Power grid fault detection method, device, computer equipment, readable storage medium and program product

Abstract

The present application relates to a power grid fault detection method, apparatus, computer equipment, readable storage medium, and program product. The method includes: constructing a power grid fault scenario and generating fault impact parameter information for multiple power grid fault points; generating a first fault impact weight based on the fault impact parameter information; detecting target fault impact parameter information; and generating a second fault impact weight based on the target fault impact parameter information and the first fault impact weight; generating a target fault impact weight for each power grid fault point based on the first fault impact weight and the second fault impact weight corresponding to each power grid fault point; screening a target power grid fault set from multiple power grid fault sets based on the target fault impact weights and the fault impact parameter information of all power grid fault points in each power grid fault set to update the power grid fault scenario; and performing fault detection on the updated power grid fault scenario. This method can accurately detect power grid faults.

Description

Technical Field

[0001] The present application relates to the field of power electronics technology, and in particular to a power grid fault detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] In the power system, ensuring the stability and reliability of the power system is of vital importance. To achieve this goal, grid operators usually use a series of security analysis tools and technologies to detect potential faults in the power system.

[0003] Among them, the static safety analysis method is a commonly used means of power grid fault detection. It first collects and organizes historical fault data of the power grid, including information such as topology, equipment parameters, power generation and load forecasts, and defines at least two groups of fault scenarios that need to be considered through expert experience and historical fault data. It then performs DC / AC power flow calculations and transient stability analysis on the network status under each fault scenario, thereby helping to identify factors that may lead to unstable or unsafe operating conditions.

[0004] However, the current power grid fault detection method has the technical problem of being inaccurate. Summary of the Invention

[0005] Based on this, it is necessary to provide an accurate power grid fault detection method, device, computer equipment, computer-readable storage medium and computer program product to address the above technical problems.

[0006] In a first aspect, the present application provides a power grid fault detection method, comprising:

[0007] Acquire historical power grid fault data, and construct a power grid fault scenario based on the historical power grid fault data, and generate fault impact parameter information of multiple power grid fault points, wherein the power grid fault scenario includes multiple power grid fault sets, and each power grid fault set includes multiple power grid fault points;

[0008] For each power grid fault point, a first fault impact weight is generated based on the fault impact parameter information, and when target fault impact parameter information is detected in the fault impact parameter information, a second fault impact weight is generated based on the target fault impact parameter information and the first fault impact weight, wherein the target fault impact parameter information is fault impact parameter information having an importance higher than a preset importance threshold;

[0009] generating a target fault impact weight for each power grid fault point according to the first fault impact weight and the second fault impact weight corresponding to each power grid fault point;

[0010] Based on the target fault impact weights and fault impact parameter information of all grid fault points in each grid fault set, a target grid fault set is screened out from multiple grid fault sets, and the grid fault scenario is updated based on the target grid fault set;

[0011] Fault detection is performed on the updated power grid fault scenario to generate a power grid fault detection result.

[0012] In one embodiment, the fault impact parameter information includes fault frequency, fault consequence severity index, fault vulnerability index, and fault recovery time index. Based on historical grid fault data, fault impact parameter information of multiple grid fault points is generated, including:

[0013] Based on historical grid fault data, the system obtains the total operating time of the node where the fault occurs for multiple grid fault points within a preset time period, the number of faults within the total operating time of the node where the fault occurs, the number of users affected by the fault, the power outage time affected by the fault, the amount of resources lost due to the fault, the fault redundancy, the fault repair time, and the fault dispatch response time;

[0014] For each grid fault point, the fault frequency is generated based on the total operating time and number of faults of the node where the fault is located;

[0015] Generate a fault consequence severity index based on the number of users affected by the fault, the power outage duration affected by the fault, and the amount of resources lost due to the fault;

[0016] Generate a fault vulnerability index based on fault frequency and fault redundancy;

[0017] Generate a fault recovery time index based on the fault repair time and the fault scheduling response time.

[0018] In one embodiment, the target fault impact parameter information includes a fault occurrence frequency and a fault consequence severity index. Generating a second fault impact weight based on the target fault impact parameter information and the first fault impact weight includes:

[0019] Generate an intermediate fault detection value based on the fault frequency and fault consequence severity index;

[0020] A second fault impact weight is generated based on the fault intermediate detection value and the first fault impact weight.

[0021] In one embodiment, a target fault set is screened from multiple power grid fault sets based on target fault impact weights and fault impact parameter information of all power grid fault points in each fault set, including:

[0022] Generate a comprehensive scoring result for each power grid fault set based on the target fault impact weights and fault impact parameter information corresponding to all power grid fault points in each power grid fault set;

[0023] The power grid fault set whose comprehensive score result is greater than the preset score threshold is taken as the target fault set.

[0024] In one embodiment, constructing a power grid fault scenario based on historical power grid fault data includes:

[0025] Detecting target fault events that meet a fault event selection condition from among all fault events of the power grid based on historical fault data of the power grid, wherein the fault event selection condition includes at least one of a fault occurrence frequency exceeding a preset frequency threshold and a fault consequence severity index exceeding a preset consequence severity index threshold;

[0026] The target fault event is regarded as the grid fault point, and the correlation between all grid fault points is obtained;

[0027] Combine all grid fault points whose correlation is higher than a preset correlation threshold value to obtain multiple grid fault sets;

[0028] Aggregate multiple power grid fault sets and construct power grid fault scenarios.

[0029] In one embodiment, there is more than one fault impact parameter information, and generating a first fault impact weight based on the fault impact parameter information includes:

[0030] For each piece of fault impact parameter information, obtain a fault weight coefficient of the fault impact parameter information, and update the fault impact parameter information based on the fault weight coefficient;

[0031] A first fault impact weight is generated according to all updated fault impact parameter information.

[0032] In a second aspect, the present application further provides a power grid fault detection device, comprising:

[0033] an acquisition module, configured to acquire historical grid fault data, construct a grid fault scenario based on the historical grid fault data, and generate fault impact parameter information of multiple grid fault points, wherein the grid fault scenario includes multiple grid fault sets, and each grid fault set includes multiple grid fault points;

[0034] a first weight processing module, configured to generate, for each power grid fault point, a first fault impact weight based on the fault impact parameter information, and, upon detecting target fault impact parameter information in the fault impact parameter information, generate a second fault impact weight based on the target fault impact parameter information and the first fault impact weight, wherein the target fault impact parameter information is fault impact parameter information having an importance higher than a preset importance threshold;

[0035] a second weight processing module, configured to generate a target fault impact weight for each power grid fault point based on the first fault impact weight and the second fault impact weight corresponding to each power grid fault point;

[0036] A power grid fault scenario update module is used to screen out a target power grid fault set from multiple power grid fault sets based on the target fault impact weights and fault impact parameter information of all power grid fault points in each power grid fault set, and update the power grid fault scenario based on the target power grid fault set;

[0037] The fault detection module is used to perform fault detection on the updated power grid fault scenario and generate a power grid fault detection result.

[0038] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Acquire historical power grid fault data, and construct a power grid fault scenario based on the historical power grid fault data, and generate fault impact parameter information of multiple power grid fault points, wherein the power grid fault scenario includes multiple power grid fault sets, and each power grid fault set includes multiple power grid fault points;

[0040] For each power grid fault point, a first fault impact weight is generated based on the fault impact parameter information, and when target fault impact parameter information is detected in the fault impact parameter information, a second fault impact weight is generated based on the target fault impact parameter information and the first fault impact weight, wherein the target fault impact parameter information is fault impact parameter information having an importance higher than a preset importance threshold;

[0041] generating a target fault impact weight for each power grid fault point according to the first fault impact weight and the second fault impact weight corresponding to each power grid fault point;

[0042] Based on the target fault impact weights and fault impact parameter information of all grid fault points in each grid fault set, a target grid fault set is screened out from multiple grid fault sets, and the grid fault scenario is updated based on the target grid fault set;

[0043] Fault detection is performed on the updated power grid fault scenario to generate a power grid fault detection result.

[0044] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0045] Acquire historical power grid fault data, and construct a power grid fault scenario based on the historical power grid fault data, and generate fault impact parameter information of multiple power grid fault points, wherein the power grid fault scenario includes multiple power grid fault sets, and each power grid fault set includes multiple power grid fault points;

[0046] For each power grid fault point, a first fault impact weight is generated based on the fault impact parameter information, and when target fault impact parameter information is detected in the fault impact parameter information, a second fault impact weight is generated based on the target fault impact parameter information and the first fault impact weight, wherein the target fault impact parameter information is fault impact parameter information having an importance higher than a preset importance threshold;

[0047] generating a target fault impact weight for each power grid fault point according to the first fault impact weight and the second fault impact weight corresponding to each power grid fault point;

[0048] Based on the target fault impact weights and fault impact parameter information of all grid fault points in each grid fault set, a target grid fault set is screened out from multiple grid fault sets, and the grid fault scenario is updated based on the target grid fault set;

[0049] Fault detection is performed on the updated power grid fault scenario to generate a power grid fault detection result.

[0050] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0051] Acquire historical power grid fault data, and construct a power grid fault scenario based on the historical power grid fault data, and generate fault impact parameter information of multiple power grid fault points, wherein the power grid fault scenario includes multiple power grid fault sets, and each power grid fault set includes multiple power grid fault points;

[0052] For each power grid fault point, a first fault impact weight is generated based on the fault impact parameter information, and when target fault impact parameter information is detected in the fault impact parameter information, a second fault impact weight is generated based on the target fault impact parameter information and the first fault impact weight, wherein the target fault impact parameter information is fault impact parameter information having an importance higher than a preset importance threshold;

[0053] generating a target fault impact weight for each power grid fault point according to the first fault impact weight and the second fault impact weight corresponding to each power grid fault point;

[0054] Based on the target fault impact weights and fault impact parameter information of all grid fault points in each grid fault set, a target grid fault set is screened out from multiple grid fault sets, and the grid fault scenario is updated based on the target grid fault set;

[0055] Fault detection is performed on the updated power grid fault scenario to generate a power grid fault detection result.

[0056] In the above-mentioned power grid fault detection method, apparatus, computer equipment, computer-readable storage medium and computer program product, throughout the entire process, for each power grid fault point in the power grid fault scenario, a target fault impact weight obtained by combining the first fault impact weight and the second fault impact weight is used to effectively reflect the importance of each power grid fault point in the overall fault detection. Moreover, based on the target fault impact weights and fault impact parameter information of all fault points in each fault set, the target fault set that truly requires focus is more accurately identified, so as to retain the power grid fault scenarios updated based on the target fault set and exclude other fault scenarios that do not require attention, thereby effectively reducing the shortcomings of traditional methods that rely on expert experience and subjective judgment, improving the objectivity, accuracy and scientific nature of fault scenario selection, and thus achieving accurate fault detection of the updated power grid fault scenarios and generating power grid fault detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 A diagram of an application environment of a power grid fault detection method according to an embodiment;

[0059] Figure 2 1 is a flow chart of a method for detecting a power grid fault in one embodiment;

[0060] Figure 3 is a flow chart of a power grid fault detection method according to another embodiment;

[0061] Figure 4 is a structural block diagram of a power grid fault detection device in one embodiment;

[0062] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are used to explain this application and are not intended to limit this application.

[0064] The power grid fault detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104 or placed on the cloud or other network servers.

[0065] The user operates on the terminal 102 to trigger the power grid fault detection control on the interface of the terminal 102 to generate a power grid fault detection request to the server 104. The server 104 receives the power grid fault detection request, obtains historical power grid fault data from a database, constructs a power grid fault scenario based on the historical power grid fault data, and generates fault impact parameter information for multiple power grid fault points. The power grid fault scenario includes multiple power grid fault sets, each of which includes multiple power grid fault points. For each power grid fault point, a first fault impact weight is generated based on the fault impact parameter information. When target fault impact parameter information in the fault impact parameter information is detected, a second fault impact weight is generated based on the target fault impact parameter information and the first fault impact weight. The target fault impact parameter information is fault impact parameter information having an importance greater than a preset importance threshold. A target fault impact weight is generated for each fault point based on the first fault impact weight and the second fault impact weight corresponding to each power grid fault point. A target fault impact weight is selected from the multiple power grid fault sets based on the target fault impact weights and the fault impact parameter information of all fault points in each fault set, and the power grid fault scenario is updated based on the target fault set. Fault detection is performed on the updated power grid fault scenario to generate a power grid fault detection result. Furthermore, the power grid fault detection result may be sent to the terminal 102 and displayed to the user by the terminal 102 .

[0066] 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, smart car devices, and projectors. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Head-mounted devices may include virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, and the like. Server 104 may be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0067] In an exemplary embodiment, Figure 2 As shown, a power grid fault detection method is provided, which is applied to Figure 1 The server 104 in FIG. 1 is used as an example for explanation.

[0068] S100 , acquiring historical power grid fault data, constructing a power grid fault scenario based on the historical power grid fault data, and generating fault impact parameter information of multiple power grid fault points.

[0069] The power grid fault scenario includes multiple power grid fault sets, and each fault set includes multiple power grid fault points.

[0070] Specifically, a user operates on a terminal, triggering a power grid fault detection control on the terminal interface to generate a power grid fault detection request to a server. The server receives the power grid fault detection request, obtains historical power grid fault data, and constructs a power grid fault scenario based on the historical power grid fault data, generating fault impact parameter information for multiple power grid fault points. The historical power grid fault data can be pre-acquired data from a database—that is, all power grid fault data within a historical time period is stored in the database for subsequent use—or it can be historical power grid fault data collected in real time. The fault impact parameter information includes fault impact parameters and the fault impact parameter data values ​​corresponding to the fault impact parameters.

[0071] In an exemplary embodiment, collecting historical power grid fault data first requires determining data requirements, including clarifying the type of data to be collected and the time range for data collection. The data type includes but is not limited to fault time, fault location, number of affected users, power outage time, direct economic loss, repair time, and dispatch response time; the time range may be data within the past three or five years.

[0072] Methods for collecting historical fault data of power grids include but are not limited to: 1. Exporting historical alarm records and event logs from the data acquisition and monitoring control system, which usually records various abnormal conditions and fault information in the operation of the power grid; 2. Extracting historical fault records from the energy management system, which not only records the operation status of the power grid, but also contains detailed information on the fault handling and recovery process; 3. Accessing paper or electronic records of the power grid operation and maintenance department, including but not limited to fault reports, maintenance records and inspection records; 4. Accessing the internal database of the power company to extract historical fault data of the power grid, which may contain detailed fault records and related technical documents; 5. Using a third-party data service provider and requesting the third-party data service provider to provide historical fault data.

[0073] S200, for each power grid fault point, generate a first fault impact weight based on the fault impact parameter information, and when target fault impact parameter information in the fault impact parameter information is detected, generate a second fault impact weight based on the target fault impact parameter information and the first fault impact weight.

[0074] The target fault impact parameter information is fault impact parameter information whose importance is higher than a preset importance threshold.

[0075] Specifically, for each power grid fault point, all fault impact parameter information is weighted to generate a first fault impact weight. The first fault impact weight is a weight obtained after processing all fault impact parameter information and includes relevant information of all fault impact parameter information.

[0076] Furthermore, if there is more than one fault impact parameter information, an importance evaluation value of each fault impact parameter information is obtained, and based on the importance evaluation value of each fault impact parameter information, target fault impact parameter information with an importance higher than a preset importance threshold is screened out from multiple fault impact parameter information.

[0077] When the target fault impact parameter information is detected in the fault impact parameter information, a second fault impact weight is generated based on the target fault impact parameter information and the first fault impact weight. The second fault impact weight is the weight obtained after processing all target fault impact parameter information and includes relevant information of all target fault impact parameter information.

[0078] In an exemplary embodiment, before obtaining the first fault impact weight, the second fault impact weight and the target fault impact weight, in order to ensure data consistency and unit uniformity, it is also necessary to uniformly perform standardization and normalization processing on the fault frequency, fault consequence severity index, fault vulnerability index and fault recovery time index of each grid fault point contained in each grid fault set in each grid fault scenario.

[0079] S300 , generating a target fault impact weight for each power grid fault point according to a first fault impact weight and a second fault impact weight corresponding to each power grid fault point.

[0080] Specifically, for each power grid fault point, the first fault impact weight is the weight associated with all fault impact parameter information at the power grid fault point, and the second fault impact weight is the weight associated with the more important target fault impact parameter information at the power grid fault point. This further emphasizes the key privacy in all fault impact parameter information. Combining the first fault impact weight and the second fault impact weight, all important factors can be comprehensively considered to generate a target fault impact weight for the fault point. The target fault impact weight includes both the weights associated with all fault impact parameter information and the weights associated with the more important target fault impact parameter information. The resulting target fault impact weight is not only more comprehensive and does not omit fault impact parameter information, but also pays more attention to the more important target fault impact parameter information. By combining the two fault impact weights, they can complement each other, making the power grid fault detection process based on the target fault impact weight more reliable and accurate. Furthermore, if the first fault impact weight or the second fault impact weight is used alone, certain factors may be overemphasized or ignored.

[0081] In an exemplary embodiment, generating a target fault impact weight for each power grid fault point based on the first fault impact weight and the second fault impact weight corresponding to each power grid fault point further includes:

[0082] For each power grid fault point, a first proportional coefficient of the first fault impact weight and a second proportional coefficient of the second fault impact weight are obtained, the first fault impact weight is updated according to the first proportional coefficient, and the second fault impact weight is updated according to the second proportional coefficient, and a target fault impact weight is generated according to the updated first fault impact weight and the updated first fault impact weight.

[0083] Furthermore, the calculation formula for the target fault impact weight of each power grid fault point is:

[0084] w final ijk =K6w 1 ijk +K7w 2ijk

[0085] Among them, w final ijk represents the target fault impact weight of the kth grid fault point contained in the jth grid fault set in the ith grid fault scenario; w 1 ijk represents the first fault impact weight of the kth grid fault point contained in the jth grid fault set in the ith grid fault scenario; w 2 ijk represents the second fault impact weight of the kth grid fault point included in the jth grid fault set in the i-th grid fault scenario; K6 and K7 represent preset proportional coefficients.

[0086] S400 , based on target fault impact weights and fault impact parameter information of all grid fault points in each grid fault set, a target grid fault set is screened out from multiple grid fault sets, and a grid fault scenario is updated based on the target grid fault set.

[0087] Specifically, each power grid fault set includes multiple power grid fault points. The target fault impact weights and fault impact parameter information of all power grid fault points in each power grid fault set are summarized to obtain the fault detection information of the power grid fault set. Then, based on the fault detection information of all power grid fault sets, the target power grid fault set is screened out from the multiple power grid fault sets, and the target power grid fault set in the power grid fault scenario is retained. The power grid fault sets that are not screened out in the power grid fault scenario are filtered out to update the power grid fault scenario.

[0088] S500 , performing fault detection on the updated power grid fault scenario and generating a power grid fault detection result.

[0089] Specifically, a power flow calculation is performed on the updated power grid fault scenario, and a transient stability analysis is performed on the updated power grid fault scenario. Based on the power flow calculation results and the transient stability analysis results, a comprehensive fault detection score data is assigned to the updated power grid fault scenario. The comprehensive fault detection score data can be regarded as the power grid fault detection result of the updated power grid fault scenario.

[0090] Furthermore, if there is more than one updated power grid fault scenario, the comprehensive fault detection score data of each updated power grid fault scenario is sorted, and a power grid fault scenario sorting result is generated based on the sorting result. The power grid fault scenario sorting result can also be regarded as the power grid fault detection result of the updated power grid fault scenario.

[0091] Finally, the power grid fault detection results are presented in the form of a report, and specific improvement measures are proposed based on the power grid fault detection results, such as strengthening the transmission capacity of specific areas, adjusting the generator output plan, etc., to improve the overall safety of the system.

[0092] In an exemplary embodiment, a power flow calculation is performed on the updated power grid fault scenario, and a transient stability analysis is performed on the updated power grid fault scenario, including: performing AC / DC power flow calculation to determine the power flow after the power grid fault, checking whether the voltage level exceeds the allowable range, branch overload conditions, and generator power limitations, etc. At the same time, in addition to the immediate power flow conditions, a transient stability analysis is also required to determine whether the system can recover to a normal working state after experiencing a large disturbance. Based on the above calculation and analysis results, a comprehensive fault detection score data is assigned to each updated power grid fault scenario. In addition, the comprehensive fault detection level of each updated power grid fault scenario can also be determined based on the comprehensive detection score data.

[0093] In the above-mentioned power grid fault detection method, during the entire process, for each power grid fault point in the power grid fault scenario, the target fault impact weight obtained by combining the first fault impact weight and the second fault impact weight effectively reflects the importance of each power grid fault point in the overall fault detection, and based on the target fault impact weights and fault impact parameter information of all fault points in each fault set, the target fault set that really needs to be focused on is more accurately identified, so as to retain the power grid fault scenarios updated based on the target fault set and exclude other fault scenarios that do not need to be paid attention to, thereby effectively reducing the shortcomings of the traditional method that relies on expert experience and subjective judgment, and improving the objectivity, accuracy and scientificity of the fault scenario selection, thereby achieving accurate fault detection of the updated power grid fault scenarios and generating power grid fault detection results.

[0094] In an exemplary embodiment, Figure 3 As shown, the fault impact parameter information includes the fault frequency, fault consequence severity index, fault vulnerability index and fault recovery time index; S100 includes:

[0095] S110, acquiring historical power grid fault data, and constructing a power grid fault scenario based on the historical power grid fault data.

[0096] S120, based on the historical fault data of the power grid, obtain the total operating time of the node where the fault is located for multiple power grid fault points within a preset time period, the number of faults within the total operating time of the node where the fault is located, the number of users affected by the fault, the power outage time affected by the fault, the amount of resources lost due to the fault, the fault redundancy, the fault repair time and the fault scheduling response time.

[0097] S130 , for each power grid fault point, generating a fault occurrence frequency based on the total operating time of the node where the fault is located and the number of faults.

[0098] S140 , generating a fault consequence severity index based on the number of users affected by the fault, the power outage duration affected by the fault, and the amount of resources lost due to the fault.

[0099] S150: Generate a fault vulnerability index based on the fault occurrence frequency and the fault redundancy.

[0100] S160: Generate a fault recovery time index based on the fault repair time and the fault scheduling response time.

[0101] Specifically, based on the historical power grid fault data, an analysis is performed on each power grid fault point included in each power grid fault set in each power grid fault scenario. Based on the analysis results, the fault influencing parameter information such as the fault occurrence frequency, fault consequence severity index, fault vulnerability index and fault recovery time index of each power grid fault point included in each power grid fault set in each fault scenario is obtained respectively.

[0102] The method for obtaining each fault impact parameter information includes:

[0103] Regarding the frequency of failure:

[0104] Based on the historical fault data of the power grid, the number of faults m of each power grid fault point within the total operating time T of the fault node within the preset time period is counted. The fault occurrence frequency f of each power grid fault point is obtained based on the total operating time T of the fault node within the preset time period and the number of faults m. More specifically, the fault occurrence frequency f of each power grid fault point is obtained based on the ratio of the total operating time T of the fault node within the preset time period to the number of faults m.

[0105] For the severity index of failure consequences:

[0106] Based on historical grid fault data, determine the number of users N affected by the fault, the power outage duration t, and the amount of resources lost E due to the fault, such as direct economic losses, at each grid fault point. Based on the number of users N affected by the fault, the power outage duration t, and the amount of resources lost E, generate a fault consequence severity index for each grid fault point.

[0107] Among them, the generation expression of the fault consequence severity index of each power grid fault point is:

[0108] S ijk =K1N ijk +K2t ijk +K3E ijk

[0109] Among them, S ijk N represents the severity index of the kth grid fault point contained in the jth grid fault set in the ith grid fault scenario; ijk represents the number of users N affected by the kth grid fault point in the jth grid fault set in the i-th grid fault scenario; ijk represents the power outage time t caused by the kth grid fault point fault included in the jth grid fault set in the i-th grid fault scenario; E ijk represents the amount of fault loss resources E caused by the kth grid fault point fault included in the jth grid fault set in the i-th grid fault scenario; K1, K2, and K3 represent preset proportional coefficients.

[0110] Regarding the Fault Vulnerability Index:

[0111] Based on the historical fault data of the power grid, the fault redundancy R of each power grid fault point is determined. d , based on the fault frequency f and fault redundancy R of each power grid fault point d , obtain the fault vulnerability index of each power grid fault point;

[0112] The calculation formula for the fault vulnerability index of each power grid fault point is:

[0113] V ijk =K4(1-R d ijk )+K5f ijk

[0114] Among them, V ijk represents the fault vulnerability index of the kth grid fault point contained in the jth grid fault set in the ith grid fault scenario; R d ijk represents the fault redundancy R of the kth grid fault point contained in the jth grid fault set in the i-th grid fault scenario d ;f ijk represents the fault occurrence frequency f of the kth grid fault point included in the jth grid fault set in the i-th grid fault scenario; K4 and K5 represent preset proportional coefficients.

[0115] For the fault recovery time index:

[0116] Determine the fault repair time T for each grid fault point based on historical grid fault data r And fault scheduling response time T S ; According to the fault repair time T of each grid fault point S and fault dispatch response time T S , obtain the fault recovery time index of each power grid fault point;

[0117] The calculation formula for the restoration time index of each grid fault point is:

[0118] R ijk =T r ijk +T S ijk

[0119] Among them, R ijk represents the fault recovery time index of the kth grid fault point included in the jth grid fault set in the ith grid fault scenario; T r ijk represents the fault repair time T of the kth grid fault point included in the jth grid fault set in the i-th grid fault scenario r ;T S ijk represents the fault dispatch response time T of the kth grid fault point included in the jth grid fault set in the i-th grid fault scenario S .

[0120] In the above embodiment, comprehensive fault impact parameters are generated from multiple aspects such as fault frequency, fault consequence severity index, fault vulnerability index and fault recovery time index, and accurate power grid fault detection can be performed based on the comprehensive fault impact parameters.

[0121] In an exemplary embodiment, the target fault impact parameter information includes a fault occurrence frequency and a fault consequence severity index. Generating a second fault impact weight based on the target fault impact parameter information and the first fault impact weight includes:

[0122] Based on the fault occurrence frequency and the fault consequence severity index, a fault intermediate detection value is generated, and based on the fault intermediate detection value and the first fault impact weight, a second fault impact weight is generated.

[0123] Specifically, the fault impact parameter information of higher importance is the fault frequency and the fault consequence severity index. Therefore, based on the fault frequency and the fault consequence severity index, a fault intermediate detection value is generated. In other words, based on the ratio of the fault frequency to the fault consequence severity index, the fault intermediate detection value is generated. The second fault impact weight is generated based on the product of the fault intermediate detection value and the first fault impact weight. The specific expression includes:

[0124] w 2 ijk =(w 1 ijk f ijk ) / S ijk

[0125] Among them, w 2 ijk represents the second fault impact weight of the kth grid fault point included in the jth grid fault set in the ith grid fault scenario; f ijk represents the fault occurrence frequency f of the kth grid fault point contained in the jth grid fault set in the i-th grid fault scenario; S ijk represents the severity index of the kth grid fault point contained in the jth grid fault set in the ith grid fault scenario, w 1 ijk Represents the first fault impact weight of the kth grid fault point included in the jth grid fault set in the i-th grid fault scenario.

[0126] By combining the primary fault impact weight with two key factors—fault frequency and fault consequence severity—this design assigns higher weights to grid fault points that occur frequently and have severe consequences. Fault frequency and the fault consequence severity index are key factors in evaluating grid fault points. They directly reflect the likelihood and impact of a fault and are key indicators in determining the importance of a fault point. By using a ratio, they balance the relationship between fault frequency and the fault consequence severity index. For example, if a grid fault point has a high frequency but low consequences, its secondary fault impact weight will be relatively low. Conversely, if a grid fault point has a low frequency but severe consequences, its secondary fault impact weight will be relatively high.

[0127] It's important to explain that the reason for selecting fault frequency and fault consequence severity index as target fault impact parameters is that they are primary factors in assessing fault point risk. They directly reflect the likelihood and impact of a fault and are core indicators for determining the importance of a fault point. However, while the fault vulnerability index and fault recovery time index are also important parameters, they more closely reflect the characteristics and recovery capabilities of a fault point. These factors are more appropriately considered in the comprehensive weighting (i.e., the target fault impact weighting) rather than in the secondary fault impact weighting. Furthermore, the primary fault impact weighting encompasses all important factors, while the secondary fault impact weighting focuses solely on the fault frequency and fault consequence severity index. This ensures a hierarchical and rational weighting system. Furthermore, reintroducing the fault vulnerability index and fault recovery time index into the secondary fault impact weighting may overemphasize or duplicate certain factors, affecting the accuracy of the weighting.

[0128] When subsequently generating the target fault impact weight for each grid fault point based on the first and second fault impact weights corresponding to each grid fault point, the first fault impact weight incorporates multiple factors, including fault frequency, fault consequence severity index, fault vulnerability index, and fault recovery time index. The second fault impact weight further emphasizes key factors of high importance through the ratio of fault frequency to fault consequence severity index. By combining the first and second fault impact weights, all important factors can be comprehensively considered, ensuring a more comprehensive and accurate fault impact weight for each grid fault point. It is worth noting that using either the first or second fault impact weight alone may result in certain factors being overemphasized or overlooked. By combining the two fault impact weights, they complement each other and improve the reliability and accuracy of the target fault impact weight.

[0129] In this embodiment, by combining the first fault impact weight with the more important fault frequency and fault consequence severity index in the fault impact parameter information, a second fault impact weight is generated. This allows for greater attention to be paid to the more important fault impact parameter information, making subsequent screening of power grid fault scenarios more accurate.

[0130] In an exemplary embodiment, based on target fault impact weights and fault impact parameter information of all grid fault points in each grid fault set, a target grid fault set is screened out from multiple grid fault sets, including:

[0131] Based on the target fault impact weights and fault impact parameter information corresponding to all grid fault points in each grid fault set, a comprehensive scoring result for each grid fault set is generated; the grid fault set with a comprehensive scoring result greater than a preset scoring threshold is used as the target fault set.

[0132] Specifically, a scoring result for each grid fault point is generated based on the product of the target fault impact weight corresponding to each grid fault point and the fault impact parameter information. A comprehensive scoring result for each grid fault set is generated based on the scoring results of all grid fault points in each grid fault set. Furthermore, grid fault points with comprehensive scores greater than a preset scoring threshold are considered target fault sets, while grid fault points with comprehensive scores less than or equal to the preset scoring threshold are considered non-target fault sets. The target fault sets in the grid fault scenario are retained, while non-target fault sets in the grid fault scenario are filtered out.

[0133] Furthermore, when the fault impact parameter information includes fault frequency, fault consequence severity index, fault vulnerability index, and fault recovery time index, a scoring result for each power grid fault point is generated based on the product of the target fault impact weight corresponding to each power grid fault point and the fault impact parameter information, including:

[0134] For each power grid fault point, the target fault impact weight is multiplied by the fault frequency, fault consequence severity index, fault vulnerability index and fault recovery time index respectively to obtain the weighted results of the fault frequency, fault consequence severity index, fault vulnerability index and fault recovery time index. The weighted results of the fault frequency, fault consequence severity index, fault vulnerability index and fault recovery time index are summed to obtain the scoring result.

[0135] Furthermore, based on the scoring results of all grid fault points in each grid fault set, a comprehensive scoring result of each grid fault set is generated, including: for each grid fault set, the scoring results of all grid fault points are added together to generate a comprehensive scoring result of each grid fault set.

[0136] The comprehensive score result S of each power grid fault set set ij The expression is as follows:

[0137]

[0138] Among them, S set ij represents the comprehensive scoring result of the jth grid fault set in the i-th grid fault scenario; w final ijk represents the target fault impact weight of the kth grid fault point contained in the jth grid fault set in the i-th grid fault scenario; f ijk represents the fault occurrence frequency f of the kth grid fault point contained in the jth grid fault set in the i-th grid fault scenario; S ijk represents the severity index of the kth grid fault point contained in the jth grid fault set in the ith grid fault scenario; V ijk represents the fault vulnerability index of the kth grid fault point contained in the jth grid fault set in the ith grid fault scenario; R ijk represents the fault recovery time index of the kth grid fault point included in the jth grid fault set in the i-th grid fault scenario; n ij Represents the number of grid fault points included in the jth grid fault set in the i-th grid fault scenario.

[0139] In addition, it is necessary to set a preset scoring threshold for the comprehensive scoring result, and use the preset scoring threshold to screen the comprehensive scoring result of each power grid fault set in each power grid fault scenario. If the comprehensive scoring result of the current power grid fault set in the current power grid fault scenario is greater than or equal to the threshold, the current power grid fault set is retained; if the comprehensive scoring result of the current power grid fault set in the current power grid fault scenario is less than the threshold, the current power grid fault set is eliminated; and the retained current power grid fault set is reassembled to form a new power grid fault scenario.

[0140] In the above embodiment, by generating a comprehensive scoring result for each power grid fault set based on the target fault impact weights and fault impact parameter information corresponding to all power grid fault points in each power grid fault set, it is possible to efficiently screen out highly important power grid fault sets from the power grid fault scenarios, thereby retaining those power grid fault scenarios that really need to be focused on, such as high-risk power grid fault scenarios, and excluding low-risk or unimportant power grid fault scenarios.

[0141] In an exemplary embodiment, constructing a power grid fault scenario based on historical power grid fault data includes:

[0142] Based on the historical fault data of the power grid, the target fault events that meet the fault event selection conditions are detected from all the fault events of the power grid. The target fault events are used as the power grid fault points, and the correlation between all the power grid fault points is obtained. The power grid fault points with correlation higher than the preset correlation threshold among all the power grid fault points are combined respectively to obtain multiple power grid fault sets. The multiple power grid fault sets are aggregated to construct a power grid fault scenario.

[0143] The fault event selection condition includes at least one of the following: the fault occurrence frequency is higher than a preset frequency threshold, and the fault consequence severity index exceeds a preset consequence severity index threshold.

[0144] Specifically, based on historical grid fault data, the process of constructing a grid fault scenario is as follows:

[0145] First, typical faults among all fault events are selected: Based on historical fault data, target fault events that meet the fault event selection conditions are detected among all fault events of the power grid. These events should have a high occurrence frequency or serious consequences, and the target fault events are used as the power grid fault points.

[0146] Secondly, grid fault points are combined: the selected grid fault points are combined into a fault set. Specifically, the correlation between all grid fault points is obtained; the grid fault points with correlation higher than a preset correlation threshold among all grid fault points are combined separately to obtain multiple grid fault sets. In other words, the correlation between the grid fault points in each grid fault set is high. For example, if historical fault data shows that line A frequently experiences disconnection faults and short circuit faults at positions X and Y, these two grid fault points can be combined into one grid fault set.

[0147] Finally, construct a grid fault scenario: combine multiple grid fault sets into one grid fault scenario. For example, a single line fault scenario can include multiple grid fault sets at different locations, while a multi-line simultaneous fault scenario can include multiple grid fault sets at different lines.

[0148] In addition, when constructing a power grid fault scenario, it is also necessary to verify the rationality of the power grid fault scenario. The specific rationality verification methods include: verifying whether the defined power grid fault scenario is reasonable through expert review, ensuring that the power grid fault scenario can cover the main risk factors during fault detection, and is feasible in actual operation.

[0149] In this embodiment, by accurately and efficiently constructing power grid fault scenarios layer by layer from power grid fault points to power grid fault sets, the constructed power grid fault scenarios can cover the main risk factors during fault detection and are feasible in actual operations.

[0150] In an exemplary embodiment, there is more than one fault impact parameter information, and generating a first fault impact weight based on the fault impact parameter information includes:

[0151] For each piece of fault impact parameter information, a fault weight coefficient of the fault impact parameter information is obtained, and the fault impact parameter information is updated based on the fault weight coefficient; and a first fault impact weight is generated according to all updated fault impact parameter information.

[0152] The fault impact parameter information includes but is not limited to the fault occurrence frequency, fault consequence severity index, fault vulnerability index and fault recovery time index.

[0153] Specifically, for each fault impact parameter information, the fault weight coefficient of the fault impact parameter information is obtained, that is, the fault weight coefficient of the fault occurrence frequency, the fault weight coefficient of the fault consequence severity index, the fault weight coefficient of the fault vulnerability index and the fault recovery time index are obtained. According to the fault weight coefficient of each fault impact parameter information, all fault impact parameter information is weighted and summed to generate a first fault impact weight, that is, based on the fault weight coefficient of each fault impact parameter information, the fault impact parameter information is updated, and then, all updated fault impact parameter information is summed to generate the first fault impact weight.

[0154] More specifically, based on the fault weight coefficient of each fault impact parameter information, the fault impact parameter information is updated, and then all updated fault impact parameter information is summed to generate a first fault impact weight, including: ijk Fault weight coefficient , get the updated fault frequency f ijk , according to the severity index S of the failure consequences ijk Fault weight coefficient , get the updated failure consequence severity index S ijk , according to the fault vulnerability index V ijk Fault weight coefficient , get the updated fault vulnerability index V ijk , according to the fault recovery time index R ijk Fault weight coefficient , get the updated fault recovery time index R ijk . Then, the updated fault frequency f ijk , Updated Failure Consequence Severity Index S ijk , updated fault vulnerability index V ijk and the updated Fault Recovery Time Index R ijk Sum up and generate the first fault impact weight w 1 ijk . Its expression is as follows:

[0155] w 1 ijk = f ijk + S ijk + Vijk + R ijk

[0156] Here, i, j, and k respectively represent the kth grid fault point contained in the jth grid fault set in the i-th grid fault scenario.

[0157] In the above embodiment, the first fault impact weight associated with all fault impact parameter information is accurately generated by obtaining the fault weight coefficients of the fault impact parameter information and performing weighted summation on the fault weight coefficients of the fault impact parameter information.

[0158] In an exemplary embodiment, the power grid fault detection method further includes:

[0159] S1: Obtain historical power grid fault data, and based on the historical power grid fault data, detect target fault events that meet the fault event selection conditions among all power grid fault events, wherein the fault event selection conditions include at least one of the following: the fault frequency is higher than a preset frequency threshold, and the fault consequence severity index exceeds a preset consequence severity index threshold; take the target fault event as the power grid fault point, and obtain the correlation between all power grid fault points; combine all power grid fault points whose correlation is higher than the preset correlation threshold to obtain multiple power grid fault sets; and aggregate the multiple power grid fault sets to construct a power grid fault scenario. In other words, the power grid fault scenario includes multiple power grid fault sets, and each power grid fault set includes multiple power grid fault points.

[0160] S2: Based on historical power grid fault data, multiple fault impact parameter information is obtained, where the fault impact parameter information includes fault frequency, fault consequence severity index, fault vulnerability index, and fault recovery time index.

[0161] Specifically, based on historical power grid fault data, the total operating time of the node where the fault is located for multiple power grid fault points within a preset time period, the number of faults within the total operating time of the node where the fault is located, the number of users affected by the fault, the power outage time affected by the fault, the amount of resources lost due to the fault, the fault redundancy, the fault repair time, and the fault scheduling response time are obtained;

[0162] For each grid fault point, the fault frequency is generated based on the total operating time and number of faults of the node where the fault is located;

[0163] Generate a fault consequence severity index based on the number of users affected by the fault, the power outage duration affected by the fault, and the amount of resources lost due to the fault;

[0164] Generate a fault vulnerability index based on fault frequency and fault redundancy;

[0165] Generate a fault recovery time index based on the fault repair time and the fault scheduling response time.

[0166] S3: For each power grid fault point, obtain the fault weight coefficient of all fault impact parameter information, and update the fault impact parameter information based on the fault weight coefficient of each fault impact parameter information; generate a first fault impact weight according to all updated fault impact parameter information.

[0167] When target fault impact parameter information in the fault impact parameter information is detected, the ratio of the fault occurrence frequency to the fault consequence severity index is multiplied by the first fault impact weight to generate a second fault impact weight, wherein the target fault impact parameter information is fault impact parameter information whose importance is higher than a preset importance threshold.

[0168] Finally, a target fault impact weight of each power grid fault point is generated according to the first fault impact weight and the second fault impact weight corresponding to each power grid fault point.

[0169] S4: Based on the target fault impact weights and fault impact parameter information corresponding to all grid fault points in each grid fault set, a comprehensive scoring result for each grid fault set is generated; and the grid fault set whose comprehensive scoring result is greater than a preset scoring threshold is used as the target fault set.

[0170] S5: Perform power flow calculation on the updated power grid fault scenario, perform transient stability analysis on the updated power grid fault scenario, and assign comprehensive fault detection score data to the updated power grid fault scenario based on the power flow calculation results and the transient stability analysis results.

[0171] S6: This application can generate comprehensive fault detection scoring data for multiple power grid fault scenarios according to steps S1-S5, and sort the power grid fault scenarios based on the comprehensive fault detection scoring data of all power grid fault scenarios to obtain power grid fault detection results, and then use the power grid fault detection results.

[0172] The present application discloses a power grid fault detection method, which quantitatively analyzes the fault frequency, fault consequence severity index, fault vulnerability index, and fault recovery time index of power grid fault points, and screens power grid fault scenarios in combination with target fault impact weights. The target fault impact weight obtained by combining the first fault impact weight and the second fault impact weight can effectively reflect the importance of each power grid fault point in the overall fault detection. The comprehensive scoring result calculated in combination with the target fault impact weight can more accurately identify high-risk or unimportant power grid fault sets, thereby retaining those power grid fault sets that truly require focus and excluding low-risk or unimportant power grid fault sets to update power grid fault scenarios. This effectively reduces the shortcomings of traditional methods that rely on expert experience and subjective judgment, and improves the objectivity, accuracy, and scientific nature of power grid fault scenario selection.

[0173] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed 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 performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0174] Based on the same inventive concept, embodiments of the present application further provide a power grid fault detection device for implementing the aforementioned power grid fault detection method. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more power grid fault detection device embodiments provided below can be found in the above-mentioned limitations of the power grid fault detection method and will not be further elaborated here.

[0175] In an exemplary embodiment, Figure 4 As shown, a power grid fault detection device is provided, comprising: an acquisition module 100, a first weight processing module 200, a second weight processing module 300, a power grid fault scenario updating module 400 and a fault detection module 500, wherein:

[0176] An acquisition module 100 is configured to acquire historical grid fault data, construct a grid fault scenario based on the historical grid fault data, and generate fault impact parameter information for multiple grid fault points, wherein the grid fault scenario includes multiple grid fault sets, and each grid fault set includes multiple grid fault points;

[0177] A first weight processing module 200 is configured to generate, for each power grid fault point, a first fault impact weight based on the fault impact parameter information, and, upon detecting target fault impact parameter information in the fault impact parameter information, generate a second fault impact weight based on the target fault impact parameter information and the first fault impact weight, wherein the target fault impact parameter information is fault impact parameter information having an importance higher than a preset importance threshold;

[0178] A second weight processing module 300 is configured to generate a target fault impact weight for each power grid fault point based on the first fault impact weight and the second fault impact weight corresponding to each power grid fault point;

[0179] A power grid fault scenario updating module 400 is configured to screen a target power grid fault set from multiple power grid fault sets based on target fault impact weights and fault impact parameter information of all power grid fault points in each power grid fault set, and update the power grid fault scenario based on the target power grid fault set;

[0180] The fault detection module 500 is configured to perform fault detection on the updated power grid fault scenario and generate a power grid fault detection result.

[0181] In one embodiment, the fault impact parameter information includes the fault frequency, the fault consequence severity index, the fault vulnerability index and the fault recovery time index; the acquisition module 100 is also used to obtain the total operating time of the fault node of multiple power grid fault points within a preset time period, the number of failures within the total operating time of the fault node, the number of users affected by the fault, the power outage time affected by the fault, the amount of resources lost due to the fault, the fault redundancy, the fault repair time and the fault scheduling response time based on the historical fault data of the power grid; for each power grid fault point, the fault frequency is generated based on the total operating time of the fault node and the number of failures; the fault consequence severity index is generated based on the number of users affected by the fault, the power outage time affected by the fault and the amount of resources lost due to the fault; the fault vulnerability index is generated based on the fault frequency and the fault redundancy; and the fault recovery time index is generated based on the fault repair time and the fault scheduling response time.

[0182] In one embodiment, the first weight processing module 200 is further configured to generate a fault intermediate detection value based on the fault occurrence frequency and the fault consequence severity index; and generate a second fault impact weight based on the fault intermediate detection value and the first fault impact weight.

[0183] In one embodiment, the power grid fault scenario update module 400 is further used to generate a comprehensive scoring result for each power grid fault set based on the target fault impact weights and fault impact parameter information corresponding to all power grid fault points in each power grid fault set; and the power grid fault set whose comprehensive scoring result is greater than a preset scoring threshold is used as the target fault set.

[0184] In one embodiment, the acquisition module 100 is further used to detect target fault events that meet the fault event selection conditions among all fault events of the power grid based on historical power grid fault data, wherein the fault event selection conditions include at least one of the fault occurrence frequency being higher than a preset frequency threshold and the fault consequence severity index exceeding a preset consequence severity index threshold; taking the target fault event as the power grid fault point, and obtaining the correlation between all power grid fault points; combining the power grid fault points whose correlation is higher than the preset correlation threshold among all power grid fault points to obtain multiple power grid fault sets; and aggregating multiple power grid fault sets to construct a power grid fault scenario.

[0185] In one embodiment, there is more than one fault impact parameter information, and the first weight processing module 200 is further used to obtain the fault weight coefficient of the fault impact parameter information for each fault impact parameter information, and update the fault impact parameter information based on the fault weight coefficient; and generate the first fault impact weight based on all updated fault impact parameter information.

[0186] Each module in the above-mentioned power grid fault detection device 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 hardware form, or can be stored in a memory in the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0187] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 computer program in the non-volatile storage medium. The database of the computer device is used to store data such as historical power grid fault data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a power grid fault detection method is implemented.

[0188] Those skilled in the art will understand that Figure 5 The structure shown in the figure is a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0189] In one embodiment, a computer device is further 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.

[0190] 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.

[0191] 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.

[0192] Those skilled in the art will understand that all or part of the processes in the above-mentioned 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 the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. 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, artificial intelligence (AI) processors, and the like.

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

[0194] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A power grid fault detection method, characterized in that: The method comprises: Obtain historical power grid fault data, and construct a power grid fault scenario based on the historical power grid fault data, and generate fault impact parameter information of multiple power grid fault points, wherein the power grid fault scenario includes multiple power grid fault sets, each of the power grid fault sets includes multiple power grid fault points; the fault impact parameter information includes fault occurrence frequency, fault consequence severity index, fault vulnerability index and fault recovery time index; generate fault impact parameter information of multiple power grid fault points based on the historical power grid fault data, including: obtaining the total operating time of the fault node of the multiple power grid fault points within a preset time period, the fault location index, the fault location index, the fault impact parameter information of the multiple power grid fault points based on the historical power grid fault data, and the fault impact parameter information of the multiple power grid fault points within a preset time period. The number of failures within the total operating time of the node, the number of users affected by the failure, the power outage time affected by the failure, the amount of resources lost due to the failure, the fault redundancy, the fault repair time, and the fault scheduling response time; for each grid fault point, based on the total operating time of the node where the failure is located and the number of failures, a fault occurrence frequency is generated; based on the number of users affected by the failure, the power outage time affected by the failure, and the amount of resources lost due to the failure, a fault consequence severity index is generated; based on the fault occurrence frequency and the fault redundancy, a fault vulnerability index is generated; based on the fault repair time and the fault scheduling response time, a fault recovery time index is generated; For each of the power grid fault points, generating a first fault impact weight based on the fault impact parameter information, and upon detecting the fault occurrence frequency and the fault consequence severity index in the fault impact parameter information, generating a fault intermediate detection value based on the fault occurrence frequency and the fault consequence severity index, and generating a second fault impact weight based on the fault intermediate detection value and the first fault impact weight; generating a target fault impact weight for each of the power grid fault points according to the first fault impact weight and the second fault impact weight corresponding to each of the power grid fault points; Based on the target fault impact weights and fault impact parameter information of all grid fault points in each of the grid fault sets, a target grid fault set is screened out from the multiple grid fault sets, and the grid fault scenario is updated based on the target grid fault set; Fault detection is performed on the updated power grid fault scenario to generate a power grid fault detection result.

2. The method according to claim 1, characterized in that The step of screening out a target fault set from the plurality of power grid fault sets based on the target fault impact weights and fault impact parameter information of all power grid fault points in each fault set includes: generating a comprehensive scoring result for each power grid fault set based on the target fault impact weights and the fault impact parameter information corresponding to all the power grid fault points in each power grid fault set; The power grid fault set whose comprehensive scoring result is greater than a preset scoring threshold is used as a target fault set.

3. The method according to claim 1, characterized in that The step of constructing a power grid fault scenario based on historical power grid fault data includes: Detecting, based on historical fault data of the power grid, target fault events that meet a fault event selection condition from among all fault events of the power grid, wherein the fault event selection condition includes at least one of a fault occurrence frequency exceeding a preset frequency threshold and a fault consequence severity index exceeding a preset consequence severity index threshold; Taking the target fault event as a power grid fault point, and obtaining the correlation between all the power grid fault points; Combine the grid fault points whose correlation is higher than a preset correlation threshold among all the grid fault points to obtain multiple grid fault sets; The plurality of power grid fault sets are collected to construct a power grid fault scenario.

4. The method according to claim 1, wherein There is more than one fault impact parameter information, and generating a first fault impact weight based on the fault impact parameter information includes: For each piece of fault impact parameter information, obtaining a fault weight coefficient of the fault impact parameter information, and updating the fault impact parameter information based on the fault weight coefficient; A first fault impact weight is generated according to all updated fault impact parameter information.

5. A power grid fault detection device, characterized in that: The device comprises: An acquisition module is used to acquire historical power grid fault data, and construct a power grid fault scenario based on the historical power grid fault data, and generate fault impact parameter information of multiple power grid fault points, wherein the power grid fault scenario includes multiple power grid fault sets, each of the power grid fault sets includes multiple power grid fault points; the fault impact parameter information includes fault occurrence frequency, fault consequence severity index, fault vulnerability index and fault recovery time index; generating fault impact parameter information of multiple power grid fault points based on the historical power grid fault data includes: based on the historical power grid fault data, acquiring the total operating time of the fault node of the multiple power grid fault points within a preset time period, the total operating time of the fault node ... The number of faults within the total operating time of the node where the fault is located, the number of users affected by the fault, the power outage time affected by the fault, the amount of resources lost due to the fault, the fault redundancy, the fault repair time, and the fault scheduling response time are calculated; for each power grid fault point, a fault occurrence frequency is generated based on the total operating time of the node where the fault is located and the number of faults; a fault consequence severity index is generated based on the number of users affected by the fault, the power outage time affected by the fault, and the amount of resources lost due to the fault; a fault vulnerability index is generated based on the fault occurrence frequency and the fault redundancy; and a fault recovery time index is generated based on the fault repair time and the fault scheduling response time; a first weight processing module, configured to generate, for each of the power grid fault points, a first fault impact weight based on the fault impact parameter information, and, upon detecting the fault occurrence frequency and the fault consequence severity index in the fault impact parameter information, generate a fault intermediate detection value based on the fault occurrence frequency and the fault consequence severity index, and generate a second fault impact weight based on the fault intermediate detection value and the first fault impact weight; a second weight processing module, configured to generate a target fault impact weight for each of the power grid fault points according to the first fault impact weight and the second fault impact weight corresponding to each of the power grid fault points; a power grid fault scenario updating module, configured to screen out a target power grid fault set from the plurality of power grid fault sets based on target fault impact weights and fault impact parameter information of all power grid fault points in each power grid fault set, and update the power grid fault scenario based on the target power grid fault set; The fault detection module is used to perform fault detection on the updated power grid fault scenario and generate a power grid fault detection result.

6. The device according to claim 5, characterized in that The power grid fault scenario updating module is further configured to generate a comprehensive scoring result for each power grid fault set based on the target fault impact weights and the fault impact parameter information corresponding to all the power grid fault points in each power grid fault set; The power grid fault set whose comprehensive scoring result is greater than a preset scoring threshold is used as a target fault set.

7. The device according to claim 5, characterized in that The acquisition module is further configured to detect, based on historical grid fault data, target fault events that meet fault event selection conditions among all grid fault events, wherein the fault event selection conditions include at least one of a fault occurrence frequency exceeding a preset frequency threshold and a fault consequence severity index exceeding a preset consequence severity index threshold; use the target fault event as a grid fault point, and obtain the correlation between all the grid fault points; combine all the grid fault points whose correlation is higher than a preset correlation threshold to obtain multiple grid fault sets; and aggregate the multiple grid fault sets to construct a grid fault scenario.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images