Network spare power automatic switching rapid fault isolation and power recovery method based on power grid dispatching control system

Abstract

The invention relates to a network spare power automatic switching rapid fault isolation and power recovery method based on a power grid dispatching control system. The power grid dispatching control system controls a power grid system, the power grid system comprises a plurality of power grid components, and the method comprises the following steps: in response to a fault in the power grid system, for each power grid component, calculating a first anomaly degree of the power grid component in a current actual fault network according to the number of associated links of the power grid component; calculating to obtain a second anomaly degree of the power grid component in the simulated fault network based on a predetermined number of associated links of the power grid component in the simulated fault network; determining an abnormal power grid component in the power grid components based on the first anomaly degree and the second anomaly degree calculated by each power grid component; and according to the simulation fault description information and the abnormal power grid component, determining an isolation component, and after the isolation component is isolated, performing power restoration on the power grid system. By adopting the method, the power grid component with the fault can be determined, and power restoration is performed after isolation, so that the power restoration efficiency is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method for rapid fault isolation and power restoration of a network standby automatic switching-in based on a power grid dispatching and control system. Background Art

[0002] With the advent of the big data era, data analysis and summarization are increasingly being used in more and more scenarios. Grid dispatch and control systems are crucial components of power system operations and consist of numerous components. Failure in a component triggers a series of component alarms, jeopardizing the safety of the power system.

[0003] As the scale of the power grid expands and the number of interconnected objects continues to increase, the number of components in the power grid system increases, and the amount of data generated is also increasing. Traditional fault point identification methods are not ideal because they do not consider the correlation and mutual influence between the various dimensions of the detection data. This leads to high false alarm rates and difficulty in detecting some underlying system anomalies. When power is restored after isolation, the inability to detect underlying system anomalies can lead to the recurrence of anomalies during the power restoration process, thereby reducing power restoration efficiency. Summary of the Invention

[0004] Based on this, it is necessary to provide a network backup automatic rapid fault isolation and power restoration method based on the power grid dispatching and control system to address the above technical problems.

[0005] In a first aspect, the present disclosure provides a method for rapid fault isolation and power restoration based on a network backup automatic switching system of a power grid dispatching and control system. The power grid dispatching and control system controls a power grid system, which includes multiple power grid components. The method includes:

[0006] In response to a fault occurring in the power grid system, for each power grid component, calculating a first abnormality degree of the power grid component in a current actual fault network according to the number of associated links of the power grid component;

[0007] Based on the number of associated links of the power grid components in a predetermined simulated fault network, a second abnormality degree of the power grid components in the simulated fault network is calculated, wherein the simulated fault network is generated based on the fault correlation coefficients of the power grid components, a preset distribution of power grid component failure rates, and simulated fault description information; the simulated fault description information is used to describe the fault association relationship between the power grid components;

[0008] determining an abnormal power grid component among the power grid components based on the first abnormality degree and the second abnormality degree calculated for each power grid component;

[0009] An isolation component is determined based on the simulated fault description information and the abnormal power grid component. After the isolation component is isolated, power is restored to the power grid system.

[0010] In one embodiment, the method further comprises:

[0011] Determining grid components included in the grid system, and determining a fault correlation coefficient between the grid components based on the fault correlation between the grid components;

[0012] Based on a preset distribution of failure rates of power grid components and a failure correlation coefficient between the power grid components, generating a simulated time sample sequence including the distribution characteristics of the power grid component failures;

[0013] Scaling the simulated data contained in the simulated time sample sequence to a preset range interval, and determining simulated fault description information according to a preset fault threshold;

[0014] Based on the simulated fault description information and the power grid components, an association relationship of power grid component faults is constructed to form a simulated fault network.

[0015] In one embodiment, the failure rate distribution is a normal distribution, and generating a simulated time sample sequence containing the failure distribution characteristics of the power grid components based on a preset power grid component failure rate distribution and a failure correlation coefficient between the power grid components includes:

[0016] generating a fault correlation coefficient matrix based on the fault correlation coefficients between the power grid components;

[0017] generating an N-dimensional independent standard normal distribution random variable sampling sequence according to the total number of the power grid components, wherein N is determined based on the total number of the power grid components;

[0018] Generate a preliminary simulation time interval sequence based on the fault correlation coefficient matrix and the N-dimensional independent standard normal distribution random variable sampling sequence;

[0019] The mean and standard deviation of the failure rate of each power grid component are determined, and a simulated time sample sequence containing the failure distribution characteristics of the power grid component is generated based on the preliminary simulation time interval sequence and the mean and standard deviation of the failure rate of each power grid component.

[0020] In one embodiment, the simulated fault description information includes: a faulty power grid component and a fault type of the faulty power grid component, wherein the fault type includes: a single fault and an associated fault. The process of constructing an association relationship between power grid component faults based on the simulated fault description information and the power grid components to form a simulated fault network includes:

[0021] generating a first-layer component network based on the power grid components, the individually faulty power grid components, and connection relationships between the power grid components;

[0022] generating a second-layer component network based on the power grid components, the faulty power grid components of the associated faults, and connection relationships between the power grid components;

[0023] A simulated fault network is generated based on the first layer component network and the generated second layer component network.

[0024] In one embodiment, determining an abnormal power grid component among the power grid components based on the first abnormality degree and the second abnormality degree calculated for each power grid component includes:

[0025] An index value for measuring the degree of fit between the simulated fault network and the actual fault network is calculated based on the first abnormality degree and the second abnormality degree;

[0026] The smallest abnormal index value among the index values ​​is determined, and the abnormal power grid component is determined based on the power grid components that match the abnormal index value.

[0027] In one embodiment, the index value for measuring the degree of fit between the simulated fault network and the actual fault network, calculated based on the first abnormality degree and the second abnormality degree, includes:

[0028] calculating a Euclidean distance based on the first abnormality and the second abnormality;

[0029] Calculating a cosine distance based on the first abnormality and the second abnormality;

[0030] An index value for measuring the degree of fit between the simulated fault network and the actual fault network is calculated based on the Euclidean distance and the cosine distance.

[0031] In one embodiment, the simulated fault description information includes: a faulty power grid component and a fault type of the faulty power grid component, wherein the fault type includes: a single fault and a correlated fault. Determining the isolation component based on the simulated fault description information and the abnormal power grid component includes:

[0032] In response to the abnormal power grid component being included in the faulty power grid component, determining a fault type that matches the abnormal power grid component in the simulated fault description;

[0033] In response to the fault type matched by the abnormal power grid component being an associated fault, determining an associated power grid component associated with the abnormal power grid component based on the associated fault;

[0034] Determining an isolated component based on the associated power grid component and the abnormal power grid component;

[0035] In response to the abnormal power grid component being included in the faulty power grid component and / or the fault type matched by the abnormal power grid component being an isolated fault, an isolation component is determined based on the abnormal power grid component.

[0036] In a second aspect, the present disclosure further provides a method and apparatus for rapid fault isolation and power restoration of a network backup automatic switching system based on a power grid dispatching and control system. The power grid dispatching and control system controls a power grid system, which includes multiple power grid components. The apparatus includes:

[0037] a first abnormality degree calculation module configured to, in response to a fault occurring in the power grid system, calculate, for each power grid component, a first abnormality degree of the power grid component in a current actual fault network based on the number of associated links of the power grid component;

[0038] a second abnormality degree calculation module, configured to calculate a second abnormality degree of the power grid component in a predetermined simulated fault network based on the number of associated links of the power grid component in the predetermined simulated fault network, wherein the simulated fault network is generated based on the fault correlation coefficient of the power grid component, a preset distribution of power grid component failure rates, and simulated fault description information; the simulated fault description information is used to describe the fault association relationship between the power grid components;

[0039] an abnormal power grid component determining module, configured to determine an abnormal power grid component among the power grid components based on the first abnormality degree and the second abnormality degree calculated for each power grid component;

[0040] The power restoration module is used to determine the isolated component based on the simulated fault description information and the abnormal power grid component, isolate the isolated component, and then restore power to the power grid system.

[0041] In a third aspect, the present disclosure further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in any of the above embodiments when executing the computer program.

[0042] In a fourth aspect, the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in any of the above embodiments when executed by a processor.

[0043] In a fifth aspect, the present disclosure further provides a computer program product, which includes a computer program that implements the steps in any of the above embodiments when executed by a processor.

[0044] In each of the above-described embodiments, by separately calculating the first abnormality degree of the grid components in the actual fault network and the second abnormality degree of the grid components in the simulated fault network, and determining the abnormal grid components based on these two abnormality degrees, it is possible to more accurately identify the components affected by or potentially causing the fault during a grid fault. This analysis method, based on quantitative indicators (such as the number of associated links), can more accurately pinpoint the problem location than traditional empirical or simple inspection methods, improving the efficiency and accuracy of fault location. Determining the isolated components based on the simulated fault description and the abnormal grid components allows for targeted isolation measures, avoiding the blind disconnection of large numbers of lines or equipment and minimizing the impact on the normal operation of the grid. Restoring power after isolating the isolated components helps quickly restore normal grid power supply, shorten outage duration, and minimize the losses caused by the fault to production and life. This method comprehensively considers the fault correlations between grid components and comprehensively understands the operation of the grid during a fault condition. By promptly isolating the isolated components, further propagation and expansion of the fault is prevented, ensuring the safe operation of other normal components in the grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A schematic diagram of an application environment of a method for rapid fault isolation and power restoration of a network backup automatic switching system based on a power grid dispatching control system in one embodiment;

[0047] Figure 2 1. A flow chart of a method for rapid fault isolation and power restoration of a network backup automatic switching system based on a power grid dispatching and control system in one embodiment;

[0048] Figure 3 A schematic diagram of a process for generating a simulated fault network in one embodiment;

[0049] Figure 4 Schematic diagram of the process of step S304 in one embodiment;

[0050] Figure 5 Schematic diagram of the process of step S308 in one embodiment;

[0051] Figure 6 Schematic diagram of the process of step S206 in one embodiment;

[0052] Figure 7Schematic diagram of the process of step S602 in one embodiment;

[0053] Figure 8 Schematic diagram of the process of step S208 in one embodiment;

[0054] Figure 9 A schematic block diagram of the structure of a network standby automatic switching rapid fault isolation and power restoration device based on a power grid dispatching control system in one embodiment;

[0055] Figure 10 is a schematic diagram of the internal structure of a computer device in one embodiment;

[0056] Figure 11 Schematic diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and are not intended to limit the present disclosure.

[0058] It should be noted that the terms "first," "second," and the like in the specification and claims herein and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0059] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" could mean: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the related objects.

[0060] As described in the background, conventional methods for determining fault points include directed graph-based methods and fault tree-based methods. Because systems are constantly updated and various components are added, resulting in numerous components and complex connections, directed graph-based modeling methods require adjustments and updates to the directed graph's logical topology every time the system structure changes or new information is added, which is costly. Constructing an accurate fault tree requires detailed system knowledge, so fault tree-based methods require the participation of experts from different fields. Only experts, drawing on their expertise and experience in their respective fields, can accurately determine the logical relationships between fault events and correctly construct a fault tree. This approach is highly restrictive and, when faced with large amounts of data, is inefficient and inefficient.

[0061] Therefore, in order to solve the above technical problems, the embodiment of the present disclosure provides a network backup automatic switching rapid fault isolation and power restoration method based on the power grid dispatching control system, which can be applied to Figure 1 In the application environment shown, terminal 102 communicates with power grid dispatching and control system 104 via a network. Power grid dispatching and control system 104 controls the power grid system. The power grid system includes multiple power grid components. In response to a power grid system fault, terminal 102 may calculate, for each power grid component, a first abnormality degree of the power grid component in the current actual fault network based on the number of associated links of the power grid component. Terminal 102 may calculate a second abnormality degree of the power grid component in a simulated fault network based on the number of associated links of the power grid component in a predetermined simulated fault network. The simulated fault network is generated based on the fault correlation coefficients of the power grid components, a preset distribution of power grid component failure rates, and simulated fault description information; the simulated fault description information describes the fault correlation relationships between the power grid components. Terminal 102 may determine an abnormal power grid component among the power grid components based on the first and second abnormality degrees calculated for each power grid component. Terminal 102 may determine an isolated component based on the simulated fault description information and the abnormal power grid component, isolate the isolated component, and then restore power to the power grid system. Terminal 102 may include, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Grid dispatch control system 104 may be implemented using a standalone server or a server cluster consisting of multiple servers.

[0062] In one embodiment, Figure 2As shown, a method for rapid fault isolation and power restoration of network backup automatic switching based on power grid dispatching control system is provided. Figure 1 The terminal 102 or the power grid dispatching control system 104 is used as an example to illustrate, including the following steps:

[0063] S202 , in response to a fault occurring in the power grid system, for each power grid component, a first abnormality degree of the power grid component in a current actual fault network is calculated based on the number of associated links of the power grid component.

[0064] The power grid system typically encompasses power generation, transmission, transformation, distribution, and consumption. It is responsible for delivering electricity from power plants to various end users, ensuring a stable supply. It is a complex and extensive system engineering project. Grid components can be the various devices and components that make up the grid system, such as generators, transformers, transmission lines, circuit breakers, and relays. They play different roles in the generation, transmission, and distribution of electricity. The number of associated links generally refers to the number of electrical or communication connections established between each grid component and other components. These connections are used to transmit power, control signals, data, and other information, reflecting the close interaction between the component and other parts. The current actual fault network refers to the network formed by the actual state of each component and their connections when a fault occurs in the grid system, reflecting the actual situation after the fault occurs. The first abnormality degree can be an indicator that quantifies the degree of abnormality of each grid component in the current actual fault network. The value reflects the degree to which the component deviates from normal operation and is an important basis for assessing the impact of the fault on each component. The power grid dispatching and control system is an automated system for monitoring, controlling and dispatching the power grid. It plays a key role in ensuring the safe, stable and economical operation of the power grid.

[0065] Specifically, during normal operation of the power grid system, the number of associated links for each power grid component is recorded in detail using tools such as the power grid topology design document and a geographic information system (GIS). (In some embodiments of the present disclosure, there are no restrictions on how the number of associated links is determined.) Simultaneously, a real-time monitoring system is used to track and record the connection status between power grid components in real time for subsequent comparison. For example, if a transmission line is connected to multiple substations and other transmission lines, the number of all connected devices is recorded to determine the number of associated links. When a power grid system fault occurs, the fault monitoring system immediately activates and uses various sensors and monitoring devices to monitor the status of the associated links of each power grid component in real time. This is compared with the link status during normal operation to determine which links are no longer functioning properly after the fault. The number of missing associated links for each component is then calculated. For example, if a transformer is originally connected to three transmission lines and one line is disconnected after the fault, the number of missing associated links for the transformer is 1. This is calculated for each power grid component using the formula: first abnormality degree = number of associated links missing for the component during the fault / total number of associated links when the component is functioning normally. For example, if a circuit breaker has five associated links when operating normally and two links disappear during a fault, its first abnormality degree is 2 / 5 = 0.4. This calculation yields the first abnormality degree of each grid component in the current actual fault network, which is used for subsequent fault analysis.

[0066] S204 : Calculate a second abnormality degree of the power grid component in the simulated fault network based on a predetermined number of associated links of the power grid component in the simulated fault network.

[0067] The predetermined simulated fault network is typically constructed in advance using specific methods and rules to simulate the network model of the power grid system under fault conditions. This model, based on an understanding of the power grid system, historical fault data, and relevant expertise, defines various fault scenarios and fault propagation relationships between components. The simulated fault network is generated based on the fault correlation coefficients of the power grid components, a preset distribution of power grid component failure rates, and simulated fault description information; this simulated fault description information describes the fault correlation relationships between the power grid components. The fault correlation coefficient of a power grid component is typically a numerical value that measures the degree of mutual impact between faults in different power grid components. It reflects the likelihood that a fault in one component will cause faults in other components. For example, a high fault correlation coefficient between a transformer and a transmission line indicates that a transformer failure is likely to cause problems in the transmission line due to the transformer. The preset power grid component failure rate distribution refers to a predetermined probability distribution of each power grid component's failure within a certain period of time, based on various factors such as historical power grid component operating data, device characteristics, and environmental factors. In some embodiments of the present disclosure, the failure rate distribution can be a normal distribution. Simulated fault description information: This is a collection of information used to describe in detail the fault correlation relationships between power grid components under simulated fault scenarios. It may include which components fail first, how the fault propagates to other components, and the order in which faults occur between components and the specific ways in which they affect each other. A simulated fault network can be constructed based on the simulated fault description information to simulate a network model of the power grid under a fault state. It shows the fault propagation path and mutual relationship between power grid components under a specific fault scenario. The second abnormality degree is usually a quantitative indicator used to measure the degree of abnormality of a power grid component in a simulated fault network. It reflects the degree to which the component deviates from the normal state under a simulated fault scenario and can be used for comparative analysis and fault simulation evaluation.

[0068] Specifically, in the simulated fault network, for each power grid component, the number of all associated links in the normal state and the number of associated links that disappeared after the simulated fault occurred are counted. This information can be obtained through the constructed network model and data records during the simulation process. For example, for a substation, record how many transmission lines and other substations it was originally connected to, and how many connections had problems after the simulated fault. Calculate according to the formula: second abnormality = number of associated links that disappeared in the component in the simulated fault network / number of all associated links when the component was normal in the simulated fault network. For example, if a switch device has 8 associated links when it is normal in the simulated fault network, and 3 links fail after the simulated fault occurs, then the second abnormality of the switch device is 3 / 8=0.375. Through such calculations, the second abnormality of each power grid component in the simulated fault network is obtained.

[0069] In some exemplary embodiments, a simulated fault network can be generated in the following manner: based on a preset distribution of grid component failure rates, one or more components are randomly selected as the initial faulty components. For example, components are sorted by failure rate, and then the initial faulty component is selected from the components with high failure rates with a certain probability. For example, if an old transformer in a substation has a high failure rate, it is likely to be selected as the initial faulty component. Starting with the initial faulty component, the fault correlation coefficient is used to determine the other components that may be affected, and then a certain rule (such as a probability threshold) is used to determine whether these components will fail. For example, if the fault correlation coefficient between the initially faulty transformer and a transmission line is 0.8, and it is assumed that when the correlation coefficient is greater than 0.6, the affected components have an 80% probability of failure, then random number generation or other methods can be used to simulate whether the transmission line will fail due to the transformer failure. If the simulation results indicate that the transmission line has failed, the fault is further propagated based on the fault correlation coefficients between the transmission line and other components until a preset simulation termination condition is met (such as when the fault propagation reaches a certain scale or the simulation time reaches a certain limit). During the fault propagation simulation, detailed fault associations between components are recorded, including the order in which faults occur and the impact paths between components. This information forms a simulated fault description. For example, a transformer fault at time t1, which then causes a fault on the connected transmission line at time t2, and the transmission line fault in turn affects downstream switchgear at time t3, forms the core of the simulated fault description. Based on the actual power grid topology, a virtual network model is constructed, in which nodes represent grid components and edges represent electrical connections or fault propagation paths between components. For example, components such as power plants, substations, and transmission lines are represented as nodes, and their connections are represented by line segments or arcs, forming a network topology similar to the actual power grid layout. Based on the generated simulated fault description, the fault status and fault propagation path of each component are marked on the network topology. For example, the faulty component node is marked red or another special color, and the direction of fault propagation is indicated by an arrow, from the faulty component to the affected components. This intuitively displays the state of the simulated faulty network in the network model.

[0070] S206 : Determine an abnormal power grid component among the power grid components based on the first abnormality degree and the second abnormality degree calculated for each power grid component.

[0071] Abnormal grid components generally refer to those that exhibit abnormal behavior or status when a fault occurs in the grid system. These components may be the cause of the fault or the part that is significantly affected during the fault propagation process.

[0072] Specifically, the thresholds of the first abnormality degree and the second abnormality degree can be set according to the operating experience and actual needs of the power grid. These thresholds are used to determine whether a component is an abnormal component. For example, the first abnormality degree threshold is set to 0.5 and the second abnormality degree threshold is set to 0.4. For each power grid component, the calculated first abnormality degree and second abnormality degree are compared with the corresponding thresholds respectively. If the first abnormality degree of a component is greater than or equal to the first abnormality degree threshold, and the second abnormality degree is greater than or equal to the second abnormality degree threshold, then the component is determined to be an abnormal power grid component. For example, if the first abnormality degree of a component is 0.6 and the second abnormality degree is 0.5, both exceeding their respective thresholds, then the component is an abnormal power grid component.

[0073] In addition to simply comparing the results with the threshold, a comprehensive evaluation of the first and second abnormality levels can also be considered. For example, different weights can be assigned to the first and second abnormality levels, and then their weighted average can be calculated to determine whether the component is abnormal.

[0074] S208: Determine an isolation component based on the simulated fault description information and the abnormal power grid component, isolate the isolation component, and then restore power to the power grid system.

[0075] Among them, the isolation components are grid components that are further screened out from the abnormal grid components and need to be isolated. The purpose of isolating these components is to prevent the fault from spreading further, protect the normal operation of other parts of the grid, and create conditions for the restoration of power to the grid system. Network backup automatic switch is an automatic device in the power system that can quickly put the backup power supply into operation to ensure continuous power supply to users when the working power supply is disconnected due to a fault or other reasons. In the power grid dispatching and control system, the role of network backup automatic switch is particularly important. It can quickly isolate the fault when a fault occurs in the power grid, avoid the expansion of the fault range, and quickly restore power supply to improve the power supply reliability of the power grid. In some embodiments of the present disclosure, the network backup automatic switch method can be used when restoring power.

[0076] Specifically, the simulated fault description information is combined with the identified abnormal grid components. For each abnormal grid component, its role and impact in the simulated fault scenario are evaluated. Thus, the isolated component is determined. After the isolation of the isolated component is completed, the overall status of the power grid system is first evaluated. Check whether there are other potential faults or safety hazards in the remaining part of the power grid, evaluate whether the power flow distribution meets the requirements of the power grid operation, and ensure that the power grid has the conditions for power restoration. Then restore power. In addition, it should be noted that if the isolated component is a necessary component in the power grid system, the power grid will not be able to operate after the isolated component is isolated. At this time, there is no need to restore power to the grid. A prompt is output to remind the staff to repair the fault.

[0077] The aforementioned method for rapid fault isolation and power restoration based on network backup automatic switching (NBS) in a power grid dispatching and control system calculates the first abnormality degree of grid components in the actual fault network and the second abnormality degree of grid components in the simulated fault network. Based on these two abnormality degrees, the abnormal grid components are identified, enabling more accurate identification of components affected by or potentially causing a fault in a power grid fault. This analysis method, based on quantitative indicators (such as the number of associated links), more accurately pinpoints the problem location than traditional empirical or simple inspection methods, improving the efficiency and accuracy of fault location. Isolating components based on simulated fault descriptions and abnormal grid components allows for targeted isolation measures, avoiding the blind shutdown of large numbers of lines or equipment and minimizing the impact on the normal operation of the power grid. Restoring power after isolating the isolated components helps quickly restore normal power supply to the grid, shortening outage duration and minimizing the losses caused by the fault to production and life. This method comprehensively considers the fault correlations between grid components and provides a holistic understanding of the grid's operation during a fault condition. By promptly isolating isolated components, further propagation and expansion of the fault is prevented, ensuring the safe operation of other normal components in the grid.

[0078] In one embodiment, Figure 3 As shown, the method further includes:

[0079] S302: Determine grid components included in the grid system, and determine a fault correlation coefficient between the grid components based on the fault correlation between the grid components.

[0080] Fault correlation generally refers to the mutual influence and correlation between various components in a power grid when faults occur. This means that a fault in one component may trigger faults in other components, or be affected by the faults of other components. The fault correlation coefficient is a numerical value used to quantify the fault correlation between power grid components. It reflects the degree of mutual influence between two components when a fault occurs. The fault correlation coefficient is typically calculated based on historical fault data, power grid topology, electrical parameters, and other factors. It can also be manually set based on experience with fault correlation. Its value generally ranges from 0 to 1, with 0 indicating no fault correlation between the two components and 1 indicating a very strong fault correlation between the two components. This means that if one component fails, the other is highly likely to fail as well.

[0081] In some exemplary embodiments, a correlation coefficient matrix may also be generated according to fault correlation coefficients between power grid components.

[0082] S304 : Based on a preset distribution of failure rates of power grid components and a failure correlation coefficient between the power grid components, a simulation time sample sequence including the distribution characteristics of the power grid component failures is generated.

[0083] The simulated time sample series is a series of data generated through simulation. This data is arranged in chronological order and describes the fault status of each power grid component at different points in time (such as the presence of a fault and the type of fault). It is generated using a specific stochastic simulation method based on a preset failure rate distribution and correlation coefficients between components. It is used to simulate possible power grid fault conditions over a period of time, thereby facilitating analysis and prediction of the grid's operational status and reliability. The fault distribution characteristics of power grid components generally refer to the probability, frequency, type, and correlation between failures of each component in the grid. For example, some components may be more prone to short-circuit failures, while others may experience overload failures more frequently. Failures between different components may follow a certain order or influence each other. These characteristics, reflected in the simulated time sample series, provide a quantitative description of power grid fault conditions.

[0084] Specifically, the failure rate distribution of the preset grid components and the failure correlation coefficient between the grid components can be used to select a simulation method (Monte Carlo simulation, Markov chain simulation, etc.) to generate a simulated time sample sequence containing the failure distribution characteristics of the grid components.

[0085] For example, based on the preset failure rate distribution, corresponding failure probability parameters can be set for each power grid component. At the same time, a fault correlation model between components is established based on the correlation coefficients between components. Within each time step, each power grid component is randomly sampled. Based on its preset failure rate distribution, it is determined whether the component has failed at the current time step. If a failure occurs, the fault type is further determined based on the probability distribution of the fault type. At the same time, the correlation coefficients between components are taken into account, and the probability of failure of other components is adjusted based on the component that has already failed. For example, if the correlation coefficient between two components is high, when one component fails, the probability of failure of the other component will increase accordingly. This process is repeated until the set time range is simulated and a simulation time sample sequence is generated.

[0086] S306 , scaling the simulation data contained in the simulation time sample sequence to a preset range, and determining simulation fault description information according to a preset fault threshold.

[0087] Simulated data refers to the specific data information contained in the simulated time sample sequence regarding the fault status and related parameters of power grid components. For example, this includes identification data indicating whether a power grid component is in a fault state at a certain point in time, or relevant parameter data at the time of the fault (such as fault current and voltage change). A preset range is a pre-defined data range used to scale the simulated data. Common ranges include [0, 1]. Simulated fault description information is generated by comparing the simulated data with preset fault thresholds, typically indicating whether a fault has occurred.

[0088] Specifically, each analog data in the simulation time sample sequence is processed according to a determined scaling method and mapped to a preset range interval. For example, for an analog data sequence that records the current value of a component in the power grid, after scaling processing, all current values ​​are converted to a preset range interval, making the data comparable and unified. According to the actual requirements and experience of power grid operation, a reasonable fault threshold is set. The scaled simulation data is compared with the preset fault threshold. For the simulation data at each time point, it is determined whether it exceeds the fault threshold. If it exceeds the threshold, it is considered that the corresponding power grid component at that time point has failed. Based on the results of the comparison and judgment, simulated fault description information is generated.

[0089] S308: Building association relationships among power grid component faults based on the simulated fault description information and the power grid components to form a simulated fault network.

[0090] The simulated fault network can be a network model constructed based on simulated fault description information and power grid components. It graphically displays the fault states of power grid components under simulated fault scenarios and the relationships between them. For example, the simulated fault network can be implemented using a knowledge graph.

[0091] Specifically, based on the simulated fault descriptions and the fault association clues obtained through analysis, fault association relationships are added between power grid components. Components with causal relationships are represented by directed edges, with arrows pointing from the fault source component to the affected component. Power grid components are represented as nodes, and fault association relationships as edges, to create a graph of the simulated fault network.

[0092] In this embodiment, by determining the components and fault correlation coefficients in the power grid system, it is possible to gain a deeper understanding of the mutual influence mechanism of faults between power grid components. By quantifying the fault correlation coefficient, the potential impact of a component failure on other components can be clearly understood, providing accurate basic data for subsequent fault analysis, making fault troubleshooting and diagnosis more targeted and accurate, avoiding blind troubleshooting, and improving fault location efficiency. Based on the preset fault rate distribution and fault correlation coefficient, a simulated time sample sequence is generated to simulate the fault distribution characteristics of the power grid under different conditions. This helps to predict possible future power grid faults and assess potential fault risks in advance. The simulated data is scaled to a preset range interval, and the simulated fault description information is determined based on the preset fault threshold, achieving data standardization. This makes simulated data of different types and magnitudes comparable and consistent, facilitating subsequent analysis. A simulated fault network is constructed based on the simulated fault description information and power grid components, presenting abstract fault relationships in an intuitive network form.

[0093] In one embodiment, Figure 4 As shown, the failure rate distribution is a normal distribution. It is assumed that the failure rates of power grid components follow the normal distribution law of independent, continuous variables. The normal distribution is widely present in many natural and engineering phenomena and has several attractive mathematical properties. Its invariance under linear transformations is exploited here to simplify the modeling process.

[0094] The generating of a simulated time sample sequence including the distribution characteristics of the grid component failures based on a preset grid component failure rate distribution and a failure correlation coefficient between the grid components comprises:

[0095] S402: Generate a fault correlation coefficient matrix based on the fault correlation coefficients between the power grid components.

[0096] Specifically, identify all grid components included in the grid system. Number these components sequentially. For example, if there are n grid components, number them 1, 2, ...n, and determine the fault correlation coefficient between each two grid components. Assume that the fault correlation coefficient between component i and component j is , its value range is usually between [0,1]. The larger the value, the stronger the fault correlation. Fill the elements in the matrix according to the following rules:

[0097] When i=j, that is, the fault correlation coefficient of the same component itself, usually =1, because the fault correlation of a component itself is complete.

[0098] For i In the case of component j, the previously calculated failure correlation coefficient between component i and component j is =1 is filled in the position of row i and column j of the matrix. At the same time, since the fault correlation coefficient is usually symmetrical, that is, = , so elements symmetrical about the main diagonal in the matrix are equal. After completing the matrix element filling, check and verify the matrix. Ensure that the elements in the matrix are within a reasonable value range and meet properties such as symmetry. If outliers or illogical elements are found, recheck the calculation process of the fault correlation coefficient and make corrections.

[0099] S404: Generate an N-dimensional independent standard normal distribution random variable sampling sequence based on the total number of grid components, where N is determined based on the total number of grid components. N represents the dimensionality of the space. Here, N is related to the total number of grid components and is typically equal to the total number of grid components. Each dimension corresponds to a grid component, and a point in the N-dimensional space can represent a certain state or attribute of all grid components. For example, in this problem, it is used to represent the value of a random variable related to the grid component. The independent standard normal distribution is generally a probability distribution. Independence means that each random variable is independent of each other and does not affect each other. The standard normal distribution is a special normal distribution with a mean of 0, a standard deviation of 1, and specific probability density functions and distribution characteristics. A random variable sampling sequence is typically a sequence consisting of a series of random variable values ​​drawn from an independent standard normal distribution. These values ​​are randomly generated but follow the probability laws of the independent standard normal distribution. This sampling sequence can simulate the random characteristics associated with grid components.

[0100] Specifically, an N-dimensional independent standard normal distribution random variable sampling sequence may be generated according to the total number of power grid components.

[0101] S406 : Generate a preliminary simulation time interval sequence based on the fault correlation coefficient matrix and the N-dimensional independent standard normal distribution random variable sampling sequence.

[0102] The initial simulation time interval series is a simulated time series used to describe the changes in the fault status of power grid components within a certain time range. It is generated based on the fault correlation coefficient matrix and the N-dimensional independent standard normal distribution random variable sampling sequence.

[0103] Specifically, the fault correlation coefficient matrix can be subjected to Cholesky decomposition, and then a preliminary simulation time interval sequence can be generated based on the data obtained after the decomposition and an N-dimensional independent standard normal distribution random variable sampling sequence.

[0104] In some exemplary embodiments, for example, the fault correlation coefficient matrix is , the sampling sequence of N-dimensional independent standard normal distribution random variables is , for the correlation coefficient matrix Perform Cholesky decomposition. Correlation coefficient matrix It is artificially defined based on the correlation between components and needs to meet the requirements of symmetry and positive definiteness. After decomposition, we get = ,in, and Decomposition The resulting matrix, is an upper triangular matrix. The purpose of Cholesky decomposition is to transform the correlation coefficient matrix into a form that is convenient for calculation, so as to subsequently generate a sequence of random variables with a specific correlation.

[0105] Then calculate = · , is the initial generated simulation time interval sequence. Through this matrix multiplication operation, The variables in the matrix have a correlation coefficient matrix The determined correlation.

[0106] S408: Determine the mean and standard deviation of the failure rate of each power grid component. Generate a simulation time sample sequence containing the failure distribution characteristics of the power grid component based on the preliminary simulation time interval sequence and the mean and standard deviation of the failure rate of each power grid component.

[0107] Specifically, through the formula (i=1,2,....,n) Right Further transformation is performed. Among them, Is a standard deviation and mean The sampling sequence of the correlated normally distributed random variables is , i represents the specified system component. This will generate the initial simulation time interval sequence , based on the pre-set mean standard deviation of each component and mean , converted into a simulated time sample sequence that conforms to the actual component failure distribution characteristics. Finally, the obtained simulated data is scaled to the interval [0,1] to generate a simulated time sample sequence that contains the power grid component failure distribution characteristics.

[0108] In some exemplary embodiments, the fault mean and standard deviation may be determined as follows:

[0109] Historical data statistics: This method collects long-term fault data from components in the power grid dispatching and control system. This data is used to count the number of component faults and their duration within a specific time period. Based on this historical data, statistics such as fault frequency and time interval between faults are calculated, and parameters that conform to a normal distribution are then fitted. For example, suppose there are 100 samples of fault time interval data for a component over the past year. The mean is calculated by averaging these samples. The dispersion (e.g., variance) of the sample data is then calculated and squared to obtain the standard deviation.

[0110] Estimation based on device characteristics and experience: The mean and standard deviation are estimated based on the component's design specifications, technical parameters, expected service life, and other information, combined with engineering experience. For example, if the theoretical mean time between failures of a certain database server model is known to be 5,000 hours, this can be used as an initial estimate of the mean. A subjective standard deviation can then be estimated based on the fluctuations in failure data for similar devices, the device's importance in the system, and the operating environment.

[0111] Combined simulation method: Using power system simulation software, simulate component operation under different operating conditions to generate a large amount of simulated fault data. Statistical analysis of this simulated data determines the mean and standard deviation of the component fault distribution. The simulation model is set with operating parameters and load conditions similar to those of the actual system. Multiple simulation runs are performed to generate different fault samples, and the mean and standard deviation are then calculated.

[0112] It should be noted that, depending on different situations, different methods can be selected to calculate the failure rate mean and standard deviation. In some embodiments of the present disclosure, there is no restriction on how the failure rate mean and standard deviation are determined.

[0113] In this embodiment, by generating a fault correlation coefficient matrix based on the fault correlation coefficients between power grid components, the degree of fault correlation between components can be clearly and accurately quantified in matrix form. An N-dimensional independent standard normal distribution random variable sampling sequence is generated based on the total number of power grid components, introducing a random factor to simulate power grid component failures. Given the many uncertainties inherent in power grid operation, this random simulation can more realistically reflect actual conditions and enhance the credibility of the simulation results. Using this random variable sampling sequence, different fault combinations and occurrence probabilities can be simulated, providing a rich data foundation for power grid reliability assessment. A preliminary simulation time interval sequence is generated based on the fault correlation coefficient matrix and the N-dimensional independent standard normal distribution random variable sampling sequence, combining the fault correlation relationships between components with the characteristics of random faults. This step further refines the simulation of the power grid fault process, reflecting the temporal development and changes of faults, as well as the temporal order of the mutual influence of faults between different components, facilitating a more comprehensive understanding of the dynamic process of power grid faults. The mean and standard deviation of the failure rate for each power grid component are determined, and combined with the preliminary simulation time interval sequence to generate a simulated time sample sequence that reflects the fault distribution characteristics of each power grid component. This accurately describes the failure probability distribution of each component at different time points.

[0114] In one embodiment, the simulated fault description information includes the faulty power grid component and the fault type of the faulty power grid component. The fault types include single faults and associated faults. For example, single faults may include: a single-time multi-component fault, which refers to a situation where multiple components fail simultaneously at the same time; a single-component continuous-time fault, which refers to a single component remaining in a faulty state for a continuous period of time; and associated faults, which may include multiple associated components failing simultaneously within a continuous period of time or within a single period of time.

[0115] like Figure 5 As shown, the association relationship of the power grid component faults is constructed based on the simulated fault description information and the power grid components to form a simulated fault network, including:

[0116] S502 : Generate a first-layer component network based on the power grid components, the individually faulty power grid components, and connection relationships between the power grid components.

[0117] S504: Generate a second-layer component network based on the power grid components, the faulty power grid components of the associated faults, and the connection relationships between the power grid components.

[0118] S506: Generate a simulated fault network based on the first-layer component network and the generated second-layer component network.

[0119] A faulty grid component with an isolated fault refers to a grid component that, when it fails within the grid, only affects itself and does not trigger the failure of other components. This means that the component's failure occurs independently and has no direct causal relationship with the failure of other components. A faulty grid component with a correlated fault refers to a grid component whose failure is triggered by the failure of other grid components, or whose failure causes the failure of other components. These components exhibit interconnected and impactful fault relationships. The connectivity relationships between grid components describe the physical or electrical connections between components within the grid, including transmission line connections and interfaces between devices. These connectivity relationships determine the power transmission path and the propagation path of faults between components. The first-level component network is a network model constructed based on grid components, faulty grid components with isolated faults, and their connectivity relationships. This network primarily displays the status of grid components and their connectivity when an isolated fault occurs, highlighting the location and connectivity of the faulty components within the grid. The second-level component network is a network model constructed based on grid components, faulty grid components with correlated faults, and their connectivity relationships. This network highlights the relationships between fault-related components, demonstrating the paths by which faults propagate and influence each other. The simulated fault network is a more comprehensive network model generated by combining the first- and second-layer component networks. It incorporates both individual and correlated faults, enabling a more complete simulation of grid operation under fault conditions and providing more detailed information for fault analysis, prediction, and resolution.

[0120] Specifically, based on the fault description information, faulty power grid components with individual faults are identified. A first-layer component network is constructed, using power grid components as nodes and their connections as edges. Faulty power grid components with individual faults can be specially marked or labeled in the network to distinguish them from other functioning components. For example, different colors or symbols can be used to represent individually faulty components. Based on the fault description information, faulty power grid components with associated faults are identified.

[0121] Similarly, the connections between these faulty grid components and other related grid components are analyzed to ensure a precise understanding of the fault propagation path and impact range. A second-layer component network is constructed, using these components as nodes and the connections between them as edges. The network clearly displays the relationships between the faulty components, using arrows and other methods to indicate the direction of fault propagation. The information from the first-layer component network and the second-layer component network is integrated. The nodes and edges in the two networks are merged while retaining their respective characteristics and labels. For example, the unique labels of individual faulty components and the fault propagation direction arrows between faulty components are retained. Any overlap between the two networks (e.g., components that may experience both individual faults and faults associated with other components) is appropriately processed and labeled to ensure the accuracy and completeness of the information.

[0122] In this embodiment, by generating a first-layer component network and a second-layer component network based on faulty grid components with individual faults and faulty grid components with associated faults, different types of fault conditions can be clearly distinguished and displayed. Individual faults are presented in the first-layer network, while associated faults are presented in the second-layer network. Combining the first-layer and second-layer component networks to generate a simulated fault network comprehensively simulates the operation of the grid under fault conditions. This simulated fault network integrates information about individual and associated faults, covering a wide range of possible fault scenarios, making the simulation of grid faults more realistic and accurate.

[0123] In one embodiment, Figure 6 As shown, the determining of abnormal grid components among the grid components based on the first abnormality degree and the second abnormality degree calculated for each grid component includes:

[0124] S602: Calculate, based on the first abnormality degree and the second abnormality degree, an index value for measuring the degree of fit between the simulated fault network and the actual fault network.

[0125] S604: Determine the smallest abnormal index value among the index values, and determine an abnormal power grid component based on the power grid components that match the abnormal index value.

[0126] Specifically, using Euclidean distance or angle cosine alone to measure the fit between simulated and actual fault networks may have limitations. Euclidean distance primarily measures differences based on the difference in node anomaly levels, while angle cosine focuses on measuring similarity based on the directional relationship between vectors (here, vectors representing node anomaly levels). Combining the two allows for a more comprehensive and accurate assessment of the fit between two networks, comprehensively considering various factors and improving the reliability of fault analysis.

[0127] The indicator value can be calculated using the following formula:

[0128]

[0129] in, : is the cosine value of the angle between the simulated fault network and the actual fault network obtained by the formula above. Indicates normalization operation (mapping the value to a specific range, usually [0,1]). The closer the value of is to 1, the more similar the two networks are, so we use 1 minus the normalized The value of this item is set so that the result of this item approaches 0 when the two networks are similar and increases when they are dissimilar. : This is the distance between the two networks calculated using the Euclidean distance formula, also normalized. Smaller Euclidean distances indicate more similarity between the two networks. Normalized distances approach 0 when the networks are similar and increase when they are dissimilar.

[0130] The calculated comprehensive fit index value corresponding to each component i Perform sorting operations. Here It is calculated for each component i using the previous formula, and it comprehensively measures the degree of fit between the simulated fault network and the relevant part of the component in the actual fault network. The lower the value, the higher the degree of fit between the simulated fault network and the corresponding component i in the actual fault network. That is, after the Euclidean distance and the angle cosine value are calculated, the more similar the performance of the component in the simulated and actual networks is, the better the simulation results can reflect the characteristics of the component in the actual fault situation. Because a high degree of fit means that the simulation situation is closer to the actual situation, when the corresponding component i The lower the value, that is, the higher the degree of fit, the greater the possibility that the component i will become the root fault (i.e., the initial fault component that triggers other faults). For example, in a power grid system, if the component If the value is very low, it is very likely that it is the source component that causes a series of failures in the entire system. This component can be identified as an abnormal power grid component.

[0131] In one embodiment, Figure 7 As shown, the index value for measuring the degree of fit between the simulated fault network and the actual fault network, calculated based on the first abnormality degree and the second abnormality degree, includes:

[0132] S702: Calculate the Euclidean distance according to the first abnormality degree and the second abnormality degree.

[0133] S704: Calculate a cosine distance based on the first abnormality degree and the second abnormality degree.

[0134] S706 : Calculate an index value for measuring the degree of fit between the simulated fault network and the actual fault network based on the Euclidean distance and the cosine distance.

[0135] Euclidean distance refers to the true distance between two points in m-dimensional space. Cosine distance, also known as the complement of cosine similarity, measures the similarity between two vectors by calculating the cosine of the angle between them. In this paper, this distance is calculated based on the first and second anomaly degrees to assess the similarity between abnormalities in power grid components in simulated and actual fault networks. The closer the cosine distance is to 0, the more similar the two vectors are.

[0136] Specifically, the Euclidean distance measures the absolute difference in the anomaly levels of corresponding nodes in two networks. It determines the distance by calculating the square root of the sum of the squares of the differences in node anomaly levels, focusing on the magnitude of the numerical differences. However, relying solely on the Euclidean distance may overlook the directional relationship between node anomaly levels. For example, while the numerical difference in the anomaly levels of nodes in two networks may be small, their trends or interrelationships may differ, and the Euclidean distance cannot effectively reflect such directional differences.

[0137] The cosine angle primarily measures the directional similarity between two vectors (here, understood as the vectors representing node anomaly levels). It is calculated by calculating the ratio of the vector dot product to the vector modulus-length product. Its value ranges from -1 to 1, with values ​​closer to 1 indicating greater directional similarity. However, the cosine angle is somewhat insensitive to the length of the vectors (i.e., the specific magnitude of the node anomaly level). For example, if two vectors have the same direction but significantly different lengths, using only the cosine angle may overestimate their similarity while ignoring significant numerical differences. Therefore, to accurately calculate the difference index between two networks, the Euclidean distance and cosine distance can be calculated based on the first and second anomaly levels. The combined data can be used to calculate the index. The index can be calculated using a weighted average, average, or other methods. Alternatively, the Euclidean and cosine distances can be normalized and added together to obtain the final index value.

[0138] In some exemplary embodiments, the Euclidean distance may be calculated using the following formula:

[0139]

[0140] in, Represents the simulated fault network and the actual fault network The Euclidean distance between . It means to sum all elements from i=1 to i=n, ​​where n is the number of nodes in the network, that is, the number of power grid components in the network. Representative Node In the simulated fault network The first abnormality degree in . Representation node In the actual fault network The second degree of abnormality in . Representation node Belong to a certain The collection may typically be a collection of power grid components.

[0141] The cosine distance can be calculated using the following formula:

[0142]

[0143] in, : represents the simulated fault network and the actual fault network The cosine value of the angle obtained after fitting is a value between -1 and 1. =1, indicating that the two networks are completely similar; when =-1, the two networks are completely opposite; when =0, the two networks are independent of each other and have no correlation.

[0144] In one embodiment, Figure 8 As shown, the determining of the isolation component based on the simulated fault description information and the abnormal power grid component includes:

[0145] S802: In response to the abnormal power grid component being included in the faulty power grid component, determine a fault type that matches the abnormal power grid component in the simulated fault description.

[0146] S804 : In response to the fault type matched by the abnormal power grid component being an associated fault, determine an associated power grid component associated with the abnormal power grid component based on the associated fault.

[0147] S806: Determine an isolated component based on the associated power grid components and the abnormal power grid components.

[0148] S808 : In response to the abnormal power grid component being included in the faulty power grid component and / or the fault type matched by the abnormal power grid component being an isolated fault, determine an isolation component based on the abnormal power grid component.

[0149] Associated grid components are those associated with an abnormal grid component. These components are those affected by or caused by the associated fault of the abnormal grid component. Isolation components are those identified from the abnormal grid component or its associated components that require isolation. Isolating these components prevents further propagation of the fault, protects the normal operation of other parts of the grid, and facilitates power restoration.

[0150] Specifically, if the abnormal power grid component is included in the faulty power grid component, the simulated fault description is searched for a matching fault type for the abnormal power grid component. The simulated fault description details the fault type of each component in the simulated fault scenario, and matching is performed using identifiers such as component name or number. If the fault type matching the abnormal power grid component is determined to be an associated fault, other components associated with the abnormal power grid component are searched based on the information about fault associations in the simulated fault description. The simulated fault description records the fault propagation path and mutual influence relationships between components. This information is used to determine which components are associated with the abnormal power grid component. For example, if the simulated fault description indicates that "the fault of component A caused the fault of abnormal power grid component B, and the fault of component B caused the fault of component C," then components A and C are associated power grid components associated with abnormal power grid component B. Based on the identified associated power grid components and abnormal power grid components, the isolation component is determined based on a comprehensive consideration of various factors. These factors include, but are not limited to, the component's importance to the power grid, the impact of the fault on other components, and the feasibility of the isolation operation. For example, if the abnormal grid component is a critical transformer, and its associated grid components include the transmission lines connected to it and some minor equipment, in order to prevent the fault from spreading further, the transformer and the critical transmission lines directly affected by it may be chosen to be isolated as isolation components. When the abnormal grid component is included in the faulty grid component, and / or the fault type matched by the abnormal grid component is a separate fault, the isolation component is determined directly based on the abnormal grid component. For abnormal grid components with separate faults, since their faults do not involve the associated impact of other components, the abnormal grid component itself can usually be used as an isolation component. For example, if a switchgear fails alone, in order to avoid its impact on other parts of the power grid, the switchgear can be used as an isolation component for isolation operation. For situations where the abnormal grid component is included in the faulty grid component but the fault type is uncertain or does not belong to an associated fault, the abnormal grid component can also be used as an isolation component to ensure that the fault does not expand further.

[0151] In this embodiment, by searching for fault types matching abnormal grid components in the simulated fault description, it is possible to quickly and accurately distinguish whether the fault is an isolated fault or a correlated fault. This helps operations and maintenance personnel gain a deeper understanding of the fault's nature and potential impact, avoid misjudging the fault situation, and provide a solid foundation for developing targeted handling strategies. When an abnormal grid component is determined to be a correlated fault, the associated grid components are further identified. This allows operations and maintenance personnel to fully understand the fault's propagation path and impact range within the grid, clearly understanding the fault's chain reaction mechanism, and more accurately localize the fault source and affected components, improving the efficiency and accuracy of fault diagnosis. Determining the components to be isolated based on the associated grid components and the abnormal grid components fully considers the fault's relevance and impact range. This makes isolation decisions more scientific and reasonable, avoiding the problems of over-isolation or under-isolation. Over-isolation may lead to unnecessary expansion of the power outage, impacting users' normal power supply; while under-isolation may fail to effectively prevent the further spread of the fault, posing a greater threat to the safe and stable operation of the grid. Timely and accurate isolation of the faulty component can effectively prevent the fault from spreading further within the grid, minimizing the impact of the fault and ensuring the continued normal operation of the rest of the grid.

[0152] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0153] Based on the same inventive concept, embodiments of the present disclosure also provide a device for isolating and restoring power to a power grid component, for implementing the aforementioned method for isolating and restoring power to a power grid component. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of the embodiments of the device for isolating and restoring power to a power grid component provided below can be found in the aforementioned definition of the method for isolating and restoring power to a power grid component, and will not be further elaborated here.

[0154] In one embodiment, Figure 9As shown, a network backup automatic switching rapid fault isolation and power restoration device 900 based on a power grid dispatching and control system is provided. The power grid dispatching and control system controls a power grid system, which includes multiple power grid components. The device includes: a first abnormality degree calculation module 902, a second abnormality degree calculation module 904, an abnormal power grid component determination module 906, and a power restoration module 908, wherein:

[0155] A first abnormality degree calculation module 902 is configured to, in response to a fault occurring in the power grid system, calculate, for each power grid component, a first abnormality degree of the power grid component in a current actual fault network based on the number of associated links of the power grid component;

[0156] A second abnormality degree calculation module 904 is configured to calculate a second abnormality degree of the power grid component in a predetermined simulated fault network based on the number of associated links of the power grid component in the predetermined simulated fault network, wherein the simulated fault network is generated based on the fault correlation coefficients of the power grid components, a predetermined distribution of power grid component failure rates, and simulated fault description information; the simulated fault description information is used to describe the fault association relationships between the power grid components;

[0157] an abnormal power grid component determining module 906, configured to determine an abnormal power grid component among the power grid components based on the first abnormality degree and the second abnormality degree calculated for each power grid component;

[0158] The power restoration module 908 is configured to determine the isolated component based on the simulated fault description information and the abnormal power grid component, isolate the isolated component, and then restore power to the power grid system.

[0159] In one embodiment of the device, the device further comprises:

[0160] a correlation coefficient determination module, configured to determine the grid components included in the grid system, and determine the fault correlation coefficients between the grid components based on the fault correlations between the grid components;

[0161] A sample sequence generation module is used to generate a simulated time sample sequence containing the fault distribution characteristics of the power grid components based on a preset power grid component failure rate distribution and a fault correlation coefficient between the power grid components;

[0162] a description information determination module, configured to scale the simulation data contained in the simulation time sample sequence to a preset range interval, and determine simulation fault description information according to a preset fault threshold;

[0163] The fault network generation module is used to construct an association relationship between grid component faults based on the simulated fault description information and the grid components to form a simulated fault network.

[0164] In one embodiment of the device, the failure rate distribution is a normal distribution, and the sample sequence generation module is further used to generate a fault correlation coefficient matrix based on the fault correlation coefficients between the power grid components; generate an N-dimensional independent standard normal distribution random variable sampling sequence according to the total number of the power grid components, wherein N is determined based on the total number of power grid components; generate a preliminary simulation time interval sequence based on the fault correlation coefficient matrix and the N-dimensional independent standard normal distribution random variable sampling sequence; determine the mean and standard deviation of the failure rate of each power grid component, and generate a simulation time sample sequence containing the fault distribution characteristics of the power grid components based on the preliminary simulation time interval sequence and the mean and standard deviation of the failure rate of each power grid component.

[0165] In one embodiment of the device, the simulated fault description information includes: a faulty power grid component and a fault type of the faulty power grid component, wherein the fault type includes: a single fault and a correlated fault; and the fault network generation module includes:

[0166] a first-layer network generation module, configured to generate a first-layer component network based on the power grid components, the individually faulty power grid components, and connection relationships between the power grid components;

[0167] A second-layer network generation module, configured to generate a second-layer component network based on the power grid components, the faulty power grid components of the associated faults, and the connection relationships between the power grid components;

[0168] The network combination module is used to generate a simulated fault network based on the first layer component network and the generated second layer component network.

[0169] In one embodiment of the device, the abnormal power grid component determination module 906 is further used to calculate an index value for measuring the degree of fit between the simulated fault network and the actual fault network based on the first abnormality degree and the second abnormality degree; determine the minimum abnormal index value among the index values, and determine the abnormal power grid component based on the power grid component that matches the abnormal index value.

[0170] In one embodiment of the device, the abnormal power grid component determination module 906 is further used to calculate the Euclidean distance based on the first abnormality degree and the second abnormality degree; calculate the cosine distance based on the first abnormality degree and the second abnormality degree; and calculate an index value for measuring the degree of fit between the simulated fault network and the actual fault network based on the Euclidean distance and the cosine distance.

[0171] In one embodiment of the device, the power restoration module 908 includes:

[0172] An isolation component determination module is configured to determine, in response to the abnormal power grid component being included in the faulty power grid component, a fault type that matches the abnormal power grid component in the simulated fault description; in response to the fault type that matches the abnormal power grid component being an associated fault, determine, based on the associated fault, an associated power grid component associated with the abnormal power grid component; determine an isolation component based on the associated power grid components and the abnormal power grid component; and in response to the abnormal power grid component being included in the faulty power grid component and / or the fault type that matches the abnormal power grid component being an individual fault, determine an isolation component based on the abnormal power grid component.

[0173] Each module in the aforementioned network backup automatic switching rapid fault isolation and power restoration device based on a power grid dispatching and control system can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in the form of software in a memory in the computer device, so that the processor can call and execute the corresponding operations of each module.

[0174] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 10 As shown. The computer device includes a processor, a memory and a network interface connected via a system bus. 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 the first abnormality degree, the second abnormality degree, and the simulated fault network. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a network backup automatic rapid fault isolation and power restoration method based on a power grid dispatching and control system is realized.

[0175] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 11As shown. The computer device includes a processor, memory, a communication interface, a display screen, and an input device connected via a system bus. 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 internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication can be achieved via Wi-Fi, mobile cellular networks, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a method for rapid fault isolation and power restoration based on network backup automatic switching of a power grid dispatching control system. The display screen of the computer device can be a liquid crystal display or an electronic ink display. The input device of the computer device can be a touch screen covering the display screen, or keys, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse.

[0176] Those skilled in the art will understand that Figure 10 The structure shown in or 11 is merely a block diagram of a portion of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the computer device to which the scheme of the present disclosure is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0177] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0178] 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 in the above-mentioned method embodiments are implemented.

[0179] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0180] It should be noted that all information in the power grid involved in this disclosure is information and data authorized by the user or fully authorized by all parties.

[0181] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, database, or other media used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may 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 may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, and the like.

[0182] The technical features of the above embodiments can 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 specification.

[0183] The above-described embodiments merely represent several implementation methods of the present disclosure. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present disclosure. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present disclosure, all of which fall within the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure shall be determined by the appended claims.

Claims

1. A method for rapid fault isolation and power restoration based on network backup automatic switching of power grid dispatching and control system, characterized in that: The power grid dispatching control system controls a power grid system, wherein the power grid system includes a plurality of power grid components, and the method includes: In response to a fault occurring in the power grid system, for each power grid component, calculating a first abnormality degree of the power grid component in a current actual fault network according to the number of associated links of the power grid component; Based on the number of associated links of the power grid components in a predetermined simulated fault network, a second abnormality degree of the power grid components in the simulated fault network is calculated, wherein the simulated fault network is generated based on the fault correlation coefficients of the power grid components, a preset distribution of power grid component failure rates, and simulated fault description information; the simulated fault description information is used to describe the fault association relationship between the power grid components; determining an abnormal power grid component among the power grid components based on the first abnormality degree and the second abnormality degree calculated for each power grid component; An isolation component is determined based on the simulated fault description information and the abnormal power grid component. After the isolation component is isolated, power is restored to the power grid system.

2. The method according to claim 1, characterized in that The method further comprises: Determining grid components included in the grid system, and determining a fault correlation coefficient between the grid components based on the fault correlation between the grid components; Based on a preset distribution of failure rates of power grid components and a failure correlation coefficient between the power grid components, generating a simulated time sample sequence including the distribution characteristics of the power grid component failures; Scaling the simulated data contained in the simulated time sample sequence to a preset range interval, and determining simulated fault description information according to a preset fault threshold; Based on the simulated fault description information and the power grid components, an association relationship of power grid component faults is constructed to form a simulated fault network.

3. The method according to claim 2, characterized in that The failure rate distribution is a normal distribution, and generating a simulated time sample sequence containing the failure distribution characteristics of the power grid components based on a preset power grid component failure rate distribution and a failure correlation coefficient between the power grid components includes: generating a fault correlation coefficient matrix based on the fault correlation coefficients between the power grid components; generating an N-dimensional independent standard normal distribution random variable sampling sequence according to the total number of the power grid components, wherein N is determined based on the total number of the power grid components; Generate a preliminary simulation time interval sequence based on the fault correlation coefficient matrix and the N-dimensional independent standard normal distribution random variable sampling sequence; The mean and standard deviation of the failure rate of each power grid component are determined, and a simulated time sample sequence containing the failure distribution characteristics of the power grid component is generated based on the preliminary simulation time interval sequence and the mean and standard deviation of the failure rate of each power grid component.

4. The method according to claim 2, characterized in that The simulated fault description information includes: a faulty power grid component and a fault type of the faulty power grid component, wherein the fault type includes: a single fault and an associated fault. The association relationship between the power grid component faults is constructed based on the simulated fault description information and the power grid components to form a simulated fault network, including: generating a first-layer component network based on the power grid components, the individually faulty power grid components, and connection relationships between the power grid components; generating a second-layer component network based on the power grid components, the faulty power grid components of the associated faults, and connection relationships between the power grid components; A simulated fault network is generated based on the first layer component network and the generated second layer component network.

5. The method according to claim 1, wherein The determining an abnormal power grid component among the power grid components based on the first abnormality degree and the second abnormality degree calculated for each power grid component includes: An index value for measuring the degree of fit between the simulated fault network and the actual fault network is calculated based on the first abnormality degree and the second abnormality degree; The smallest abnormal index value among the index values ​​is determined, and the abnormal power grid component is determined based on the power grid components that match the abnormal index value.

6. The method according to claim 5, characterized in that The index value for measuring the degree of fit between the simulated fault network and the actual fault network, calculated based on the first abnormality degree and the second abnormality degree, includes: calculating a Euclidean distance based on the first abnormality and the second abnormality; Calculating a cosine distance based on the first abnormality and the second abnormality; An index value for measuring the degree of fit between the simulated fault network and the actual fault network is calculated based on the Euclidean distance and the cosine distance.

7. The method according to claim 1, characterized in that The simulated fault description information includes: a faulty power grid component and a fault type of the faulty power grid component, wherein the fault type includes: a single fault and a correlated fault. Determining the isolation component based on the simulated fault description information and the abnormal power grid component includes: In response to the abnormal power grid component being included in the faulty power grid component, determining a fault type that matches the abnormal power grid component in the simulated fault description; In response to the fault type matched by the abnormal power grid component being an associated fault, determining an associated power grid component associated with the abnormal power grid component based on the associated fault; determining an isolated component based on the associated power grid component and the abnormal power grid component; In response to the abnormal power grid component being included in the faulty power grid component and / or the fault type matched by the abnormal power grid component being an isolated fault, an isolation component is determined based on the abnormal power grid component.

8. A network backup automatic rapid fault isolation and power restoration device based on a power grid dispatching and control system, characterized in that: The power grid dispatching control system controls a power grid system, wherein the power grid system includes a plurality of power grid components, and the device includes: a first abnormality degree calculation module configured to, in response to a fault occurring in the power grid system, calculate, for each power grid component, a first abnormality degree of the power grid component in a current actual fault network based on the number of associated links of the power grid component; a second abnormality degree calculation module, configured to calculate a second abnormality degree of the power grid component in a predetermined simulated fault network based on the number of associated links of the power grid component in the predetermined simulated fault network, wherein the simulated fault network is generated based on the fault correlation coefficient of the power grid component, a preset distribution of power grid component failure rates, and simulated fault description information; the simulated fault description information is used to describe the fault association relationship between the power grid components; an abnormal power grid component determining module, configured to determine an abnormal power grid component among the power grid components based on the first abnormality degree and the second abnormality degree calculated for each power grid component; The power restoration module is used to determine the isolated component based on the simulated fault description information and the abnormal power grid component, isolate the isolated component, and then restore power to the power grid system.

9. 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 7 are implemented.

10. 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 7 are implemented.

Images