Multi-dimensional spatial data processing method and device of power distribution network, equipment and storage medium

Abstract

The invention relates to a multi-dimensional spatial data processing method and device of a power distribution network, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring machine account data, operation data and geographic space data of a power grid; constructing a dynamic and static data model according to the standing book data and the operation data; constructing a spatial structure model of the power grid based on the dynamic and static data model and the machine account data; and carrying out fusion processing on the space structure model and the geographic space data to generate a power grid model. The method is beneficial to improving the data processing efficiency of the power distribution network.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method, device, equipment, and storage medium for processing multi-dimensional spatial data of a distribution network. Background Art

[0002] With the development of smart grid technology and the advent of the big data era, the scale of the power grid continues to expand, business needs continue to increase, and the amount of data is growing explosively. In addition, the distribution network system is large and complex, involving many devices and a large amount of data, which makes the data management and application of the distribution network face new challenges and opportunities.

[0003] Traditional distribution network data processing processes such as updating, processing and analysis are mostly performed manually, which is inefficient. Summary of the invention

[0004] Based on this, it is necessary to provide a multi-source data processing method, device, computer equipment, computer-readable storage medium and computer program product that can improve the data processing efficiency of the distribution network in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for processing multidimensional spatial data of a distribution network, comprising:

[0006] Obtain the ledger data, operation data and geospatial data of the power grid;

[0007] Build dynamic and static data models based on ledger data and operation data;

[0008] Based on dynamic and static data models and ledger data, a spatial structure model of the power grid is constructed;

[0009] The spatial structure model and geospatial data are integrated to generate a power grid model.

[0010] In one embodiment, fusing the spatial structure model with the geospatial data includes:

[0011] Perform format conversion on the layers in the spatial structure model and the geographic spatial data respectively, and convert the converted layers to the same spatial reference coordinate system;

[0012] Determine the feature points and descriptors of the feature points in the converted layer;

[0013] Based on the descriptors of the feature points, feature point matching is performed on the feature points to determine matching feature point pairs;

[0014] Perform affine transformation on the layer where the matched feature points are located, and determine the spatial transformation parameters based on the affine transformation results;

[0015] Based on the spatial transformation parameters, the layers of the spatial structure model and the geospatial data are aligned and integrated to perform fusion processing on the spatial structure model and the geospatial data.

[0016] In one embodiment, fusing the spatial structure model with the geospatial data includes:

[0017] Prioritize different layers in geospatial data;

[0018] Based on the priorities of different layers, the spatial structure model and geospatial data are fused and processed. The layers in the geospatial data include standard map layer, satellite map layer, urban planning layer and natural geography layer.

[0019] In one embodiment, determining feature points and descriptors of feature points in the converted layer includes:

[0020] For each layer:

[0021] Generate a Gaussian difference image corresponding to the layer, and determine the extreme points of the Gaussian difference image;

[0022] Filter out feature points from extreme points and determine the positions of feature points;

[0023] Assign one or more directions to feature points;

[0024] Based on the position and direction of the feature points, the descriptors corresponding to the feature points are generated.

[0025] In one embodiment, generating a Gaussian difference image corresponding to the layer and determining the extreme points of the Gaussian difference image include:

[0026] Perform Gaussian blur and Gaussian difference on the layer to generate the Gaussian difference image corresponding to the layer;

[0027] Perform local extrema detection on the Gaussian difference image to determine the extreme points of the Gaussian difference image.

[0028] In one embodiment, constructing a spatial structure model of a power grid based on a dynamic and static data model and ledger data includes:

[0029] For device components in the power grid, create layers corresponding to the device components;

[0030] Create device nodes corresponding to each device component based on the geographic location information in the ledger data;

[0031] Based on the device connection relationship in the ledger data, determine the connection relationship between each device node;

[0032] Based on the dynamic and static data models, the attribute data of the device nodes and connection relationships are determined to obtain the spatial structure model.

[0033] In a second aspect, the present application also provides a multi-dimensional spatial data processing device for a distribution network, comprising:

[0034] The acquisition module is used to obtain the ledger data, operation data and geospatial data of the power grid;

[0035] The data processing module is used to build dynamic and static data models based on ledger data and operation data;

[0036] The first spatial data module is used to construct a spatial structure model of the power grid based on the dynamic and static data models and the ledger data;

[0037] The second spatial data processing module is used to integrate the spatial structure model and the geographic spatial data to generate a power grid model.

[0038] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the multi-dimensional spatial data processing method of the distribution network when executing the computer program.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the multi-dimensional spatial data processing method of the distribution network described above is implemented.

[0040] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the multi-dimensional spatial data processing method of the above-mentioned distribution network.

[0041] The above-mentioned multi-dimensional spatial data processing method, device, computer equipment, computer-readable storage medium and computer program product of the distribution network, first, by collecting the ledger data, operation data and geographic spatial data of the distribution network, a comprehensive data basis is provided for the diversified management of the power grid system; secondly, by constructing a dynamic and static data model based on the ledger data and operation data of the power grid, since the dynamic and static data model supports the real-time update and analysis of the operation data, the timeliness and dynamic monitoring capabilities of the data are enhanced, and at the same time, the data structure is simplified, which can improve the data quality and data processing efficiency; finally, the spatial structure model of the power grid is constructed based on the dynamic and static data model, and the geographic spatial data is then fused with the spatial structure model to generate a power grid model that integrates multi-source data, thereby realizing the integrated management of power grid data and spatial data, which is conducive to improving the data processing efficiency of the distribution network. Furthermore, the use of the power grid model that integrates multi-dimensional spatial data for power grid management can improve the efficiency of power grid operation management. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0043] Figure 1 An application environment diagram of a multi-dimensional spatial data processing method for a power distribution network in one embodiment;

[0044] Figure 2 A schematic flow chart of a method for processing multi-dimensional spatial data of a power distribution network in one embodiment;

[0045] Figure 3 A schematic flow chart of a method for processing multi-dimensional spatial data of a power distribution network in another embodiment;

[0046] Figure 4 A schematic flow chart of a method for processing multi-dimensional spatial data of a power distribution network in another embodiment;

[0047] Figure 5 A schematic flow chart of a method for processing multi-dimensional spatial data of a power distribution network in yet another embodiment;

[0048] Figure 6 It is a flowchart of a method for processing multi-dimensional spatial data of a power distribution network in a detailed embodiment;

[0049] Figure 7 It is a structural block diagram of a multi-dimensional spatial data processing device for a power distribution network in one embodiment;

[0050] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] The multi-dimensional spatial data processing method of the distribution network 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.

[0053] Specifically, the operator may upload the collected inventory data, operation data and geospatial data to the server 104 through the terminal 102, and then send a power grid model generation message to the server 104 through the terminal 102. The server 104 obtains the inventory data, operation data and geospatial data, and then constructs a dynamic and static data model based on the inventory data and operation data. Then, based on the dynamic and static data model and the inventory data, a spatial structure model of the power grid is constructed. Finally, the spatial structure model and the geospatial data are integrated to generate a power grid model.

[0054] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0055] In an exemplary embodiment, Figure 2 As shown, a multi-dimensional spatial data processing method for a distribution network is provided, and the method is applied to Figure 1 The server 104 in the example is used for explanation, and includes the following S100 to S400. Among them:

[0056] S100, obtaining the inventory data, operation data and geographic space data of the power grid.

[0057] The ledger data of the power grid may include, but are not limited to, the equipment component information in the power grid, the basic information of the power system, the connection information of the line, the maintenance record of the line, etc. Among them, the equipment components in the power grid include substations, switch stations, transformers, circuit breakers, cables, distribution boxes, etc. It is understandable that different equipment components in the power grid have different equipment component information. For example, the equipment component information of the switch station includes the number, model, location, distribution box, etc. of the switch station; the equipment component information of the circuit breaker includes the model, rated voltage, rated current, short-circuit capacity, etc. of the circuit breaker; the equipment component information of the cable includes the model, cross-section, length, wiring method, etc. of the cable. The way to obtain the ledger data can be to collect data through manual on-site surveys, digital management systems, etc.

[0058] The operation data of the power grid may include the real-time operation data of the equipment components in the power grid, patrol records, etc. The real-time operation data of the equipment components may include voltage, current, power, switch status, etc. The real-time operation data of the equipment components may be collected through data acquisition terminals, smart meters, sensors, and detection equipment.

[0059] Geospatial data refers to layers that contain geographic information. Geographic information can be provincial and county administrative boundaries, river systems, road and railway networks, and world administrative boundaries. Geospatial data can be obtained directly through the data open platform, or it can be obtained by obtaining the corresponding geographic feature data through the data open platform according to needs, and then integrated and processed according to the geographic feature data. Among them, the data open platform can be the China National Basic Geographic Information System, OpenStreetMap, Earth System Science Data Sharing Platform, etc.

[0060] S200, build dynamic and static data models based on ledger data and operation data.

[0061] In order to improve the data quality and accuracy of dynamic and static data models, before building dynamic and static data models, the ledger data and operation data can be pre-processed by data verification, format conversion and other data cleaning, as well as keyword comparison.

[0062] In practical applications, after data cleaning and comparison of ledger data and operation data, the format of ledger data and operation data can be standardized according to preset fields. Exemplarily, the preset fields may include device unique identifier, device name, device type, device status, installation location, device geographic location, device connection relationship, device static attributes, device dynamic attributes, etc. After the format of ledger data and operation data is standardized, the data after format standardization can also be quality-checked according to verification rules. The verification rules may include data integrity verification, format verification, domain verification, uniqueness verification, and logic verification, etc.

[0063] After completing the format standardization of operation data and ledger data, use the unique identifier of the equipment to match the ledger data and operation data, create a database table for each type of equipment component, and associate the ledger data table and the operation data table with the equipment unique identifier through foreign keys. Build a dynamic and static data model containing dynamic and static attributes for each type of equipment component. The dynamic attributes come from the operation data of the equipment component, and the static attributes come from the ledger data of the equipment component. In the dynamic and static equipment data model corresponding to each type, create a data instance according to the associated data corresponding to the equipment unique identifier to form a dynamic and static data model.

[0064] S300, constructing a spatial structure model of the power grid based on the dynamic and static data models and the ledger data.

[0065] The spatial structure model is composed of multiple layers and is used to visualize the topological relationship of the power grid. The topological relationship includes physical topology and operational topology. The physical topology refers to the physical connection relationship between the equipment components in the power grid, which generally shows the permanent connection relationship between the equipment components. The operational topological relationship reflects the operating status of the power grid. The separation and connection status of switches and other equipment in the power grid or the occurrence of faults will affect the results of the operational topology. The update of the operational topological relationship can be achieved by providing real-time data from a dynamic database.

[0066] In practical applications, the equipment coordinates, line direction and other information in the equipment geographic location information of the ledger data can be used as spatial data, and the data in the dynamic and static data models can be used as attribute data. Through GIS (Geographic Information System) tools, different layers can be created, and nodes and lines can be created for the layers based on the spatial data. The nodes or lines in the layers can be labeled based on the attribute data, thereby obtaining the spatial structure model of the power grid.

[0067] S400, the spatial structure model and the geographic spatial data are integrated and processed to generate a power grid model.

[0068] In practical applications, the spatial structure model of the power grid and the geospatial data containing geographic information can be fused through an image fusion algorithm to obtain a power grid model that integrates ledger data, operation data, and geospatial data. Specifically, image fusion algorithms include wavelet transform, principal component analysis, etc. After obtaining the power grid model, the power grid model can also be stored in a database to verify the accuracy of the spatial position and the correctness of the topological relationship of the power grid model, as well as to display the power grid in three dimensions.

[0069] In the above-mentioned multi-dimensional spatial data processing method of the distribution network, firstly, by collecting the inventory data, operation data and geographic spatial data of the distribution network, a comprehensive data foundation is provided for the diversified management of the power grid system; secondly, by constructing a dynamic and static data model based on the inventory data and operation data of the power grid, since the dynamic and static data model supports the real-time update and analysis of the operation data, the timeliness and dynamic monitoring capabilities of the data are enhanced, and at the same time, the data structure is simplified, which can improve the data quality and data processing efficiency; finally, the spatial structure model of the power grid is constructed based on the dynamic and static data model, and then the geographic spatial data is integrated with the spatial structure model to generate a power grid model that integrates multi-source data, realizing the integrated management of power grid data and spatial data, which is conducive to improving the data processing efficiency of the distribution network. Furthermore, the use of the power grid model that integrates multi-dimensional spatial data for power grid management can improve the efficiency of power grid operation management.

[0070] In an exemplary embodiment, Figure 3 As shown, S400 includes S402 to S410. Among them:

[0071] S402, respectively converting the formats of the layers in the spatial structure model and the geographic spatial data, and converting the converted layers to the same spatial reference coordinate system.

[0072] The formats of the layer can include .mif, .shp, .csv, .pbf, .png, and Webp. The spatial reference coordinate system is a framework used to define the precise location and layout of a dataset on the earth. The spatial reference coordinate system includes the geographic coordinate system and the projected coordinate system. The geographic coordinate system is a spherical coordinate system used to describe the location on the surface of the earth, using longitude and latitude as coordinate values ​​to locate the location of the point.

[0073] In practical applications, GIS tools can be used to convert the spatial structure model and the layers of geographic spatial data into the same format, and then convert the spatial structure model and the layers of geographic spatial data after format conversion into the same spatial reference coordinate system to ensure that the GIS tools can correctly understand the spatial reference of the layers and perform correct projection conversion and spatial analysis.

[0074] S404, determining feature points and descriptors of the feature points in the converted layer.

[0075] Descriptors are used to characterize the visual features of feature points.

[0076] In practical applications, feature points in the converted layer and the descriptors of the feature points can be determined through feature point extraction algorithms, such as ORB (Oriented FAST and Rotated BRIEF) algorithm, SIFT (Scale-invariant feature transform) algorithm, SURF (Speeded UpRobust Feature) algorithm, etc.

[0077] S406, performing feature point matching on the feature points based on the descriptors of the feature points to determine matching feature point pairs.

[0078] In practical applications, feature point matching algorithms can be used to match feature points of similar descriptors, determine the matching feature points, and calculate the similarity of descriptors through Euclidean distance and Hamming distance. Feature point matching algorithms include (Brute-Force Matcher) algorithm, (Fast Approximate Nearest Neighbor Library) algorithm. For example, a brute force matching algorithm is used to match feature points. For the feature points in layer A and the feature points in layer B , whose descriptors are and ; Calculate the similarity by the Euclidean distance between descriptors:

[0079]

[0080] Where: Representing feature points and The descriptor distance between them; and They are and The k-th descriptor element; Represents the dimension of the descriptor;

[0081] For each feature point in layer A , find the layer B that uses The smallest feature point As matching points, matching point pairs are obtained.

[0082] S408, performing affine transformation on the layer where the matched feature points are located, and determining spatial transformation parameters based on the affine transformation result.

[0083] Affine transformation is a type of spatial rectangular coordinate transformation, which is a linear transformation from two-dimensional coordinates (x, y) to two-dimensional coordinates (u, v). For example, the points in layer A can be transformed as follows Transform to the corresponding point in layer B :

[0084] ;

[0085] ;

[0086] For the original layer and the transformed layer, take three matching feature point pairs and obtain the spatial transformation parameters through the linear equation system. :

[0087]

[0088] in: , as well as Indicates the coordinates of the three matching feature points in the original layer; as well as Represents the coordinates of the corresponding three matching feature points in the transformed layer.

[0089] S410, aligning and integrating the spatial structure model and the layers of the geographic spatial data based on the spatial transformation parameters, so as to perform fusion processing on the spatial structure model and the geographic spatial data.

[0090] The spatial transformation parameters can be used to align all layers of the spatial structure model and the geographic spatial data, and then the fusion processing of the spatial structure model and the geographic spatial data can be realized through the image fusion algorithm. For example, the weighted average algorithm is used to fuse the layers.

[0091] In this embodiment, firstly, by converting the formats of the layers in the spatial structure model and the geographic spatial data respectively, the converted layers are converted to the same spatial reference coordinate system to ensure the accuracy of the spatial processing of the layers. Secondly, the feature points in the converted layers and the descriptors of the feature points are determined, and the feature points are matched based on the descriptors of the feature points to determine the matching feature point pairs. The layers where the matching feature points are located are affine transformed, and the spatial transformation parameters are determined based on the affine transformation results. Based on the spatial transformation parameters, the layers of the spatial structure model and the geographic spatial data are aligned and integrated to fuse the spatial structure model and the geographic spatial data, thereby realizing the fusion of power grid data and spatial data, which is beneficial to improving the distribution network data processing efficiency.

[0092] In an exemplary embodiment, S400 further includes S401 to S403. Among them:

[0093] S401, determine the priorities of different layers in the geospatial data.

[0094] S403, based on the priorities of different layers, the spatial structure model and the geospatial data are fused and processed, and the layers in the geospatial data include a standard map layer, a satellite map layer, a city planning layer, and a physical geography layer.

[0095] It is understandable that, depending on the different geographic information contained in the geospatial data, the geospatial data may have different categories of layers, such as a standard map layer, a satellite map layer, an urban planning layer, and a natural geographic layer. Before the spatial structure model and the geospatial data are fused, the priority of the layers of different categories may be set according to the preset priority rules. Specifically, the priority rules may be set according to the accuracy, update time, and other standards of the layer data. When the spatial structure model and the geospatial data are fused, the priority of each geospatial data is determined, and the spatial structure model and the geospatial data are aligned and integrated in sequence. Exemplarily, the layers in each category are processed in sequence according to the set priority. The layers with high priority may be processed first to ensure that the feature points of these layers are accurately aligned, and then the layers with low priority may be processed. The processing order may be: S1, standard map class: usually used as a reference layer because they usually contain the most comprehensive and accurate geographic information. S2, satellite map class: used for high-precision alignment. S3, urban planning map class: used to consider artificial structures and planning factors. S4, natural geographic map class: used to supplement natural geographic information.

[0096] In some embodiments, after determining the priorities of different layers in the geospatial data, the spatial structure model and the layers of the geospatial data may be format converted respectively, the converted layers may be converted to the same spatial reference coordinate system, and the feature points in the converted layers and the descriptors of the feature points may be determined, in order of priority: based on the descriptors of the feature points, feature points of the spatial structure model and the layers of the geospatial data may be matched to determine matching feature point pairs; affine transformation may be performed on the layers where the matched feature points are located, and spatial transformation parameters may be determined based on the affine transformation results; based on the spatial transformation parameters, the spatial structure model and the layers of the geospatial data may be aligned and integrated to perform fusion processing on the spatial structure model and the geospatial data.

[0097] In this embodiment, by determining the priorities of different layers in the geographic spatial data and fusing the spatial structure model and the geographic spatial data based on the priorities of the different layers, the accuracy of the layer fusion can be improved and the content of the power grid spatial data can be enriched.

[0098] In an exemplary embodiment, Figure 4As shown, S404 includes S442 to S448. Among them:

[0099] S442, for each layer, generating a Gaussian difference image corresponding to the layer, and determining the extreme points of the Gaussian difference image.

[0100] S444, filtering out feature points from the extreme points and determining the positions of the feature points.

[0101] Extreme points show the greatest contrast change in the local area around them, indicating that they may be points of interest in the image. Feature points are more stable and accurate extreme points. In order to enhance the stability of feature point matching and improve noise resistance, the detected extreme points can be screened and unstable points can be eliminated to determine the feature points and their positions. Specifically, the fine positioning of feature points can be performed based on the Taylor expansion:

[0102] ;

[0103] Where: Represents the Taylor expansion of the feature point position to the differential Gaussian function D; Represents the displacement vector of the feature point, where x and y represent the displacement in spatial coordinates; Indicates displacement on scale; represents the first-order derivative of the differential Gaussian function D with respect to the displacement vector X; Represents the second derivative of the differential Gaussian function D with respect to the displacement vector X.

[0104] The exact location of the feature point is at the location of the extreme point in the above equation. The location of the extreme point is obtained by taking the derivative of the above equation and setting the derivative to zero. By determining the extreme points of the Gaussian difference image of the layer, the layer can be made to have the property of being invariant to scaling features.

[0105] S446, assign one or more directions to the feature points.

[0106] In order to make it invariant to image rotation features, the direction of the feature points is assigned by finding the gradient of each feature point:

[0107]

[0108] In the formula, Representing coordinates The main direction of the feature point at represents the result of the feature point direction assignment; Represents the gradient of the image in the x direction, which is calculated by calculating the rate of change of the brightness of the image in the x direction; It represents the gradient of the image in the y direction, which is calculated by calculating the rate of change of the brightness of the image in the y direction.

[0109] You can also select a neighborhood near the feature point, count the direction of each point in the neighborhood, and determine the main direction and auxiliary direction of the feature point. For example, 0-360 degrees are divided into 8 directions, with each 45 degrees being a direction. The directions of the points in the neighborhood of a feature point are counted to form a bar graph of 8 directions. The direction corresponding to the peak value represents the main direction of the feature point, and the direction greater than 80% of the peak value is taken as the auxiliary direction of the feature point.

[0110] S448, generating a descriptor corresponding to the feature point based on the position and direction of the feature point.

[0111] In this embodiment, the SIFT algorithm may be used to generate a descriptor corresponding to the feature point. The descriptor of the SIFT feature point is used to describe the scale information of the feature point, including scaling, direction and other information, which is mainly contributed by the pixels around the feature point. A vector is used to store this information, and this vector is the descriptor of the feature point.

[0112] Based on the position and direction of the feature point, the descriptor corresponding to the feature point is generated so that the feature point will not change due to changes in factors such as image lighting and viewing angle. Specifically:

[0113] On the image where the feature point is located, a 16*16 rectangular image centered on the feature point is drawn, and the 16*16 rectangular image is divided into 16 small grids, each of which is 4*4, and the gradient and amplitude of each pixel, that is, the direction and magnitude of the pixel value change, are calculated; each small grid is statistically analyzed, and the amplitude in 8 directions is statistically analyzed to form a gradient histogram. The amplitude histograms of the 16 small grids are connected and represented by a vector, which is the descriptor. There are 128 (8*16) dimensions in total, and the vector is represented as: R=(r1,r2,...,r128), and then the vector is normalized to remove the influence of illumination changes. After normalization, feature vectors greater than 0.2 can be truncated, that is, values ​​greater than 0.2 are only taken as 0.2, and then normalized again, which can improve the discriminability of the descriptor of the feature point.

[0114] In this embodiment, firstly, for each layer, a Gaussian difference image corresponding to the layer is generated, the extreme points of the Gaussian difference image are determined, feature points are screened out from the extreme points, and the positions of the feature points are determined, so as to achieve determination of feature points from the Gaussian difference image with a scale space, which can prevent the feature points from changing with the scaling of the layer; secondly, one or more directions are assigned to the feature points, which can prevent the feature points from changing with the rotation of the image; finally, based on the position and direction of the feature points, a descriptor corresponding to the feature points is generated, which can enable the descriptor of the feature points to carry the position information and direction information of the feature points, thereby making the feature points both scale invariant and rotation invariant, thereby improving the accuracy of the feature points and the descriptors.

[0115] In an exemplary embodiment, S444 includes S4441 to S4442. Among them:

[0116] S4441, performing Gaussian blur and Gaussian difference on the layer to generate a Gaussian difference image corresponding to the layer.

[0117] S4442, perform local extrema detection on the Gaussian difference image to determine the extreme points of the Gaussian difference image.

[0118] In this embodiment, a SIFT (Scale-invariant feature transform) algorithm may be used to generate a Gaussian difference image corresponding to the layer.

[0119] First, Gaussian blur the layer to construct images of different scales:

[0120] ;

[0121] In the formula, Representation scale The image below; Indicates the center is And the standard deviation is Gaussian function of represents the original image; Represents a convolution operation.

[0122] Perform Gaussian difference on images in different scale spaces to obtain Gaussian difference images:

[0123]

[0124] Where: Represents the ratio between adjacent scales.

[0125] After obtaining the Gaussian difference image corresponding to the layer, the Gaussian difference image can be subjected to local extreme value detection to determine the extreme point. Specifically, the extreme point is found in the range of the second positive layer and the second to last layer of the Gaussian difference image. For any pixel point in any layer, it is compared with the adjacent 8 pixels and the corresponding 9+9 pixels in the upper and lower layers. If this point meets the minimum or maximum value, then this point is an extreme point.

[0126] In this embodiment, by performing Gaussian blur and Gaussian difference on the layer, a Gaussian difference image corresponding to the layer is generated, local extrema detection is performed on the Gaussian difference image, and the extreme points of the Gaussian difference image are determined. This can identify potential points that are invariant to the scale and rotation of the image, so as to facilitate determining the feature points of the layer based on the extreme points.

[0127] In an exemplary embodiment, Figure 5 As shown, S200 includes S202 to S208. Among them:

[0128] S202, for the device components in the power grid, create a layer corresponding to the device components.

[0129] According to the types of equipment components in the power grid, the equipment components can be divided into substations, switch stations, transformers, circuit breakers, cables, distribution boxes, etc. In practical applications, GIS tools can be used to create layers corresponding to the types of equipment components in the power grid.

[0130] S204, creating a device node corresponding to each device component based on the geographic location information in the ledger data.

[0131] A GIS tool may be used to create a device node for each device component in a layer according to the geographic location (such as longitude and latitude) in the ledger data.

[0132] S206, based on the device connection relationship in the ledger data, determine the connection relationship between each device node.

[0133] It is possible to use GIS tools to establish connection relationships between device nodes in the layer based on the device connection relationships in the ledger data, so as to facilitate the visualization of the topological structure of the power grid.

[0134] S208, based on the dynamic and static data models, determine the attribute data of the device nodes and the connection relationships to obtain the spatial structure model.

[0135] The spatial structure model can be obtained by using GIS tools to determine the corresponding attribute data in the dynamic and static data model for the device nodes and connection relationships in the layer, and using the attribute data to annotate the device nodes and connection relationships. Exemplarily, each device node is identified using the device unique identifier in the dynamic and static data model, and the device nodes are annotated using the static attribute data and dynamic attribute data in the dynamic and static data model. The static attribute data includes basic information about the device, such as device type, device manufacturer, device capacity, etc., and the dynamic attribute data includes real-time operation data of the device, such as voltage, current, etc. The annotated dynamic attribute data can be updated in real time through the dynamic and static data model.

[0136] In this embodiment, corresponding layers are created for the equipment components in the power grid, and equipment nodes corresponding to each equipment component are created based on the geographic location information in the ledger data. The connection relationship between each equipment node is determined based on the equipment connection relationship in the ledger data. Based on the dynamic and static data models, the attribute data of the equipment nodes and the connection relationship are determined to obtain a spatial structure model, which is conducive to improving the data processing efficiency of the distribution network.

[0137] In order to make a clearer description of the multi-dimensional spatial data processing method for the distribution network provided by the present application, the following is a specific embodiment and the attached Figure 6 To illustrate, this specific embodiment includes the following steps:

[0138] S501, obtaining the inventory data, operation data and geographic space data of the power grid.

[0139] S502, construct a dynamic and static data model based on the ledger data and operation data.

[0140] S503, for the equipment components in the power grid, create layers corresponding to the equipment components, create equipment nodes corresponding to each equipment component based on the geographic location information in the ledger data, determine the connection relationship between each equipment node based on the equipment connection relationship in the ledger data, determine the attribute data of the equipment nodes and the connection relationship based on the dynamic and static data models, and obtain the spatial structure model.

[0141] S504, respectively converting the formats of the layers in the spatial structure model and the geographic spatial data, and converting the converted layers to the same spatial reference coordinate system.

[0142] S505, for each layer: perform Gaussian blur and Gaussian difference on the layer to generate a Gaussian difference image corresponding to the layer. Perform local extreme value detection on the Gaussian difference image to determine the extreme value points of the Gaussian difference image.

[0143] S506, filter out feature points from the extreme points, determine the positions of the feature points, assign one or more directions to the feature points, and generate descriptors corresponding to the feature points based on the positions and directions of the feature points.

[0144] S507, performing feature point matching on the feature points based on the descriptors of the feature points to determine matching feature point pairs.

[0145] S508, performing affine transformation on the layer where the matched feature points are located, and determining spatial transformation parameters based on the affine transformation result.

[0146] S509, based on the spatial transformation parameters, align and integrate the layers of the spatial structure model and the geographic spatial data to perform fusion processing on the spatial structure model and the geographic spatial data.

[0147] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0148] In an exemplary embodiment, Figure 7 As shown, a multi-dimensional spatial data processing 600 of a power distribution network is provided, comprising: an acquisition module 610, a data processing module 620, a first spatial data processing module 630 and a second spatial data processing module 640, wherein:

[0149] The acquisition module 610 is used to acquire the inventory data, operation data and geographic space data of the power grid.

[0150] The data processing module 620 is used to construct dynamic and static data models based on the ledger data and operation data.

[0151] The first spatial data processing module 630 is used to construct a spatial structure model of the power grid based on the dynamic and static data models and the ledger data.

[0152] The second spatial data processing module 640 is used to perform fusion processing on the spatial structure model and the geographic spatial data to generate a power grid model.

[0153] In an exemplary embodiment, the second spatial data processing module 640 is also used to convert the formats of the layers in the spatial structure model and the geographic spatial data respectively, convert the converted layers to the same spatial reference coordinate system, determine the feature points and descriptors of the feature points in the converted layers, match the feature points based on the descriptors of the feature points, determine matching feature point pairs, perform affine transformation on the layers where the matching feature points are located, determine spatial transformation parameters based on the affine transformation results, and align and integrate the layers of the spatial structure model and the geographic spatial data based on the spatial transformation parameters to perform fusion processing on the spatial structure model and the geographic spatial data.

[0154] In an exemplary embodiment, the second spatial data processing module 640 is also used to determine the priorities of different layers in the geospatial data; based on the priorities of different layers, the spatial structure model and the geospatial data are fused, and the layers in the geospatial data include standard map layers, satellite map layers, urban planning layers, and natural geography layers.

[0155] In an exemplary embodiment, the second spatial data processing module 640 is also used to generate, for each layer: a Gaussian difference image corresponding to the layer, and determine the extreme points of the Gaussian difference image; filter out feature points from the extreme points and determine the positions of the feature points; assign one or more directions to the feature points; and generate a descriptor corresponding to the feature points based on the positions and directions of the feature points.

[0156] In an exemplary embodiment, the second spatial data processing module 640 is also used to perform Gaussian blur and Gaussian difference on the layer to generate a Gaussian difference image corresponding to the layer; perform local extreme value detection on the Gaussian difference image to determine the extreme value points of the Gaussian difference image.

[0157] In an exemplary embodiment, the first spatial data processing module 630 is also used to create layers corresponding to device components in the power grid; create device nodes corresponding to each device component based on the geographic location information in the ledger data; determine the connection relationship between each device node based on the device connection relationship in the ledger data; determine the attribute data of the device nodes and the connection relationship based on the dynamic and static data models to obtain a spatial structure model.

[0158] Each module in the above-mentioned multi-dimensional spatial data processing 600 of the power distribution network can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0159] 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 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the number of ledgers, operating data and geographic spatial data of the power grid. 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 multi-dimensional spatial data processing method for a distribution network is implemented.

[0160] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0161] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in any one of the above-mentioned embodiments of the multi-dimensional spatial data processing method for a distribution network are implemented.

[0162] 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 any one of the above-mentioned embodiments of the multi-dimensional spatial data processing method for a power distribution network are implemented.

[0163] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in any one of the above-mentioned embodiments of the method for processing multi-dimensional spatial data of a power distribution network.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0165] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0166] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0167] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A multi-dimensional spatial data processing method for a distribution network, characterized in that: The method comprises: Obtain the ledger data, operation data and geospatial data of the power grid; Constructing a dynamic and static data model based on the ledger data and operation data; Based on the dynamic and static data models and the ledger data, construct a spatial structure model of the power grid; The spatial structure model and the geographic spatial data are fused to generate a power grid model.

2. The method according to claim 1, characterized in that: The fusing process of the spatial structure model and the geographic spatial data comprises: Performing format conversion on the layers in the spatial structure model and the geographic spatial data respectively, and converting the converted layers to the same spatial reference coordinate system; Determine feature points in the converted layer and descriptors of the feature points; Based on the descriptors of the feature points, feature point matching is performed on the feature points to determine matching feature point pairs; Performing an affine transformation on the layer where the matched feature points are located, and determining spatial transformation parameters based on the affine transformation result; Based on the spatial transformation parameters, the spatial structure model and the layers of the geographic spatial data are aligned and integrated to perform fusion processing on the spatial structure model and the geographic spatial data.

3. The method according to claim 1, characterized in that The fusing process of the spatial structure model and the geographic spatial data further includes: prioritizing different layers in the geospatial data; Based on the priorities of the different layers, the spatial structure model and the geographic spatial data are fused, and the layers in the geographic spatial data include a standard map layer, a satellite map layer, a city planning layer and a physical geography layer.

4. The method according to claim 2, characterized in that: The determining of the feature points in the converted layer and the descriptors of the feature points comprises: For each of these layers: Generate a Gaussian difference image corresponding to the layer, and determine the extreme points of the Gaussian difference image; Filter out feature points from the extreme value points and determine the positions of the feature points; assigning one or more directions to the feature points; Based on the position and direction of the feature point, a descriptor corresponding to the feature point is generated.

5. The method according to claim 4, characterized in that The step of generating a Gaussian difference image corresponding to the layer and determining the extreme points of the Gaussian difference image comprises: Performing Gaussian blur and Gaussian difference on the layer to generate a Gaussian difference image corresponding to the layer; Perform local extrema detection on the Gaussian difference image to determine the extreme points of the Gaussian difference image.

6. The method according to any one of claims 1 to 5, characterized in that: The constructing of the spatial structure model of the power grid based on the dynamic and static data models and the ledger data includes: For a device component in the power grid, create a layer corresponding to the device component; Based on the geographic location information in the ledger data, create a device node corresponding to each of the device components; Determine the connection relationship between each of the device nodes based on the device connection relationship in the ledger data; Based on the dynamic and static data models, the attribute data of the device nodes and the connection relationships are determined to obtain the spatial structure model.

7. A multi-dimensional spatial data processing device for a distribution network, characterized in that: The device comprises: The acquisition module is used to obtain the ledger data, operation data and geospatial data of the power grid; A data processing module, used to construct a dynamic and static data model based on the ledger data and operation data; A first spatial data processing module, used to construct a spatial structure model of the power grid according to the dynamic and static data models and the ledger data; The second spatial data processing module is used to fuse the spatial structure model and the geographic spatial data to generate a power grid model.

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

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

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

Images