Photovoltaic module arrangement method, apparatus and electronic device

Abstract

The application provides a photovoltaic module arrangement method and device and electronic equipment, the method comprises the following steps: acquiring a region image of a region where a module can be installed; sequentially performing image processing and grid division on the region image, and generating a plurality of points according to all the grids obtained by division; determining the neighborhood of each point respectively; scoring each neighborhood by using a pre-trained evaluation model to obtain the score value of each neighborhood; generating a plurality of initial regions according to the score value of each neighborhood based on a region growing algorithm, and determining the priority and estimated installation capacity of each initial region; and determining an optimal installation region of a photovoltaic module according to the actual capacity demand of the photovoltaic power station, the priority and the estimated installation capacity of each initial region. The technical scheme of the application can dynamically adjust the region where a photovoltaic module can be installed, and improve the installability and power generation of the photovoltaic module.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic power generation, in particular to a photovoltaic module arrangement method and device and electronic equipment. BACKGROUND

[0002] A photovoltaic power station refers to a photovoltaic power generation system composed of photovoltaic modules and electronic components such as inverters using solar energy. When a photovoltaic power station is built in complex terrain such as mountains, pre-layout of the photovoltaic power station is often required, and photovoltaic module arrangement is performed according to the pre-layout area.

[0003] Currently, photovoltaic power station design software (PDP software, etc.) is often used to read the CAD contour map of the project site, automatically analyze the slope and shadow of the project site, generate a region where the installed modules meet the conditions and have no shadow obstruction, and then automatically arrange the photovoltaic modules in the region where the installed modules meet the conditions, and estimate the installed capacity and power generation of the photovoltaic modules. However, this method automatically arranges the photovoltaic modules in the region where the installed modules meet the conditions, and when there is a deviation between the actual capacity demand and the estimated installed capacity in the region where the installed modules meet the conditions, the photovoltaic modules are randomly arranged at a position, which can easily result in poor installability and power generation of the photovoltaic modules. SUMMARY

[0004] The problem solved by the present application is how to determine the optimal installation region of the photovoltaic modules and improve the installability and power generation of the photovoltaic modules.

[0005] To solve the above problems, the present application provides a photovoltaic module arrangement method, device and electronic equipment.

[0006] In a first aspect, the present application provides a photovoltaic module arrangement method, comprising:

[0007] obtaining a region image of a region where installed modules meet the conditions;

[0008] sequentially performing image processing and grid division on the region image, and generating a plurality of points according to all the grids obtained by the division, and determining the neighborhood of each point;

[0009] scoring each neighborhood using a pre-trained evaluation model to obtain a score value of each neighborhood, wherein the evaluation model is used to evaluate the installability and power generation of photovoltaic modules in a region;

[0010] generating a plurality of initial regions according to the score values of each neighborhood based on a region growing algorithm, and determining the priority and estimated installed capacity of each initial region;

[0011] determining the optimal installation region of the photovoltaic modules according to the actual capacity demand of the photovoltaic power station, the priority and the estimated installed capacity of each initial region.

[0012] Optionally, the sequentially performing image processing and grid division on the region image comprises:

[0013] contour extraction is performed on the region image to obtain a contour of the installable component region;

[0014] a circumscribed rectangle of the contour is generated, and grid division is performed on the circumscribed rectangle to obtain a plurality of grids.

[0015] Optionally, the generating a plurality of points according to all the grids obtained by the division comprises:

[0016] determining a proportion of an area in each grid that does not belong to the installable component region to a total area of the corresponding grid;

[0017] eliminating, from all the grids, a grid whose proportion is greater than a first preset threshold to obtain screened grids;

[0018] generating a plurality of points according to the screened grids, all the points constituting a point distribution map.

[0019] Optionally, before the scoring each neighborhood using the pre-trained evaluation model, the method further comprises:

[0020] obtaining geographical environment data of a plurality of regions in an existing power station, and power generation and installability of photovoltaic components in each region;

[0021] performing correlation analysis on the geographical environment data and the power generation and installability of the photovoltaic components, and determining impact factor data in the geographical environment data according to an analysis result;

[0022] determining a comprehensive index of each region according to the power generation and installability of the photovoltaic components, respectively, and constructing a training data set according to the corresponding impact factor data and the comprehensive index;

[0023] training a pre-established neural network using the training data set to obtain the trained evaluation model.

[0024] Optionally, the scoring each neighborhood using the pre-trained evaluation model comprises:

[0025] obtaining the impact factor data of each neighborhood;

[0026] inputting the impact factor data into the evaluation model to output the score value of each neighborhood.

[0027] Optionally, after obtaining the score value of each of the neighborhoods, the method further comprises: converting the score value into a gray value, representing each of the neighborhoods with the corresponding gray value, and obtaining a score gray map.

[0028] Optionally, generating a plurality of initial regions based on the region growing algorithm according to the score value of each of the neighborhoods comprises:

[0029] sequentially sorting all of the neighborhoods according to the score value based on a preset sorting rule;

[0030] selecting a plurality of the neighborhoods to generate a point set according to the sorting result, each point in the point set corresponding to one of the neighborhoods;

[0031] selecting a plurality of points from the point set as initial seed points, and constructing a seed point neighborhood for each of the initial seed points;

[0032] for any of the initial seed points, determining a difference value between the score value of the initial seed point and the score value of each point in the corresponding seed point neighborhood, and fusing the point with the initial seed point to generate the initial region if the difference value is less than a second preset threshold.

[0033] Optionally, determining the priority and the estimated installation capacity of each of the initial regions comprises:

[0034] determining an average value of the score value of all of the neighborhoods in the initial region, and determining the priority of each of the initial regions according to the average value;

[0035] performing component pre-layout on each of the initial regions, and determining the estimated installation capacity of each of the initial regions according to the pre-layout result.

[0036] Optionally, determining the optimal installation region of the photovoltaic component according to the actual capacity demand of the photovoltaic power station, the priority and the estimated installation capacity of each of the initial regions comprises:

[0037] selecting the initial regions in order of the priority from high to low according to the actual capacity demand of the photovoltaic power station and the estimated installation capacity of each of the initial regions, and taking the initial regions as the optimal installation region of the photovoltaic component.

[0038] In a second aspect, the present application provides a photovoltaic component arrangement device, comprising:

[0039] an acquisition module configured to acquire a region image of a region in which a component can be installed in a photovoltaic power station;

[0040] a processing module configured to sequentially perform image processing and grid division on the region image, and generate a plurality of points according to all of the grids obtained by the division, and determine a neighborhood of each of the points.

[0041] a scoring module configured to score each of the neighborhoods using a pre-trained evaluation model to obtain a score value of each of the neighborhoods, wherein the evaluation model is used to evaluate the installability and power generation of photovoltaic modules in a region;

[0042] a generating module configured to generate a plurality of initial regions based on a region growing algorithm according to the score values of each of the neighborhoods, and determine a priority and an estimated installation capacity of each of the initial regions;

[0043] an optimizing module configured to determine an optimal installation region of photovoltaic modules according to an actual capacity requirement of the photovoltaic power station, the priority and the estimated installation capacity of each of the initial regions.

[0044] In a third aspect, the present application provides an electronic device comprising a memory and a processor;

[0045] the memory is configured to store a computer program;

[0046] the processor is configured to implement the photovoltaic module arrangement method according to any one of the first aspect when executing the computer program.

[0047] The photovoltaic module arrangement method, device and electronic device have the following advantages: the photovoltaic power station design software can generate a region image of installable module regions of a project site, and the installable module regions represent regions in the project site that meet the conditions of slope and have no shadow obstruction. The region image can be subjected to image processing such as filtering and edge detection, and then the processed image can be subjected to grid division to obtain a plurality of grids. A plurality of points can be generated according to all the grids, all the points can constitute a point distribution map, and the neighborhoods of each point can be determined. A pre-trained evaluation model can be used to score the installability and power generation of photovoltaic modules in each neighborhood to obtain a score value of each neighborhood, and the evaluation model can be trained by collecting the power generation, installability and influencing factor data of each region in an existing power station. Based on a region growing algorithm, a plurality of initial regions can be generated according to each neighborhood, each initial region includes at least one neighborhood, i.e., neighborhoods with similar score values can be merged into one region, and the priority and estimated installation capacity of each initial region can be determined, wherein the higher the priority, the stronger the comprehensive performance of the installability and power generation of photovoltaic modules in the initial region. Therefore, the initial regions with higher priority can be preferentially selected as the optimal installation region of photovoltaic modules, until the sum of the estimated installation capacities of the selected initial regions meets the actual capacity requirement of the photovoltaic power station. By preferentially selecting the initial regions with strong comprehensive performance of installability and power generation of photovoltaic modules as the optimal installation region, the arrangement of photovoltaic modules is improved, and the installability and power generation of photovoltaic modules in the project site are improved. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 A flowchart of a photovoltaic module arrangement method according to an embodiment of the present application;

[0049] Figure 2 A flowchart of obtaining an installable module region according to an embodiment of the present application;

[0050] Figure 3 A structure diagram of an evaluation model according to an embodiment of the present application;

[0051] Figure 4 A structure diagram of a photovoltaic module arrangement device according to another embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the above objectives, features and advantages of the present application more apparent, specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, rather, these embodiments are provided so as to more thoroughly and completely understand the present application. It should be understood that the drawings and embodiments of the present application are for exemplary purposes only, and are not intended to limit the scope of protection of the present application.

[0053] It should be understood that each of the steps recited in the method embodiments of the present application can be executed in different orders, and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the execution of the steps shown. The scope of the present application is not limited in this respect.

[0054] The term "comprising" and variations thereof as used herein are open-ended, that is, "comprising but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optional" means "optional in at least some embodiments". Related definitions will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in the present application are only used to distinguish different devices, modules or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules or units.

[0055] It should be noted that the modification of "one", "multiple" mentioned in the present application is illustrative and not limiting, and those skilled in the art should understand that, unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0056] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present application are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0057] As shown in Figure 1 The photovoltaic module arrangement method provided by the embodiment of the present application comprises:

[0058] In step S100, a region image of a region where a module can be installed is acquired.

[0059] Specifically, as shown in Figure 2 The process of acquiring a region (a region where a module can be installed) that meets a slope condition and has no shadow comprises a high-precision topographic mapping method, slope and shadow analysis. The high-precision topographic mapping method comprises acquiring a land red line of a project land according to a target land range, using a Zhonghaida PPK package software to map a coordinate system, using a drone to take a photo of the target land range, and using a DJI ZhiTu software to perform DEM (Digital Elevation Model) fine processing to generate a contour map of the project land. The specific processing process is a prior art, and will not be described here. Then, according to the contour map, a PDP photovoltaic power station design software developed by Bochao Times Company is used to perform slope analysis and shadow analysis on the project land to obtain a region in the project land that meets the installation condition and has no shadow obstruction. This region is a region where a module can be installed. The specific slope analysis and shadow analysis process is a prior art, and will not be described here.

[0060] In step S200, image processing and grid division are sequentially performed on the region image, and a plurality of points are generated according to all the grids obtained by the division, and a neighborhood of each point is determined.

[0061] In step S300, a pre-trained evaluation model is used to score each neighborhood to obtain a score value of each neighborhood. The evaluation model is used to evaluate the installability of a photovoltaic module in a region and the power generation capacity.

[0062] Specifically, the installability can represent whether a corresponding region can install a photovoltaic module, and the convenience of installing a photovoltaic module, etc.

[0063] In step S400, based on a region growing algorithm, a plurality of initial regions are generated according to the score values of the neighborhoods, and a priority and an estimated installation capacity of each initial region are determined.

[0064] In step S500, an optimal installation region of a photovoltaic module is determined according to an actual capacity demand of the photovoltaic power station, the priority and the estimated installation capacity of each initial region.

[0065] In the embodiment, the region image of the installable component region in the project land can be generated by a photovoltaic power station design software, the installable component region representing a region in the project land with a qualified slope and no shadow obstruction. The region image can be subjected to image processing such as filtering and edge detection, and then the processed image is subjected to grid division to obtain a plurality of grids. A plurality of points are generated according to all the grids, all the points can constitute a point distribution map, and the neighborhood of each point is determined. An evaluation model trained in advance is used to score the installability and power generation of photovoltaic components in each neighborhood to obtain the score value of each neighborhood, and the evaluation model can be trained by collecting the power generation, installability and influencing factor data of each region in an existing power station. Based on the region growing algorithm, a plurality of initial regions are generated according to each neighborhood, each initial region including at least one neighborhood, i.e. the neighborhoods with similar score values are merged into one region, and the priority and estimated installation capacity of each initial region are determined, wherein the higher the priority, the stronger the comprehensive performance of the installability and power generation of photovoltaic components in the initial region. Therefore, the initial region with higher priority can be preferentially selected as the optimal installation region of photovoltaic components, until the sum of the estimated installation capacities of the selected initial regions meets the actual capacity demand of the photovoltaic power station. By preferentially selecting the initial region with strong comprehensive performance of installability and power generation of photovoltaic components as the optimal installation region, the arrangement of photovoltaic components is performed, and the installability and power generation of photovoltaic components in the project land are improved.

[0066] Optionally, the sequentially performing image processing and grid division on the region image comprises:

[0067] contour extraction is performed on the region image to obtain the contour of the installable component region.

[0068] Specifically, the region image can be preprocessed first, such as filtering and morphological operation, wherein the filtering can adopt methods such as median filtering and Gaussian filtering, and the morphological operation can include opening operation, closing operation, dilation and corrosion, etc., and different preprocessing operations can be performed according to actual needs, which are not limited herein. Various existing contour extraction algorithms can be used to extract the contour of the installable component region, such as edge detection algorithm (Canny edge detection, etc.) for edge detection to obtain the contour of the installable component region, which is not limited herein.

[0069] The circumscribed rectangle of the contour is generated, and the circumscribed rectangle is subjected to grid division to obtain a plurality of grids.

[0070] Specifically, the method of generating the circumscribed rectangle of the contour includes a minimum enclosing rectangle algorithm and a rectangular coordinate system-based method, etc. For example, a rectangular coordinate system can be established according to the orientation of the project site installation component; the two points with the closest and farthest distances perpendicular to the x-axis on the contour are found, and parallel lines of the x-axis are drawn through the two points, respectively; the two points with the closest and farthest distances perpendicular to the y-axis on the contour are found, and parallel lines of the y-axis are drawn through the two points, respectively; the four parallel lines intersect, and the circumscribed rectangle enclosing the contour of the installable component region is obtained, which is not limited herein.

[0071] The method of grid division of the circumscribed rectangle includes but is not limited to a uniform division method, a middle sparse and four-side dense division method, and a terrain-based grid division method. The grid spacing can be set as an integer multiple of the size of the photovoltaic component during the grid division process.

[0072] The uniform division method: according to the side length of the circumscribed rectangle, a fixed grid spacing is set, and the circumscribed rectangle is divided according to the spacing. This method is simple and efficient, and can quickly complete the grid division.

[0073] The middle sparse and four-side dense division method: the center point of the circumscribed rectangle is determined, and the grid is divided outward from the center point according to the grid spacing from large to small, wherein the grid spacing gradually decreases during the outward division. Since the central region can better meet the conditions for arranging photovoltaic components, and the edge region has poor conditions for arranging components, a larger grid spacing can be used in the middle region to improve the grid division speed, and a smaller grid spacing can be used in the edge region to improve the grid division accuracy.

[0074] The terrain-based grid division method: the areas with large terrain changes in the project site are determined through the CAD contour map of the project site, and the grid division is performed in the areas with small grid spacing, and the grid division is performed in other areas with large grid spacing. The areas with large terrain changes are usually not suitable for installing photovoltaic components, so a small grid spacing is needed for detailed division to improve the grid division accuracy, and the areas with flat terrain can use a large grid spacing for division, which can reduce the calculation amount and improve the speed.

[0075] Optionally, the method further comprises:

[0076] determining the proportion of the area in each grid that does not belong to the installable component region to the total area of the corresponding grid;

[0077] eliminating the grids with the proportion greater than a first preset threshold from all the grids to obtain screened grids;

[0078] generating a plurality of points from the screened grids, and all the points constitute a point distribution map.

[0079] Specifically, since the generated mountable component area is usually irregular, the generated circumscribed rectangle usually not only includes the mountable component area, but also includes some areas that do not meet the slope condition and / or are shaded (i.e., areas outside the mountable component area), which need to be removed.

[0080] Suppose that the area of the mountable component area in a grid is A, the area of the area that does not belong to the mountable component area is B, and the ratio of the area that does not belong to the mountable area to the total area of the grid is S, then

[0081]

[0082] The ratio S can be compared with a first preset threshold value, and the invalid grid greater than the first preset threshold value can be removed. The grid left after removing the invalid grid is the screened grid, and the circumscribed polygon of the mountable component area is obtained. The first preset threshold value can be related to the demand capacity of the project site. If the demand capacity is large, the first preset threshold value can be set to be large, and vice versa.

[0083] Generating a plurality of points according to the screened grid includes but is not limited to the following ways:

[0084] (1) generating a point distribution map with the vertices of the internal grid of the circumscribed polygon (not including the vertices on the contour of the circumscribed polygon).

[0085] (2) calculating the center point of each grid in the circumscribed polygon, and generating a point distribution map with these center points.

[0086] (3) dividing all the grids in the circumscribed polygon into a plurality of N*N (M) large grids, calculating the center point of each large grid, and generating a point distribution map with these center points.

[0087] In the prior art, photovoltaic power station design software mostly performs triangular grid division on CAD contour drawings to generate a three-dimensional model of the project site, and performs shadow analysis according to the three-dimensional model. In this way, the accuracy of the shadow analysis is not high, and some areas where photovoltaic components can be installed are easily ignored. After grid division of the mountable component area, some grids include both the mountable component area and the non-mountable component area, and the distance between them is very close. These areas are usually easily ignored by software processing.

[0088] In the optional embodiment, the grids whose proportion of the area of the non-mountable component region to the total area of the grid is greater than the first preset threshold are removed, and the grids whose proportion is less than the first preset threshold are retained, that is, a part of the region outside the mountable component region is retained, which can compensate for the error in the shadow analysis by the software to some extent, make more regions have the possibility of installing photovoltaic components, and increase the capacity of the mountable components of the project land.

[0089] Optionally, before the scoring of each of the neighborhoods by using the pre-trained evaluation model, the method further comprises:

[0090] Obtaining geographical environment data of a plurality of regions in an existing power station, and power generation and mountability of photovoltaic components in each of the regions.

[0091] Specifically, the geographical environment data can include average height, slope, land hardness, presence of non-removable objects, distance from a river, and distance from a region center of the region.

[0092] Performing correlation analysis on the geographical environment data and the power generation and mountability of the photovoltaic components, and determining influence factor data in the geographical environment data according to an analysis result.

[0093] Specifically, the mountability can be scored by a construction worker and represented in the form of a numerical value. The correlation analysis method includes but is not limited to the following methods:

[0094] (1) calculating the covariance between the geographical environment data and the power generation and mountability of the photovoltaic components.

[0095] (2) calculating the correlation coefficient between the geographical environment data and the power generation and mountability of the photovoltaic components.

[0096] (3) performing regression analysis between the geographical environment data and the power generation and mountability of the photovoltaic components.

[0097] A corresponding threshold value can be set for the correlation, and the correlation analysis result corresponding to each geographical environment data is compared with the threshold value to determine that the geographical environment data whose correlation analysis result is greater than the threshold value is the influence factor data.

[0098] A comprehensive index of each of the regions is determined according to the power generation and mountability of the photovoltaic components, and a training data set is constructed according to the corresponding influence factor data and the comprehensive index.

[0099] Specifically, the power generation and the installability of the photovoltaic module can be normalized, and the process is as follows: y=σ1y1+σ2y2, wherein y represents the comprehensive index of the region, y1 represents the installability of the photovoltaic module, y2 represents the power generation of the photovoltaic module, σ1 represents the weight of the installability, and σ2 represents the weight of the power generation. The weights σ1 and σ2 can be dynamically adjusted according to actual conditions.

[0100] The pre-established neural network is trained by using the training data set, and a trained evaluation model is obtained.

[0101] Specifically, as shown in the figure, the neural network is trained by using the influence factor data as input data and the comprehensive index as a label. Figure 3

[0102] Optionally, the scoring of each of the neighborhoods by using the pre-trained evaluation model comprises:

[0103] The influence factor data of each of the neighborhoods is obtained.

[0104] The influence factor data is input into the evaluation model, and the score value of each of the neighborhoods is output.

[0105] Specifically, the influence factor data of a neighborhood is input into the evaluation model, and the evaluation model outputs the comprehensive index of the neighborhood, which is the score value of the neighborhood.

[0106] In the prior art, the priority of installing photovoltaic modules in each sub-region in the installable module region generated by the photovoltaic power station design software has no difference. However, the installability and power generation of photovoltaic modules are quite different when the modules are arranged at different positions in the installable module region (especially in a large mountainous area or other complex project area). For example, the power generation of photovoltaic modules in a position with better light in the installable module region is better than that in a position with poor light; the installability of photovoltaic modules in a flat position is better than that in a position with a slope, and so on.

[0107] In this optional embodiment, the trained evaluation model is used to score each neighborhood. Since the evaluation model is used to evaluate the comprehensive index of the installability and power generation of photovoltaic modules in a region, the score value of each neighborhood output by the evaluation model reflects the installability and power generation of photovoltaic modules in each neighborhood. The priority of each neighborhood can be divided by using the score value, and the neighborhood with a high score value can be preferentially selected for module arrangement, thereby improving the installability and power generation of photovoltaic modules.

[0108] Optionally, after obtaining the score value of each of the neighborhoods, the score value is converted into a gray value, each of the neighborhoods is represented by the corresponding gray value, and a score gray map is obtained.​

[0109] Specifically, a neighborhood of each point in the point distribution map is determined, and the neighborhood size can be determined according to the accuracy requirement of the pre-layout, the higher the accuracy requirement, the smaller the neighborhood, and the lower the accuracy requirement, the larger the neighborhood. The neighborhood shape can be set as a rectangular neighborhood according to the component size (or an integer multiple of the component size) and the component orientation and mounting angle.

[0110] After determining the score value of each neighborhood through the evaluation model, the score value can be normalized to 0-225, converted into a gray value, and each point in the neighborhood is represented by the corresponding gray value, so that the score gray map can be obtained.

[0111] In this optional embodiment, each neighborhood is represented by a corresponding gray value to generate a score gray map, and the gray scale of different regions on the score gray map can intuitively reflect the comprehensive score of the photovoltaic component installability and power generation capacity of each region, thereby improving the intuitiveness.

[0112] Optionally, the generating a plurality of initial regions based on the region growing algorithm according to the score values of the neighborhoods comprises:

[0113] According to a preset sorting rule, all the neighborhoods are sorted according to the score values.

[0114] Specifically, each neighborhood can be sorted in descending order or ascending order of the score value (or gray value).

[0115] According to the sorting result, a point set is generated from a plurality of the neighborhoods, and each point in the point set corresponds to one of the neighborhoods.

[0116] Specifically, each neighborhood is regarded as a whole, which is equivalent to a point. The first a percent of points can be selected in descending order or ascending order of the score value (or gray value) to form a point set A, and the last b percent of points can be selected to form a point set B, wherein the values of a and b can be adjusted according to actual conditions. The greater the values of a and b, the higher the accuracy, but the longer the calculation time.

[0117] A plurality of points are selected from the point set as initial seed points, and a seed point neighborhood is constructed for each initial seed point.

[0118] Specifically, one point is randomly selected from the point set A, and then n / 2-1 points are randomly selected according to the distance to form initial seed points. The same operation is performed on the point set B, and finally n initial seed points are obtained. For each initial seed point, a seed point neighborhood σ is constructed.

[0119] For any initial seed point, a difference value between the score value of the initial seed point and the score value of each point in the corresponding seed point neighborhood is determined, and the point with the difference value less than a second preset threshold is fused with the initial seed point to generate the initial region.

[0120] Specifically, if the absolute value of the difference between the score value (gray value) of an initial seed point and the score value (gray value) of a point in the seed point neighborhood σ of the initial seed point is within a second preset threshold α, the point is fused with the initial seed point. The initial seed point is fused with all points in the seed point neighborhood σ that meet the condition to obtain an initial region. The values of σ and α can be adjusted according to actual conditions, and the smaller the value, the higher the accuracy.

[0121] In the optional embodiment, region growing is an algorithm often used in image segmentation scenarios, and the basic idea is to merge pixels with similar properties together. For each region, a seed point is first specified as the starting point of growth, and then the pixels in the neighborhood of the seed point are compared with the seed point, and the points with similar properties are merged to continue to grow outward until no pixel point meeting the condition is included. The neighborhoods with similar score values (gray values) are merged to generate an initial region, and subsequent processing of the initial region can reduce the amount of calculation and improve the processing speed.

[0122] Optionally, the determination of the priority of each initial region and the estimated installation capacity comprises:

[0123] An average value of the score values of all the neighborhoods in the initial region is determined, and the priority of each initial region is determined according to the average value.

[0124] Specifically, an average value of the score values of all the neighborhoods in an initial region is obtained to obtain a comprehensive score of the initial region. The priority of each initial region is determined according to the average value (i.e., the comprehensive score), for example: the comprehensive scores of all the initial regions in the project site can be used to divide the levels, the comprehensive scores of the initial regions are normalized, then the first proportion of the initial regions with the highest scores are divided into priority installation regions, the second proportion of the initial regions with intermediate scores are divided into ordinary installation regions, and the initial regions with the lowest scores are divided into non-recommended installation regions; or the priority of each initial region is determined in the order of the average values from large to small, and the larger the average value, the higher the priority of the initial region; the smaller the average value, the lower the priority of the initial region.

[0125] The component pre-layout is performed on each initial region, and the estimated installation capacity of each initial region is determined according to the pre-layout result.

[0126] Specifically, if the size of the neighborhood of each point in the setpoint distribution map is the size of the component, the neighborhood shape is a rectangle in which the components are oriented in the same direction, and the grid division uses a grid spacing that is an integer multiple of the size of the photovoltaic component, then the number of photovoltaic components in each initial region can be determined by calculating the number of grids in each initial region, and the estimated installation capacity of each initial region can be determined by multiplying the capacity of a single photovoltaic component by the number of photovoltaic components in each initial region.

[0127] In this optional embodiment, the initial regions are prioritized, which facilitates the prioritized selection of initial regions with higher priority for component arrangement, thereby improving the installation of components and power generation.

[0128] Optionally, determining the optimal installation region of the photovoltaic component based on the actual capacity requirement of the photovoltaic power station, the priority and the estimated installation capacity of each initial region comprises:

[0129] According to the actual capacity requirement of the photovoltaic power station and the estimated installation capacity of each initial region, the initial regions are sequentially selected as the optimal installation region of the photovoltaic component in order of the priority from high to low.

[0130] Specifically, the initial regions are sequentially selected as the optimal installation region of the photovoltaic component in order of the priority from high to low until the sum of the estimated installation capacities of the selected initial regions is greater than or equal to the actual capacity requirement of the photovoltaic power station.

[0131] Alternatively, assuming that the initial regions are classified into three levels of priority installation region, ordinary installation region, and non-recommended installation region according to the priority, the sum of the estimated installation capacities of the priority installation regions is A, the sum of the estimated installation capacities of the ordinary installation regions is B, the sum of the estimated installation capacities of the non-recommended installation regions is C, and the actual capacity requirement is D.

[0132] If D < A, then photovoltaic component arrangement is only performed in the priority installation region, and the photovoltaic component arrangement is preferentially performed in the region with a higher score in the priority installation region.

[0133] If A < D < (A + B), then the priority installation region is first arranged with photovoltaic components, and then component arrangement is considered in the ordinary installation region, and the component arrangement is preferentially performed in the region with a higher score in the ordinary installation region.

[0134] If (A + B) < D < (A + B + C), then the priority installation region and the ordinary installation region are first arranged with photovoltaic components, and then component arrangement is considered in the non-recommended installation region, and the component arrangement is preferentially performed in the region with a higher score in the non-recommended installation region.

[0135] If (A + B + C) < D, the actual capacity requirement needs to be adjusted.

[0136] In the optional embodiment, the method for determining the optimal installation area includes, but is not limited to, the above two cases, and the installation priority is selected in order from high to low to select the initial area as the optimal installation area of the photovoltaic module, until the sum of the estimated installation capacities of all selected initial areas is greater than or equal to the actual capacity demand of the photovoltaic power station, so that the installability and power generation of the photovoltaic module can be improved while meeting the actual capacity demand of the photovoltaic power station.

[0137] As shown in Figure 4 Another embodiment of the present application provides a photovoltaic module arrangement device, which comprises:

[0138] An acquisition module is configured to acquire a region image of an installable component region in a photovoltaic power station;

[0139] A processing module is configured to sequentially perform image processing and grid division on the region image, and generate a plurality of points according to all the grids obtained by the division, and determine the neighborhood of each point;

[0140] A scoring module is configured to score each neighborhood by using a pre-trained evaluation model, to obtain a score value of each neighborhood, wherein the evaluation model is used to evaluate the installability and power generation of photovoltaic modules in a region;

[0141] A generation module is configured to generate a plurality of initial areas according to the score values of each neighborhood based on a region growing algorithm, and determine the priority and estimated installation capacity of each initial area;

[0142] An optimization module is configured to determine the optimal installation area of the photovoltaic module according to the actual capacity demand of the photovoltaic power station, the priority and the estimated installation capacity of each initial area.

[0143] The photovoltaic module arrangement device of the embodiment is used to implement the photovoltaic module arrangement method as described above, and the beneficial effects of the two are corresponding, which will not be described here.

[0144] Optionally, the processing module is specifically configured to perform contour extraction on the region image to obtain a contour of the installable component region, generate a circumscribed rectangle of the contour, and perform grid division on the circumscribed rectangle to obtain a plurality of grids.

[0145] Optionally, the processing module is specifically further configured to determine the proportion of the area in each grid that does not belong to the installable component region to the total area of the corresponding grid, and eliminate the grids with a proportion greater than a first preset threshold from all the grids to obtain screened grids, and generate a plurality of points according to the screened grids, and all the points constitute a point distribution map.

[0146] Optionally, the method further comprises: obtaining geographical environment data of a plurality of regions in an existing power station, and power generation capacity and installability of photovoltaic components in each of the regions; performing correlation analysis on the geographical environment data and the power generation capacity and installability of the photovoltaic components, determining impact factor data in the geographical environment data according to an analysis result; determining a comprehensive index of each of the regions according to the power generation capacity and installability of the photovoltaic components respectively, and constructing a training data set according to the corresponding impact factor data and the comprehensive index; and training a pre-established neural network using the training data set to obtain a trained evaluation model.

[0147] Optionally, the scoring module is specifically configured to: obtain the impact factor data of each of the neighborhoods; and input the impact factor data into the evaluation model to output the score value of each of the neighborhoods.

[0148] Optionally, the scoring module is specifically configured to: convert the score value into a gray value, represent each of the neighborhoods with the corresponding gray value, and obtain a score gray map.

[0149] Optionally, the generating module is specifically configured to: sort all the neighborhoods according to the score value based on a preset sorting rule; select a plurality of the neighborhoods to generate a point set according to a sorting result, each point in the point set corresponding to one of the neighborhoods; select a plurality of points from the point set as initial seed points, and construct a seed point neighborhood for each of the initial seed points; and for any initial seed point, determine a difference value between the score value of the initial seed point and score values of points in the corresponding seed point neighborhood, fuse a point with the initial seed point if the difference value is less than a second preset threshold value, and generate the initial region.

[0150] Optionally, the generating module is specifically configured to: determine an average value of the score values of all the neighborhoods in the initial region, and determine the priority of each of the initial regions according to the average value; perform component pre-layout on each of the initial regions, and determine the estimated installation capacity of each of the initial regions according to a pre-layout result.

[0151] Optionally, the optimization module is specifically configured to: select the initial regions as optimal installation regions of the photovoltaic components in order of the priority from high to low according to actual capacity requirements of the photovoltaic power station and the estimated installation capacity of each of the initial regions.

[0152] Another embodiment of the application provides an electronic device, comprising a memory and a processor; the memory is configured to store a computer program; and the processor is configured to implement the photovoltaic component arrangement method when executing the computer program.

[0153] A further embodiment of the present application provides a computer readable storage medium storing a computer program, when the computer program is executed by a processor, realizing the photovoltaic module arrangement method as described above.

[0154] An electronic device that can be a server or a client of the present application will now be described, which is an example of a hardware device that can be applied to aspects of the present application. The electronic device is intended to represent various forms of digital electronic computing devices such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computing devices. The electronic device can also represent various forms of mobile devices such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components, their connections, and their functions, as described herein, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed herein.

[0155] The electronic device includes a computing unit that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) or a computer program loaded into a random access memory (RAM) from a storage unit. In the RAM, various programs and data required for device operation can also be stored. The computing unit, the ROM, and the RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0156] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0157] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, the program can include the processes of the above-mentioned embodiment methods. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), or the like. In this application, the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present application. In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0158] Although the present application is disclosed as above, the protection scope of the present application is not limited to this. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application, and these changes and modifications will fall within the protection scope of the present application.

Claims

1. A method of arranging photovoltaic modules, characterized in that, The method comprises: acquiring a region image of a region where a photovoltaic module can be installed in a photovoltaic power station; sequentially performing image processing and grid division on the region image, and generating a plurality of points from all the grids obtained by the division, and determining a neighborhood of each of the points; scoring each of the neighborhoods by using a pre-trained evaluation model, to obtain a score value of each of the neighborhoods, wherein the evaluation model is used to evaluate the installability and power generation of a photovoltaic module in a region, the evaluation model is trained by using influence factor data as input data and a comprehensive index as a label, the influence factor data is geographic environment data whose correlation with the power generation and installability of a photovoltaic module is greater than a threshold value, and the comprehensive index is determined according to the power generation and installability of a photovoltaic module; generating a plurality of initial regions according to the score values of the neighborhoods based on a region growing algorithm, and determining a priority and an estimated installation capacity of each of the initial regions, each of the initial regions comprising at least one of the neighborhoods; determining an optimal installation region of a photovoltaic module according to an actual capacity requirement of the photovoltaic power station, the priority and the estimated installation capacity of each of the initial regions.

2. The photovoltaic module arrangement method of claim 1, wherein, The sequentially performing image processing and grid division on the region image comprises: performing contour extraction on the region image to obtain a contour of the region where the photovoltaic module can be installed; generating a circumscribed rectangle of the contour, and performing grid division on the circumscribed rectangle to obtain a plurality of grids.

3. The photovoltaic module arrangement method according to claim 1, wherein The generating a plurality of points from all the grids obtained by the division comprises: determining a proportion of an area in each of the grids that does not belong to the region where the photovoltaic module can be installed to a total area of the corresponding grid; eliminating, from all the grids, a grid whose proportion is greater than a first preset threshold value, to obtain screened grids; generating a plurality of points from the screened grids, all the points forming a point distribution map.

4. The photovoltaic module arrangement method according to claim 1, wherein Before the scoring each of the neighborhoods by using the pre-trained evaluation model, the method further comprises: acquiring geographic environment data of a plurality of regions in an existing power station, and power generation and installability of photovoltaic modules in each of the regions; performing correlation analysis on the geographic environment data and the power generation and installability of the photovoltaic modules, and determining influence factor data in the geographic environment data according to an analysis result; determining a comprehensive index of each of the regions according to the power generation and installability of the photovoltaic modules, and constructing a training data set according to the corresponding influence factor data and the comprehensive index; training a pre-established neural network by using the training data set, to obtain the trained evaluation model.

5. The photovoltaic module arrangement method according to claim 4, wherein The scoring each of the neighborhoods by using the pre-trained evaluation model comprises: acquiring the influence factor data of each of the neighborhoods; inputting the influence factor data into the evaluation model, and outputting the score value of each of the neighborhoods.

6. The photovoltaic module arrangement method according to any one of claims 1 to 5, characterized in that, After the obtaining the score value of each of the neighborhoods, the method further comprises: converting the score value into a gray value, representing each of the neighborhoods by using the corresponding gray value, and obtaining a score gray map.

7. The photovoltaic module arrangement method according to any one of claims 1 to 5, characterized in that, The generating a plurality of initial regions according to the score values of the neighborhoods based on the region growing algorithm comprises: sort all the neighborhoods according to the score values based on a preset sorting rule; select a plurality of the neighborhoods to generate a point set according to the sorting result, each point in the point set corresponding to one of the neighborhoods; select a plurality of points from the point set as initial seed points, and construct a seed point neighborhood for each initial seed point; for any initial seed point, determine a difference value between the score value of the initial seed point and the score value of each point in the corresponding seed point neighborhood, and fuse the point with the difference value less than a second preset threshold with the initial seed point to generate the initial region.

8. The photovoltaic module arrangement method according to any one of claims 1 to 5, wherein The determination of the priority and the estimated installation capacity of each initial region includes: determining an average value of the score values of all the neighborhoods in the initial region, and determining the priority of each initial region according to the average value; performing component pre-layout on each initial region, and determining the estimated installation capacity of each initial region according to the pre-layout result.

9. The photovoltaic module arrangement method according to any one of claims 1 to 5, wherein, The determination of the optimal installation region of the photovoltaic component according to the actual capacity demand of the photovoltaic power station, the priority and the estimated installation capacity of each initial region includes: selecting the initial regions in order of the priority from high to low according to the actual capacity demand of the photovoltaic power station and the estimated installation capacity of each initial region, and taking the initial regions as the optimal installation region of the photovoltaic component.

10. An arrangement for photovoltaic modules, characterized in that It includes: an acquisition module configured to acquire a region image of a region where a component can be installed in a photovoltaic power station; a processing module configured to sequentially perform image processing and grid division on the region image, and generate a plurality of points according to all the grids obtained by the division, and determine a neighborhood of each point; a scoring module configured to score each neighborhood by using a pre-trained evaluation model, and obtain a score value of each neighborhood, wherein the evaluation model is used to evaluate the installability and power generation of a photovoltaic component in a region, the evaluation model is trained by using influence factor data as input data and a comprehensive index as a label, the influence factor data is geographic environment data whose correlation analysis result with the power generation and installability of the photovoltaic component is greater than a threshold, and the comprehensive index is determined according to the power generation and installability of the photovoltaic component; a generation module configured to generate a plurality of initial regions according to the score values of the neighborhoods based on a region growing algorithm, and determine a priority and an estimated installation capacity of each initial region, wherein each initial region includes at least one neighborhood; an optimization module configured to determine an optimal installation region of a photovoltaic component according to the actual capacity demand of the photovoltaic power station, the priority and the estimated installation capacity of each initial region.

11. An electronic device, comprising: It includes a memory and a processor; the memory is configured to store a computer program; the processor is configured to implement the photovoltaic component arrangement method in any one of claims 1 to 9 when the computer program is executed.

Images