Photovoltaic tracking support control method, device, system, equipment and program product

Abstract

The application discloses a photovoltaic tracking support control method, device, system, equipment and program product, and relates to the technical field of photovoltaic power generation. After obtaining a photovoltaic array image, an image recognition technology is used to identify a first shadow area of the photovoltaic array image, and a second shadow area caused by terrain undulation in the photovoltaic array is determined according to a digital elevation model of photovoltaic array arrangement and a sun position. The occluded area of the photovoltaic array is accurately evaluated by combining the first shadow area and the second shadow area, so that the maximum unoccluded area of the photovoltaic array is taken as an optimization target, the photovoltaic tracking support corresponding to the photovoltaic array is individually and accurately controlled, the power generation efficiency of the photovoltaic array is improved, and the overall power generation efficiency of the photovoltaic power station is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic power generation, and particularly to a photovoltaic tracking support control method, device, system, equipment and program product. BACKGROUND

[0002] With the increasing demand for renewable energy worldwide, photovoltaic power generation, as a clean and sustainable form of energy, has been widely used. Photovoltaic tracking systems adjust the orientation of photovoltaic arrays to always face the sun, thereby maximizing the collection efficiency of solar energy.

[0003] The photovoltaic tracking system usually calculates the position of the sun according to the date or the location of the photovoltaic tracking system, and adjusts the angle of the photovoltaic tracking support. This method works well in flat terrain, but in mountainous environments, complex shadow changes are caused by terrain obstruction. The way of adjusting the angle of the photovoltaic tracking support according to the position of the sun cannot adapt to such shadow changes, affecting the power generation efficiency. SUMMARY

[0004] In view of the above problems, the present application provides a photovoltaic tracking support control method, device, system, equipment and program product. The specific scheme is as follows:

[0005] The first aspect of the present application provides a photovoltaic tracking support control method, comprising:

[0006] obtaining a photovoltaic array image;

[0007] identifying a first shadow area of the photovoltaic array image;

[0008] determining a second shadow area of the photovoltaic array according to a digital elevation model of the photovoltaic array arrangement and a position of the sun;

[0009] adjusting the angle of the photovoltaic tracking support corresponding to the photovoltaic array according to the first shadow area and the second shadow area, with the maximum unshaded area of the photovoltaic array as the optimization target.

[0010] In one possible implementation, the identification of the first shadow area of the photovoltaic array image comprises:

[0011] adopting a quadtree segmentation algorithm to identify photovoltaic panels in the photovoltaic array image;

[0012] using the maximum inter-class variance method to identify the shadow area on the photovoltaic panels;

[0013] correcting the boundary of the shadow area on the photovoltaic panels by a sub-pixel gradient matching method to obtain the first shadow area.

[0014] In a possible implementation, the determining, according to the digital elevation model and the solar position, of the second shadow area of the photovoltaic array includes:

[0015] The solar ray is converted into a three-dimensional vector according to the solar position.

[0016] For each grid point of the photovoltaic array in the digital elevation model, if there is an obstruction along the direction of the solar ray irradiating on the grid point, the grid point is located in the second shadow area.

[0017] In a possible implementation, the adjusting, according to the first shadow area and the second shadow area, of the angle of the photovoltaic tracking support corresponding to the photovoltaic array with the maximum unobstructed area of the photovoltaic array as an optimization target includes:

[0018] A target function is constructed, the target function being a weighted difference value of a first subfunction and a second subfunction, the first subfunction representing the number of unobstructed grid points in the photovoltaic array, and the second subfunction representing the number of obstructed grid points corresponding to the overlapping area of the first shadow area and the second shadow area.

[0019] The angle of the photovoltaic tracking support is adjusted by using a genetic algorithm to maximize the target function.

[0020] In a possible implementation, the adjusting, by using a genetic algorithm, of the angle of the photovoltaic tracking support to maximize the target function includes:

[0021] The number of grid points of the photovoltaic array is used as a population size, and a binary gene of a grid point represents whether the grid point is obstructed, and the population is initialized according to the first shadow area and the second shadow area.

[0022] The fitness of the population is calculated according to the target function.

[0023] The fitness of the population is iteratively calculated by adjusting the angle of the photovoltaic tracking support by a preset step size, and the weights of the first subfunction and the second subfunction are adjusted in the iteration process.

[0024] In a case where the iterative calculation ends, the adjustment of the angle of the photovoltaic tracking support is stopped.

[0025] In a possible implementation, the photovoltaic tracking support control method further includes:

[0026] In a case where an image of a target photovoltaic array is not collected, the first shadow area of the photovoltaic array image is determined as the first shadow area of the target photovoltaic array, the target photovoltaic array being a photovoltaic array consistent with the orientation and slope change of the photovoltaic array.

[0027] In a possible implementation, the photovoltaic tracking support control method further includes:

[0028] determining a visual shadow state of each grid point in the target photovoltaic array according to a first shadow area of the target photovoltaic array;

[0029] determining an elevation shadow state of each grid point in the target photovoltaic array according to a second shadow area of the target photovoltaic array;

[0030] for each grid point in the target photovoltaic array, determining a shading weight of the grid point at different solar angles in a day according to the visual shadow state and the elevation shadow state of the grid point at different solar angles in a day;

[0031] determining a target shading probability of the grid point according to an initial shading probability of the grid point at different solar angles in a day and the shading weight.

[0032] In a possible implementation, the photovoltaic tracking support control method further includes:

[0033] calculating a root mean square error of an overlapping area of the first shadow area and the second shadow area;

[0034] in a case where the root mean square error is not less than a threshold value, obtaining a first grid point and a second grid point in the photovoltaic array, wherein the first grid point is located in the first shadow area and not in the second shadow area, and the second grid point is located in the second shadow area and not in the first shadow area;

[0035] correcting elevation data of a grid point after the first grid point in a direction of a sunlight ray, and correcting elevation data of a grid point before the second grid point in the direction of the sunlight ray, until the root mean square error is less than the threshold value.

[0036] The second aspect of the present application provides an edge computing device, comprising at least one processor and a memory connected with the processor, wherein:

[0037] the memory is configured to store a computer program;

[0038] the processor is configured to execute the computer program, so that the edge computing device can implement the photovoltaic tracking support control method in the first aspect or any implementation manner of the first aspect.

[0039] The third aspect of the present application provides a photovoltaic tracking support control system, comprising: an image acquisition device, a photovoltaic support driving device, and an edge computing device;

[0040] The image acquisition device is configured to acquire a photovoltaic array image and send the photovoltaic array image to the edge computing device.

[0041] The photovoltaic support driving device comprises a communication control unit and a plurality of tracking controllers.

[0042] The plurality of tracking controllers are respectively configured to control corresponding photovoltaic tracking supports in response to control instructions issued by the edge computing device.

[0043] The plurality of tracking controllers comprise a master tracking controller and a plurality of slave tracking controllers, and each of the slave tracking controllers is communicatively connected to the master tracking controller.

[0044] The master tracking controller communicates with the edge computing device through the communication control unit.

[0045] The edge computing device is configured to execute the photovoltaic tracking support control method of the first aspect or any implementation manner of the first aspect.

[0046] The fourth aspect of the present application provides a computer program product comprising computer readable instructions, which, when executed on an edge computing device, cause the edge computing device to implement the photovoltaic tracking support control method of the first aspect or any implementation manner of the first aspect.

[0047] The fifth aspect of the present application provides a computer storage medium carrying one or more computer programs, which, when executed by an edge computing device, can cause the edge computing device to implement the photovoltaic tracking support control method of the first aspect or any implementation manner of the first aspect.

[0048] By the above technical solution, the photovoltaic tracking support control method, device, system, equipment and program product provided by the present application can, after acquiring a photovoltaic array image, identify a first shadow area of the photovoltaic array image using image recognition technology, determine a second shadow area of the photovoltaic array caused by terrain undulations according to a digital elevation model of the photovoltaic array arrangement and a solar position, accurately evaluate a shadowed area of the photovoltaic array by combining the first shadow area and the second shadow area, and thus take the maximum unshadowed area of the photovoltaic array as an optimization target to individually and accurately control photovoltaic tracking supports corresponding to the photovoltaic array, thereby improving the power generation efficiency of the photovoltaic array and the overall power generation efficiency of the photovoltaic power station. BRIEF DESCRIPTION OF DRAWINGS

[0049] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The same or similar components have the same or similar reference labels. It should be understood that the drawings are schematic and elements and features not essential to the understanding of the application are omitted from the drawings so as not to obscure the concepts underlying the present application.

[0050] Figure 1 A schematic diagram of a photovoltaic tracking support control system provided by an embodiment of the present application;

[0051] Figure 2 A schematic diagram of a camera measurement point layout for a ridge terrain provided by an embodiment of the present application;

[0052] Figure 3 A schematic diagram of a camera measurement point layout for a valley terrain provided by an embodiment of the present application;

[0053] Figure 4 A schematic diagram of a flow of a photovoltaic tracking support control method provided by an embodiment of the present application;

[0054] Figure 5 A schematic diagram of a shadow length on a photovoltaic panel provided by an embodiment of the present application;

[0055] Figure 6 A schematic diagram of a check of an obstruction detected by a camera and an obstruction detected based on a digital elevation model provided by an embodiment of the present application. DETAILED DESCRIPTION

[0056] The embodiments of the present application are described below in conjunction with the accompanying drawings. The terms used in the embodiments section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0057] The embodiments of the present application are described below in conjunction with the accompanying drawings. It is known to those skilled in the art that, as technology develops and new scenarios appear, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0058] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged, and this is only a distinguishing way used in the description of the embodiments of the present application to describe the objects with the same attributes. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that the processes, methods, systems, products, or equipment containing a series of units are not necessarily limited to those units, but can include other units not clearly listed or inherent to these processes, methods, products, or equipment.

[0059] In a flexible tracking support photovoltaic power station, photovoltaic arrays are usually laid in the north-south direction, and the tracking angle of the photovoltaic arrays is adjusted in the east-west direction. Laying photovoltaic arrays on mountainous terrain is more complex than laying photovoltaic arrays on flat ground, and there is a problem of large differences in shadow shielding of different photovoltaic arrays.

[0060] Embodiments of the present application provide a photovoltaic tracking support control system, which can be applied to a flexible tracking support photovoltaic power station in a mountainous scene, and is particularly suitable for a scene where trees, mountain undulations, temporary obstacles, etc. cause uneven distribution of photovoltaic array shadows. Referring to Figure 1 , Figure 1 A structural schematic diagram of a photovoltaic tracking support control system provided by embodiments of the present application is provided, which includes an image acquisition device (for example, a camera is taken as an example in the description), a photovoltaic support driving device, and an edge computing device. Figure 1 The image acquisition device is used to acquire photovoltaic array images and send the photovoltaic array images to the edge computing device.

[0061] The photovoltaic support driving device includes a communication control unit and a plurality of tracking controllers.

[0062] The plurality of tracking controllers are respectively used to control corresponding photovoltaic tracking supports in response to control instructions issued by the edge computing device.

[0063] The plurality of tracking controllers include one master tracking controller and a plurality of slave tracking controllers, and each slave tracking controller is in communication connection with the master tracking controller, and the communication mode can be any existing master-slave controller communication mode.

[0064] The master tracking controller communicates with the edge computing device through the communication control unit.

[0065] The edge computing device is used for any photovoltaic tracking support control method provided by embodiments of the present application.

[0066] The photovoltaic array can be an end column, and the image acquisition device support is fixed by a hoop column. The image acquisition device support is above the photovoltaic array (the installation height is determined according to on-site monitoring coverage), and a 180-degree rotatable gun-type visible light camera can be installed, for example. The camera can capture part of the photovoltaic array image in real time through a 180-degree rotation shooting angle on the board.

[0067]

[0068] ​Generally, the photovoltaic array layout (in the northern hemisphere) is to select the south side of the mountain, and the photovoltaic panel is laid in the north-south direction, and the photovoltaic panel inclination (i.e. the photovoltaic tracking support angle) is adjusted in the east-west direction to realize light tracking. The image acquisition device is usually laid at the south end of the photovoltaic array, and the ridge or valley and other special topography is selected to monitor the photovoltaic array in real time from the south to the north. The north-south length of the photovoltaic array group affects the visual distance and resolution selection of the image acquisition device. Among them, the camera measurement point layout of the ridge topography is as shown in Figure 2 , Figure 3 .

[0069] In one possible implementation, in order to balance economy and practicability, the image acquisition device usually monitors the first cross-group string at the south end of the photovoltaic array, and the remaining group strings north of the same array can be calculated by the digital elevation model of the photovoltaic array, or special areas such as gullies and array edges need to add image acquisition devices.

[0070] The embodiment of the present application provides a photovoltaic tracking support control method. The photovoltaic tracking support control method of the embodiment of the present application will be described in detail below with reference to the drawings.

[0071] Referring to Figure 4 , Figure 4 , the flowchart of the photovoltaic tracking support control method provided by the embodiment of the present application is shown in Figure 4 , the photovoltaic tracking support control method provided by the embodiment of the present application can include steps 401 to 404, which will be described in detail below.

[0072] 401: Obtain a photovoltaic array image;

[0073] The photovoltaic array image is collected by an image acquisition device.

[0074] One image acquisition device is responsible for multiple row string coverage inspection (180° camera rotation angle inspection), and multiple array images are obtained through image acquisition device inspection.

[0075] The photovoltaic array image here can be an image that has been subjected to Gaussian filter denoising and / or histogram equalization enhancement.

[0076] 402: Identify a first shadow area of the photovoltaic array image;

[0077] The photovoltaic array includes multiple rows of photovoltaic group strings. Taking the south-north arrangement of the tracking support as an example, the photovoltaic group strings are numbered in a fixed direction, such as from east to west, during the photovoltaic array layout design. After obtaining the photovoltaic array image, the photovoltaic row string number can be identified and labeled. For example, Figure 5The length of the shadow on the photovoltaic panel is shown, where I represents the pixel length of the photovoltaic panel at the visual focus point, d1 and d2 represent the pixel length of the two shadow inflection points on the photovoltaic panel to the lateral edge of the shadow side photovoltaic panel, that is, the pixel length of the shadow inflection point on the photovoltaic panel at the visual focus point, s represents the pixel length of the shadow inflection point on the photovoltaic panel to the longitudinal edge of the shadow side photovoltaic panel, according to the camera inspection angle, focal point distance and real size of the photovoltaic panel, the real photovoltaic panel transverse size of the target photovoltaic panel is inferred and the image size mapping ratio is identified. The length of the key inflection point of the shadow area on the board.

[0078] The first shadow area of the photovoltaic array image is identified by using image recognition technology.

[0079] 403: According to the digital elevation model of the photovoltaic array arrangement and the position of the sun, the second shadow area of the photovoltaic array is determined;

[0080] Based on the digital terrain elevation data and the pile height and laying angle of the photovoltaic array, the digital elevation model (DEM, Digital Elevation Data) of the photovoltaic array arrangement is modeled.

[0081] The position of the sun is calculated according to the current time, date and geographical coordinates, which can be expressed as the altitude angle and azimuth angle of the sun. The altitude angle is the angle between the sun's rays and the horizontal plane (0°~90°), and the azimuth angle is the projection direction of the sun's rays on the horizontal plane (0°~360°, north is 0°, clockwise increase).

[0082] According to the position of the sun, the sun's rays can be simulated to shine on the digital elevation model, based on which it can be determined whether each grid point in the photovoltaic array is blocked. If it is blocked, the grid point is located in the shadow area, so as to obtain the second shadow area composed of the blocked grid points.

[0083] 404: According to the first shadow area and the second shadow area, the angle of the photovoltaic tracking support corresponding to the photovoltaic array is adjusted with the maximum unblocked area of the photovoltaic array as the optimization target.

[0084] Combining the first shadow area and the second shadow area can reduce the misjudgment of the shadow, so as to be able to adjust the angle of the photovoltaic tracking support corresponding to the photovoltaic array based on the accurate shadow area with the maximum unblocked area of the photovoltaic array as the optimization target.

[0085] The photovoltaic tracking support control method provided by the embodiment comprises the following steps: obtaining an image of a photovoltaic array; identifying a first shadow area of the photovoltaic array image by using an image recognition technology; determining a second shadow area of the photovoltaic array caused by terrain undulations according to a digital elevation model of the photovoltaic array arrangement and a sun position; accurately evaluating a shadow area of the photovoltaic array by combining the first shadow area and the second shadow area; and individually and accurately controlling photovoltaic tracking supports corresponding to the photovoltaic array with the maximum unshaded area of the photovoltaic array as an optimization target, so as to improve the power generation efficiency of the photovoltaic array and the overall power generation efficiency of the photovoltaic power station.

[0086] In a possible implementation, the step 402 in the above embodiment includes the following steps 4021-4023:

[0087] 4021: A quadtree segmentation algorithm is used to identify the photovoltaic panels in the photovoltaic array image.

[0088] The photovoltaic panels have a pixel difference with the surrounding environment of the photovoltaic panels, and the quadtree segmentation algorithm is used to identify the contour of the photovoltaic panels based on the pixel difference. The quadtree segmentation algorithm is an existing algorithm, and thus will not be described here.

[0089] 4022: An Otsu's Thresholding Method is used to identify the shadow area on the photovoltaic panels.

[0090] The brightness of the shadowed part and the non-shaded part on the photovoltaic panels is inconsistent, and the Otsu's Thresholding Method is used to identify the shadow area on the photovoltaic panels based on this. The Otsu's Thresholding Method is also an existing algorithm, and thus will not be described here.

[0091] 4023: The shadow area boundary on the photovoltaic panels is corrected by using a sub-pixel gradient matching method to obtain a first shadow area.

[0092] In order to solve the shadow boundary positioning defects caused by the quadtree segmentation algorithm + Otsu's Thresholding Method, the gradient direction constraint and the sub-pixel difference are used to make the shadow boundary clearer.

[0093] Specifically, the Sobel operator or the Canny edge detection algorithm is used to calculate the gradient direction of the shadow area, the shadow area is sub-pixel interpolated, and a smoother transition is generated. The edge is detected at the sub-pixel level, and the edge is refined according to the gradient direction, so as to correct the shadow area boundary on the photovoltaic panels.

[0094] In a possible implementation, the step 403 in the above embodiment includes the following steps 4031-4032:

[0095] 4031: The sun rays are converted into three-dimensional vectors according to the sun position.

[0096] 4032: For each grid point of the photovoltaic array in the digital elevation model, if there is an obstruction along the direction of the sunlight ray that strikes the grid point, the grid point is in the second shadow region.

[0097] For example: the sunlight ray that strikes grid point A, if there is a higher point of the digital elevation model along the direction of the sunlight ray, then grid point A is obstructed.

[0098] If the cost is not considered, enough image acquisition devices can be deployed in the photovoltaic power station to obtain the image of each photovoltaic array in the photovoltaic power station. In order to balance the economy and practicability, the image acquisition device usually monitors the first cross group string at the south end of the photovoltaic array, and the rest of the group strings in the north of the same array do not acquire the image of the photovoltaic array. In order to solve this problem, the shadow region of the photovoltaic array of the photovoltaic array image that has not been acquired can be inferred according to the first shadow region of the identified photovoltaic array image and the digital elevation model of the photovoltaic array arrangement. In one possible implementation, in the case that the image of the target photovoltaic array is not acquired, the first shadow region of the identified photovoltaic array image is determined as the first shadow region of the target photovoltaic array, wherein the target photovoltaic array is consistent with the orientation and slope change of the photovoltaic array. The implementation deduces the shadow region of the photovoltaic array that cannot be shot by the camera according to the shadow region of the photovoltaic array shot by the camera, and reduces the cost of deploying the camera in the photovoltaic power station.

[0099] Further, for the above-mentioned target photovoltaic array, a Bayesian fusion model can also be used to calculate the obstruction probability of each grid point in the target photovoltaic array to evaluate whether the angle of the photovoltaic tracking support corresponding to the target photovoltaic array needs to be adjusted.

[0100] For example, one implementation of calculating the obstruction probability of each grid point in the target photovoltaic array includes the following steps 501-504:

[0101] 501: According to the first shadow region of the target photovoltaic array, determine the visual shadow state of each grid point in the target photovoltaic array;

[0102] For example, for each grid point in the target photovoltaic array, if the grid point is in the first shadow region, the visual shadow state of the grid point is 1, and if the grid point is not in the first shadow region, the visual shadow state of the grid point is 0.

[0103] 502: According to the second shadow region of the target photovoltaic array, determine the elevation shadow state of each grid point in the target photovoltaic array;

[0104] For example, for each grid point in the target photovoltaic array, if the grid point is in the second shadow area, the grid point's elevation shadow state is 1, and if the grid point is not in the second shadow area, the grid point's elevation shadow state is 0.

[0105] 503: For each grid point in the target photovoltaic array, determine the grid point's shading weight at different solar angles in a day according to the grid point's visual shadow state and elevation shadow state at different solar angles in a day.

[0106] For example, the way to determine the grid point's shading weight is as follows:

[0107]

[0108] It can be understood that if the two sources confirm shading, the probability of the grid point being shaded is higher, and the corresponding shading weight is the largest; if the two sources confirm no shading, the probability of the grid point being shaded is very low, and the corresponding shading weight is the smallest; if the image indicates shading but the terrain indicates no shading or the terrain indicates shading but the image indicates no shading, there may be visual recognition error or elevation recognition error or the grid point is in a shadow transition area, and the corresponding shading weight is in the middle.

[0109] The shading weight represents the influence of the visual shadow state and the elevation shadow state on the shading probability.

[0110] 504: Determine the target shading probability of the grid point according to the initial shading probability of the grid point at different solar angles in a day and the shading weight.

[0111] It can be understood that the shading weight corresponding to different solar angles is different, for example, at 9:00 and 15:00, the solar angle is low, the probability of the grid point being shaded is larger, and the corresponding initial shading probability is larger; at 12:00, the solar angle is high, the probability of the grid point being shaded is smaller, and the corresponding initial shading probability is smaller. The initial shading probability represents the influence of the solar angle on the shading probability.

[0112] In summary, by combining the initial shading probability of the grid point at different solar angles in a day and the shading weight, the target shading probability of the grid point can be accurately evaluated.

[0113] For example, the solar angle The corresponding target shading weight , wherein is the solar angle The corresponding initial shading probability, is the solar angle The corresponding shading weight.

[0114] The target shadow probability of the final grid point is Pfinal= Max{P1, P2, …, Pn}, n is the number of solar angles.

[0115] Further, the connected domain can be filtered to remove isolated shadow areas with an area <100 pixels to achieve noise removal.

[0116] Further, the shadow weight can be increased at the mutation of the digital elevation model, such as ridges, steep slopes, and valleys, such as ×1.2, to enhance the target shadow probability of the terrain sensitive area and improve the accuracy of the shadow probability.

[0117] In one possible implementation, if the target shadow probability is greater than a threshold value, it is considered that the corresponding grid point is shadowed. In one photovoltaic array, if the proportion of the grid points determined to be shadowed according to the target shadow probability is greater than a target proportion, the angle of the photovoltaic tracking support corresponding to the target photovoltaic array is adjusted to reduce the shadow area of the target photovoltaic array and improve the power generation efficiency.

[0118] It can be understood that if the deviation between the first shadow area and the second shadow area is large, the control accuracy of the angle of the photovoltaic tracking support will be affected. Since the first shadow area identified based on the image is relatively accurate, if the deviation between the first shadow area and the second shadow area is large, the digital elevation model of the photovoltaic array arrangement needs to be adjusted.

[0119] For example, the root mean square error of the overlapping area of the first shadow area and the second shadow area is calculated. If the root mean square error is less than a threshold value, no adjustment is needed. If the root mean square error is not less than the threshold value, the digital elevation model of the photovoltaic array arrangement needs to be adjusted.

[0120] Please refer to Figure 6 the camera detected shadow and the shadow detected based on the digital elevation model verification diagram. For each grid point on the photovoltaic array, if no shadow is detected based on the digital elevation model but the camera detects a shadow, the grid point is recorded as a first grid point. The elevation data of the grid points after the first grid point in the direction of the solar ray is corrected. If the camera does not detect a shadow but the digital elevation model detects a shadow, the grid point is recorded as a second grid point. The elevation data of the grid points before the second grid point in the direction of the solar ray is corrected until the root mean square error is less than a threshold value. The gradient descent method or genetic algorithm can be used to correct the elevation data.

[0121] In the case where the root mean square error is less than the threshold value, step 404 in the above embodiment can be performed. In one possible implementation, step 404 in the above embodiment includes steps 4041-4042:

[0122] 4041: constructing an objective function;

[0123] The objective function is a weighted difference between a first sub-function and a second sub-function, the first sub-function representing a number of unshaded grid points in the photovoltaic array, and the second sub-function representing a number of shaded grid points corresponding to an overlapping area of the first shadow area and the second shadow area.

[0124] For example, the objective function is ;

[0125] , is a weight coefficient, and N is a number of grid points of the photovoltaic array.

[0126] The first sub-function is , , where 1 indicates that the grid point is shaded, and 0 indicates that the grid point is not shaded. .

[0127] The second sub-function is , , , where 1 indicates that the grid point is located in the first shadow area, and 0 indicates that the grid point is located in the second shadow area.

[0128] 4042: adjusting the angle of the photovoltaic tracking support using a genetic algorithm to maximize the objective function.

[0129] Specifically, the number N of grid points of the photovoltaic array is used as the population size, and the binary gene of the grid point indicates whether the grid point is shaded, where 0 indicates that the grid point is shaded, and 1 indicates that the grid point is not shaded. The population is initialized according to the first shadow area and the second shadow area.

[0130] The fitness of the population is calculated according to the objective function.

[0131] The fitness of the population is iteratively calculated by adjusting the angle of the photovoltaic tracking support according to a preset step size, and the weights of the first sub-function and the second sub-function are adjusted during the iteration process. For example, in the early stage of iteration, more attention is paid to maximizing the direct light reception, and w1 can be appropriately increased; in the later stage of iteration, more attention is paid to minimizing the shadow overlapping area, and w2 can be appropriately increased.

[0132] In the case where the iterative calculation is completed, the adjustment of the angle of the photovoltaic tracking support is stopped.

[0133] The condition of the iterative calculation result can be that the maximum number of iterations is reached, or the unshaded area is N times a preset proportion, and the preset proportion can be 80%.

[0134] ​​​​​The embodiment of the present application further provides an edge computing device, comprising at least one processor and a memory connected with the processor, wherein:

[0135] The memory is used for storing a computer program.

[0136] The processor is used for executing the computer program, so that the edge computing device can implement the photovoltaic tracking support control method provided in any of the embodiments of the present application.

[0137] The embodiment of the present application further provides a computer program product comprising computer readable instructions, which, when executed on an edge computing device, cause the edge computing device to implement the photovoltaic tracking support control method provided in any of the embodiments of the present application.

[0138] The embodiment of the present application further provides a computer readable storage medium, which carries one or more computer programs, which, when executed by an edge computing device, can cause the edge computing device to implement the photovoltaic tracking support control method provided in any of the embodiments of the present application.

[0139] In addition, it should be noted that the apparatus embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the embodiment. In addition, in the apparatus embodiment provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines.

[0140] Those skilled in the art can clearly understand that the application can be implemented by means of software plus necessary universal hardware, and of course can also be implemented by means of dedicated hardware including special integrated circuit, special CPU, special memory, special component, etc. Generally, any function completed by computer program can be easily implemented by corresponding hardware, and the specific hardware structure for implementing the same function can also be various, such as analog circuit, digital circuit or special circuit, etc. However, for the application, software program implementation is a better embodiment. Based on such understanding, the technical solution of the application or the part of the application which makes contribution to the prior art can be embodied in the form of software product, which is stored in readable storage medium, such as computer floppy disk, U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a plurality of instructions for making a computer device (which can be personal computer, training device or network device, etc.) execute the method described in various embodiments of the application.

[0141] In the above embodiments, the implementation can be achieved by software, hardware, firmware or any combination thereof, entirely or partially. When implemented by software, the implementation can be achieved in the form of a computer program product, entirely or partially.

[0142] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the flow or function described in the embodiments of the application is generated entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, training device or data center to another website, computer, training device or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be stored by the computer or a data storage device such as training device, data center, etc. integrated with one or more available media sets. The available medium can be magnetic medium (such as floppy disk, hard disk, magnetic tape), optical medium (such as DVD) or semiconductor medium (such as solid state disk (SSD)) etc.

Claims

1. A photovoltaic tracking support control method, characterized in that, The method comprises the following steps: acquiring a photovoltaic array image; identifying a first shadow area of the photovoltaic array image; determining a second shadow area of the photovoltaic array according to a digital elevation model of the photovoltaic array arrangement and a sun position; adjusting the angle of a photovoltaic tracking support corresponding to the photovoltaic array according to the first shadow area and the second shadow area, with the maximum unshaded area of the photovoltaic array as the optimization target, comprising: constructing a target function, which is the weighted difference between a first sub-function and a second sub-function, the first sub-function representing the number of unshaded grid points in the photovoltaic array, and the second sub-function representing the number of shaded grid points corresponding to the overlapping area of the first shadow area and the second shadow area; and adjusting the angle of the photovoltaic tracking support using a genetic algorithm to maximize the target function; the step of adjusting the angle of the photovoltaic tracking support using a genetic algorithm to maximize the target function comprises: taking the number of grid points of the photovoltaic array as the population size, and taking the binary genes of the grid points as an indication of whether the grid points are shaded, and initializing the population according to the first shadow area and the second shadow area; calculating the fitness of the population according to the target function; iteratively calculating the fitness of the population by adjusting the angle of the photovoltaic tracking support by a preset step size, and adjusting the weights of the first sub-function and the second sub-function during the iteration process; stopping adjusting the angle of the photovoltaic tracking support when the iterative calculation is completed.

2. The photovoltaic tracking support control method according to claim 1, characterized in that, the step of identifying the first shadow area of the photovoltaic array image comprises: identifying the photovoltaic panels in the photovoltaic array image using a quadtree segmentation algorithm; identifying the shadow area on the photovoltaic panels using the maximum inter-class variance method; correcting the boundary of the shadow area on the photovoltaic panels using a sub-pixel gradient matching method to obtain the first shadow area.

3. The photovoltaic tracking support control method according to claim 1, characterized in that, the step of determining the second shadow area of the photovoltaic array according to the digital elevation model of the photovoltaic array arrangement and the sun position comprises: converting the sun rays into a three-dimensional vector according to the sun position; for each grid point of the photovoltaic array in the digital elevation model, if there is an obstruction along the direction of the sun rays illuminating the grid point, the grid point is located in the second shadow area.

4. The photovoltaic tracking support control method according to claim 1, characterized in that, The photovoltaic tracking support control method further comprises: in the case where no image of a target photovoltaic array is acquired, determining the first shadow area of the photovoltaic array image as the first shadow area of the target photovoltaic array, the target photovoltaic array being a photovoltaic array with the same orientation and slope change as the photovoltaic array.

5. The photovoltaic tracking support control method according to claim 4, characterized in that, The photovoltaic tracking support control method further comprises: determining the visual shadow state of each grid point in the target photovoltaic array according to the first shadow area of the target photovoltaic array; determining the elevation shadow state of each grid point in the target photovoltaic array according to the second shadow area of the target photovoltaic array; for each grid point in the target photovoltaic array, determining the shading weight of the grid point at different sun angles in a day according to the visual shadow state and the elevation shadow state of the grid point at different sun angles in a day. Determine a target shading probability of the grid point according to an initial shading probability of the grid point at different solar angles in a day and the shading weight.

6. The photovoltaic tracking support control method according to claim 1, characterized in that, The photovoltaic tracking support control method further includes: calculating a root mean square error of an overlapping area of the first shadow area and the second shadow area; in a case where the root mean square error is not less than a threshold value, obtaining a first grid point and a second grid point in the photovoltaic array, wherein the first grid point is located in the first shadow area and not in the second shadow area, and the second grid point is located in the second shadow area and not in the first shadow area; correcting elevation data of a grid point after the first grid point in a direction of a sunlight ray and correcting elevation data of a grid point before the second grid point in the direction of the sunlight ray until the root mean square error is less than the threshold value.

7. An edge computing device, characterized by comprise at least one processor and a memory connected with the processor, wherein: the memory is configured to store a computer program; the processor is configured to execute the computer program to enable the edge computing device to implement the photovoltaic tracking support control method according to any one of claims 1 to 6.

8. A photovoltaic tracking racking control system, characterized by, comprise: an image acquisition device, a photovoltaic support driving device, and an edge computing device; the image acquisition device is configured to acquire a photovoltaic array image and send the photovoltaic array image to the edge computing device; the photovoltaic support driving device comprises a communication control unit and a plurality of tracking controllers; the plurality of tracking controllers are respectively configured to control corresponding photovoltaic tracking supports in response to a control instruction issued by the edge computing device; the plurality of tracking controllers comprise one master tracking controller and a plurality of slave tracking controllers, and each of the slave tracking controllers is in communication connection with the master tracking controller; the master tracking controller communicates with the edge computing device through the communication control unit; the edge computing device is configured to execute the photovoltaic tracking support control method according to any one of claims 1 to 6.

9. A computer program product, characterised in that, comprise computer readable instructions that, when executed on an edge computing device, cause the edge computing device to implement the photovoltaic tracking support control method according to any one of claims 1 to 6.

10. A computer storage medium, characterized in that, the storage medium carries one or more computer programs that, when executed by an edge computing device, enable the edge computing device to implement the photovoltaic tracking support control method according to any one of claims 1 to 6.

Images