Medium-voltage power distribution network fault data compensation method, device, equipment, medium and product

Abstract

The embodiment of the invention provides a medium-voltage power distribution network fault data compensation method and device, equipment, a medium and a product, and is applied to the technical field of data processing. The method comprises the steps of collecting multi-source fault data of a target power grid in real time; the multi-source fault data comprises electrical parameters and environmental parameters of each electrical node of the target power grid; missing value detection is carried out on the multi-source fault data, and an electrical node corresponding to each missing value and a missing time period are determined; when the missing time period is a mid-term missing time period, for the electrical node corresponding to the missing value, adopting a spatial dimension interpolation calculation mode to obtain a spatial compensation value corresponding to the missing value; adopting a time dimension interpolation calculation mode to obtain a time compensation value corresponding to the missing value; and performing compensation fusion based on the space compensation value and the time compensation value to obtain a target compensation value corresponding to the missing value. The technical effect of improving the data compensation precision is achieved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, equipment, medium and product for compensating for fault data in medium-voltage distribution networks. Background Technology

[0002] In medium-voltage power distribution networks, numerous smart distribution terminals are deployed, which collect real-time power grid operation data. Due to the highly dynamic and heterogeneous nature of this data, data loss is common during data acquisition due to data transformations. Therefore, for further data analysis, data compensation processing is necessary to address the missing data.

[0003] In existing technologies, the main method for data compensation in medium-voltage distribution networks is to use the data of neighboring nodes associated with the missing data node to perform linear interpolation calculations, thereby obtaining the compensation value used for missing value compensation.

[0004] Because existing data compensation methods only consider the continuity of time and ignore the spatial correlation of the power grid topology, the accuracy of the compensation data generated is low in scenarios of sudden changes in electrical quantities during power grid faults. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, medium, and product for compensating fault data in medium-voltage distribution networks, in order to achieve the technical effect of improving the accuracy of data compensation.

[0006] In a first aspect, embodiments of this application provide a method for compensating fault data in a medium-voltage distribution network, including:

[0007] Real-time acquisition of multi-source fault data of the target power grid; multi-source fault data includes electrical parameters and environmental parameters of each electrical node of the target power grid;

[0008] For multi-source fault data, missing value detection is performed to determine the electrical node and missing time period corresponding to each missing value;

[0009] When the missing period is a medium-term missing period, spatial interpolation is used to calculate the spatial compensation value corresponding to the missing value for the electrical node corresponding to the missing value; temporal interpolation is used to calculate the temporal compensation value corresponding to the missing value.

[0010] The compensation is fused based on spatial compensation values ​​and temporal compensation values ​​to obtain the target compensation value corresponding to the missing value.

[0011] In one possible implementation, spatial dimension interpolation is used to obtain the spatial compensation value corresponding to the missing value, including:

[0012] Based on the topology of the target power grid, obtain the set of electrical neighbor nodes corresponding to the missing values;

[0013] Based on the electrical distance and topological level of each node in the set of electrical nodes and electrical neighboring nodes, the spatial weighting coefficient is calculated;

[0014] Based on multi-source fault data, the normal values ​​of each node in the electrical proximity node set during the missing time period are determined;

[0015] Spatial interpolation is performed based on normal values ​​and spatial weighting coefficients to obtain spatial compensation values ​​corresponding to missing values.

[0016] In one possible implementation, time-dimensional interpolation is used to obtain the time compensation value corresponding to the missing value, including:

[0017] Based on multi-source fault data, determine the current operating mode of the target power grid;

[0018] Based on the operating mode, search the historical database of the target power grid to obtain historical fault data under the same operating mode;

[0019] Determine the historical data corresponding to the missing value during the missing period based on historical fault data;

[0020] Based on historical data and the matching degree between the current operating mode and the historical operating mode corresponding to historical fault data, time interpolation is performed to obtain the time compensation value corresponding to the missing value.

[0021] In one possible implementation, after performing missing value detection on multi-source fault data and determining the electrical node and missing time period corresponding to each missing value, the method further includes:

[0022] When the duration of the missing period is less than a first preset threshold, the missing period is determined to be a short-term missing period.

[0023] When the duration of the missing period is greater than or equal to the first preset threshold and less than the second preset threshold, the missing period is determined to be a medium-term missing period.

[0024] When the duration of the missing period is greater than or equal to the second preset threshold, the missing period is determined to be a long-term missing period.

[0025] In one possible implementation, after performing missing value detection on multi-source fault data and determining the electrical node and missing time period corresponding to each missing value, the method further includes:

[0026] When the missing period is a short-term missing period, the spatial compensation value corresponding to the missing value is calculated based on the topology data of the electrical nodes and the target power grid, and it is determined as the target compensation value corresponding to the missing value.

[0027] When the missing period is a long-term missing period, a data alarm is triggered and the missing values ​​are marked as uncompensable data.

[0028] In one possible implementation, the method further includes:

[0029] The multi-source fault data after compensation is denoised to obtain standardized data.

[0030] The fault monitoring results of the target power grid at the current moment are generated based on standardized data;

[0031] Based on the fault monitoring results, the fault handling strategy corresponding to the target power grid is determined, and the fault isolation and fault recovery processes of the target power grid are carried out based on the fault handling strategy.

[0032] Secondly, embodiments of this application provide a medium-voltage distribution network fault data compensation device, comprising:

[0033] The acquisition module is used to collect multi-source fault data of the target power grid in real time; the multi-source fault data includes electrical parameters and environmental parameters of each electrical node of the target power grid;

[0034] The first processing module is used to perform missing value detection on multi-source fault data and determine the electrical node and missing time period corresponding to each missing value.

[0035] The second processing module is used to calculate the spatial compensation value corresponding to the missing value by using spatial interpolation for the electrical node corresponding to the missing value when the missing period is a medium-term missing period; and to calculate the time compensation value corresponding to the missing value by using temporal interpolation.

[0036] The third processing module is used to perform compensation fusion based on spatial compensation values ​​and temporal compensation values ​​to obtain the target compensation value corresponding to the missing value.

[0037] In one possible implementation, the second processing module is further configured to:

[0038] Based on the topology of the target power grid, obtain the set of electrical neighbor nodes corresponding to the missing values;

[0039] Based on the electrical distance and topological level of each node in the set of electrical nodes and electrical neighboring nodes, the spatial weighting coefficient is calculated;

[0040] Based on multi-source fault data, the normal values ​​of each node in the electrical proximity node set during the missing time period are determined;

[0041] Spatial interpolation is performed based on normal values ​​and spatial weighting coefficients to obtain spatial compensation values ​​corresponding to missing values.

[0042] In one possible implementation, the second processing module is further configured to:

[0043] Based on multi-source fault data, determine the current operating mode of the target power grid;

[0044] Based on the operating mode, search the historical database of the target power grid to obtain historical fault data under the same operating mode;

[0045] Determine the historical data corresponding to the missing value during the missing period based on historical fault data;

[0046] Based on historical data and the matching degree between the current operating mode and the historical operating mode corresponding to historical fault data, time interpolation is performed to obtain the time compensation value corresponding to the missing value.

[0047] In one possible implementation, the first processing module is further configured to:

[0048] When the duration of the missing period is less than a first preset threshold, the missing period is determined to be a short-term missing period.

[0049] When the duration of the missing period is greater than or equal to the first preset threshold and less than the second preset threshold, the missing period is determined to be a medium-term missing period.

[0050] When the duration of the missing period is greater than or equal to the second preset threshold, the missing period is determined to be a long-term missing period.

[0051] In one possible implementation, the second processing module is further configured to:

[0052] When the missing period is a short-term missing period, the spatial compensation value corresponding to the missing value is calculated based on the topology data of the electrical nodes and the target power grid, and it is determined as the target compensation value corresponding to the missing value.

[0053] When the missing period is a long-term missing period, a data alarm is triggered and the missing values ​​are marked as uncompensable data.

[0054] In one possible implementation, the third processing module is further configured to:

[0055] The multi-source fault data after compensation is denoised to obtain standardized data.

[0056] The fault monitoring results of the target power grid at the current moment are generated based on standardized data;

[0057] Based on the fault monitoring results, the fault handling strategy corresponding to the target power grid is determined, and the fault isolation and fault recovery processes of the target power grid are carried out based on the fault handling strategy.

[0058] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0059] The memory stores the instructions that the computer executes;

[0060] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect above and various possible implementations of the first aspect.

[0061] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and various possible implementations thereof.

[0062] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and various possible implementations thereof.

[0063] This application provides a method, apparatus, equipment, medium, and product for compensating fault data in medium-voltage distribution networks. The method involves real-time acquisition of multi-source fault data from the target power grid, detection of missing values ​​in the multi-source fault data, and determination of the missing time period and electrical node corresponding to each missing value. When the missing time period is a medium-term missing period, spatial compensation values ​​are obtained by spatial interpolation based on the electrical nodes corresponding to the missing values; temporal compensation values ​​are obtained by temporal interpolation. The obtained spatial and temporal compensation values ​​are then fused to obtain the target compensation value corresponding to the missing value. Compared with existing technologies, this application, when processing missing data, combines the spatial correlation of electrical nodes to obtain spatial compensation values ​​incorporating spatial relationships; simultaneously, it combines temporal interpolation to focus on the temporal variation patterns of electrical quantities, combining these two types of variation information to obtain the target compensation value, thereby achieving the technical effect of improving data compensation accuracy. Attached Figure Description

[0064] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0065] Figure 1 A flowchart illustrating the medium-voltage distribution network fault data compensation method provided in this application. Figure 1 ;

[0066] Figure 2A flowchart illustrating the medium-voltage distribution network fault data compensation method provided in this application. Figure 2 ;

[0067] Figure 3 A schematic diagram of the structure of the medium-voltage distribution network fault data compensation device provided in this application;

[0068] Figure 4 A schematic diagram of the structure of the electronic device provided in this application.

[0069] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0070] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0071] In existing technologies, the main method for data compensation of power grid data is to use linear interpolation to handle missing data. When a missing value is determined, linear interpolation is performed using normal data from neighboring electrical nodes to obtain the compensation value.

[0072] However, since the existing technology mainly uses linear interpolation calculations based on data from neighboring nodes, it ignores the spatial correlation between electrical nodes in the power grid topology. As a result, the final compensation result cannot reflect the abrupt change characteristics of electrical quantities during the fault, thus leading to the technical problem of low data compensation accuracy in the existing technology.

[0073] To address the aforementioned technical issues, this application proposes the following technical concept: Spatial interpolation is used to incorporate the inherent spatial correlation of electrical nodes in the power grid topology, thus overcoming the core deficiency of existing technologies that neglect spatial correlation; temporal interpolation is used to focus on the temporal variation patterns of electrical quantities, taking into account the abrupt changes in electrical quantities; and through the fusion of two compensation values, spatial correlation and temporal variation information are integrated to obtain a target compensation value that balances spatial rationality and temporal accuracy, thereby achieving the technical effect of improving the accuracy of data compensation.

[0074] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0075] Figure 1 A flowchart illustrating the medium-voltage distribution network fault data compensation method provided in this application. Figure 1 ,like Figure 1 As shown, the method includes:

[0076] S101. Real-time acquisition of multi-source fault data of the target power grid.

[0077] In this step, the multi-source fault data includes the electrical parameters and environmental parameters of each electrical node in the target power grid. This multi-source fault data can be collected based on the fault monitoring network of the target power grid.

[0078] Alternatively, one possible implementation for collecting multi-source fault data is as follows:

[0079] a1. In response to the fault handling request of the target power grid, obtain the electrical parameters and environmental parameters of each electrical node of the target power grid within a preset time period before and after the fault occurs; at the same time, it can also collect the equipment operation status of the physical equipment related to each electrical node in the target power grid.

[0080] a2. Generate multi-source fault data based on the electrical parameters and environmental parameters generated by each electrical node within a preset time period, as well as the equipment operating status of each physical device.

[0081] In this step, the prerequisite for the fault monitoring network to collect multi-source fault data is the installation of corresponding monitoring terminals at the electrical nodes of the target power grid. These electrical nodes can be substation outgoing switches, main line sectionalizing switches, branch line tie switches, access points for important users, and critical operating equipment within the target power grid. Monitoring terminals can be fault indicators, distribution terminal units, partial discharge sensors, and temperature sensors. The monitoring terminals are primarily used to collect electrical and environmental parameters from each electrical node. The operational status data of the relevant equipment at each electrical node can be uploaded to the fault monitoring network by the data acquisition terminals deployed on the equipment.

[0082] It should be noted that before collecting multi-source fault data, a digital twin model containing the location, connection relationship, and equipment parameters of all monitoring equipment can be constructed based on a geographic information system and a distribution network data monitoring system to clarify the logical relationships between each node. The generated digital twin model can be used as part of the target power grid topology data to determine the neighboring nodes of electrical nodes, or it can be used to perform data simulation of the operating status of the target power grid.

[0083] S102. For multi-source fault data, perform missing value detection to determine the electrical node and missing time period corresponding to each missing value.

[0084] In this step, missing values ​​refer to valid data items that should have been collected but were not. For example, at a specified timestamp, the voltage, current, and equipment switch status of an electrical node that should have been uploaded might not have been recorded due to signal obstruction during data acquisition. In this case, the data at that timestamp would be displayed as either controlled or unrecorded, which is a missing value in the multi-source fault data.

[0085] Electrical nodes refer to the entities to which multi-source fault data belongs. Fault data can be bound to specific electrical nodes, and missing values ​​can be determined based on the mapping relationship between fault data and nodes. In multi-source fault data scenarios, electrical nodes can be divided into two categories: physical nodes and logical nodes. Physical nodes refer to the actual monitoring locations of equipment or lines in the target power grid; logical nodes refer to monitoring units at the system level.

[0086] A missing period refers to the duration of missing values. It is the continuous time interval from the timestamp of the first missing data to the moment before the timestamp of the next valid data. The missing period needs to be determined in conjunction with the data collection period, and is not the absolute duration between two moments.

[0087] Optionally, after obtaining the missing time period, the corresponding time period type can be determined based on the duration of the missing time period, specifically:

[0088] S1021. When the duration of the missing period is less than the first preset threshold, the missing period is determined to be a short-term missing period.

[0089] In this step, the first preset threshold refers to the critical value between short-term and medium-term data loss. When collecting multi-source fault data for the target power grid, short-term data loss may occur due to instantaneous or temporary interference. Instantaneous or temporary interference factors can include communication signal flickering or momentary sensor lag.

[0090] For example, the phase voltage of bus A is collected, corresponding to electrical node 001, with a collection cycle of 1 minute / time, and the first preset threshold is set to 3 minutes. Missing data: This node has no voltage data between 10:05:00 and 10:07:00, a missing period of 2 minutes. Since 2 minutes < 3 minutes, this missing period can be determined as a short-term missing period.

[0091] S1022. When the duration of the missing period is greater than or equal to the first preset threshold and less than the second preset threshold, the missing period is determined to be a mid-term missing period.

[0092] In this step, the second preset threshold refers to the critical duration for distinguishing between medium-term and long-term data gaps. When collecting multi-source fault data from the target power grid, temporary faults can lead to prolonged data gaps. For example, when the data acquisition device or equipment enters a signal dead zone, the data transmission network experiences lag, or the sensors used for data acquisition temporarily go offline, long periods of missing data may occur in the multi-source fault data.

[0093] For example, based on the RFID device monitoring the status of switch cabinet door number 2, corresponding to electrical node 003, the data collection cycle is 1 hour / time, the first threshold is set to 3 hours, and the second threshold is set to 30 hours. Missing data scenario: This node has no status data between 08:00 and 12:00 on a certain day. The data missing time is 4 hours. 3 hours ≤ 4 hours < 30 hours indicates that this missing period is a medium-term missing period. The reason for the medium-term missing data could be that the switch cabinet enters the signal blind zone of the RFID device reader, resulting in the data not being reported for 4 collection cycles, which is a temporary fault.

[0094] S1023. When the duration of the missing period is greater than or equal to the second preset threshold, the missing period is determined to be a long-term missing period.

[0095] In this step, if data is missing for an extended period, data compensation is not necessary. This is because prolonged data loss may be caused by a serious system failure, requiring fault detection of the data monitoring and collection system. To alert maintenance personnel to perform fault detection, alarm messages can be generated and pushed to relevant personnel.

[0096] For example, if the data collection cycle for missing values ​​is 1 second / time, then the short-term missing period is the missing period with a missing time of less than 5 seconds; the medium-term missing period is the missing period with a missing time of 5-30 seconds; and the long-term missing period is the missing period with a missing time of 30 seconds or more.

[0097] S103. When the missing period is a medium-term missing period, spatial interpolation is used to calculate the spatial compensation value corresponding to the missing value for the electrical node corresponding to the missing value; temporal interpolation is used to calculate the temporal compensation value corresponding to the missing value.

[0098] In this step, spatial interpolation calculation refers to performing spatial interpolation calculation based on the normal data corresponding to other electrical nodes that are adjacent to the current electrical node in the power grid topology during the missing period, as well as the spatial distance between each node and the current electrical node, to obtain the spatial compensation value corresponding to the missing value.

[0099] It should be noted that there are multiple missing values ​​in the missing time period where the missing value is located. Spatial compensation interpolation needs to be calculated based on each missing value and its corresponding specific timestamp to obtain the spatial compensation value of each missing value in the missing time period.

[0100] Interpolation calculation in the time dimension refers to finding the corresponding historical synchronous mode based on the current operating mode of the target power grid; and compensating for the missing values ​​of the current data based on the data of the historical synchronous mode to obtain the time compensation value corresponding to the time dimension interpolation calculation.

[0101] Optionally, when the missing period is a short-term missing period, the spatial compensation value corresponding to the missing value is calculated based on the topology data of the electrical nodes and the target power grid, and this value is determined as the target compensation value corresponding to the missing value.

[0102] Optionally, when the missing period is a long-term missing period, a data alarm is triggered and the missing values ​​are marked as uncompensable data.

[0103] It should be noted that the methods for spatial and temporal interpolation calculations in this step are as follows: Figure 2 Further explanation will be provided in the embodiments shown, and will not be repeated here.

[0104] S104. Based on the spatial compensation value and the temporal compensation value, perform compensation fusion to obtain the target compensation value corresponding to the missing value.

[0105] In this step, the target compensation value is calculated using a weighted fusion method, as shown in Formula 1:

[0106]

[0107] Where Xcomp refers to the target compensation value corresponding to the missing value at time t; Xspatial refers to the spatial compensation value corresponding to the missing value at time t; and Xtime refers to the temporal compensation value corresponding to the missing value at time t. t represents the preset weight values ​​used for weighted fusion calculation, and t represents the specific timestamp corresponding to the missing value.

[0108] Optionally, the preset weight value can be determined by: calculating based on the duration of the missing period to which the missing value belongs; the longer the duration of the missing period, the greater the deviation between historical data and the current state, and the lower the reliability of the time compensation value; the real-time state of adjacent nodes is more referential, and the higher the reliability of the spatial compensation value.

[0109] Alternatively, the reliability of count data can be quantified by preset weight values. The reliability of spatial compensation values ​​is the correlation between missing nodes and adjacent nodes; the reliability of time compensation values ​​is the fit between historical data and the current trend; the reliability of spatial compensation values ​​and time compensation values ​​is normalized, and the preset weight values ​​corresponding to spatial compensation values ​​and time compensation values ​​are calculated.

[0110] Optionally, after compensating for multi-source fault data, the compensated data can also be used for fault monitoring and fault handling of the target power grid, specifically:

[0111] S1041. Perform noise reduction processing on the multi-source fault data after compensation processing to obtain standardized data.

[0112] In this step, the noise reduction process can be performed using an adaptive threshold denoising algorithm based on wavelet packet decomposition to denoise the multi-source fault data. Specifically:

[0113] b1. The db8 (Daubechies 8 Wavelet Basis Function) wavelet basis function is used to perform 3-level wavelet packet decomposition on the multi-source fault data.

[0114] b2. Calculate the signal energy percentage for each sub-band.

[0115] b3. Define the noise sensitivity factor γ.

[0116] b4. Dynamically adjust the threshold based on the noise sensitivity factor.

[0117] b4. Perform noise reduction processing on multi-source fault data based on threshold values.

[0118] The threshold determination formula is shown in Formula 2:

[0119]

[0120] Among them, T n The threshold for the nth sub-band. N represents the estimated standard deviation of noise in the nth sub-band. n This indicates the number of coefficients in that frequency band. The interference coefficient is the noise sensitivity factor. hour, Take 1.5, otherwise, Take 1.

[0121] S1042. Generate the fault monitoring results of the target power grid at the current moment based on standardized data.

[0122] In this step, standardized data can be input into a pre-trained power grid fault monitoring model to obtain fault monitoring results. The power grid fault monitoring model refers to a predictive model trained using historical fault monitoring data from the target power grid.

[0123] S1043. Determine the fault handling strategy corresponding to the target power grid based on the fault monitoring results, and perform fault isolation and fault recovery processing on the target power grid based on the fault handling strategy.

[0124] In this step, the fault handling strategy can be determined by comparing the fault prediction result with a pre-defined fault handling knowledge graph to obtain the corresponding fault handling strategy. If the pre-defined fault handling knowledge graph does not contain a corresponding fault handling strategy, the fault handling strategy can be input into a pre-trained large language model, prompting the large oracle model to output the corresponding fault handling strategy. Simultaneously, the fault prediction result and the fault handling strategy are updated in the pre-defined fault handling knowledge graph. The pre-trained large language model can be trained using historical fault handling data, avoiding the data and computational resource constraints of directly training the entire large language model.

[0125] The medium-voltage distribution network fault data compensation method provided in this application collects multi-source fault data of the target power grid in real time, performs missing value detection on the multi-source fault data, and determines the missing time period and electrical node corresponding to each missing value. When the missing time period is a medium-term missing period, spatial compensation value corresponding to the missing value is obtained by spatial interpolation based on the electrical node corresponding to the missing value; temporal compensation value is obtained by temporal interpolation. The obtained spatial compensation value and temporal compensation value are fused to obtain the target compensation value corresponding to the missing value. Compared with the prior art, this application, when processing missing data, combines the spatial correlation of electrical nodes to obtain a spatial compensation value that incorporates spatial correlation; at the same time, it combines temporal interpolation to focus on the temporal variation law of electrical quantities, combining the two types of variation information to obtain the target compensation value, thereby achieving the technical effect of improving the accuracy of data compensation.

[0126] Figure 2 A flowchart illustrating the medium-voltage distribution network fault data compensation method provided in this application. Figure 2 ,like Figure 2 As shown, this embodiment addresses the above-mentioned... Figure 1The calculation of spatial compensation value and temporal compensation value in step S103 is further described below. The method includes:

[0127] S201. Based on the topology of the target power grid, obtain the set of electrical neighbor nodes corresponding to the missing values.

[0128] In this step, based on the topology of the target power grid, a set of nodes with close electrical connections and similar topological levels corresponding to the missing values ​​is selected. The core principle is electrical proximity rather than physical proximity; that is, there is a direct / indirect power transmission relationship between the nodes, and the data trends show a strong correlation, such as adjacent monitoring points on the same bus or nodes at both ends of the same line. Here, topology refers to the connection relationships between nodes, lines, and equipment in the target power grid.

[0129] For example, one possible implementation for obtaining the set of electrically neighboring nodes of an electrical node is as follows:

[0130] c1. Obtain the structured topology model of the target power grid, which includes the basic node information, topological connection relationships and electrical parameters of the target power grid.

[0131] In this step, the basic node information includes the node identifier, voltage level, and the type of equipment corresponding to the node. Topology links refer to the connection relationships between nodes and lines; electrical parameters refer to the line impedance and admittance information of the lines connecting the electrical nodes.

[0132] c2. In the topology model, locate the target node based on the node identifier of the electrical node and the device identifier corresponding to the electrical node, and clarify the topology position of the target node.

[0133] c3. Prioritize the direct connection points of the target node as electrical proximity nodes, and then extend to the indirect connection points of the secondary association as electrical proximity nodes.

[0134] c4. From the selected multiple electrical proximity nodes, select nodes with the same voltage level as the target node, and based on multi-source fault data, exclude nodes with a data missing rate greater than 5%, faulty outage nodes, and maintenance nodes to obtain a candidate electrical proximity node set.

[0135] c5. For each node in the candidate electrical neighbor set, calculate the correlation between the historical data of the target node and the node, and retain the nodes with a correlation coefficient greater than 0.6 to form the electrical neighbor set.

[0136] S202. Based on the electrical distance and topological level of each node in the set of electrical nodes and electrical neighboring nodes, the spatial weighting coefficient is calculated.

[0137] In this step, the topology hierarchy refers to the association hierarchy between electrical nodes and their electrical neighbors, which can be direct or indirect connections. Electrical distance refers to the impedance distance between two electrical nodes.

[0138] Alternatively, one possible implementation for calculating the spatial weighting coefficients is as follows:

[0139] d1. Based on the electrical distance between the electrical node and its electrically neighboring nodes, the initial weight of the electrically neighboring node relative to the electrical node is calculated. The calculation method is shown in Formula 3:

[0140]

[0141] in, Refers to the electrically adjacent node N i The electrical node N corresponding to the missing value miss The initial weights; d i This refers to electrical node N. miss and electrical neighbor node N i electrical distance; d j This refers to electrical node N. miss and electrical neighbor node N j Electrical distance; This refers to the smoothing term, used to avoid the denominator being 0 when the electrical distance is 0, and k refers to the number of nodes in the set of electrical neighboring nodes.

[0142] d2. Based on the topological hierarchy between electrical nodes and each electrical neighboring node, a topological hierarchy correction is introduced to correct the calculated initial weights, thereby obtaining the spatial weighting coefficient of each electrical neighboring node relative to the current electrical node.

[0143] In this step, the topology hierarchy is corrected as shown in Formula 4:

[0144]

[0145] in, Refers to the electrically adjacent node N i The electrical node N corresponding to the missing value miss The initial weights; This refers to the topology level correction factor. When electrically adjacent nodes are directly connected to each other, the correction factor is 1.2. When electrically adjacent nodes are connected to branches of each other, the correction factor is 1.0.

[0146] S203. Based on multi-source fault data, determine the normal values ​​of each node in the electrical proximity node set during the missing time period.

[0147] In this step, normal values ​​refer to data from electrical neighboring nodes that are valid, without abnormalities, and reflect the true operating status during the missing period of the target node. Missing values, invalid values, and fault-distorted values ​​need to be excluded to ensure the reliability of the data used for interpolation.

[0148] S204. Based on the normal values ​​and spatial weighting coefficients, perform spatial interpolation to obtain the spatial compensation values ​​corresponding to the missing values.

[0149] In this step, spatial interpolation uses the normal values ​​of neighboring nodes and spatial weighting coefficients to estimate the missing value of the target node through a weighted average method. Neighboring nodes with larger weights have a greater impact on the spatial compensation value, ensuring that the result closely reflects the actual operating state of the target node.

[0150] The specific calculation method is as follows: the weighted average interpolation method is used; the sum of the normal value of each neighboring node multiplied by the corresponding spatial weighting coefficient is calculated to obtain the spatial compensation value.

[0151] S205. Based on multi-source fault data, determine the current operating mode of the target power grid.

[0152] In this step, the power grid operation mode is a classification description of the current overall operating status of the power grid. It is based on key operating parameters, and the power grid data trends are consistent within the same operation mode. These key operating parameters can be: load factor, voltage level, switch status, and distributed generation output. The operation modes can be: peak load mode, maintenance mode, and normal power supply mode.

[0153] Alternatively, the current operating mode of the target power grid can be determined in the following ways:

[0154] Based on multi-source fault data, characteristic indicator data are extracted for a period of time before and after the missing period. This characteristic indicator data is compared with multiple indicator threshold combinations in a preset indicator database. The mode corresponding to the indicator threshold combination with the highest matching degree is determined as the current operating mode of the target power grid. The preset indicator database stores multiple operating modes and the corresponding characteristic indicator threshold combinations for each operating mode.

[0155] S206. Search the historical database of the target power grid based on the operating mode to obtain historical fault data under the same operating mode.

[0156] In this step, the purpose of filtering historical fault data that is consistent with the current operating mode from the power grid historical database is to ensure that the historical data and the current data have the same operating conditions, so that the time interpolation results are more reliable.

[0157] Optionally, historical fault data can be obtained in the following ways:

[0158] Search criteria are set based on the operating mode, including operating mode labels, time characteristics of the missing period, and the absence of missing historical fault data within the corresponding period. A search is performed in the historical database based on these criteria, and after filtering out abnormal data values, historical fault data under the same operating mode is obtained.

[0159] S207. Determine the historical data corresponding to the missing value during the missing period based on historical fault data.

[0160] In this step, we find the historical data that best matches the current missing period in terms of time characteristics from the filtered historical fault data.

[0161] For example, historical data is obtained by aligning the current missing time period with the historical fault data using minute-level timestamps. If the current missing time period contains timestamps t1 and t2, records with timestamps t1 and t2 from the historical fault data are filtered out; where t1 and t2 are the start and end times of the missing time period. For the matched historical fault data, the average of each timestamp within the missing time period is taken as the historical data corresponding to that timestamp. If the missing time period consists of multiple timestamps, the final historical data is the average of the averages of all timestamps.

[0162] S208. Based on historical data and the matching degree between the current operating mode and the historical operating mode corresponding to the historical fault data, time interpolation calculation is performed to obtain the time compensation value corresponding to the missing value.

[0163] In this step, time interpolation uses historical data under the same operating mode and combines it with the matching degree between the current and historical operating modes to estimate the missing value of the target node.

[0164] For example, by using the current amplitude of electrical nodes to calculate the matching degree between the current operating mode and the historical operating mode, the calculation method of the time compensation value is as shown in Formula 5:

[0165]

[0166] Where Xtime(t) refers to the time compensation value corresponding to the missing value at time t; Xhist(t) refers to the normal data at time t in the historical data; I current This refers to the current amplitude of the electrical node corresponding to the missing value at time t; I hist This refers to the current amplitude of the electrical node at time t in historical data.

[0167] Figure 3 The schematic diagram of the medium-voltage distribution network fault data compensation device provided in this application is as follows: Figure 3 As shown, the medium-voltage distribution network fault data compensation device provided in this embodiment includes:

[0168] The acquisition module 301 is used to collect multi-source fault data of the target power grid in real time; the multi-source fault data includes electrical parameters and environmental parameters of each electrical node of the target power grid.

[0169] The first processing module 302 is used to perform missing value detection on multi-source fault data and determine the electrical node and missing time period corresponding to each missing value.

[0170] The second processing module 303 is used to calculate the spatial compensation value corresponding to the missing value by using spatial dimension interpolation for the electrical node corresponding to the missing value when the missing period is a medium-term missing period; and to calculate the time compensation value corresponding to the missing value by using time dimension interpolation.

[0171] The third processing module 304 is used to perform compensation fusion based on spatial compensation value and temporal compensation value to obtain the target compensation value corresponding to the missing value.

[0172] Optionally, in one possible implementation, the second processing module 303 is further configured to:

[0173] Based on the topology of the target power grid, obtain the set of electrical neighbor nodes corresponding to the missing values.

[0174] The spatial weighting coefficients are calculated based on the electrical distance and topological level of each node in the set of electrical nodes and electrical neighboring nodes.

[0175] Based on multi-source fault data, the normal values ​​of each node in the electrical proximity node set during the missing time period are determined.

[0176] Spatial interpolation is performed based on normal values ​​and spatial weighting coefficients to obtain spatial compensation values ​​corresponding to missing values.

[0177] Optionally, in one possible implementation, the second processing module 303 is further configured to:

[0178] Based on multi-source fault data, the current operating mode of the target power grid is determined.

[0179] Based on the operating mode, a search is performed in the historical database of the target power grid to obtain historical fault data under the same operating mode.

[0180] Based on historical fault data, determine the historical data corresponding to the missing period for the missing value.

[0181] Based on historical data and the matching degree between the current operating mode and the historical operating mode corresponding to historical fault data, time interpolation is performed to obtain the time compensation value corresponding to the missing value.

[0182] Optionally, in one possible implementation, the first processing module 302 is further configured to:

[0183] When the duration of the missing period is less than a first preset threshold, the missing period is determined to be a short-term missing period.

[0184] When the duration of the missing period is greater than or equal to the first preset threshold and less than the second preset threshold, the missing period is determined to be a mid-term missing period.

[0185] When the duration of the missing period is greater than or equal to the second preset threshold, the missing period is determined to be a long-term missing period.

[0186] Optionally, in one possible implementation, the second processing module 303 is further configured to:

[0187] When the missing period is a short-term missing period, the spatial compensation value corresponding to the missing value is calculated based on the topology data of the electrical nodes and the target power grid, and this value is determined as the target compensation value corresponding to the missing value.

[0188] When the missing period is a long-term missing period, a data alarm is triggered and the missing values ​​are marked as uncompensable data.

[0189] Alternatively, in one possible implementation, the third processing module 304 is further configured to:

[0190] The multi-source fault data after compensation processing is subjected to noise reduction processing to obtain standardized data.

[0191] The fault monitoring results of the target power grid at the current moment are generated based on standardized data.

[0192] Based on the fault monitoring results, the fault handling strategy corresponding to the target power grid is determined, and the fault isolation and fault recovery processes of the target power grid are carried out based on the fault handling strategy.

[0193] The apparatus provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0194] Figure 4 A schematic diagram of the structure of the electronic device provided in this application. Figure 4 As shown, the electronic device provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the device further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0195] In the specific implementation process, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to execute the above-mentioned medium-voltage distribution network fault data compensation method or approach.

[0196] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0197] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0198] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0199] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0200] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0201] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0202] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0203] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0204] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0205] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0206] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0207] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0208] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0209] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for fault data compensation in a medium voltage distribution network, characterized by, The method comprises: real-time acquisition of multi-source fault data of a target power grid; the multi-source fault data comprises electrical parameters and environmental parameters of each electrical node of the target power grid; missing value detection is performed on the multi-source fault data to determine the electrical node corresponding to each missing value and the missing time period; when the missing time period is a medium-term missing time period, a spatial dimension interpolation calculation method is used to obtain a spatial compensation value corresponding to the missing value for the electrical node corresponding to the missing value; a time dimension interpolation calculation method is used to obtain a time compensation value corresponding to the missing value; compensation fusion is performed based on the spatial compensation value and the time compensation value to obtain a target compensation value corresponding to the missing value.

2. The method of claim 1, wherein, The spatial dimension interpolation calculation method comprises: based on the topological structure of the target power grid, an electrical adjacent node set of the electrical node corresponding to the missing value is obtained; based on the electrical distance and topological level of each node in the electrical node and the electrical adjacent node set, a spatial weighting coefficient is calculated; based on the multi-source fault data, the normal value of each node in the electrical adjacent node set in the missing time period is determined; based on the normal value and the spatial weighting coefficient, spatial interpolation calculation is performed to obtain the spatial compensation value corresponding to the missing value.

3. The method of claim 1, wherein, The time dimension interpolation calculation method comprises: based on the multi-source fault data, the current operation mode of the target power grid is determined; based on the operation mode, a search is performed in a historical database of the target power grid to obtain historical fault data under the same operation mode; based on the historical fault data, historical data corresponding to the missing value in the missing time period is determined; based on the historical data and the matching degree between the current operation mode and the historical operation mode corresponding to the historical fault data, time interpolation calculation is performed to obtain the time compensation value corresponding to the missing value.

4. The method of claim 1, wherein, After the missing value detection on the multi-source fault data and the determination of the electrical node corresponding to each missing value and the missing time period, the method further comprises: when the time length of the missing time period is less than a first preset threshold, the missing time period is determined to be a short-term missing time period; when the time length of the missing time period is greater than or equal to the first preset threshold and less than a second preset threshold, the missing time period is determined to be a medium-term missing time period; when the time length of the missing time period is greater than or equal to the second preset threshold, the missing time period is determined to be a long-term missing time period.

5. The method of claim 4, wherein, After the missing value detection on the multi-source fault data and the determination of the electrical node corresponding to each missing value and the missing time period, the method further comprises: when the missing time period is a short-term missing time period, the spatial compensation value corresponding to the missing value is calculated based on the electrical node and the topological structure data of the target power grid, and is determined as the target compensation value corresponding to the missing value; when the missing time period is a long-term missing time period, data alarm is triggered and the missing value is marked as un-compensatable data.

6. The method of claim 1, wherein, The method further comprises: The multi-source fault data after compensation processing is denoised to obtain standardized data; A fault monitoring result of the target power grid at the current time is generated based on the standardized data; A fault processing strategy corresponding to the target power grid is determined based on the fault monitoring result, and fault isolation and fault recovery processing are performed on the target power grid based on the fault processing strategy.

7. A medium voltage distribution network fault data compensation device, characterized in that, Comprise: An acquisition module is configured to collect multi-source fault data of a target power grid in real time; The multi-source fault data includes electrical parameters and environmental parameters of each electrical node of the target power grid; A first processing module is configured to detect missing values in the multi-source fault data, determine an electrical node corresponding to each missing value, and determine a missing period corresponding to each missing value; A second processing module is configured to, when the missing period is a medium-term missing period, obtain a spatial compensation value corresponding to the missing value by using a spatial dimension interpolation calculation for the electrical node corresponding to the missing value, and obtain a time compensation value corresponding to the missing value by using a time dimension interpolation calculation; A third processing module is configured to perform compensation fusion based on the spatial compensation value and the time compensation value to obtain a target compensation value corresponding to the missing value.

8. An electronic device, comprising: Comprise: A memory and a processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the method of any one of claims 1-6.

10. A computer program product, characterised in that, A computer program is executed by the processor to implement the method of any one of claims 1-6.

Images