of the power grid, the system stability is evaluated, which can significantly improve the accuracy of the stability evaluation while ensuring the evaluation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A diagram showing an application environment of a power grid stability assessment method in one embodiment;

[0044] Figure 2 is a schematic flow chart of a method for evaluating power grid stability in one embodiment;

[0045] Figure 3 is a schematic diagram of a flow chart for obtaining a second determination result in one embodiment;

[0046] Figure 4 A schematic diagram of a process for performing consistency determination in one embodiment;

[0047] Figure 5 A schematic diagram of a process for constructing a sample to be analyzed in one embodiment;

[0048] Figure 6A schematic diagram of a process for predicting and obtaining a stability index in one embodiment;

[0049] Figure 7 It is a flowchart of a power grid stability assessment method in an application example;

[0050] Figure 8 is a structural block diagram of a power grid stability assessment device in one embodiment;

[0051] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] The power grid stability assessment method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 constructs samples to be analyzed for stability analysis of the power grid (or power grid system, power system), takes the samples to be analyzed as the input of the pre-trained stability prediction model, and predicts the stability of the power grid through the stability prediction model, and obtains the system-level stability index corresponding to the entire power grid system and the device-level stability index corresponding to each operating power device in the power grid system; then, the server 104 determines the target analysis method of the power grid stability analysis based on the consistency between the first judgment result determined according to the system-level stability index and the second judgment result determined according to the device-level stability index, and finally determines the final stability evaluation result of the power grid based on the target analysis method to improve the accuracy of the evaluation.

[0054] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. The portable wearable devices may be smart watches, smart bracelets, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0055] In one embodiment, Figure 2 As shown in FIG. 1 , a method for evaluating the stability of a power grid is provided. The method is applied to Figure 1 The server 104 in FIG. 1 is used as an example to illustrate. It is understandable that the method can also be applied to Figure 1 The terminal 102 in the embodiment may also be applied to a system including the terminal 102 and the server 104, and implemented through interaction between the terminal 102 and the server 104. The method of this embodiment includes:

[0056] Step 201, according to a preset operation mode of the power grid, determine operation parameters and at least one preset operation fault type, and construct a sample to be analyzed of the power grid according to the fault parameters and operation parameters corresponding to the at least one preset operation fault type.

[0057] Among them, the preset operating mode of the power grid refers to the operating mode and state of the power grid under pre-set operating conditions. The operating conditions usually include but are not limited to at least one of the key parameters such as the structure of the power grid, power flow distribution, generator output, voltage level, power factor, load distribution, etc., which are used to simulate and analyze the behavior of the power grid in different scenarios.

[0058] Among them, operating parameters refer to various parameters used to characterize the current operating status of the power grid when the power grid operates according to a preset operating mode, including but not limited to at least one of the voltage amplitude, current size, power factor, active power, reactive power, and frequency corresponding to each system node in the power grid. The system node can refer to a simplified representation of a bus in the power grid, or it can be a simplified representation of various operating power equipment in the power grid. The operating power equipment can include but is not limited to generators, transformers and other equipment.

[0059] The preset operation fault type refers to various pre-set fault types that may occur in the power grid, including but not limited to at least one of the fault types such as line tripping, generator failure, and load mutation, which is used to simulate the behavior of the power grid under abnormal conditions to evaluate its stability. In this embodiment, the preset operation fault type corresponds to the preset operation mode; in specific implementation, the preset operation fault type can be pre-set according to the historical data, operation experience and safety analysis of the power grid, and various situations that may cause instability or failure of the power grid under the corresponding preset operation mode.

[0060] Among them, fault parameters refer to various parameters used to characterize the fault characteristics of the power grid under a preset operating fault type, including but not limited to at least one of the fault location, fault type, fault duration, voltage drop, current increase, power imbalance, frequency deviation, etc. corresponding to each system node in the power grid after a fault occurs.

[0061] The sample to be analyzed refers to a data set constructed based on the operating parameters corresponding to the preset operating mode and the fault parameters corresponding to the preset operating fault type, and is used for power grid stability analysis and control.

[0062] Exemplarily, the server obtains a preset operating mode set for the power grid, so that the power grid operates in accordance with the preset operating mode. During the operation, the server determines the operating parameters of the power grid and at least one preset operating fault type corresponding to the power grid operating in the preset operating mode. Subsequently, the server constructs a sample to be analyzed of the power grid based on the fault parameters corresponding to at least one preset operating fault type and the operating parameters of the power grid, so as to predict the stability of the power grid under the preset operating mode and preset operating fault type.

[0063] Step 202 , using a pre-trained stability prediction model, a stability prediction is performed on the power grid based on the samples to be analyzed, and a system-level stability index of the power grid and a device-level stability index of the power equipment running in the power grid are obtained.

[0064] Among them, the pre-trained stability prediction model refers to a model that has been trained with a large amount of historical data, and the stability prediction model can predict the stability of the power grid under a preset operating mode and a preset operating fault type based on the input sample to be analyzed. In an exemplary embodiment, the stability prediction model can be implemented based on a graph depth model. It is understandable that in some other embodiments, the stability prediction model can also be constructed using at least one of the methods including but not limited to convolutional neural networks, recurrent neural networks, feature extraction algorithms, adversarial learning algorithms, etc., to determine the system-level stability index and device-level stability index of the power grid based on the sample to be analyzed.

[0065] Among them, the system-level stability index refers to an indicator that evaluates the stability of the entire power grid from the overall power grid level, which is used to reflect the overall operating status of the power grid under normal operation or under preset operating fault types.

[0066] Among them, the equipment-level stability index refers to an indicator that evaluates the stability of each operating power equipment from the level of a single operating power equipment, and is used to reflect the operating status of the operating power equipment during normal operation or when it is disturbed; a single operating power equipment can indirectly reflect the stability of the operating status of the entire power grid. For example, when a certain operating power equipment is determined to be unstable, the operating status of the power grid will also be affected by the unstable operating power equipment and become unstable.

[0067] Exemplarily, the server inputs the sample to be analyzed into a pre-trained stability prediction model, performs stability prediction on the power grid through the pre-trained stability prediction model, and obtains system-level stability indicators of the power grid and equipment-level stability indicators of power equipment running in the power grid.

[0068] Step 203, performing stability determination on the power grid based on the system-level stability index to obtain a first determination result of the power grid, and performing stability determination on the power grid based on the device-level stability index to obtain a second determination result of the power grid.

[0069] The first determination result refers to the result of a preliminary determination of the stability of the entire power grid based on the system-level stability index, and the first determination result is used to reflect the stability state of the power grid at the overall level. The first determination result includes a result indicating that the power grid is in an unstable state at the overall level and a result indicating that the power grid is not in an unstable state (i.e., a stable state) at the overall level.

[0070] The second determination result refers to the result of a preliminary determination of the stability of the power grid from the level of the operating power equipment in the power grid based on the device-level stability index. The second determination result is used to reflect the stability state at the level of each operating power equipment in the power grid. The second determination result includes a result indicating that the power grid is in an unstable state at the level of the operating power equipment and a result indicating that the power grid is not in an unstable state at the level of the operating power equipment.

[0071] Exemplarily, the server performs a stability judgment on the power grid at the overall level based on the system-level stability index to determine whether the power grid is unstable at the overall level to obtain a first judgment result of the power grid. The server also performs a stability judgment on the power grid at the operating power equipment level based on the device-level stability index to determine whether the power grid is unstable at the operating power equipment level to obtain a second judgment result of the power grid.

[0072] Step 204: Determine a target analysis method for the power grid according to the first determination result and the second determination result.

[0073] Among them, the target analysis method refers to the method or means for evaluating the stability of the power grid determined according to the first judgment result and the second judgment result; in specific implementation, the corresponding target analysis method is determined by whether the first judgment result and the second judgment result are consistent with the stability judgment results of the power grid, so that the corresponding analysis method can be adopted according to different judgment results to ensure the accuracy of the evaluation results.

[0074] Exemplarily, the server determines whether the first determination result and the second determination result are consistent with each other in terms of the stability of the power grid, and determines a target analysis method for the power grid based on the consistency determination result.

[0075] Step 205: Perform stability assessment on the power grid using a target analysis method to obtain a stability assessment result of the power grid.

[0076] The stability assessment result refers to the final conclusion obtained after the stability assessment of the power grid is carried out using the target analysis method. The stability assessment result includes the analysis results corresponding to the stability indicators at the system level and the equipment level.

[0077] Exemplarily, the server performs stability assessment on the power grid according to a determined target analysis method to obtain a stability assessment result of the power grid.

[0078] In the above-mentioned power grid stability assessment method, by determining the operating parameters and at least one preset operating fault type according to the preset operating mode of the power grid, and constructing the sample to be analyzed of the power grid according to the fault parameters and operating parameters corresponding to at least one preset operating fault type; by using the pre-trained stability prediction model, the stability prediction of the power grid is performed based on the sample to be analyzed, and the system-level stability index of the power grid and the device-level stability index of the power equipment running in the power grid are obtained, so that the preliminary assessment result can be quickly given, and with the introduction of the system-level stability index and the device-level stability index, the stability assessment can fully cover the overall performance of the power grid and the operating status of key equipment; then, the stability of the power grid is determined based on the system-level stability index to obtain a first determination result of the power grid, and the stability of the power grid is determined based on the device-level stability index to obtain a second determination result of the power grid; according to the first determination result and the second determination result, the target analysis method for the power grid is determined; the stability of the power grid is evaluated using the target analysis method to obtain the stability assessment result of the power grid; by using the pre-trained stability prediction model to predict the stability state of the power grid at the system level and the device level respectively, and combining the time domain simulation to evaluate the stability of the system when the results of the stability determination of the power grid at the system level and the device level are inconsistent, the accuracy of the stability assessment can be significantly improved while ensuring the assessment efficiency.

[0079] In one embodiment, the system-level stability index includes a system stability state parameter and a system stability level parameter.

[0080] The system stability state parameter refers to a parameter describing the stability of the current operation state of the power grid, which is used to reflect the stability state of the power grid when it is operating normally or when it is disturbed. The system stability state parameter may include but is not limited to at least one of the parameters such as voltage level, frequency deviation, and power angle difference.

[0081] The system stability level parameter refers to a parameter that measures the ability of the power grid to maintain stable operation under a preset operation mode and preset operation fault type, and is used to reflect the ability of the power grid to maintain stable operation during normal operation or when disturbed. The system stability level parameter includes but is not limited to at least one of the power grid's transmission capacity, spare capacity, and recovery speed after a fault.

[0082] In this embodiment, a stability determination is performed on the power grid based on the system-level stability index to obtain a first determination result of the power grid, including:

[0083] Performing system-level parameter determination on system stability state parameters and system stability level parameters to obtain a third determination result; determining the system-level instability state of the power grid based on the third determination result, and determining the first determination result of the power grid based on the system-level instability state.

[0084] The system-level parameter determination refers to the process of evaluating the stability of the power grid based on the system stable state parameters and the system stable level parameters to obtain the third determination result.

[0085] The third determination result refers to the result on the stability state of the power grid obtained through system-level parameter determination.

[0086] Among them, the system-level instability state refers to the stable state of the power grid at the overall level.

[0087] Exemplarily, the server performs system-level parameter judgment on system stability state parameters and system stability level parameters to obtain a third judgment result of the power grid; determines the system-level instability state of the power grid based on the third judgment result, and determines the first judgment result of the power grid based on the system-level instability state.

[0088] In an exemplary embodiment, the system steady state parameter is Indicates that when When , it indicates that the power grid is not in an unstable state. On the contrary, when When , it indicates that the power grid is in an unstable state. The system stability level parameter is express, , at this time, define a preset threshold parameter ,and ,when When , it indicates that the power grid is not in an unstable state. When , it indicates that the power grid is in an unstable state. When , it indicates that the stability of the power grid is uncertain. and system stability level parameters According to the above rules, the system-level parameter determination can determine the system-level instability state of the power grid, and then the first determination result of the power grid can be determined by the system-level instability state. The first determination result includes the system stability state parameter and system stability level parameters The results of judging the instability state of the power grid are shown respectively.

[0089] In this embodiment, by making a comprehensive judgment on the system stability state parameters and the system stability level parameters, the system-level instability state of the power grid can be accurately identified, and then the first judgment result of the power grid is determined based on the system-level instability state, which is beneficial to improving the accuracy and reliability of the stability assessment of the power grid at the overall level.

[0090] In one embodiment, the device-level stability index includes a dominant unstable state parameter and a disturbance severity parameter of the operating power device.

[0091] The dominant instability state parameter refers to a parameter that can reflect the key state and characteristics of the running power equipment during the dominant instability process. Dominant instability refers to the instability of the running power equipment due to the unstable factors within the system after the running power equipment is disturbed or fails. The dominant instability state parameter includes but is not limited to at least one of the electrical parameters such as power, voltage, current, frequency, etc. of the running power equipment, and the physical parameters such as mechanical stress and temperature of the equipment.

[0092] The disturbance severity parameter is used to describe the degree to which the stability of the operating power equipment is affected when it is subjected to external disturbances, and is used to reflect the sensitivity and recovery ability of the operating power equipment to external disturbances. The disturbance severity parameter includes but is not limited to at least one of the following parameters: voltage recovery time after disturbance, frequency deviation, power oscillation amplitude, etc.

[0093] In this embodiment, a stability determination is performed on the power grid based on the device-level stability index to obtain a second determination result of the power grid, including:

[0094] Perform device-level parameter determination on each dominant instability state parameter and disturbance severity parameter to obtain a fourth determination result; determine the device-level instability state of the power grid based on the fourth determination result, and determine a second determination result of the power grid based on the device-level instability state.

[0095] Among them, device-level parameter determination refers to the process of evaluating the stability of a single operating power device in the power grid based on the dominant instability state parameters and disturbance severity parameters.

[0096] The fourth determination result refers to the result of the stability state of a single operating power device in the power grid obtained through device-level parameter determination.

[0097] Among them, the equipment-level instability state refers to the stable state of a single operating power device in the power grid.

[0098] Exemplarily, the server performs device-level parameter determination on each dominant instability state parameter and disturbance severity parameter to obtain a fourth determination result of the power grid; determines the device-level instability state of the power grid based on the fourth determination result, and determines the second determination result of the power grid based on the device-level instability state.

[0099] In an exemplary embodiment, the dominant unstable state parameter set of each operating power device is In other words, the dominant instability state parameter corresponding to the i-th operating power equipment is expressed as , ,when When , it indicates that the i-th running power equipment is in the dominant unstable state. When , it indicates that the i-th running power equipment is not in the dominant unstable state; among all running power equipment, if , it means that there is a dominant instability state in the running power equipment. At this time, the power grid is also in an unstable state.

[0100] The disturbance severity parameters of each operating power equipment are combined into In other words, the disturbance severity parameter corresponding to the i-th operating power equipment is expressed as , , ,when When , it indicates that the i-th running power equipment is in an unstable state. On the contrary, when When , it indicates that the i-th running power equipment is not in an unstable state; among all running power equipment, if , then the manual indicates that the operating power equipment is in an unstable state. At this time, the corresponding power grid is also in an unstable state.

[0101] Based on the above, define a system-level discrimination parameter , to obtain the second determination result, such as Figure 3 As shown, the determination process includes:

[0102] like ,but , indicating that the power grid is in an unstable state at the level of operating power equipment. On the contrary, if , then determine the disturbance severity parameter of the operating power equipment. If ,but , indicating that the power grid is in an unstable state at the level of operating power equipment. On the contrary, if ,but , indicating that the power grid is not in an unstable state at the level of operating power equipment. Therefore, based on the dominant instability state parameter and disturbance severity parameters By performing device-level parameter determination, the device-level instability state of the power grid can be determined, and then the second determination result of the power grid can be determined by the device-level instability state. The second determination result is the system-level determination parameter. The result of judging the instability state of the power grid.

[0103] In this embodiment, by making a comprehensive judgment on the dominant instability state parameters and the disturbance severity parameters, the device-level instability state of the power grid can be accurately identified, and then the second judgment result of the power grid can be determined based on the device-level instability state, which is beneficial to improving the accuracy and reliability of the stability assessment of the power grid at the level of single operating power equipment.

[0104] In one embodiment, determining a target analysis method for a power grid according to the first determination result and the second determination result includes:

[0105] When the first judgment result and the second judgment result are consistent, the stability of the power grid is evaluated based on the system-level stability index and the equipment-level stability index; when the first judgment result and the second judgment result are inconsistent, the power grid is simulated in the time domain based on the sample to be analyzed to obtain the stability simulation parameters of the power grid, and the stability of the power grid is evaluated based on the stability simulation parameters.

[0106] The situation where the first determination result and the second determination result are consistent means that the stability state of the power grid represented by the first determination result from the overall power grid level is the same as the stability state of the power grid represented by the second determination result from the level of operating power equipment, that is, the first determination result and the second determination result both indicate that the power grid is in an unstable state or both indicate that the power grid is not in an unstable state. In this case, the system-level stability index and the equipment-level stability index can be directly used to evaluate the stability of the power grid.

[0107] The inconsistency between the first determination result and the second determination result means that the stability state of the power grid represented by the first determination result from the overall power grid level is different from the stability state of the power grid represented by the second determination result from the operating power equipment level, that is, one of the first determination result and the second determination result indicates that the power grid is in an unstable state while the other indicates that the power grid is not in an unstable state. In this state, the evaluation of the stability of the power grid by the system-level stability index and the equipment-level stability index is contradictory. Therefore, the system-level stability index and the equipment-level stability index cannot be directly used to evaluate the stability of the power grid. For this reason, it is necessary to use time domain simulation to further evaluate the stability of the power grid in order to obtain accurate stability evaluation results.

[0108] Among them, time domain simulation refers to a technical means for simulating the dynamic operation state of the power grid. Time domain simulation can be based on the physical model and / or mathematical model of the power grid, and can simulate the operation state of the power grid under the preset operation mode through numerical calculation to provide a detailed dynamic response of the power grid after a fault or disturbance occurs, including the changes in parameters such as voltage, current, and frequency, and then obtain the stability simulation parameters of the power grid. After the time domain simulation is completed, the stability of the power grid can be evaluated based on the obtained stability simulation parameters.

[0109] The stability simulation parameters refer to various parameters obtained during the time domain simulation process for evaluating the stability of the power grid, and are used to reflect the dynamic behavior of the power grid under the time domain simulation. The stability simulation parameters may include, but are not limited to, at least one of the voltage amplitude and phase angle of each system node in the power grid, the power flow of the line, the output power and speed of the generator, and other parameters.

[0110] Exemplarily, the server makes a consistency judgment on the first judgment result and the second judgment result. When the first judgment result and the second judgment result both indicate that the power grid is in an unstable state or both indicate that the power grid is not in an unstable state, the stability of the power grid is evaluated based on the system-level stability index and the device-level stability index; when one of the first judgment result and the second judgment result indicates that the power grid is in an unstable state and the other indicates that the power grid is not in an unstable state, the power grid is simulated in the time domain based on the sample to be analyzed to obtain stability simulation parameters of the power grid, and the stability of the power grid is evaluated based on the stability simulation parameters.

[0111] In an exemplary embodiment, Figure 4 As shown, the process of performing consistency determination based on the first determination result and the second determination result includes:

[0112] Based on the system steady state parameters , System stability level parameters and system-level discrimination parameters , determine the corresponding judgment results.

[0113] Determine the system stable state parameters Is it 1? When , it indicates that the power grid is not in an unstable state. At this time, the first signal with a Boolean value of True is output. , and simultaneously outputs a second signal with a Boolean value of False , on the contrary, if (Right now ), indicating that the power grid is in an unstable state. At this time, the first signal with a Boolean value of False is output. , and simultaneously outputs a second signal with a Boolean value of True .

[0114] Determine the system stability level parameters Is it greater than ,like When , it indicates that the power grid is not in an unstable state. At this time, the third signal with a Boolean value of True is output. , on the contrary, if When the power grid is stable, it indicates that the stability of the power grid is uncertain and further judgment of the system stability level parameters is required. Is it less than ,like When , it indicates that the power grid is in an unstable state. At this time, the fourth signal with a Boolean value of True is output. , and simultaneously outputs a fifth signal with a Boolean value of False , on the contrary, if When the stable state is uncertain, the fourth signal with a Boolean value of False is output. , and simultaneously outputs a fifth signal with a Boolean value of True .

[0115] Determine system-level discrimination parameters Is it equal to 0? When the surface power grid is in an unstable state, the sixth signal with a Boolean value of True is output. , and simultaneously outputs the seventh signal with a Boolean value of False , on the contrary, if (Right now ), indicating that the power grid is not in an unstable state. At this time, the sixth signal with a Boolean value of True is output. , and simultaneously outputs the seventh signal with a Boolean value of False .

[0116] The first signal , the third signal and the Seventh Signal The Boolean value of is determined by an AND gate, and the first intermediate result is output. If the first signal , the third signal and the Seventh Signal If at least one signal has a False Boolean value among the Boolean values ​​of , the third signal and the Seventh Signal If there is no signal with a Boolean value of False in the Boolean value of , the first intermediate result is True. If the first intermediate result is True, it indicates that the first determination result is consistent with the second determination result. On the contrary, if the first intermediate result is False, it indicates that the first determination result is inconsistent with the second determination result.

[0117] Similarly, the second signal , the fourth signal and the Sixth Signal The Boolean value of the signal is determined by an AND gate and the second intermediate result is output. , the fourth signal and the Sixth Signal If at least one signal has a False Boolean value among the Boolean values ​​of , the fourth signal and the Sixth Signal If there is no signal with a Boolean value of False in the Boolean value of , the second intermediate result is True. If the second intermediate result is True, it indicates that the first determination result is consistent with the second determination result. On the contrary, if the second intermediate result is False, it indicates that the first determination result is inconsistent with the second determination result.

[0118] Finally, the first intermediate result and the second intermediate result are judged through an OR gate to obtain a final parameter judgment result, so as to determine the target analysis method for the power grid. If at least one of the first intermediate result and the second intermediate result is True, it indicates that the first judgment result is consistent with the second judgment result. At this time, the stability of the power grid can be evaluated based on the system-level stability index and the device-level stability index. Conversely, if the first intermediate result and the second intermediate result are both False, it indicates that the first judgment result is inconsistent with the second judgment result. At this time, it is necessary to perform time domain simulation on the power grid based on the sample to be analyzed, obtain the stability simulation parameters of the power grid, and evaluate the stability of the power grid based on the stability simulation parameters.

[0119] It is understandable that in some other embodiments, machine learning algorithms and deep learning algorithms can also be used to analyze the system stable state parameters. , System stability level parameters and system-level discrimination parameters After identifying and extracting the characteristics of each parameter, the system stable state parameters are calculated based on the corresponding characteristics of each parameter. , System stability level parameters and system-level discrimination parameters Make consistency determination.

[0120] In this embodiment, a consistency judgment is made between a first judgment result of the stability state of the power grid represented at the overall power grid level and a second judgment result of the stability state of the power grid represented at the level of operating power equipment. When the two judgment results are consistent, the stability of the power grid is quickly evaluated directly using system-level and device-level stability indicators. When the two judgment results are inconsistent, more detailed stability parameters are obtained through time domain simulation for accurate evaluation, thereby ensuring the comprehensiveness and reliability of the evaluation results, so as to flexibly and accurately evaluate the stability of the power grid.

[0121] In one embodiment, Figure 5 As shown, according to the preset operation mode of the power grid, the operation parameters and at least one preset operation fault type are determined, and according to the fault parameters and operation parameters corresponding to the at least one preset operation fault type, the sample to be analyzed of the power grid is constructed, including:

[0122] Step 501, obtaining the topology of the power grid.

[0123] Among them, the topological structure of the power grid refers to the connection relationship between each system node in the power grid; the topological result includes vertices and edges. The vertices can be used to represent each system node in the power grid, and the edges can be used to represent the connection relationship between each system node.

[0124] Exemplarily, the server obtains the topology of the power grid.

[0125] Step 502, determining a preset operation mode of the power grid, and determining operation parameters corresponding to each system node in the topology structure according to the preset operation mode.

[0126] Exemplarily, the server determines a preset operation mode for the power grid so that the power grid operates according to the preset operation mode, and determines the operation parameters corresponding to each system node in the topology structure according to the preset operation mode.

[0127] Step 503: determine at least one preset operation fault type corresponding to the preset operation mode, and determine fault parameters corresponding to each system node in the topology structure according to the operation parameters and the preset operation fault type.

[0128] Exemplarily, the server determines at least one corresponding preset operation fault type according to a preset operation mode of the power grid, and determines fault parameters corresponding to each system node in the topology structure according to the operation parameters and the preset operation fault type.

[0129] Step 504, constructing an adjacency matrix and a node feature matrix based on a graph structure based on the topological structure, the operating parameters corresponding to each system node, and the fault parameters corresponding to each system node, and obtaining samples to be analyzed based on the adjacency matrix and the node feature matrix.

[0130] Among them, the adjacency matrix based on the graph structure refers to a matrix used to represent the topological structure of the power grid. In the adjacency matrix, the rows and columns represent the system nodes in the power grid respectively, and the elements in the matrix represent the connection relationship between the nodes. If there is a directly connected transmission line between the two system nodes, the element at the corresponding position is 1 (or weight value), otherwise it is 0. In this embodiment, the weights of the non-zero elements in the adjacency matrix are determined by the admittance matrix of the corresponding system node in the adjacency matrix.

[0131] The node characteristic matrix refers to a matrix used to represent the parameter characteristics corresponding to each system node in the power grid. In the node characteristic matrix, each row represents a system node, and each column represents a specific attribute or parameter of the system node. In this embodiment, the node characteristic matrix is ​​determined based on the electrical parameters of each system node when the power grid is running in the corresponding preset operating mode, such as voltage, power, etc.

[0132] Exemplarily, the server constructs a graph-based adjacency matrix and a node feature matrix based on the topological structure of the power grid, the operating parameters corresponding to each system node, and the fault parameters corresponding to each system node, and obtains samples to be analyzed based on the adjacency matrix and the node feature matrix.

[0133] In an optional embodiment, after the samples to be analyzed are constructed, the samples to be analyzed may be preprocessed to unify the dimensions of the samples to be analyzed. When performing the preprocessing, at least one of methods including but not limited to z-score, min-max, etc. may be used.

[0134] In this embodiment, by obtaining the topological structure of the power grid, determining the operating parameters of each system node according to the preset operating mode, and further determining the fault parameters in combination with the preset operating fault type, finally constructing an adjacency matrix and a node feature matrix based on the graph structure as samples to be analyzed, it can not only improve the accuracy and efficiency of power grid fault analysis, but also help to realize the intelligent monitoring and management of power grid operation, and provide strong support for the safe and stable operation of the power grid.

[0135] In one embodiment, Figure 6 As shown, through the pre-trained stability prediction model, the stability of the power grid is predicted based on the samples to be analyzed, and the system-level stability index of the power grid and the device-level stability index of the power equipment running in the power grid are obtained, including:

[0136] Step 601: Input the sample to be analyzed into the pre-trained stability prediction model.

[0137] Step 602 , using the system-level stability prediction sub-model of the stability prediction model, a system-level stability prediction is performed on the power grid based on the sample to be analyzed to obtain a system-level stability index of the power grid.

[0138] Among them, the system-level stability prediction sub-model refers to the model in the pre-trained stability prediction model used to predict the overall (or system-level) stability of the power grid. The system-level stability prediction sub-model is based on information such as the power grid topology, operating parameters and fault parameters in the sample to be analyzed. It evaluates the overall stability state of the power grid under the preset operating mode and preset operating fault type, and outputs the system-level stability index.

[0139] Among them, system-level stability prediction refers to the process of using a pre-trained system-level stability prediction sub-model to process the samples to be analyzed to predict the stability state of the power grid.

[0140] Exemplarily, the server calls the system-level stability prediction sub-model in the stability prediction model, and processes information such as the power grid topology, operating parameters, and fault parameters in the sample to be analyzed through the system-level stability prediction sub-model to perform system-level stability prediction on the power grid, and obtain a system-level stability indicator for characterizing the overall stability of the power grid.

[0141] Step 603 , using the device-level stability prediction sub-model of the stability prediction model, perform device-level stability prediction on each operating power device in the power grid based on the sample to be analyzed, and obtain the device-level stability index of each operating power device in the power grid.

[0142] Among them, the device-level stability prediction sub-model refers to the pre-trained stability prediction model used to perform device-level stability prediction on a single operating power device in the power grid. The device-level stability prediction sub-model is based on the relevant information of the operating power equipment in the sample to be analyzed (such as the operating parameters, fault parameters, etc. of the equipment), evaluates the stability status of the operating power equipment in the grid under the preset operating mode and preset operating fault type, and outputs the device-level stability index.

[0143] Among them, device-level stability prediction refers to the process of using a pre-trained device-level stability prediction sub-model to process the samples to be analyzed to predict the stability status of the power equipment running in the power grid.

[0144] Exemplarily, the server calls the device-level stability prediction sub-model of the stability prediction model, and processes the relevant information of the operating power equipment in the sample to be analyzed through the device-level stability prediction sub-model to perform device-level stability prediction for each operating power equipment in the power grid, and obtain the device-level stability index used to characterize the stability of each operating power equipment in the power grid.

[0145] In this embodiment, different prediction processing is performed on different data in the sample to be analyzed through the stability prediction model, so that the system-level stability of the power grid and the equipment-level stability of each operating power equipment can be predicted efficiently and accurately, and the system-level stability index and the equipment-level stability index can be obtained respectively. On the one hand, it is conducive to improving the efficiency and accuracy of the power grid stability assessment. On the other hand, it can also provide important decision-making basis for the operation scheduling, fault prevention and equipment management of the power grid.

[0146] In a specific application example, a power grid stability assessment method is provided. The assessment process is as follows: Figure 7 As shown in the figure, by giving the number of power system nodes, before a fault occurs, the operator constructs a sample to be analyzed with a graph data structure according to the operation mode (i.e., the preset operation mode) and the expected fault (i.e., the preset operation fault type), and the adjacency matrix is ​​composed of a set of and node feature matrix set Indicates. Among them, the mth adjacency matrix The non-zero element weights of are determined by the corresponding power system node admittance matrix, and the mth node characteristic matrix Depends on the electrical properties of each node corresponding to the selected operating state, such as voltage, power, etc. It is expressed as:

[0147] (1)

[0148] in, Represents the electrical properties of the nodes on the corresponding row or column, that is, the node characteristics, such as represents the electrical property of the first row and first column, that is, the first feature or electrical property of the first node. For example, Represents the electrical property of the Nth row and the Cth column, that is, the Cth feature or electrical property of the Nth node.

[0149] In this example, the samples to be analyzed can be preprocessed based on mature normalization algorithms such as z-score and min-max as input to the stability assessment model. The stability assessment model can provide stability indicators at the system level and generator level, including system-level stability indicators including system stability status. and system stability level , the generator-level stability index includes the dominant instability state vector and the disturbance severity vector .

[0150] The ADM-G module processes the generator-level stability index and gives the system-level discrimination index , system-level discrimination index Together with the other two system-level stability indicators, it is processed by the ADM-S module.

[0151] In this example, the ADM-G module operation logic is as follows:

[0152] The input of the ADM-G module is the dominant instability state vector and the disturbance severity vector :

[0153] 1) For the dominant instability state vector , the i-th element Indicates the dominant instability state of the i-th generator, and its value is 0 or 1. , then the generator is in a dominant unstable state, otherwise it is not in a dominant unstable state.

[0154] 2) For the disturbance severity vector , the i-th element Indicates the severity of the disturbance of the i-th generator, and its value range is -1~1. , then the generator is in an unstable state, otherwise it is not in an unstable state.

[0155] Based on the above, the ADM-G module is responsible for the dominant unstable state vector and the disturbance severity vector The processing process is as follows:

[0156] 1) Upon receiving the dominant unstable state vector After that, the ADM-G module determines whether there is an element If it exists, the indicator indicates that there is a dominant unstable group in the generator group, and the system state is also unstable, so the output system-level judgment index is .

[0157] 2) If the dominant instability state vector If all elements in are less than 0.5, then the receiving disturbance severity vector , determine the disturbance severity vector Is there an element in If it exists, then this indicator indicates that there is an unstable group in the generator group, and the system state is also unstable, so the output system-level judgment index .

[0158] 3) If the above judgment process is not satisfied, the system-level judgment index is output .

[0159] In this example, the operation logic of the ADM-S module is as follows:

[0160] The input of the ADM-S module is the system stable state , System stability level and system-level discrimination indicators :

[0161] 1) System stable state The value of is 0 or 1. , then the indicator indicates that the system state is unstable, otherwise it indicates that the system state is not unstable.

[0162] 2) System stability level The value range is -1~1, and contains the threshold parameter .like , then this indicator indicates that the system state is unstable. , it indicates that the system is not unstable. , it indicates that the system state is uncertain.

[0163] ADM-S module integrated system stable state , System stability level and system-level discrimination indicators In the case of uncertainty, it is decided to use the model prediction results of the stable evaluation model or mark them as uncertain and send them to the precise time domain simulation for calculation.

[0164] Based on the above, the ADM-S module has a great impact on the system stability. , System stability level and system-level discrimination indicators The processing process is as follows:

[0165] 1) First, according to the stable state of each system , System stability level and system-level discrimination indicators The numerical output signal Boolean value, system stable state , System stability level and system-level discrimination indicators The value and signal of The Boolean value relationship is as follows:

[0166] Table 1

[0167]

[0168] 2) In addition to Other than the signal press Figure 4 middle( Figure 4 In In this example Meaning corresponding, Figure 4 System steady state parameters , System stability level parameters and system-level discrimination parameters Compared with the system stable state in this example , System stability level and system-level discrimination indicators The final judgment Boolean value is obtained by the logical output of the AND gate and the OR gate (one-to-one correspondence). This Boolean value measures the consistency of the meaning of each indicator. If the Boolean value is True, it means that the system is in a stable state. , System stability level and system-level discrimination indicators If the sample is consistent, it indicates instability or not, which is a confirmed sample. Otherwise, the system is in a stable state. , System stability level and system-level discrimination indicators If it is inconsistent, the system stable state is uncertain, which is an uncertain sample.

[0169] 3) If the Boolean value is True, output the four prediction indicators of the stability evaluation model, that is, the system stability state , System stability level , dominant instability state vector and the disturbance severity vector Otherwise, the time domain simulation is called to recalculate the sample to be analyzed to obtain accurate values ​​of the four indicators.

[0170] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0171] Based on the same inventive concept, the embodiment of the present application also provides a power grid stability assessment device for implementing the power grid stability assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power grid stability assessment device embodiments provided below can refer to the limitations of the power grid stability assessment method above, and will not be repeated here.

[0172] In an exemplary embodiment, Figure 8 As shown, a power grid stability assessment device is provided, comprising: a sample construction module 801, an indicator prediction module 802, an indicator determination module 803, a mode determination module 804 and a stability assessment module 805, wherein:

[0173] The sample construction module 801 is used to determine the operation parameters and at least one preset operation fault type according to the preset operation mode of the power grid, and to construct the sample to be analyzed of the power grid according to the fault parameters and operation parameters corresponding to the at least one preset operation fault type;

[0174] The indicator prediction module 802 is used to predict the stability of the power grid based on the samples to be analyzed by using the pre-trained stability prediction model, and obtain the system-level stability indicator of the power grid and the device-level stability indicator of the power equipment running in the power grid;

[0175] The indicator determination module 803 is used to determine the stability of the power grid based on the system-level stability indicator to obtain a first determination result of the power grid, and to determine the stability of the power grid based on the device-level stability indicator to obtain a second determination result of the power grid;

[0176] A method determination module 804 is used to determine a target analysis method for the power grid according to the first determination result and the second determination result;

[0177] The stability assessment module 805 is used to perform stability assessment on the power grid by using a target analysis method to obtain a stability assessment result of the power grid.

[0178] In an optional embodiment, the sample construction module 801 is also used to obtain the topological structure of the power grid; determine the preset operating mode of the power grid, and determine the operating parameters corresponding to each system node in the topological structure according to the preset operating mode; determine at least one preset operating fault type corresponding to the preset operating mode, and determine the fault parameters corresponding to each system node in the topological structure according to the operating parameters and the preset operating fault type; construct an adjacency matrix and a node feature matrix based on a graph structure based on the topological structure, the operating parameters corresponding to each system node, and the fault parameters corresponding to each system node, and obtain the sample to be analyzed based on the adjacency matrix and the node feature matrix.

[0179] In an optional embodiment, the indicator prediction module 802 is also used to input the samples to be analyzed into a pre-trained stability prediction model; through the system-level stability prediction sub-model of the stability prediction model, a system-level stability prediction is performed on the power grid based on the samples to be analyzed, and the system-level stability indicator of the power grid is obtained; through the device-level stability prediction sub-model of the stability prediction model, a device-level stability prediction is performed on each operating power device in the power grid based on the samples to be analyzed, and the device-level stability indicator of each operating power device in the power grid is obtained.

[0180] In an optional embodiment, the system-level stability index includes a system stable state parameter and a system stable level parameter.

[0181] The indicator determination module 803 is also used to perform system-level parameter determination on the system stability state parameters and the system stability level parameters to obtain a third determination result; determine the system-level instability state of the power grid based on the third determination result, and determine the first determination result of the power grid based on the system-level instability state.

[0182] In an optional embodiment, the device-level stability index includes a dominant unstable state parameter and a disturbance severity parameter of the operating power equipment.

[0183] The indicator determination module 803 is also used to perform device-level parameter determination on each dominant instability state parameter and disturbance severity parameter to obtain a fourth determination result; determine the device-level instability state of the power grid based on the fourth determination result, and determine the second determination result of the power grid based on the device-level instability state.

[0184] In an optional embodiment, the method determination module 804 is also used to evaluate the stability of the power grid based on the system-level stability index and the device-level stability index when the first determination result and the second determination result are consistent; when the first determination result and the second determination result are inconsistent, perform time domain simulation on the power grid based on the sample to be analyzed to obtain stability simulation parameters of the power grid, and evaluate the stability of the power grid based on the stability simulation parameters.

[0185] Each module in the above-mentioned power grid stability assessment device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0186] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as operating parameters, fault parameters, samples to be analyzed, system-level stability indicators, device-level stability indicators, first judgment results, and second judgment results. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a power grid stability assessment method is implemented.

[0187] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0188] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the power grid stability assessment method of the above embodiment are implemented.

[0189] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the power grid stability assessment method of the above embodiment are implemented.

[0190] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of the power grid stability assessment method of the above embodiment when executed by a processor.

[0191] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0192] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0193] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0194] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for evaluating power grid stability, characterized in that: The method comprises: Determine operating parameters and at least one preset operating fault type according to a preset operating mode of the power grid, and construct a sample to be analyzed of the power grid according to the fault parameters corresponding to the at least one preset operating fault type and the operating parameters; By using a pre-trained stability prediction model, stability prediction is performed on the power grid based on the sample to be analyzed to obtain a system-level stability index of the power grid and a device-level stability index of the power equipment running in the power grid; Performing stability determination on the power grid based on the system-level stability index to obtain a first determination result of the power grid, and performing stability determination on the power grid based on the device-level stability index to obtain a second determination result of the power grid; Determining a target analysis method for the power grid according to the first determination result and the second determination result; The target analysis method is used to perform stability assessment on the power grid to obtain a stability assessment result of the power grid.

2. The method according to claim 1, characterized in that The step of determining a target analysis method for the power grid according to the first determination result and the second determination result includes: When the first determination result and the second determination result are consistent, evaluating the stability of the power grid based on the system-level stability index and the device-level stability index; When the first determination result and the second determination result are inconsistent, the power grid is simulated in the time domain based on the sample to be analyzed to obtain stability simulation parameters of the power grid, and the stability of the power grid is evaluated based on the stability simulation parameters.

3. The method according to claim 1, characterized in that The system-level stability index includes a system stability state parameter and a system stability level parameter; The performing stability determination on the power grid based on the system-level stability index to obtain a first determination result of the power grid includes: Performing system-level parameter determination on the system stable state parameter and the system stable level parameter to obtain a third determination result; A system-level instability state of the power grid is determined based on the third determination result, and a first determination result of the power grid is determined based on the system-level instability state.

4. The method according to claim 1, characterized in that: The equipment-level stability index includes the dominant instability state parameter and the disturbance severity parameter of the operating power equipment; The performing stability determination on the power grid based on the device-level stability index to obtain a second determination result of the power grid includes: Performing device-level parameter determination on each of the dominant instability state parameters and the disturbance severity parameter to obtain a fourth determination result; A device-level instability state of the power grid is determined based on the fourth determination result, and a second determination result of the power grid is determined based on the device-level instability state.

5. The method according to any one of claims 1 to 4, characterized in that: The determining, according to a preset operation mode of the power grid, an operation parameter and at least one preset operation fault type, and constructing a sample to be analyzed of the power grid according to the fault parameter corresponding to the at least one preset operation fault type and the operation parameter, comprises: Obtain the topology of the power grid; Determining a preset operation mode of the power grid, and determining operation parameters corresponding to each system node in the topological structure according to the preset operation mode; Determine at least one preset operation fault type corresponding to the preset operation mode, and determine the fault parameters corresponding to each of the system nodes in the topological structure according to the operation parameters and the preset operation fault type; Based on the topological structure, the operating parameters corresponding to each of the system nodes and the fault parameters corresponding to each of the system nodes, an adjacency matrix and a node feature matrix based on a graph structure are constructed, and samples to be analyzed are obtained according to the adjacency matrix and the node feature matrix.

6. The method according to any one of claims 1 to 4, characterized in that: The pre-trained stability prediction model performs stability prediction on the power grid based on the sample to be analyzed to obtain a system-level stability index of the power grid and a device-level stability index of the power equipment running in the power grid, including: Inputting the sample to be analyzed into a pre-trained stability prediction model; By using the system-level stability prediction sub-model of the stability prediction model, a system-level stability prediction is performed on the power grid based on the sample to be analyzed to obtain a system-level stability index of the power grid; By using the device-level stability prediction sub-model of the stability prediction model, device-level stability prediction is performed for each operating power device in the power grid based on the samples to be analyzed, so as to obtain the device-level stability index of each operating power device in the power grid.

7. A power grid stability assessment device, characterized in that: The device comprises: A sample construction module, used to determine operating parameters and at least one preset operating fault type according to a preset operating mode of the power grid, and to construct a sample to be analyzed of the power grid according to the fault parameters corresponding to the at least one preset operating fault type and the operating parameters; An indicator prediction module, used to perform stability prediction on the power grid based on the sample to be analyzed by using a pre-trained stability prediction model, and obtain a system-level stability indicator of the power grid and a device-level stability indicator of the power equipment running in the power grid; An indicator determination module, configured to perform stability determination on the power grid based on the system-level stability indicator to obtain a first determination result of the power grid, and perform stability determination on the power grid based on the device-level stability indicator to obtain a second determination result of the power grid; A method determination module, configured to determine a target analysis method for the power grid according to the first determination result and the second determination result; The stability assessment module is used to perform stability assessment on the power grid using the target analysis method to obtain a stability assessment result of the power grid.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images