Method and system for acquiring height difference between installed photovoltaic panel supports, and storage medium

Abstract

Embodiments of the present description provide a method and system for acquiring a height difference between installed photovoltaic panel supports, and a storage medium. The method comprises: acquiring a target photovoltaic panel image at a preset time, the target photovoltaic panel image comprising a plurality of photovoltaic panels; on the basis of the target photovoltaic panel image, determining an actual shadow region of at least one photovoltaic panel; and on the basis of the actual shadow region, determining a height difference between a photovoltaic panel support corresponding to the actual shadow region and other photovoltaic panel supports. The system is configured to implement the method for acquiring a height difference between installed photovoltaic panel supports, and comprises: an acquisition module, configured to acquire a target photovoltaic panel image at a preset time, the target photovoltaic panel image comprising a plurality of photovoltaic panels; a first determination module, configured to determine, on the basis of the target photovoltaic panel image, an actual shadow region of at least one photovoltaic panel; and a second determination module, configured to determine, on the basis of the actual shadow region, a height difference between a photovoltaic panel support corresponding to the actual shadow region and other photovoltaic panel supports.

Description

Method, system and storage medium for obtaining height difference of installed photovoltaic panel support TECHNICAL FIELD

[0001] The present specification relates to the field of photovoltaic power generation, and in particular, to a method, system and storage medium for obtaining height difference of installed photovoltaic panel support. BACKGROUND

[0002] Photovoltaic assemblies for generating electricity are usually composed of a plurality of photovoltaic panels in series. If some photovoltaic panels in the series path are shaded and cannot generate electricity, it may cause other photovoltaic panels in the series path to also not work normally. Due to topographic reasons, construction errors, etc., the heights of photovoltaic panel supports after installation cannot be completely consistent, resulting in shading and blocking.

[0003] Therefore, it is desirable to provide a method, system and storage medium for obtaining height difference of installed photovoltaic panel support.

[0004] SUMMARY

[0005] One or more embodiments of the present specification provide a method for obtaining height difference of installed photovoltaic panel support, the method is executed by a processor, and the method comprises: obtaining a target photovoltaic panel image at a preset time, the target photovoltaic panel image comprising a plurality of photovoltaic panels; determining an actual shadow area of at least one photovoltaic panel based on the target photovoltaic panel image; and determining a height difference between a photovoltaic panel support corresponding to the actual shadow area and other photovoltaic panel supports based on the actual shadow area.

[0006] In some embodiments, the determining the height difference between the photovoltaic panel support corresponding to the actual shadow area and the other photovoltaic panel supports based on the actual shadow area comprises: determining the height difference based on a theoretical shadow area and the actual shadow area; the theoretical shadow area being a shadow area on the at least one photovoltaic panel corresponding to the actual shadow area when the height difference does not exist.

[0007] In some embodiments, the determining the theoretical shadow area comprises: determining a theoretical shadow length based on a solar elevation angle, an angle between a photovoltaic panel and a horizontal line, and a distance between a photovoltaic panel and a pile foundation; and determining the theoretical shadow area based on the theoretical shadow length.

[0008] In some embodiments, the shape of the actual shadow area comprises a rectangle and a trapezoid.

[0009] In some embodiments, when the shape of the actual shadow area is the trapezoid, the height difference is determined based on a lower base of the trapezoid.

[0010] In some embodiments, the determining the height difference between the photovoltaic panel support corresponding to the actual shadow area and other photovoltaic panel supports comprises: obtaining an actual shadow area of a first photovoltaic panel and an actual shadow area of a second photovoltaic panel; determining a height difference between a first photovoltaic support and a second photovoltaic support based on a ratio between the actual shadow area of the first photovoltaic panel and the actual shadow area of the second photovoltaic panel.

[0011] In some embodiments, the determining the height difference between the first photovoltaic support and the second photovoltaic support comprises: determining a reference ratio based on processing the ratio by a clustering algorithm; determining the height difference based on the reference ratio.

[0012] In some embodiments, the method further comprises: determining a height difference sequence based on at least one of the height differences; inputting the height difference sequence to a photovoltaic panel controller; and performing anti-shadow control based on the height difference sequence by the photovoltaic panel controller.

[0013] In some embodiments, the actual shadow area is composed of a first shadow area formed in a first direction and a second shadow area formed in a second direction.

[0014] In some embodiments, the determining the actual shadow area of at least one photovoltaic panel based on the target photovoltaic panel image comprises: processing the target photovoltaic panel image based on a shadow area recognition model to determine the actual shadow area, the shadow area recognition model being a machine learning model; and the shadow area recognition model being obtained by training.

[0015] In some embodiments, the shadow area recognition model is obtained by: obtaining a training sample, the training sample comprising training data and a label thereof, the training data comprising a sample photovoltaic panel image, and the label comprising an actual shadow area corresponding to the sample photovoltaic panel image; and training an initial shadow area recognition model based on the training sample to obtain the trained shadow area recognition model.

[0016] In some embodiments, the preset time comprises a first preset time and / or a second preset time, and the obtaining the target photovoltaic panel image at the preset time comprises: obtaining an overhead image of the at least one photovoltaic panel by a shooting device based on the first preset time and / or the second preset time; and determining the target photovoltaic panel image based on the overhead image to determine the actual shadow area.

[0017] One or more embodiments of the present specification provide a system for obtaining height difference of installed photovoltaic panel support, the system is used to implement a method for obtaining height difference of installed photovoltaic panel support, the system comprises: an obtaining module configured to obtain a target photovoltaic panel image at a preset time, the target photovoltaic panel image comprising a plurality of photovoltaic panels; a first determining module configured to determine an actual shadow area of at least one photovoltaic panel based on the target photovoltaic panel image; and a second determining module configured to determine a height difference between a photovoltaic panel support corresponding to the actual shadow area and other photovoltaic panel supports based on the actual shadow area.

[0018] In some embodiments, the second determining module is further configured to determine the height difference based on a theoretical shadow area and the actual shadow area, the theoretical shadow area being a shadow area on the at least one photovoltaic panel corresponding to the actual shadow area when the height difference does not exist.

[0019] In some embodiments, determining the theoretical shadow area comprises determining a theoretical shadow length based on a solar elevation angle, an angle between a photovoltaic panel and a horizontal line, and a distance between a photovoltaic panel and a pile foundation; and determining the theoretical shadow area based on the theoretical shadow length.

[0020] In some embodiments, the second determining module is further configured to obtain an actual shadow area of a first photovoltaic panel and an actual shadow area of a second photovoltaic panel; and determine a height difference between a first photovoltaic support and a second photovoltaic support based on a ratio between the actual shadow area of the first photovoltaic panel and the actual shadow area of the second photovoltaic panel.

[0021] In some embodiments, the system further comprises a control module configured to determine a height difference sequence based on at least one of the height differences, and input the height difference sequence to a photovoltaic panel controller; and the photovoltaic panel controller performs anti-shadow control based on the height difference sequence.

[0022] In some embodiments, the first determining module is further configured to determine the actual shadow area by processing the target photovoltaic panel image based on a shadow area recognition model, the shadow area recognition model being a machine learning model; and the shadow area recognition model is obtained by training.

[0023] In some embodiments, the preset time comprises a first preset time and / or a second preset time, and the obtaining module is further configured to obtain a top view image of the at least one photovoltaic panel by a shooting device based on the first preset time and / or the second preset time; and determine the target photovoltaic panel image based on the top view image, and determine the actual shadow area.

[0024] One or more embodiments of the present specification provide a computer readable storage medium, the storage medium stores computer instructions, when the computer reads the computer instructions in the storage medium, the computer executes the method for obtaining the height difference of the installed photovoltaic panel support. BRIEF DESCRIPTION OF DRAWINGS

[0025] The present specification will be further described in the manner of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same numbers refer to the same structures, wherein:

[0026] FIG. 1 is a schematic diagram of a system for obtaining the height difference of the installed photovoltaic panel support according to some embodiments of the present specification;

[0027] FIG. 2 is an exemplary flowchart of a system method for obtaining the height difference of the installed photovoltaic panel support according to some embodiments of the present specification;

[0028] FIG. 3 is a schematic diagram of determining the actual shadow area according to some embodiments of the present specification;

[0029] FIG. 4A is a schematic diagram of determining the theoretical shadow length according to some embodiments of the present specification;

[0030] FIG. 4B is a schematic diagram of determining the actual shadow length according to some embodiments of the present specification;

[0031] FIG. 5 is a top view schematic diagram of a photovoltaic panel according to some embodiments of the present specification. DETAILED DESCRIPTION

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some examples or embodiments of the present specification, and for those skilled in the art, the present specification can also be applied to other similar scenarios without creative labor on the basis of these drawings. Unless it is obvious from the language environment or otherwise stated, the same reference numbers in the drawings represent the same structure or operation.

[0033] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0034] As shown in the specification and claims, unless the context clearly indicates otherwise, the words "comprise", "comprising", "consist", "consisting", "include", "including", "contain", "containing", "one", "a", "an", and / or "the" do not exclude the presence of other steps, elements, steps and elements, methods and / or devices. In general, the term "comprising" should not be interpreted as implying the exclusion of other steps, elements, steps and elements, methods and / or devices.

[0035] Flowcharts in the present specification are used to illustrate the operations performed by the system according to the embodiments of the present specification. It should be understood that the preceding or subsequent operations are not necessarily performed in sequence. Instead, the steps can be processed in reverse order or simultaneously. Meanwhile, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0036] FIG. 1 is a schematic diagram of a system for acquiring height difference of installed photovoltaic panel support according to some embodiments of the present specification.

[0037] In some embodiments, the system 100 for acquiring height difference of installed photovoltaic panel support can include an acquisition module 110, a first determination module 120, and a second determination module 130.

[0038] In some embodiments, the acquisition module 110 can be configured to acquire a target photovoltaic panel image at a preset time.

[0039] In some embodiments, the acquisition module 110 can be further configured to acquire at least one overhead image of the photovoltaic panel based on the first preset time and / or the second preset time by using the photographing device; determine the target photovoltaic panel image based on the overhead image, and determine the actual shadow area.

[0040] In some embodiments, the first determination module 120 can be configured to determine the actual shadow area of the at least one photovoltaic panel based on the target photovoltaic panel image.

[0041] In some embodiments, the first determination module 120 can be further configured to process the target photovoltaic panel image based on a shadow area recognition model, and determine the actual shadow area.

[0042] In some embodiments, the second determination module 130 can be configured to determine the height difference between the photovoltaic panel support corresponding to the actual shadow area and other photovoltaic panel supports based on the actual shadow area.

[0043] In some embodiments, the second determination module 130 can be further configured to determine the height difference based on the theoretical shadow area and the actual shadow area; the theoretical shadow area is a shadow area on the at least one photovoltaic panel when there is no height difference.

[0044] In some embodiments, the second determining module 130 is further configured to determine a theoretical shadow length based on the solar elevation angle, the angle between the photovoltaic panel and the horizontal line, and the distance between the photovoltaic panel and the pile foundation; and determine a theoretical shadow area based on the theoretical shadow length.

[0045] In some embodiments, the second determining module 130 is further configured to obtain an actual shadow area of the first photovoltaic panel and an actual shadow area of the second photovoltaic panel; and determine the height difference between the first photovoltaic support and the second photovoltaic support based on a ratio between the actual shadow area of the first photovoltaic panel and the actual shadow area of the second photovoltaic panel.

[0046] In some embodiments, the system 100 for obtaining the height difference of the installed photovoltaic panel support can further include a control module 140.

[0047] The control module 140 can be configured to determine a height difference sequence based on the at least one height difference, and input the height difference sequence to a photovoltaic panel controller; and the photovoltaic panel controller performs anti-shadow control based on the height difference sequence.

[0048] For more information about the above-mentioned terms, such as, but not limited to, the time, the first preset time, the second preset time, the overhead image, the target photovoltaic panel image, the actual shadow area, the shadow area identification model, the height difference, the theoretical shadow area, the solar elevation angle, the angle between the photovoltaic panel and the horizontal line, the distance between the photovoltaic panel and the pile foundation, the theoretical shadow length, the first photovoltaic panel, the second photovoltaic panel, the first photovoltaic support, the second photovoltaic support, the clustering algorithm, the clustering center, the height difference sequence, the photovoltaic panel controller, and the anti-shadow control, please refer to FIG. 2, FIG. 3 and the related descriptions thereof.

[0049] It should be noted that the above description of the system for obtaining the height difference of the installed photovoltaic panel support and its modules is for the convenience of description only, and cannot limit the scope of the present specification to the embodiments. It can be understood that, for those skilled in the art, after understanding the principle of the system, the modules can be combined arbitrarily or connected to form a subsystem without departing from the principle. In some embodiments, the obtaining module 110, the first determining module 120, and the second determining module 130 disclosed in FIG. 1 can be different modules in a system, or can be a module to realize the functions of two or more modules described above. For example, the modules can share a storage module, and the modules can also have their own storage modules. Variations such as this are within the scope of protection of the present specification.

[0050] FIG. 2 is an exemplary flowchart of a system method for obtaining the height difference of the installed photovoltaic panel support according to some embodiments of the present specification. As shown in FIG. 2, the flow 200 includes the following steps. In some embodiments, the flow 200 can be executed by a processor.

[0051] At step 210, a target photovoltaic panel image is acquired at a preset time, and the target photovoltaic panel image includes a plurality of photovoltaic panels.

[0052] The preset time can refer to a time at which image acquisition is performed in advance. The preset time can be a time period, a time point, etc. For example, the preset time can be 08:00-10:30; for another example, the preset time can be 13:00. In some embodiments, the preset time can be set based on experience or demand.

[0053] In some embodiments, the preset time can include a first preset time and / or a second preset time. The first preset time can be set before the second preset time.

[0054] In some embodiments, the first preset time can be a sunrise time. For example, the first preset time can be 06:00. In some embodiments, the second preset time can be a sunset time. For example, the second preset time can be 18:00. It can be understood that the sunrise time and the sunset time will change with the change of place and season, and the above sunrise time and sunset time are only examples and are not intended to limit the scope of the present specification.

[0055] In some embodiments, the first preset time and the second preset time can be acquired in various ways. For example, the processor can acquire the first preset time and the second preset time based on input information of the user. For another example, the processor can acquire the first preset time and the second preset time based on a third-party platform, web crawling, etc.

[0056] The target photovoltaic panel image can refer to a related image of a photovoltaic panel that needs to be acquired. For example, an on-site image taken after installation of the photovoltaic panel. In some embodiments, the target photovoltaic panel image can include a plurality of photovoltaic panels.

[0057] The photovoltaic panel, also known as a solar panel, is a device that converts solar radiation energy into electrical energy and can be used for solar power generation. In some embodiments, a plurality of photovoltaic panels can be connected in series for power generation. For example, the anode and cathode of a plurality of photovoltaic panels can be connected in sequence. The specific series connection method can be preset according to the performance of the photovoltaic panel and the circuit design requirements.

[0058] In some embodiments, the processor can acquire the target photovoltaic panel image at the preset time in various ways. For example, the processor can acquire the target photovoltaic panel image by acquiring input information of the user at the preset time. For another example, the processor can acquire the target photovoltaic panel image by capturing the installation site of the photovoltaic panel at the preset time through a sensing device. The sensing device can include a shooting device (e.g., a camera, etc.), a flying sensing device (e.g., a drone, etc.), etc.

[0059] In some embodiments, the processor can acquire, based on the first preset time and / or the second preset time, a top-view image of the at least one photovoltaic panel by the photographing device; determine a target photovoltaic panel image based on the top-view image, and determine the actual shadow area.

[0060] The top-view image can refer to an image taken from a top-view angle.

[0061] In some embodiments, the processor can acquire, based on the first preset time and / or the second preset time, a top-view image of the at least one photovoltaic panel by the photographing device directly. For example, the processor can control a camera carried by a drone to take a photograph of the installation site of the photovoltaic panel from the sky at the first preset time and / or the second preset time, and acquire the top-view image of the at least one photovoltaic panel.

[0062] In some embodiments, the processor can determine the target photovoltaic panel image based on the top-view image in multiple ways. For example, the processor can determine the top-view image as the target photovoltaic panel image directly. For another example, the processor can pre-process the top-view image by software, models, etc., and determine the top-view image as the target photovoltaic panel image. The pre-processing can include, but is not limited to, Gaussian filtering, image denoising, image enhancement, etc.

[0063] In some embodiments, the processor can determine the actual shadow area based on the target photovoltaic panel image determined based on the top-view image. The specific determination method can be referred to in the relevant content described later, which will not be described here.

[0064] It can be understood that the area of the shadow cast by sunlight on the photovoltaic panel is the largest at sunrise and sunset. In some embodiments of the present specification, the top-view image of the at least one photovoltaic panel is acquired based on the first preset time and / or the second preset time by the photographing device; the actual shadow area is determined based on the top-view image, which can accurately and efficiently acquire the shadow area cast by sunlight on the photovoltaic panel at sunrise and sunset, and thus facilitate subsequent processing of the shadow area. If it can be ensured that there is no shadow on the photovoltaic panel at sunrise or sunset, i.e., the photovoltaic panel will not be shaded in the entire working process.

[0065] In step 220, the actual shadow area of the at least one photovoltaic panel is determined based on the target photovoltaic panel image.

[0066] It can be understood that when multiple photovoltaic panels are arranged in series, sunlight can project the previous photovoltaic panel onto the next photovoltaic panel, forming a shadow area.

[0067] The actual shadow area can refer to an actual shadow area on the photovoltaic panel. In some embodiments, the actual shadow area can be represented in various forms. For example, the actual shadow area can be represented by an actual shadow area parameter (e.g., an area, a length, a width, etc. of the actual shadow area); for another example, the actual shadow area can be represented by different color or pattern filling (e.g., equidistant diagonal line filling, etc.) on the target photovoltaic panel image.

[0068] In some embodiments, the actual shadow area can be composed of a first shadow area formed in a first direction and a second shadow area formed in a second direction.

[0069] The first direction can refer to a longitudinal direction, for example, the first direction can be a south-north direction, a z-axis direction in a three-dimensional coordinate system, etc. As shown in FIG. 4A, the first direction can be the A direction.

[0070] The second direction can refer to a transverse direction, for example, the second direction can be an east-west direction, an x-axis direction in a three-dimensional coordinate system, etc. The first direction and the second direction can be perpendicular to each other. As shown in FIG. 4A, the second direction can be the B direction (perpendicular to the paper).

[0071] It can be understood that when measuring the actual shadow area, not only the shadow blocking of the previous photovoltaic panel to the subsequent photovoltaic panel in the first direction under sunlight irradiation needs to be considered, but also the shadow blocking of the previous photovoltaic panel to the subsequent photovoltaic panel in the second direction under sunlight irradiation needs to be considered, and the two together constitute the actual shadow area of the previous photovoltaic panel to the subsequent photovoltaic panel.

[0072] The first shadow area can refer to a shadow area formed on the photovoltaic panel in the first direction under sunlight irradiation. The second shadow area can refer to a shadow area formed on the photovoltaic panel in the second direction under sunlight irradiation.

[0073] In some embodiments of the present specification, by setting the actual shadow area to be composed of the first shadow area formed in the first direction and the second shadow area formed in the second direction, the shadow area formed by sunlight irradiation in the south-north direction and the east-west direction can be considered, and the determination process of the actual shadow area can be ensured to be more accurate.

[0074] In some embodiments, the processor can determine the actual shadow area of the at least one photovoltaic panel based on the target photovoltaic panel image in various ways. For example, the processor can determine the actual shadow area of the at least one photovoltaic panel based on the target photovoltaic panel image through user input information (e.g., actual shadow area information labeled by the user, etc.). For another example, the processor can process the target photovoltaic panel image through a shadow detection algorithm (e.g., Mean Shift algorithm, etc.), software (e.g., Matlab software, etc.), a machine learning model (e.g., a deep neural network model, etc.) to determine the actual shadow area of the at least one photovoltaic panel.

[0075] In some embodiments, the processor can process the target photovoltaic panel image based on the shadow area identification model to determine the actual shadow area. More details about the shadow area identification model can be found in FIG. 3 and the related description thereof.

[0076] At step 230, based on the actual shadow area, the height difference between the photovoltaic panel support corresponding to the actual shadow area and other photovoltaic panel supports is determined.

[0077] The photovoltaic panel support refers to a special support for installing and supporting photovoltaic panels. In some embodiments, the photovoltaic panel support can include pile foundation, main beam, welding piece, etc.

[0078] The height difference can refer to the height difference between different photovoltaic panel supports.

[0079] It can be understood that due to uneven terrain, construction errors, etc., there are differences in the heights of multiple photovoltaic panel supports after installation, which can cause height differences in the first direction and the second direction, resulting in shadow blocking between multiple photovoltaic panels.

[0080] The photovoltaic panel support corresponding to the actual shadow area can refer to the photovoltaic panel support of the photovoltaic panel that produces the actual shadow area. The other photovoltaic panel support can refer to the photovoltaic panel support other than the photovoltaic panel support corresponding to the actual shadow area among the multiple photovoltaic panel supports. For example, as shown in FIG. 4A, the photovoltaic panel s1 produces an actual shadow area on the photovoltaic panel s2 (the area of the photovoltaic panel s2 located on the lower side of the sunlight irradiation path y), then the photovoltaic panel support of the photovoltaic panel s1 can be the photovoltaic panel support corresponding to the actual shadow area, the photovoltaic panel support of the photovoltaic panel s2 can be the other photovoltaic panel support, and the height difference between the photovoltaic panel support corresponding to the actual shadow area and the other photovoltaic panel support can be the height difference between the photovoltaic panel support of the photovoltaic panel s1 and the photovoltaic panel support of the photovoltaic panel s2.

[0081] In some embodiments, the processor can determine the height difference between the photovoltaic panel support corresponding to the actual shadow area and the other photovoltaic panel support in multiple ways based on the actual shadow area. For example, the processor can determine the height difference between the photovoltaic panel support corresponding to the actual shadow area and the other photovoltaic panel support based on the actual shadow area through a preset algorithm. The preset algorithm can include a corresponding relationship between the actual shadow area parameter and the height difference, which can be set based on experience. For example, the preset algorithm can be height difference = b x actual shadow area parameter, b is a constant set based on experience. For another example, the processor can determine the height difference between the photovoltaic panel support corresponding to the actual shadow area and the other photovoltaic panel support based on the actual shadow area through an algorithm, a machine learning model (such as a convolutional neural network model, etc.), etc.

[0082] In some embodiments, the processor can determine the height difference based on the theoretical shadow area and the actual shadow area.

[0083] In some embodiments, the theoretical shadow area is a shadow area on the at least one photovoltaic panel corresponding to the actual shadow area when there is no height difference. For example, as shown in FIG. 4B, if the actual shadow area is a shadow area of the photovoltaic panel s1 under sunlight irradiation projected onto the photovoltaic panel s2' (i.e., an area of the photovoltaic panel s2' located on the lower side of the sunlight irradiation path y); then the theoretical shadow area is a shadow area of the photovoltaic panel s1 projected onto the photovoltaic panel s2' when the height difference between the photovoltaic panel s1 and the photovoltaic panel s2' is 0 (i.e., a shadow area of the photovoltaic panel s1 projected onto the photovoltaic panel s2, which is shown as an area of the photovoltaic panel s2 located on the lower side of the sunlight irradiation path y).

[0084] In some embodiments, when the theoretical shadow area is smaller than the actual shadow area, the photovoltaic panel of the theoretical shadow area is higher than the photovoltaic panel of the actual shadow area. For example, as shown in FIG. 4B, when the theoretical shadow area is smaller than the actual shadow area, the photovoltaic panel s2 of the theoretical shadow area is higher than the photovoltaic panel s2' of the actual shadow area.

[0085] In some embodiments, the processor can obtain the theoretical shadow area in various ways. For example, the processor can obtain the theoretical shadow area through a preset theoretical algorithm. The preset theoretical algorithm can include a corresponding relationship between a measured parameter of the at least one photovoltaic panel (e.g., a length of the photovoltaic panel, a solar elevation angle, etc.) and a theoretical shadow area parameter (e.g., an area, a length, a width, etc. of the theoretical shadow area), which can be set based on experience. For example, the preset algorithm can be theoretical shadow area parameter = c x measured parameter of the at least one photovoltaic panel, where c is a constant set based on experience. For another example, the processor can determine the theoretical shadow area based on the measured parameter of the at least one photovoltaic panel through an algorithm, a machine learning model (e.g., a convolutional neural network model, etc.), etc.

[0086] In some embodiments, the processor can determine the theoretical shadow length based on the solar elevation angle, the angle between the photovoltaic panel and the horizontal line, and the distance between the photovoltaic panel and the pile foundation; and determine the theoretical shadow area based on the theoretical shadow length.

[0087] The theoretical shadow length can refer to the length of the theoretical shadow area on the photovoltaic panel. For example, as shown in FIG. 4A, the theoretical shadow area corresponding to the photovoltaic panel s1 is an area of the photovoltaic panel s2 located on the lower side of the sunlight irradiation path y; and the theoretical shadow length corresponding to the photovoltaic panel s1 can be q-w (where q is the length of the photovoltaic panel, and w is the length of the non-shadow area).

[0088] The solar elevation angle refers to the angle between the direction of sunlight incidence and the horizontal plane at a certain location on Earth. For example, as shown in FIG. 4A and FIG. 4B, the solar elevation angle is the angle β between the sunlight irradiation path y and the horizontal line z.

[0089] The pile foundation distance of the photovoltaic panel can refer to the distance between the pile foundations in different photovoltaic panel supports. For example, as shown in FIG. 4A, the pile foundation distance of the photovoltaic panel s1 and the photovoltaic panel s2 is P.

[0090] In some embodiments, the processor can determine the theoretical shadow length based on the geometric relationship between the solar elevation angle, the angle between the photovoltaic panel and the horizontal line, the pile foundation distance of the photovoltaic panel, and the theoretical shadow length. For example, as shown in FIG. 4A, y is the sunlight irradiation path, z is the horizontal line on which the upper edge of the theoretical shadow area on the photovoltaic panel s2 is located, x is the length of the photovoltaic panel s1 above the horizontal line z, w is the length of the photovoltaic panel s2 above the horizontal line z (i.e., the length of the photovoltaic panel s2 that is not blocked), q is the length of the photovoltaic panel (the length of the photovoltaic panel is the same), β is the solar elevation angle, α is the angle between the photovoltaic panel and the horizontal line, and P is the pile foundation distance of the photovoltaic panel. Since the height difference between the photovoltaic panel s1 and the photovoltaic panel s2 is 0, x = w. According to the geometric relationship x / sinα = P / (sin(180-α-β), the theoretical shadow length q-w = q-x = q-P*sinα / (sin(180-α-β).

[0091] In some embodiments, the processor can determine the theoretical shadow area based on the theoretical shadow length by a first preset condition. The first preset condition can be set based on the geometric relationship, experience, etc. For example, the first preset condition can be that the ratio of the theoretical shadow length to the length of the photovoltaic panel is the same as the ratio of the theoretical shadow area to the photovoltaic panel. For example, as shown in FIG. 4A, the processor can determine the theoretical shadow area of the photovoltaic panel q-w / q based on the above first preset condition.

[0092] In some embodiments of the present disclosure, the determination of the theoretical shadow length based on the solar elevation angle, the angle between the photovoltaic panel and the horizontal line, and the pile foundation distance of the photovoltaic panel, and the determination of the theoretical shadow area can be based on the geometric relationship between the existing measurement data, and the theoretical shadow area can be accurately and conveniently obtained.

[0093] In some embodiments, the processor can determine the height difference based on the theoretical shadow area and the actual shadow area by a second preset condition. The second preset condition can be set based on the geometric relationship, experience, etc. For example, the second preset condition can be that the ratio of the theoretical shadow area to the actual shadow area is the same as the ratio of the theoretical shadow length to the actual shadow length. The actual shadow length can refer to the length of the actual shadow area on the photovoltaic panel. For example, as shown in FIG. 4B, the actual shadow area corresponding to the photovoltaic panel s1 is the area of the photovoltaic panel s2' located below the sunlight irradiation path y; and the actual shadow length corresponding to the photovoltaic panel s1 can be q-w'.

[0094] As shown in FIG. 4B by way of example only, the processor can determine the actual shadow length q-w' based on the second preset condition, the theoretical shadow length, the theoretical shadow area, and the actual shadow area. Then, the processor can determine the height difference Ah=(w-w') / cos β based on the geometric relationship.

[0095] In some embodiments of the present disclosure, the determination of the height difference based on the theoretical shadow area and the actual shadow area can be based on known measurement data to determine an accurate height difference, which facilitates subsequent adjustment and elimination of the shadow.

[0096] In some embodiments, the shape of the actual shadow area can include a rectangle and a trapezoid. As shown in FIG. 5, the rectangle is a photovoltaic panel, and the area on the left side of the rectangle is the shape of the actual shadow area.

[0097] It can be understood that, due to the height difference between the photovoltaic panel supports in the first direction and the second direction, the actual shadow length in the first direction and the second direction is different. When the height difference exists only in the first direction (direction A in FIG. 5), the shape of the actual shadow area is a rectangle, i.e., the actual shadow length in the second direction (direction B in FIG. 5) is the same. When the height difference exists in both the first direction and the second direction, the shape of the actual shadow area is a trapezoid, i.e., the actual shadow length in the second direction is different.

[0098] In some embodiments, when the shape of the actual shadow area is a trapezoid, the processor can determine the height difference based on the lower base of the trapezoid.

[0099] The lower base can refer to the longer side of the trapezoid among the two parallel sides.

[0100] In some embodiments, when the shape of the actual shadow area is a trapezoid, the processor can determine the lower base of the trapezoid as the actual shadow length, and then determine the height difference based on the second preset condition. The specific determination method is described above and will not be repeated here.

[0101] In some embodiments of the present disclosure, when the shape of the actual shadow area is a trapezoid, the lower base of the trapezoid is the longest actual shadow length in the first direction, and the height difference between the photovoltaic panels determined based on the lower base is also the largest height difference in the first direction. Based on this height difference, the adjustment and anti-shadow control can completely eliminate the shadow on the photovoltaic panel and improve the anti-shadow effect in complex terrain.

[0102] In some embodiments of the present disclosure, by setting the shape of the actual shadow area to include a rectangle and a trapezoid, various cases of the height difference in the first direction and the second direction can be fully considered, which is conducive to accurate determination of the height difference.

[0103] In some embodiments, the processor can acquire an actual shadow area of the first photovoltaic panel and an actual shadow area of the second photovoltaic panel; determine a height difference between the first photovoltaic support and the second photovoltaic support based on a ratio between the actual shadow area of the first photovoltaic panel and the actual shadow area of the second photovoltaic panel.

[0104] The first photovoltaic panel and the second photovoltaic panel can refer to photovoltaic panels adjacent to each other, wherein the first photovoltaic panel can be located in front of the second photovoltaic panel in a first direction.

[0105] In some embodiments, the processor can determine the height difference between the first photovoltaic support and the second photovoltaic support through a geometric relationship based on a ratio between the actual shadow area of the first photovoltaic panel and the actual shadow area of the second photovoltaic panel.

[0106] In some embodiments, the processor can determine a reference ratio by processing the ratio based on a clustering algorithm; determine the height difference based on the reference ratio.

[0107] The type of clustering algorithm can include a plurality of types, for example, the clustering algorithm can include K-Means clustering, density-based clustering method (DBSCAN), etc.

[0108] The reference ratio can refer to the ratio used for determining the height difference after clustering.

[0109] In some embodiments, the processor can determine at least one cluster center by processing the ratio based on a clustering algorithm. The at least one cluster center serves as the reference ratio. For example, the processor can process the ratio between the actual shadow area of the photovoltaic panel 1 and the actual shadow area of the photovoltaic panel 2, …, the ratio between the actual shadow area of the photovoltaic panel n-1 and the actual shadow area of the photovoltaic panel n based on the clustering algorithm to obtain three cluster centers a1, a2 and a3, take the three cluster centers as the reference ratio, and group the photovoltaic support corresponding to the reference ratio into three groups based on the cluster center.

[0110] In some embodiments, the processor can determine the height difference between the grouped photovoltaic supports through a geometric relationship based on the reference ratio. The specific determination method is referred to the foregoing related content, which will not be described here.

[0111] In some embodiments of the present specification, the reference ratio is determined by processing the ratio based on a clustering algorithm; the height difference is determined based on the reference ratio, which can cluster and group the photovoltaic panels with smaller changes in the actual shadow area, determine the height difference based on the grouped result, and improve the calculation efficiency of the height difference.

[0112] In some embodiments of the present disclosure, by acquiring the actual shadow area of the first photovoltaic panel and the actual shadow area of the second photovoltaic panel, and determining the height difference between the first photovoltaic support and the second photovoltaic support based on the ratio of the two, the related calculation of the theoretical shadow area can be simplified, and the actual height difference data can be obtained by taking the actual data as the standard.

[0113] In some embodiments, the processor can determine a height difference sequence based on the at least one height difference, and input the height difference sequence to a photovoltaic panel controller; the photovoltaic panel controller performs anti-shadow control based on the height difference sequence.

[0114] The height difference sequence can refer to a sequence formed by a plurality of height differences in the order of arrangement of the photovoltaic panels in the first direction. The height difference sequence can be represented by a vector. For example, the height difference between the photovoltaic panel 1 and the photovoltaic panel 2 is +Am, the height difference between the actual shadow area of the photovoltaic panel 2 and the photovoltaic panel 3 is -Bm, …, the height difference between the actual shadow area of the photovoltaic panel n-1 and the photovoltaic panel n is 0m, and the height difference sequence can be represented as (+A, -B, …, 0). Wherein, the positive sign indicates that the height of the next photovoltaic panel exceeds that of the previous photovoltaic panel; the negative sign indicates that the height of the next photovoltaic panel is lower than that of the previous photovoltaic panel.

[0115] The photovoltaic panel controller can refer to a photovoltaic panel control device used for anti-shadow control.

[0116] The anti-shadow control can refer to a control method for eliminating the shadow between the photovoltaic panels. In some embodiments, the anti-shadow control can include a control method of reducing the height difference between the photovoltaic panels.

[0117] In some embodiments, the photovoltaic panel controller can adjust the height of the photovoltaic panel in sequence based on the height difference sequence to perform anti-shadow control. For example, the photovoltaic panel controller can reduce the height of the photovoltaic panel 2 by Am, reduce the height of the photovoltaic panel 3 by A-Bm, …, reduce the height of the photovoltaic panel n by A-B+…+0m based on the height difference sequence (+A, -B, …, 0) to perform anti-shadow control.

[0118] In some embodiments, the processor can process the height difference based on a clustering algorithm to determine at least one cluster center. The at least one cluster center serves as a reference height difference to form a reference height difference sequence for subsequent anti-shadow control. For example, the processor can process the height difference between the photovoltaic panel 1 and the photovoltaic panel 2, …, the height difference between the photovoltaic panel n-1 and the photovoltaic panel n based on the clustering algorithm to obtain four cluster centers b1, -b2, +b3, -b4, take the four cluster centers as the reference height difference to form the reference height difference sequence (+b1, -b2, +b3, -b4), and divide the photovoltaic panels corresponding to the reference height difference into 4 groups based on the cluster center.

[0119] In some embodiments, the processor can adjust the height of the grouped photovoltaic panels based on the reference height difference sequence to implement the anti-shadowing control. For example, the processor can lower the height of the photovoltaic panels in the photovoltaic panel group 1 by b1m, lower the height of the photovoltaic panels in the photovoltaic panel group 2 by b1-b2m, lower the height of the photovoltaic panels in the photovoltaic panel group 3 by b1-b2+b3m, and lower the height of the photovoltaic panels in the photovoltaic panel group 4 by b1-b2+b3-b4m based on the reference height difference sequence (+b1, -b2, +b3, -b4).

[0120] In some embodiments of the present specification, the height difference sequence is determined based on the at least one height difference, the height difference sequence is input to the photovoltaic panel controller to implement the anti-shadowing control, and the accurate height difference adjustment of the photovoltaic panels can be implemented based on the obtained height difference sequence to ensure the effect of the anti-shadowing control.

[0121] In some embodiments of the present specification, the actual shadow area of at least one photovoltaic panel is determined by obtaining the target photovoltaic panel image at a preset time, and the height difference between the photovoltaic panel support corresponding to the actual shadow area and other photovoltaic panel supports is determined. The effect of determining the height difference to eliminate the shadow can be achieved by using the unmanned aerial vehicle to take a photo only once, and the cost is low. In addition, the effects of the longitudinal and transverse height differences on the shadow are considered at the same time to ensure the accuracy and effectiveness of the height difference result between the photovoltaic panels. The height difference between the photovoltaic panels is calculated by the machine learning model, so that the determination process of the height difference is efficient and accurate.

[0122] FIG. 3 is a schematic diagram illustrating the determination of the actual shadow area according to some embodiments of the present specification.

[0123] In some embodiments, the processor can process the target photovoltaic panel image based on the shadow area identification model 320 to determine the actual shadow area.

[0124] The shadow area identification model 320 can be a machine learning model. The type of the shadow area identification model 320 can be various. For example, the demand model can include a neural network model (Neural Network, NN), a deep neural network (Deep Neural Network, DNN) model, a convolutional neural network (Convolutional Neural Network, CNN) model, or the like or any combination thereof.

[0125] In some embodiments, the input of the shadow area identification model 320 can be the target photovoltaic panel image 310, and the output of the shadow area identification model 320 can be the actual shadow area 330. More details about the target photovoltaic panel image and the actual shadow area can be found in FIG. 2 and the related description thereof.

[0126] In some embodiments, the shadow area identification model 320 can be obtained by training.

[0127] In some embodiments, the processor can obtain training samples; train the initial shadow area identification model 350 based on the training samples to obtain the trained shadow area identification model 320.

[0128] In some embodiments, the training samples can include training data and labels thereof; the training data can include sample photovoltaic panel images 341; and the labels can include actual shadow areas 342 corresponding to the sample photovoltaic panel images 341.

[0129] In some embodiments, the processor can obtain the training samples in various ways. For example, the processor can obtain the training data in the training samples from historical data. Illustratively, the processor can obtain historical photovoltaic panel images as sample photovoltaic panel images from the historical data to determine the training data in the training samples. For another example, the processor can obtain the labels in the training samples from manual annotation. Illustratively, the processor can obtain the actual shadow areas in the aforementioned sample photovoltaic panel images annotated manually as the labels in the training samples.

[0130] In some embodiments, the processor can train the initial shadow area identification model 350 based on the training samples to determine the shadow area identification model 320. In some embodiments, the processor can input the training samples to the initial shadow area identification model 350, and establish a loss function based on the labels and the output results of the initial shadow area identification model 350 to update the parameters of the initial shadow area identification model 350. When the loss function of the initial shadow area identification model 350 meets a preset condition, the model training is completed, and the shadow area identification model 320 is determined. The preset condition can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0131] The actual shadow area is affected by many information features, which are not sufficient to determine the actual shadow area alone or through simple rules. Based on the shadow area identification model to determine the actual shadow area described in some embodiments of the present specification, the actual shadow area can be determined based on a large amount of and extensive information features, breaking the limitations of traditional rule-based determination of the actual shadow area. Based on the rule-based method, limited by its complexity, only a small amount of information features can be used, and the accuracy of the actual shadow area is difficult to obtain due to the limitation of human-defined rules. However, based on the machine learning technology for prediction, more and richer information features can be used for training, and the accuracy of the determined actual shadow area can be higher.

[0132] One or more embodiments of this specification also provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for obtaining the height difference of the installed photovoltaic panel support as described in any of the above embodiments.

[0133] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0134] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Additionally, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0135] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0136] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0137] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0138] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0139] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method of acquiring installed photovoltaic panel rack height differences, the method performed by a processor, characterized by, The method comprises: acquiring a target photovoltaic panel image at a preset time, the target photovoltaic panel image comprising a plurality of photovoltaic panels; determining an actual shadow area of at least one photovoltaic panel based on the target photovoltaic panel image; determining a height difference between a photovoltaic panel support corresponding to the actual shadow area and other photovoltaic panel supports based on the actual shadow area.

2. The method of claim 1, wherein, The determination of the height difference between the photovoltaic panel support corresponding to the actual shadow area and the other photovoltaic panel supports based on the actual shadow area comprises: determining the height difference based on a theoretical shadow area and the actual shadow area, the theoretical shadow area being a shadow area on the at least one photovoltaic panel corresponding to the actual shadow area in the absence of the height difference.

3. The method of claim 2, wherein, The determination of the theoretical shadow area comprises: determining a theoretical shadow length based on a solar elevation angle, an angle between a photovoltaic panel and a horizontal line, and a distance between a photovoltaic panel and a pile foundation; determining the theoretical shadow area based on the theoretical shadow length.

4. The method of claim 1, wherein, The shape of the actual shadow area comprises a rectangle and a trapezoid.

5. The method of claim 4, wherein, When the shape of the actual shadow area is the trapezoid, the height difference is determined based on a lower base of the trapezoid.

6. The method of claim 1, wherein, The determination of the height difference between the photovoltaic panel support corresponding to the actual shadow area and the other photovoltaic panel supports comprises: acquiring an actual shadow area of a first photovoltaic panel and an actual shadow area of a second photovoltaic panel; determining a height difference between a first photovoltaic support and a second photovoltaic support based on a ratio between the actual shadow area of the first photovoltaic panel and the actual shadow area of the second photovoltaic panel.

7. The method of claim 6, wherein, The determination of the height difference between the first photovoltaic support and the second photovoltaic support comprises: processing the ratio based on a clustering algorithm to determine a reference ratio; determining the height difference based on the reference ratio.

8. The method of claim 1, wherein, The method further comprises: determining a height difference sequence based on at least one of the height differences, and inputting the height difference sequence to a photovoltaic panel controller; the photovoltaic panel controller performing anti-shadow control based on the height difference sequence.

9. The method of claim 1, wherein, The actual shadow area is composed of a first shadow area formed in a first direction and a second shadow area formed in a second direction.

10. The method of claim 1, wherein, The determination of the actual shadow area of the at least one photovoltaic panel based on the target photovoltaic panel image comprises: processing the target photovoltaic panel image based on a shadow area identification model to determine the actual shadow area, the shadow area identification model being a machine learning model; the shadow area identification model being obtained through training.

11. The method of claim 10, wherein, The shadow area identification model is obtained by: acquiring training samples, the training samples comprising training data and labels thereof, the training data comprising sample photovoltaic panel images, and the labels comprising actual shadow areas corresponding to the sample photovoltaic panel images; training an initial shadow area identification model based on the training samples to obtain the trained shadow area identification model.

12. The method of claim 1, wherein, The preset time comprises a first preset time and / or a second preset time, and the acquisition of the target photovoltaic panel image at the preset time comprises: acquiring a top view image of the at least one photovoltaic panel through a shooting device based on the first preset time and / or the second preset time; Determine the target photovoltaic panel image based on the overhead image, and determine the actual shadow area.

13. A system for acquiring installed photovoltaic panel rack height differences, characterized by The system is used to implement the method for obtaining the height difference of the installed photovoltaic panel support, and the system comprises: An acquisition module is configured to obtain a target photovoltaic panel image at a preset time, wherein the target photovoltaic panel image comprises a plurality of photovoltaic panels. A first determination module is configured to determine an actual shadow area of at least one photovoltaic panel based on the target photovoltaic panel image. A second determination module is configured to determine a height difference between a photovoltaic panel support corresponding to the actual shadow area and other photovoltaic panel supports based on the actual shadow area.

14. The system of claim 13, wherein, The second determination module is further configured to: Determine the height difference based on a theoretical shadow area and the actual shadow area, wherein the theoretical shadow area is a shadow area on the at least one photovoltaic panel corresponding to the actual shadow area when the height difference does not exist.

15. The system of claim 14, wherein, The determination of the theoretical shadow area comprises: Determine a theoretical shadow length based on a solar elevation angle, an angle between a photovoltaic panel and a horizontal line, and a distance between a photovoltaic panel and a pile foundation. Determine the theoretical shadow area based on the theoretical shadow length. The second determination module is further configured to:

16. The system of claim 13, wherein, Obtain an actual shadow area of a first photovoltaic panel and an actual shadow area of a second photovoltaic panel. Determine a height difference between a first photovoltaic support and a second photovoltaic support based on a ratio between the actual shadow area of the first photovoltaic panel and the actual shadow area of the second photovoltaic panel. The system further comprises:

17. The system of claim 13, wherein, A control module is configured to determine a height difference sequence based on at least one of the height differences, and input the height difference sequence to a photovoltaic panel controller. The photovoltaic panel controller performs anti-shadow control based on the height difference sequence. The first determination module is further configured to:

18. The system of claim 13, wherein, Determine the actual shadow area by processing the target photovoltaic panel image based on a shadow area recognition model, wherein the shadow area recognition model is a machine learning model, and the shadow area recognition model is obtained through training. The preset time comprises a first preset time and / or a second preset time, and the acquisition module is further configured to:

19. The method of claim 13, wherein, Obtain an overhead image of the at least one photovoltaic panel based on the first preset time and / or the second preset time through a shooting device. Determine the target photovoltaic panel image based on the overhead image, and determine the actual shadow area. 20.A computer readable storage medium, wherein the storage medium stores computer instructions, and when a computer reads the computer instructions in the storage medium, the computer executes the method for obtaining the height difference of the installed photovoltaic panel support according to any one of claims 1 to 12. ​

Images