A multi-scenario new energy production and sales integrated power distribution network planning method and system

Abstract

The present application relates to the field of power system planning, and more particularly to a multi-scenario new energy production and distribution integrated power distribution network planning method and system, the present application obtains scene image information, labels a virtual path in the image information and constructs a reference area, solves the jump parameter based on the closed contour density jump variable and the gray jump variable, calibrates the reference area, adjusts the sampling parameter according to the relative position relationship between the mobile acquisition unit and the center of the calibration area, constructs a temporary model based on the adjusted sampling data and analyzes the model eigenvalue, accordingly corrects the sampling data, finally constructs a panoramic model and stores it in the database. The present application effectively adapts the sampling parameter to different scenes in the entire acquisition path, reduces the problem of incoherent model boundary parameters and unsuitable sampling parameters when switching scenes, ensures the coherence and accuracy of the sampling data, guarantees the reliability of the constructed panoramic model, and improves the reliability and effectiveness of subsequent application for power distribution network planning.

Description

[0001] performing feature jump analysis based on the image information, including, marking a virtual path in the image information, constructing a plurality of reference regions according to the virtual path, determining a closed contour density jump variable and a gray level jump variable between adjacent reference regions;

[0002] calculating a jump parameter based on the closed contour density jump variable and the gray level jump variable, and demarcating the reference regions in the image information according to the jump parameter;

[0003] determining whether to adjust the sampling of the mobile acquisition unit based on the distance between the mobile acquisition unit and the demarcated reference regions, so as to adjust the sampling parameters based on the jump parameter;

[0004] determining a temporary verification period, performing temporary pre-modeling based on the sampling data of the temporary verification period after adjusting the sampling parameters, constructing a temporary model, analyzing the model characteristic value of the temporary model, and determining whether to correct the sampling data and the sampling parameters;

[0005] completing the planned acquisition path, constructing a panoramic model based on all the sampling data, and storing the panoramic model into the power distribution network planning database;

[0006] The model characteristics include a model missing area ratio and a structure fracture rate.

[0007] Further, the process of marking a virtual path in the image information and constructing a plurality of reference regions according to the virtual path includes,

[0008] determining a current moving direction of the mobile acquisition unit, marking a virtual line in the image information based on the current moving direction, and determining the virtual line as the virtual path;

[0009] constructing a plurality of division lines perpendicular to the virtual path at a predetermined interval, and determining the regions divided by the division lines as the reference regions.

[0010] Further, the process of determining the closed contour density jump variable and the gray level jump variable between adjacent reference regions includes,

[0011] determining the difference between the closed contour density of the reference region and the closed contour density of the adjacent previous reference region in the extension direction of the virtual path, to obtain the closed contour density jump variable;

[0012] determining the difference between the gray level of the reference region and the gray level of the adjacent previous reference region in the extension direction of the virtual path, to obtain the closed gray level jump variable.

[0013] Further, the process of calculating a jump parameter based on the closed contour density jump variable and the gray level jump variable includes,

[0014] determining a ratio of the absolute value of the closed contour density jump value and a preset closed contour density jump value as a first jump parameter factor;

[0015] determining a ratio of the absolute value of the closed grayscale jump value and a preset closed grayscale jump value as a second jump parameter factor;

[0016] weighting and summing the first jump parameter factor and the second jump parameter factor to obtain the jump parameter.

[0017] Further, the marking the reference region in the image information according to the jump parameter comprises,

[0018] if the jump parameter corresponding to the reference region is greater than or equal to a preset jump standard parameter, marking the reference region in the image information.

[0019] Further, determining whether to adjust the sampling process of the mobile acquisition unit based on the distance between the mobile acquisition unit and the marked reference region comprises,

[0020] if the distance is less than or equal to a preset sampling distance threshold, adjusting the sampling of the mobile acquisition unit.

[0021] Further, the adjusting the sampling parameter based on the jump parameter comprises,

[0022] if the closed contour density jump value corresponding to the marked reference region is a positive value, increasing the sampling density, the increase being related to the jump parameter, and decreasing the sampling moving speed, the decrease being related to the sampling parameter;

[0023] if the closed contour density jump value corresponding to the marked reference region is a non-positive value, decreasing the sampling density, the decrease being related to the jump parameter, and increasing the sampling moving speed, the increase being related to the sampling parameter;

[0024] wherein, the sampling parameter comprises a sampling density and a sampling moving speed.

[0025] Further, the constructing the temporary model and analyzing the model characteristic value of the temporary model comprises,

[0026] analyzing the model characteristic value of the temporary model, comprising a missing area ratio and a structure fracture rate;

[0027] determining a ratio of the missing area ratio and a missing area ratio reference value as a first model interference characteristic value;

[0028] determining a ratio of the structure fracture rate and a structure fracture rate reference value as a second model interference characteristic value;

[0029] The first model interference characteristic value and the second model interference characteristic value are weighted and summed to obtain a model characteristic value of the temporary model.

[0030] Further, the sampling data is corrected,

[0031] If the model characteristic value is greater than or equal to a preset model characteristic value, the current sampling density is increased and the current sampling moving speed is reduced.

[0032] In another aspect, the application provides a system applying a multi-scene new energy production and sales integrated power distribution network planning method, comprising:

[0033] The acquisition module is configured to control the mobile acquisition unit to move according to the acquisition route while carrying the acquisition equipment, and to acquire image information of a region to be passed through by the mobile acquisition unit in real time.

[0034] The analysis module is connected to the acquisition module and is configured to perform feature jump analysis based on the image information, including marking a virtual path in the image information, constructing a plurality of reference regions according to the virtual path, determining a closed contour density jump variable and a gray scale jump variable between adjacent reference regions.

[0035] The calibration module is connected to the analysis module and is configured to calculate a jump parameter based on the closed contour density jump variable and the gray scale jump variable, and to calibrate the reference regions in the image information according to the jump parameter.

[0036] The adjustment and correction module is connected to the calibration module and is configured to determine whether to adjust the sampling of the mobile acquisition unit based on the distance between the mobile acquisition unit and the calibrated reference regions, and to adjust the sampling parameters based on the jump parameter.

[0037] A temporary verification period is determined, and temporary pre-modeling is performed based on the sampling data of the temporary verification period after the adjustment of the sampling parameters, a temporary model is constructed, a model characteristic value of the temporary model is analyzed, and the sampling parameters are corrected.

[0038] The data integration and model storage module is connected to the acquisition module, the analysis module, the calibration module and the adjustment and correction module, respectively, and is configured to complete the planning of the acquisition path, construct a panoramic model based on all the sampling data, and store the panoramic model in a power distribution network planning database.

[0039] Compared with existing technologies, this invention plans a data acquisition route based on the target scene, acquires scene image information, marks a virtual path and constructs a reference region in the image information, solves the jump parameters based on closed contour density jump variables and grayscale jump variables, calibrates the reference region, adjusts the sampling parameters according to the relative positional relationship between the mobile acquisition unit and the center of the calibrated region, constructs a temporary model based on the adjusted sampling data and analyzes the model feature values, corrects the sampling data accordingly, and finally constructs a panoramic model and stores it in the database. This invention enables effective adaptation of sampling parameters for different scenes throughout the acquisition path, reduces the problems of parameter inconsistency and inapplicability at model boundaries when switching scenes, ensures the continuity and accuracy of sampling data, guarantees the reliability of the constructed panoramic model, and improves the reliability and effectiveness of subsequent applications in power distribution network planning.

[0040] In particular, this invention calculates transition parameters using closed contour density jump variables and grayscale jump variables, and uses these jump parameters to define reference areas in the image information. In practical applications, power distribution network coverage areas are complex and varied, containing diverse terrain and environmental features, such as densely built-up urban areas, mountainous vegetation-covered areas, and water areas. The scene characteristics of each area are significantly different. However, closed contour density jump variables can effectively capture the density of object edges in the scene, representing the complexity of terrain or building distribution. Grayscale jump variables, on the other hand, sensitively reflect the detailed features of lighting changes and material differences, helping to identify material transitions or shadow effects in different areas. Calculating jump parameters from these two dimensions can accurately represent the feature differences of different scenes, thus providing reliable support for the subsequent construction of temporary models. In practice, when switching between these significantly different scenarios, inconsistencies in parameters and inapplicable sampling parameters may occur at the scenario boundaries. Therefore, by calibrating a reference area in the image information based on the jump parameters, and identifying significantly different scenarios as reference areas, the sampling parameters of the mobile acquisition unit can be adjusted in advance before the mobile acquisition unit enters the next significantly different scenario, i.e., the calibrated reference area, to ensure the continuity and accuracy of the sampling data, thereby improving the reliability and effectiveness of power distribution network planning.

[0041] In particular, this invention determines whether to adjust the sampling of the mobile acquisition unit based on the distance between the mobile acquisition unit and the calibration reference area, thereby adjusting the sampling parameters based on jump parameters. In reality, different scenarios have significantly different requirements for data acquisition. If the mobile acquisition unit performs high-density sampling indiscriminately during flight, it will lead to data redundancy, wasting storage space and computing resources. By introducing a positional relationship judgment mechanism, the sampling parameters are adjusted in advance only when the distance between the mobile acquisition unit and the calibration reference area is less than a preset sampling distance. This ensures that the sampling parameters can adapt to the next scenario, ensuring that resource investment is accurately matched with actual needs, effectively avoiding resource waste, and thus improving the reliability and effectiveness of power distribution network planning.

[0042] In particular, this invention constructs a temporary model based on sampling data from a temporary verification period after adjusting sampling parameters. In practice, power distribution network planning involves a massive amount of data. If a model is directly built from the panoramic data after each adjustment of sampling parameters, it will result in huge resource waste and time delays. The temporary model, through rapid verification and optimization on a small-scale dataset, can effectively improve the efficiency of the entire planning process. The temporary model can optimize the final model construction strategy, enabling effective adaptation of sampling parameters to different scenarios throughout the acquisition path, timely modification and correction of sampling parameters, and improved accuracy of the final model. Attached Figure Description

[0043] Figure 1 A schematic diagram illustrating the steps of a multi-scenario integrated new energy production and sales distribution network planning method according to an embodiment of the invention;

[0044] Figure 2 This is a logic decision diagram for identifying whether the current model marks a reference region in image information, as shown in the embodiments of the invention.

[0045] Figure 3 A logic diagram for identifying whether the current model needs to adjust the sampling of the mobile acquisition unit, as shown in an embodiment of the invention.

[0046] Figure 4 This is a logic block diagram illustrating the modification of sampling parameters based on model feature values, as an embodiment of the invention. Detailed Implementation

[0047] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0048] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0049] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0050] Please see Figure 1 The diagram illustrates the steps of a multi-scenario integrated new energy production and sales distribution network planning method according to an embodiment of the invention. The multi-scenario integrated new energy production and sales distribution network planning method according to an embodiment of the invention includes:

[0051] Step S1: Plan the acquisition route according to the target scene, control the mobile acquisition unit to move according to the acquisition route, and acquire image information of the area to be traversed by the mobile acquisition unit in real time;

[0052] Step S2, based on the image information, performs feature jump analysis, including marking virtual paths in the image information, constructing several reference regions based on the virtual paths, and determining the closed contour density jump variable and grayscale jump variable between adjacent reference regions.

[0053] Step S3: Calculate the jump parameter based on the closed contour density jump variable and the grayscale jump variable, and mark the reference area in the image information according to the jump parameter;

[0054] Step S4: Determine whether to adjust the sampling of the mobile acquisition unit based on the distance between the mobile acquisition unit and the calibration reference area, so as to adjust the sampling parameters based on the jump parameter;

[0055] Step S5: Determine the temporary verification period; based on the sampling data of the temporary verification period after adjusting the sampling parameters, perform temporary pre-modeling, construct a temporary model, and analyze the model feature values ​​of the temporary model to correct the sampling parameters.

[0056] Step S6: Complete the planned data collection path, construct a panoramic model based on all sampled data, and store the panoramic model in the power distribution network planning database;

[0057] The model features include the area ratio of missing regions and the structural fracture rate.

[0058] In implementation, there are no restrictions on the method of planning the acquisition route for the target scene. Those skilled in the art can plan based on the actual target scene so that the mobile acquisition unit can carry out comprehensive acquisition of the entire target scene. This will not be elaborated further.

[0059] In practice, the mobile acquisition unit can be a drone, which carries an image acquisition device to acquire image information and a sampling device to perform sampling. The image acquisition device can be a high-precision photography device to capture image information in front of the drone, and the sampling device can be a lidar, which will not be elaborated further.

[0060] Specifically, there are no restrictions on the method of constructing a model based on the sampled data. Those skilled in the art can achieve the corresponding technical effect by constructing a model based on the sampled data in any existing technology, which will not be elaborated here.

[0061] Specifically, the process of annotating virtual paths in image information and constructing several reference regions based on these virtual paths includes:

[0062] Determine the current moving direction of the mobile acquisition unit, mark virtual lines in the image information based on the current moving direction, and determine the virtual lines as virtual paths;

[0063] Several dividing lines perpendicular to the virtual path are constructed at predetermined intervals, and the resulting regions are determined as reference regions.

[0064] It is understandable that the image information is the image in front of the mobile acquisition unit. Since the image will cover a region in front, the purpose of constructing a virtual line is to represent the path that the drone will pass through. Usually, the virtual line is a virtual line segment that passes through the center of the image and is perpendicular to the bottom edge of the image. This will not be elaborated further.

[0065] The virtual path interval is predetermined and can be set to 0.25 times the total length of the virtual lines. Since the dividing lines are arranged at equal intervals perpendicular to the virtual lines, the dividing lines divide the image into several regions. The regions in the image correspond to the regions of the target scene, which will not be elaborated further.

[0066] The sampling moving speed is the moving speed of the mobile acquisition unit.

[0067] Specifically, the process of determining the closed contour density jump variable and grayscale jump variable between adjacent reference regions includes:

[0068] Along the virtual path extension direction, determine the difference in closed contour density between the reference region and the adjacent previous reference region to obtain the closed contour density jump variable;

[0069] By extending along the virtual path, the difference in grayscale between the reference region and the adjacent previous reference region is determined, thus obtaining the closed grayscale jump variable.

[0070] In practice, the closed profile density is the ratio of the area of ​​the closed profile to the area of ​​the reference region.

[0071] In practice, there are no restrictions on the method for determining the gray values ​​of each reference area. The gray values ​​can be determined by the corresponding image processing algorithm or by other methods. As long as the determined gray values ​​can accurately reflect the gray characteristics of the reference area, this will not be elaborated further.

[0072] It is understandable that, due to visual factors, the area below the image is closer to the mobile acquisition unit, while the area above the image is relatively farther away from the mobile acquisition unit. Therefore, the virtual path extends from the bottom of the image to the top of the image, which will not be elaborated further.

[0073] Specifically, the process of calculating the jump parameters based on the closed contour density jump variable and the grayscale jump variable includes,

[0074] The ratio of the absolute value of the closed contour density jump variable to the preset closed contour density jump variable is determined as the first jump variable parameter factor;

[0075] The ratio of the absolute value of the closed gray-scale jump variable to the preset closed gray-scale jump variable is determined as the second jump variable parameter factor;

[0076] The first jump parameter factor and the second jump parameter factor are weighted and summed to obtain the jump parameter.

[0077] In implementation, the preset closed contour density jump variable is predetermined. Those skilled in the art can pre-record the closed contour density jump variables in several image scenes, determine the closed contour density of each reference region, calculate the absolute value of the difference between the closed contour density of each reference region and the previous reference region, and determine the preset closed contour density jump variable by multiplying the average value of the absolute values ​​of the differences between several closed contour densities and the accuracy coefficient. The product of the accuracy coefficient is selected between [0.85, 1.15].

[0078] In implementation, the preset closed gray-level jump variable is predetermined. Those skilled in the art can pre-record several closed gray-level jump variables in image scenes, determine the closed gray-level jump variables of each reference region, calculate the absolute value of the difference between the closed gray-level jump variables of each reference region and the previous reference region, and determine the preset closed gray-level jump variable by multiplying the average value of the absolute values ​​of the differences of several closed gray-level jump variables with the precision coefficient. The product of the precision coefficient is selected between [0.85, 1.15].

[0079] In implementation, the closed contour density jump variable and the closed grayscale jump variable need to be normalized to ensure that the closed contour density jump variable and the closed grayscale jump variable are in the same dimension.

[0080] In practice, when the first jump parameter factor and the second jump parameter factor are weighted and summed, the weight of the first jump parameter factor is 0.55 and the weight of the second jump parameter factor is 0.45.

[0081] This invention calculates transition parameters using closed contour density transition variables and grayscale transition variables. Reference regions are then defined in the image information based on these transition parameters. In practical applications, power distribution network coverage areas are complex and varied, encompassing diverse terrain and environmental features, such as densely built-up urban areas, mountainous vegetation-covered areas, and water bodies. Each region exhibits significant differences in scene characteristics. However, closed contour density transition variables effectively capture the density of object edges within the scene, characterizing the complexity of terrain or building distribution. Grayscale transition variables sensitively reflect detailed features related to lighting changes and material differences, helping to identify material transitions or shadow effects in different areas. Calculating transition parameters from these two dimensions accurately characterizes the feature differences of different scenes, thus providing reliable support for the subsequent construction of temporary models. In practice, when switching between these significantly different scenarios, inconsistencies in parameters and inapplicable sampling parameters may occur at the scenario boundaries. Therefore, by calibrating a reference area in the image information based on the jump parameters, and identifying significantly different scenarios as reference areas, the sampling parameters of the mobile acquisition unit can be adjusted in advance before the mobile acquisition unit enters the next significantly different scenario, i.e., the calibrated reference area, to ensure the continuity and accuracy of the sampling data, thereby improving the reliability and effectiveness of power distribution network planning.

[0082] Please see Figure 2 As shown, it is a logic decision diagram for identifying whether the current model has marked a reference region in the image information according to an embodiment of the invention. Specifically, marking a reference region in the image information according to the jump parameter includes,

[0083] If the jump parameter corresponding to the reference region is greater than or equal to the preset jump standard parameter, then the reference region is marked in the image information.

[0084] In practice, the jump standard parameter is the jump parameter calculated when the absolute value of the closed contour density jump variable is equal to the preset closed contour density jump variable and the absolute value of the closed grayscale jump variable is equal to the preset closed grayscale jump variable.

[0085] Please see Figure 3 As shown, this is a logic decision diagram for identifying whether the current model needs to adjust the sampling of the mobile acquisition unit according to an embodiment of the invention. Specifically, the process of determining whether to adjust the sampling of the mobile acquisition unit based on the distance between the mobile acquisition unit and the calibration reference area includes:

[0086] If the distance is less than or equal to a preset sampling distance threshold, the sampling of the mobile acquisition unit is adjusted.

[0087] Specifically, there is no limitation on the method for determining the distance between the calibration reference area and the mobile acquisition unit. Currently, UAV flight control systems have the ability to identify targets and determine the distance between the target and the UAV. Those skilled in the art can use any method in the existing technology to achieve the corresponding technical effect, which will not be elaborated here.

[0088] In practice, it is preferable to consider the center position of the calibrated reference area when measuring distance, which will not be elaborated further.

[0089] In practice, the purpose of setting a sampling distance threshold is to characterize the situation in the vicinity of the calibration reference area, and it is selected within the interval [30m, 50m].

[0090] This invention determines whether to adjust the sampling of the mobile acquisition unit based on the distance between the mobile acquisition unit and the calibration reference area. This adjustment of sampling parameters is based on jump parameters. In practice, different scenarios have significantly different data acquisition requirements. If the mobile acquisition unit performs high-density sampling indiscriminately during flight, it will lead to data redundancy, wasting storage space and computing resources. By introducing a positional relationship judgment mechanism, the sampling parameters are adjusted in advance only when the distance between the mobile acquisition unit and the calibration reference area is less than a preset sampling distance. This ensures that the sampling parameters are adapted to the next scenario, ensuring that resource investment accurately matches actual needs, effectively avoiding resource waste, and thus improving the reliability and effectiveness of power distribution network planning.

[0091] Specifically, the adjustment of sampling parameters based on jump parameters includes,

[0092] If the density jump variable of the closed contour corresponding to the calibration reference area is positive, then increase the sampling density. The amount of increase is related to the jump parameter. Also, decrease the sampling movement speed. The amount of decrease is related to the sampling parameter.

[0093] If the density jump variable of the closed contour corresponding to the calibration reference area is non-positive, then reduce the sampling density. The amount of reduction is related to the jump parameter. Also, increase the sampling movement speed. The amount of increase is related to the sampling parameter.

[0094] The sampling parameters include sampling density and sampling movement speed.

[0095] It is understandable that when the density jump variable of the closed contour corresponding to the calibration reference area is positive, it indicates that there are more features in the calibration reference area, thereby increasing the sampling density and reducing the sampling movement speed.

[0096] In implementation, optional,

[0097] Set the first transition reference value and the second transition reference value.

[0098] If the jump parameter is less than the first jump reference value, when increasing the sampling density, the increase is 0.15 times the initial sampling density; when decreasing the sampling density, the decrease is 0.15 times the initial sampling density; when increasing the sampling movement speed, the increase is 0.15 times the initial sampling movement speed; when decreasing the sampling movement speed, the decrease is 0.15 times the initial sampling movement speed.

[0099] If the jump parameter is greater than or equal to the first jump reference value and less than or equal to the second jump reference value, when increasing the sampling density, the increase is 0.25 times the initial sampling density; when decreasing the sampling density, the decrease is 0.25 times the initial sampling density; when increasing the sampling movement speed, the increase is 0.25 times the initial sampling movement speed; when decreasing the sampling movement speed, the decrease is 0.25 times the initial sampling movement speed.

[0100] If the jump parameter is greater than the second jump reference value, when increasing the sampling density, the increase amount is 0.35 times the initial sampling density; when decreasing the sampling density, the decrease amount is 0.35 times the initial sampling density; when increasing the sampling movement speed, the increase amount is 0.35 times the initial sampling movement speed; when decreasing the sampling movement speed, the decrease amount is 0.35 times the initial sampling movement speed.

[0101] The first jump reference value is 1.25 times the jump standard parameter, and the second jump reference value is 1.5 times the jump standard parameter.

[0102] It is understandable that increasing the sampling density can capture more details and ensure the integrity of the modeling, while reducing the sampling movement speed is equivalent to increasing the number of sampling points for a single region within a time period, thereby improving the integrity of subsequent modeling.

[0103] Specifically, the model feature values ​​of the temporary model are analyzed, including the area ratio of missing regions and the structural fracture rate.

[0104] The ratio of the area ratio of the missing region to the reference value of the area ratio of the missing region is determined as the first model interference characteristic value;

[0105] The ratio of the structural fracture rate to the reference value of the structural fracture rate is determined as the second model interference characteristic value;

[0106] The model feature values ​​of the temporary model are obtained by weighted summing of the first model interference feature value and the second model interference feature value.

[0107] To comprehensively consider the area ratio of the missing region and the structural fracture rate, the weights for the weighted summation of the interference eigenvalues ​​of the first model and the second model are 0.5 respectively.

[0108] In practice, temporary pre-modeling is performed to model the sampled data of local areas and obtain the model of the local area. Based on this, after the model is completed, the area ratio of the missing area in the model and the structural fracture rate can be analyzed.

[0109] The structural fracture rate is the ratio of the number of fractured structures in the model to the total number of structures in the model.

[0110] The missing region area ratio is the ratio of the area of ​​the missing region in the model to the total area of ​​the model.

[0111] Specifically, the reference values ​​for the area ratio of missing regions and the reference values ​​for the structural fracture rate are predetermined. Several panoramic models that meet the application requirements are selected by those skilled in the art, and the average structural fracture rate and the average area ratio of missing regions of each region of the panoramic model are obtained. The reference value for the area ratio of missing regions is set as the product of the average area ratio of missing regions of the model and the error coefficient. The reference value for the structural fracture rate is set as the product of the average structural fracture rate and the error coefficient. The error coefficient is selected within the interval [0.75, 0.85].

[0112] During implementation, the temporary verification period is selected within the range [3s, 5s].

[0113] Please see Figure 4 As shown, it is a logic block diagram of a method for correcting sampling parameters based on model feature values ​​according to an embodiment of the invention. Specifically, the corrected sampling data includes:

[0114] If the model feature value is greater than or equal to the preset model feature value, the current sampling density is increased and the current sampling movement speed is decreased. In practice, the increase in sampling density is 0.25 times the current sampling density, and the decrease in movement speed is 0.25 times the current sampling movement speed.

[0115] This invention constructs a temporary model based on sampling data from a temporary verification period after adjusting sampling parameters. In practice, power distribution network planning involves a massive amount of data. If a model is directly built from the panoramic data after each adjustment of sampling parameters, it will result in significant resource waste and time delays. The temporary model, through rapid verification and optimization on a small-scale dataset, can effectively improve the efficiency of the entire planning process. The temporary model can optimize the final model construction strategy, enabling effective adaptation of sampling parameters to different scenarios throughout the data acquisition path, timely modification and correction of sampling parameters, and improved accuracy of the final model.

[0116] Specifically, a system for planning a multi-scenario integrated new energy production and sales distribution network is also provided, which includes:

[0117] The acquisition module is used to control the mobile acquisition unit to move according to the acquisition route and to acquire image information of the area that the mobile acquisition unit is about to pass through in real time.

[0118] An analysis module, connected to the acquisition module, is used to perform feature jump analysis based on the image information, including marking virtual paths in the image information, constructing several reference regions based on the virtual paths, and determining the closed contour density jump variable and grayscale jump variable between adjacent reference regions.

[0119] A calibration module, connected to the analysis module, is used to calculate jump parameters based on closed contour density jump variables and grayscale jump variables, and to calibrate a reference area in the image information based on the jump parameters;

[0120] An adjustment and correction module, which is connected to the calibration module, is used to determine whether to adjust the sampling of the mobile acquisition unit based on the distance between the mobile acquisition unit and the calibration reference area, so as to adjust the sampling parameters based on the jump parameter;

[0121] A temporary verification period is determined. Based on the sampling data of the temporary verification period after adjusting the sampling parameters, temporary pre-modeling is performed to construct a temporary model. The model feature values ​​of the temporary model are analyzed to correct the sampling parameters.

[0122] The data integration and model storage module is connected to the acquisition module, analysis module, calibration module and adjustment and correction module respectively, and is used to complete the planning of the acquisition path, construct a panoramic model based on all sampled data, and store the panoramic model in the power distribution network planning database.

[0123] In implementation, there are no restrictions on the structure of the acquisition module, analysis module, calibration module, and adjustment and correction module. They can be composed of logic components or combinations of logic components, including field-programmable processors, computers, or microprocessors in computers.

[0124] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A multi-scenario new energy production and sales integrated power distribution network planning method, characterized in that, Comprising: According to the target scene planning collection route, controlling the mobile collection unit to carry the collection equipment to move according to the collection route, and acquiring the image information of the area through which the mobile collection unit is expected to pass in real time; Based on the image information, the feature jump analysis includes marking a virtual path in the image information, constructing a plurality of reference areas according to the virtual path, determining the closed contour density jump variable and the gray jump variable between adjacent reference areas; Based on the closed contour density jump variable and the gray jump variable, calculate the jump parameter, and mark the reference area in the image information according to the jump parameter; Based on the distance between the mobile collection unit and the marked reference area, determine whether to adjust the sampling of the mobile collection unit, and adjust the sampling parameters based on the jump parameter; Determine the temporary verification period, based on the sampling data of the temporary verification period after adjusting the sampling parameters, temporarily pre-modeling, constructing a temporary model, analyzing the model characteristic value of the temporary model, and correcting the sampling parameters, Comprising, Analyzing the model characteristic value of the temporary model, Including, the missing area ratio and the structure fracture rate; Determine the ratio of the missing area ratio to the missing area ratio reference value as the first model interference characteristic value; Determine the ratio of the structure fracture rate to the structure fracture rate reference value as the second model interference characteristic value; The first model interference characteristic value and the second model interference characteristic value are weighted and summed to obtain the model characteristic value of the temporary model; If the model characteristic value is greater than or equal to the preset model characteristic value, increase the current sampling density and reduce the current sampling moving speed; Complete the planned collection path, construct a panoramic model based on all the sampling data, and store the panoramic model in the power distribution network planning database; Wherein, the model characteristic includes, model missing area ratio and structure fracture rate.

2. The multi-scenario new energy production and sales integrated power distribution network planning method according to claim 1, characterized in that, The process of marking a virtual path in the image information and constructing a plurality of reference areas according to the virtual path includes, Determine the current moving direction of the mobile collection unit, mark a virtual line in the image information based on the current moving direction, and determine the virtual line as the virtual path; Along the predetermined interval, a plurality of partitioning lines perpendicular to the virtual path are constructed, and the areas divided by the partitioning lines are determined as the reference areas.

3. The multi-scenario new energy production and sales integrated power distribution network planning method according to claim 2, characterized in that, The process of determining the closed contour density jump variable and the gray jump variable between adjacent reference areas includes, Along the extension direction of the virtual path, determine the difference between the closed contour density of the reference area and the adjacent last reference area to obtain the closed contour density jump variable; Along the extension direction of the virtual path, determine the difference between the gray scale of the reference area and the adjacent last reference area to obtain the closed gray scale jump variable.

4. The multi-scenario new energy production and sales integrated power distribution network planning method according to claim 3, characterized in that, The process of calculating the jump parameter based on the closed contour density jump variable and the gray jump variable includes, Determine the ratio of the absolute value of the closed contour density jump variable to the preset closed contour density jump variable as the first jump parameter factor; Determine the ratio of the absolute value of the closed gray jump variable to the preset closed gray jump variable as the second jump parameter factor; The first jump parameter factor and the second jump parameter factor are weighted and summed to obtain the jump parameter.

5. The multi-scenario new energy production and sales integrated power distribution network planning method according to claim 1, characterized in that, Marking the reference area in the image information according to the jump parameter includes, If the jump parameter corresponding to the reference region is greater than or equal to the preset jump standard parameter, the reference region is marked in the image information. 6.The multi-scenario new energy production and consumption integrated power distribution network planning method according to claim 1, characterized in that, The process of determining whether to adjust the sampling of the mobile acquisition unit based on the distance between the mobile acquisition unit and the marked reference region includes, If the distance is less than or equal to the preset sampling distance threshold, the sampling of the mobile acquisition unit is adjusted.

7. The multi-scenario new energy production and sales integrated power distribution network planning method according to claim 1, characterized in that, The adjustment of the sampling parameters based on the jump parameter includes, If the closed contour density jump variable corresponding to the marked reference region is a positive value, the sampling density is increased, the amount of increase being related to the jump parameter, and the sampling movement speed is reduced, the amount of reduction being related to the sampling parameters; If the closed contour density jump variable corresponding to the marked reference region is a non-positive value, the sampling density is reduced, the amount of reduction being related to the jump parameter, and the sampling movement speed is increased, the amount of increase being related to the sampling parameters; The sampling parameters include the sampling density and the sampling movement speed.

8. A system for applying the multi-scenario new energy production and sales integrated power distribution network planning method of any one of claims 1-7, characterized in that, It includes: The acquisition module is used to control the mobile acquisition unit to carry the acquisition device to move according to the acquisition route, and to acquire the image information of the pre-passing region of the mobile acquisition unit in real time; The analysis module is connected with the acquisition module and is used to perform feature jump analysis based on the image information, including marking a virtual path in the image information, constructing a plurality of reference regions according to the virtual path, determining the closed contour density jump variable and the gray jump variable between adjacent reference regions; The calibration module is connected with the analysis module and is used to calculate the jump parameter based on the closed contour density jump variable and the gray jump variable, and to mark the reference region in the image information according to the jump parameter; The adjustment and correction module is connected with the calibration module and is used to determine whether to adjust the sampling of the mobile acquisition unit based on the distance between the mobile acquisition unit and the marked reference region, and to adjust the sampling parameters based on the jump parameter; A temporary verification period is determined, temporary modeling is performed based on the sampling data of the temporary verification period after the adjustment of the sampling parameters, a temporary model is constructed, the model characteristic value of the temporary model is analyzed, and the sampling parameters are corrected; The data integration and model storage module is connected with the acquisition module, analysis module, calibration module and adjustment and correction module respectively, and is used to complete the planning of the acquisition path, construct a panoramic model based on all the sampling data, and store the panoramic model in the power distribution network planning database.

Images