Adjustable support control model training method and device, equipment and storage medium

Abstract

The application discloses a kind of adjustable support control model training method, device, equipment and computer readable storage medium, method includes: obtaining various environment simulation parameter values, through photovoltaic panel simulation model in simulated environment adjustable support is controlled at various preset control angles, simulate the illumination coverage condition of photovoltaic panel, simulated environment is by the environment defined by simulation parameter value;According to the illumination coverage area of photovoltaic panel, select the control angle from various preset control angles, so that the preset power generation parameter of photovoltaic panel meets preset condition, as the selected control angle corresponding to target environment simulation parameter value;Multiple training samples generated based on various environment simulation parameter values are iteratively optimized to adjustable support control model, and target adjustable support control model is obtained.The application realizes a kind of adjustable support control model training scheme through environment simulation simulation, to improve the training efficiency of adjustable support control model.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation technology, and in particular to an adjustable support control model training method, apparatus, equipment, and computer-readable storage medium. Background Technology

[0002] In the field of photovoltaic power generation technology, the role of photovoltaic panels is to convert solar energy into electrical energy. Photovoltaic panels are mainly fixed at a certain height above the ground by their photovoltaic panel supports. Currently, there are three types of photovoltaic panel supports: fixed supports, strut supports, and adjustable supports. Since actual weather conditions change over time, fixed supports, due to their fixed structure, cannot adjust the position of the photovoltaic panels. Strut supports, because their struts can only be adjusted slightly by hand, result in a small range of adjustment for the photovoltaic panels. This makes it easy for the photovoltaic conversion efficiency to be poor when weather conditions are poor, that is, when the sun cannot directly cover the entire photovoltaic panel. Adjustable supports, on the other hand, because they have controllers and drive components, can adjust the photovoltaic panels to a larger extent, thereby ensuring high photovoltaic conversion efficiency.

[0003] However, currently, when training the adjustable bracket control model to ensure high control accuracy so that the adjustable bracket can drive the photovoltaic panel to rotate and ensure high photoelectric conversion efficiency, it is necessary to collect the angle information of the adjustable bracket at which the photovoltaic panel has the maximum photoelectric conversion efficiency under various environmental parameters. Based on these environmental parameters and angle information, the adjustable bracket control model is trained. However, since the actual environmental parameters are not fixed, the time for acquiring training samples for the adjustable bracket control model is often long, resulting in low training efficiency. Summary of the Invention

[0004] The main objective of this invention is to provide a method, apparatus, device, and computer-readable storage medium for training adjustable scaffold control models, aiming to provide a scheme for training adjustable scaffold control models through environmental simulation, thereby improving the training efficiency of adjustable scaffold control models.

[0005] To achieve the above objectives, the present invention provides a training method for an adjustable scaffold control model, the training method comprising the following steps:

[0006] Various environmental simulation parameter values ​​are obtained, and the photovoltaic panel illumination coverage is simulated in the simulated environment when the adjustable bracket is controlled at various preset control angles. The adjustable bracket is a bracket connected to the photovoltaic panel, and the simulated environment is the environment defined by the target environment simulation parameter values, which are any one of the various environmental simulation parameter values.

[0007] Based on the solar irradiance coverage of the photovoltaic panel, a control angle is selected from the various preset control angles so that the preset power generation parameters of the photovoltaic panel meet the preset conditions, and this angle is used as the selected control angle corresponding to the target environment simulation parameter value. The preset power generation parameters include power generation.

[0008] The target environment simulation parameter value is used as the input feature data in the training sample, and the selected control angle corresponding to the target environment simulation parameter value is used as the training label in the training sample to generate a training sample.

[0009] Based on multiple training samples generated from the various environmental simulation parameter values, the adjustable stent control model is iteratively optimized to obtain the target adjustable stent control model.

[0010] Optionally, the photovoltaic panel simulation model includes a photovoltaic panel arrangement simulation model and a photovoltaic panel illumination coverage simulation model.

[0011] The steps of simulating the photovoltaic panel illumination coverage under various preset control angles using a photovoltaic panel simulation model include:

[0012] Obtain the photovoltaic panel parameters;

[0013] Based on the photovoltaic panel parameters, the photovoltaic panel arrangement state is simulated using the photovoltaic panel arrangement simulation model to obtain photovoltaic panel arrangement information;

[0014] Based on the photovoltaic panel arrangement information and the target environment simulation parameter values, the photovoltaic panel illumination coverage is simulated using the photovoltaic panel illumination coverage simulation model when the adjustable support is controlled at various preset control angles.

[0015] Optionally, the multiple training samples generated based on the various environmental simulation parameter values ​​include a first type of training samples and a second type of training samples. The input feature data in the first type of training samples also includes conventional operating condition parameter values.

[0016] The method further includes:

[0017] Obtain parameter values ​​for special operating conditions;

[0018] The target environment simulation parameter value and the special working condition parameter value are used as input feature data in the training sample of the second type, and the special control angle corresponding to the special working condition parameter value is used as the training label in the training sample of the second type to generate a training sample of the second type.

[0019] Optionally, the step of obtaining the parameter values ​​for special operating conditions includes:

[0020] The first state of the inverter in the photovoltaic panel, the second state of the adjustable bracket, the installation position simulation parameter value of the photovoltaic panel and / or the climate simulation parameter value are obtained, wherein the first state value is used to characterize the working condition of the inverter, and the second state value is used to characterize the control stability of the adjustable bracket.

[0021] Based on the first state, the second state, the simulated parameter value of the installation position, and / or the simulated parameter value of the climate, it is determined whether the adjustable bracket is in a special working condition;

[0022] If it is in the state, then the first state, the second state, the simulation parameter value of the installation location condition and / or the climate simulation parameter value shall be used as the special working condition parameter value.

[0023] If not, the first state, the second state, the simulated parameter value of the installation location, and / or the simulated parameter value of the climate will be used as the normal operating condition parameter value.

[0024] Optionally, determining whether the adjustable bracket is in a special working condition based on the first state includes:

[0025] If the first state is the running state, then it is determined that the adjustable bracket is not in a special working condition;

[0026] If the first state is a stopped state, then the adjustable bracket is determined to be in a special working condition.

[0027] Optionally, determining whether the adjustable bracket is in a special working condition based on the second state includes:

[0028] If the second state is a stable control state, then it is determined that the adjustable support is not in a special working condition;

[0029] If the second state is an unstable control state, then the adjustable support is determined to be in a special working condition.

[0030] Optionally, determining whether the adjustable bracket is under special working conditions based on the simulated parameter values ​​of the installation location and / or the simulated climate parameter values ​​includes:

[0031] Based on the simulated parameter values ​​of the installation location and / or the simulated climate parameter values, determine whether the photovoltaic panel poses a risk of shading.

[0032] If it exists, the adjustable bracket is determined to be in a special working condition;

[0033] If it does not exist, it is determined that the adjustable bracket is not in a special working condition.

[0034] Optionally, after the step of iteratively optimizing the adjustable stent control model based on multiple training samples generated from the various environmental simulation parameter values ​​to obtain the target adjustable stent control model, the method further includes:

[0035] Obtain the real-time environmental parameter values ​​of the environment where the photovoltaic panel is located and the real-time operating condition parameter values ​​of the photovoltaic panel;

[0036] Based on the real-time environmental parameter values ​​and the real-time operating condition parameter values, the real-time control angle of the adjustable support is predicted by the target adjustable support control model.

[0037] Optionally, the step of selecting a control angle from various preset control angles that makes the preset power generation parameters of the photovoltaic panel meet preset conditions, based on the photovoltaic panel's illumination coverage, as the selected control angle corresponding to the target environment simulation parameter value, includes:

[0038] If the preset power generation parameters include power generation efficiency and power generation, then based on the photovoltaic panel's light coverage, a selected control angle is chosen from the various preset control angles such that the power generation efficiency is greater than a preset efficiency threshold and the power generation is greater than a first preset power generation threshold.

[0039] If the preset power generation parameters include the number of angle adjustments of the adjustable bracket, then based on the photovoltaic panel's illumination coverage, a selected control angle is chosen from the various preset control angles such that the number of angle adjustments is less than a preset threshold and the power generation is greater than a second preset power generation threshold.

[0040] To achieve the above objectives, the present invention also provides an adjustable scaffold control model training device, the adjustable scaffold control model training device comprising:

[0041] The acquisition module is used to acquire various environmental simulation parameter values ​​and simulate the photovoltaic panel's light coverage under various preset control angles in a simulated environment using a photovoltaic panel simulation model. The adjustable support is a support connected to the photovoltaic panel, and the simulated environment is defined by the target environment simulation parameter values, which are any one of the various environmental simulation parameter values.

[0042] The selection module is used to select a control angle from various preset control angles based on the photovoltaic panel's light coverage, such that the preset power generation parameters of the photovoltaic panel meet preset conditions, as the selected control angle corresponding to the target environment simulation parameter value, wherein the preset power generation parameters include power generation.

[0043] The generation module is used to take the target environment simulation parameter value as the input feature data in the training sample, and take the selected control angle corresponding to the target environment simulation parameter value as the training label in the training sample to generate a training sample.

[0044] The iteration module is used to iteratively optimize the adjustable stent control model based on multiple training samples generated from the various environmental simulation parameter values, so as to obtain the target adjustable stent control model.

[0045] To achieve the above objectives, the present invention also provides an adjustable scaffold control model training device, the adjustable scaffold control model training device comprising: a memory, a processor, and an adjustable scaffold control model training program stored in the memory and executable on the processor, wherein the adjustable scaffold control model training program, when executed by the processor, implements the steps of the adjustable scaffold control model training method as described above.

[0046] Furthermore, to achieve the above objectives, the present invention also proposes a computer-readable storage medium storing an adjustable scaffold control model training program, wherein the adjustable scaffold control model training program, when executed by a processor, implements the steps of the adjustable scaffold control model training method as described above.

[0047] In this invention, various environmental simulation parameter values ​​are obtained, and a photovoltaic panel simulation model is used to simulate the photovoltaic panel's illumination coverage under various preset control angles within a simulated environment using an adjustable support. The adjustable support is a support connected to the photovoltaic panel, and the simulated environment is defined by the target environment simulation parameter values, which are any one of the various environmental simulation parameter values. Based on the photovoltaic panel's illumination coverage, a control angle is selected from the various preset control angles that ensures the preset power generation parameters of the photovoltaic panel meet preset conditions. This selected angle corresponds to the target environment simulation parameter value, where the preset power generation parameters include power generation. The target environment... Simulated parameter values ​​are used as input feature data in training samples. The selected control angle corresponding to the simulated parameter values ​​of the target environment is used as the training label in the training sample to generate a training sample. Based on multiple training samples generated from the simulated parameter values ​​of various environments, the adjustable support control model is iteratively optimized to obtain the target adjustable support control model. The photovoltaic panel simulation model is used to simulate the photovoltaic panel illumination coverage under various environmental influences, which greatly shortens the time for collecting training samples for the adjustable support control model. Furthermore, by selecting the control angle of the adjustable support based on the photovoltaic panel illumination coverage, the training labels for the training samples are automatically generated, thereby improving the training efficiency of the adjustable support control model. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of the hardware operating environment involved in the embodiments of the present invention;

[0049] Figure 2 This is a flowchart illustrating the first embodiment of the adjustable support control model training method of the present invention;

[0050] Figure 3 This is a top view example of a photovoltaic panel installation area arrangement according to an embodiment of the present invention;

[0051] Figure 4 This is a schematic diagram of the functional modules of a preferred embodiment of the adjustable support control model training device of the present invention.

[0052] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0053] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0054] like Figure 1 As shown, Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention.

[0055] It should be noted that the adjustable scaffold control model training device in this embodiment of the invention can be a smartphone, personal computer, server, or other device, and no specific limitation is made here.

[0056] like Figure 1 As shown, the adjustable scaffold control model training device may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to establish communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or stable non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0057] Those skilled in the art will understand that Figure 1 The device structure shown does not constitute a limitation on the adjustable support control model training device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0058] like Figure 1 As shown, the memory 1005, serving as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an adjustable scaffold control model training program. The operating system is a program that manages and controls the hardware and software resources of the device, supporting the operation of the adjustable scaffold control model training program and other software or programs. Figure 1 In the device shown, the user interface 1003 is mainly used for data communication with the client; the network interface 1004 is mainly used for establishing a communication connection with the server; and the processor 1001 can be used to call the adjustable scaffold control model training program stored in the memory 1005 and perform the following operations:

[0059] Various environmental simulation parameter values ​​are obtained, and the photovoltaic panel illumination coverage is simulated in the simulated environment when the adjustable bracket is controlled at various preset control angles. The adjustable bracket is a bracket connected to the photovoltaic panel, and the simulated environment is an environment defined by target environmental simulation parameter values, which are any one of the various environmental simulation parameter values.

[0060] Based on the solar irradiance coverage of the photovoltaic panel, a control angle is selected from the various preset control angles so that the preset power generation parameters of the photovoltaic panel meet the preset conditions, and this angle is used as the selected control angle corresponding to the target environment simulation parameter value. The preset power generation parameters include power generation.

[0061] The target environment simulation parameter value is used as the input feature data in the training sample, and the selected control angle corresponding to the target environment simulation parameter value is used as the training label in the training sample to generate a training sample.

[0062] Based on multiple training samples generated from the various environmental simulation parameter values, the adjustable stent control model is iteratively optimized to obtain the target adjustable stent control model.

[0063] Furthermore, the photovoltaic panel simulation model includes a photovoltaic panel arrangement simulation model and a photovoltaic panel illumination coverage simulation model. The operation of simulating the photovoltaic panel illumination coverage under various preset control angles using the photovoltaic panel simulation model includes:

[0064] Obtain the photovoltaic panel parameters;

[0065] Based on the photovoltaic panel parameters, the photovoltaic panel arrangement state is simulated using the photovoltaic panel arrangement simulation model to obtain photovoltaic panel arrangement information;

[0066] Based on the photovoltaic panel arrangement information and the target environment simulation parameter values, the photovoltaic panel illumination coverage is simulated using the photovoltaic panel illumination coverage simulation model when the adjustable support is controlled at various preset control angles.

[0067] Furthermore, the multiple training samples generated based on the various environmental simulation parameter values ​​include a first type of training samples and a second type of training samples. The input feature data in the first type of training samples also includes conventional operating condition parameter values. The processor 1001 can also be used to call the adjustable support control model training program stored in the memory 1005 to perform the following operations:

[0068] Obtain parameter values ​​for special operating conditions;

[0069] The target environment simulation parameter value and the special working condition parameter value are used as input feature data in the training sample of the second type, and the special control angle corresponding to the special working condition parameter value is used as the training label in the training sample of the second type to generate a training sample of the second type.

[0070] Furthermore, the operation of obtaining the parameter values ​​for special operating conditions includes:

[0071] The first state of the inverter in the photovoltaic panel, the second state of the adjustable bracket, the installation position simulation parameter value of the photovoltaic panel and / or the climate simulation parameter value are obtained, wherein the first state is used to characterize the working condition of the inverter, and the second state is used to characterize the control stability of the adjustable bracket.

[0072] Based on the first state, the second state, the simulated parameter value of the installation position, and / or the simulated parameter value of the climate, it is determined whether the adjustable bracket is in a special working condition;

[0073] If it is in the state, then the first state, the second state, the simulation parameter value of the installation location condition and / or the climate simulation parameter value shall be used as the special working condition parameter value.

[0074] If not, the first state, the second state, the simulated parameter value of the installation location, and / or the simulated parameter value of the climate will be used as the normal operating condition parameter value.

[0075] Furthermore, the operation of determining whether the adjustable support is in a special working condition based on the first state includes:

[0076] If the first state is the running state, then it is determined that the adjustable bracket is not in a special working condition;

[0077] If the first state is a stopped state, then the adjustable bracket is determined to be in a special working condition.

[0078] Furthermore, the operation of determining whether the adjustable support is in a special working condition based on the second state includes:

[0079] If the second state is a stable control state, then it is determined that the adjustable support is not in a special working condition;

[0080] If the second state is an unstable control state, then the adjustable support is determined to be in a special working condition.

[0081] Furthermore, the operation of determining whether the adjustable bracket is under special working conditions based on the simulated parameter values ​​of the installation location and / or the simulated climate parameter values ​​includes:

[0082] Based on the simulated parameter values ​​of the installation location and / or the simulated climate parameter values, determine whether the photovoltaic panel poses a risk of shading.

[0083] If it exists, the adjustable bracket is determined to be in a special working condition;

[0084] If it does not exist, it is determined that the adjustable bracket is not in a special working condition.

[0085] Furthermore, after iteratively optimizing the adjustable stent control model based on multiple training samples generated from the various environmental simulation parameter values ​​to obtain the target adjustable stent control model, the processor 1001 can also call the adjustable stent control model training program stored in the memory 1005 to perform the following operations:

[0086] Obtain the real-time environmental parameter values ​​of the environment where the photovoltaic panel is located and the real-time operating condition parameter values ​​of the photovoltaic panel;

[0087] Based on the real-time environmental parameter values ​​and the real-time operating condition parameter values, the real-time control angle of the adjustable support is predicted by the target adjustable support control model.

[0088] Furthermore, the operation of selecting a control angle from various preset control angles that makes the preset power generation parameters of the photovoltaic panel meet preset conditions, based on the photovoltaic panel's illumination coverage, as the selected control angle corresponding to the target environment simulation parameter value, includes:

[0089] If the preset power generation parameters include power generation efficiency and power generation, then based on the photovoltaic panel's light coverage, a selected control angle is chosen from the various preset control angles such that the power generation efficiency is greater than a preset efficiency threshold and the power generation is greater than a first preset power generation threshold.

[0090] If the preset power generation parameters include the number of angle adjustments of the adjustable bracket and the power generation, then based on the photovoltaic panel's illumination coverage, a selected control angle is chosen from the various preset control angles such that the number of angle adjustments is less than a preset threshold and the power generation is greater than a second preset power generation threshold.

[0091] Based on the above structure, various embodiments of the adjustable scaffold control model training method are proposed.

[0092] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the adjustable support control model training method of the present invention.

[0093] This invention provides an embodiment of an adjustable scaffold control model training method. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order. In this embodiment, the executing entity of the adjustable scaffold control model training method can be a personal computer, smartphone, server, or other device; no limitation is made in this embodiment. For ease of description, the execution entity is omitted from the description of each embodiment. In this embodiment, the adjustable scaffold control model training method includes:

[0094] Step S10: Obtain various environmental simulation parameter values, and simulate the photovoltaic panel illumination coverage under various preset control angles when the adjustable bracket is controlled in the simulated environment through the photovoltaic panel simulation model. The adjustable bracket is a bracket connected to the photovoltaic panel, and the simulated environment is the environment defined by the target environment simulation parameter values. The target environment simulation parameter values ​​are any one of the various environmental simulation parameter values.

[0095] In this embodiment, it should be noted that the photovoltaic panel illumination coverage refers to the coverage of the photovoltaic panel under sunlight. This illumination coverage can refer to the location or area of ​​the photovoltaic panel. The environmental simulation parameter values ​​are pre-set values ​​for various environmental simulation parameters. These values ​​can be pre-set by the user or based on search results from a database. The photovoltaic panel simulation model is used to simulate the photovoltaic panel under the conditions defined by the various environmental simulation parameter values. The preset control angle is a pre-set control angle for the adjustable support.

[0096] For example, various environmental simulation parameter values ​​are obtained, and a photovoltaic panel is simulated in a simulated environment using a photovoltaic panel simulation model. The photovoltaic panel is rotated by an adjustable bracket at various preset control angles to obtain the photovoltaic panel's light coverage status at the various preset control angles.

[0097] As a feasible implementation, the environmental simulation parameter values ​​include the parameter values ​​of the environmental simulation parameters at each time point.

[0098] As another feasible implementation, various environmental simulation parameters are simulated using an environmental simulation model to obtain the values ​​of the various environmental simulation parameters.

[0099] Specifically, the environmental simulation model includes an installation location simulation model and a climate simulation model. The environmental simulation parameter values ​​include installation location simulation parameter values ​​and climate simulation parameter values. The installation location simulation model is used to simulate the altitude and environment of the installation location of the photovoltaic panel and / or the adjustable bracket to obtain the installation location simulation parameter values. The climate simulation model is used to simulate the climate of the photovoltaic panel and / or the adjustable bracket to obtain the climate simulation parameter values.

[0100] Furthermore, the climate simulation model includes at least one of a sunshine simulation model, a temperature simulation model, a meteorological simulation model, and a cloud simulation model. The sunshine simulation model simulates solar illumination information at various times to obtain sunshine simulation parameters, wherein the solar illumination information includes at least one of solar irradiance and incident angle; and / or, the temperature simulation model simulates the temperature at various times to obtain temperature simulation parameters; and / or, the cloud simulation model simulates cloud parameters for at least one cloud layer at various times to obtain cloud simulation parameters, wherein the cloud parameters include at least one of cloud movement speed, cloud cross-sectional area, cloud thickness, and cloud movement direction; and / or, the meteorological simulation model simulates meteorological conditions at various times to obtain meteorological simulation parameters, wherein the meteorological conditions include meteorological states and meteorological parameters. The meteorological states include at least one of snowy days, rainy days, foggy days, sunny days, cloudy days, and hail days, and the meteorological parameters include at least one of rainfall, snowfall, hail size, rainfall duration, snowfall duration, visible particulate matter information, and hail duration.

[0101] By simulating various environments, the training samples collected from the environmental simulation parameter values ​​obtained from these simulations become more comprehensive, thereby improving the training comprehensiveness of the adjustable scaffold control model.

[0102] The photovoltaic panel simulation model includes a photovoltaic panel arrangement simulation model and a photovoltaic panel illumination coverage simulation model. Step S10 includes:

[0103] Step S11: Obtain the photovoltaic panel parameters of the photovoltaic panel;

[0104] In this embodiment, it should be noted that the photovoltaic panel parameters are used to characterize the selection of the target photovoltaic panel. The photovoltaic panel parameters include at least one of the following: photovoltaic panel type, photovoltaic panel power specification, and photovoltaic panel material. The photovoltaic panel type can be a single-sided photovoltaic panel, a double-sided photovoltaic panel, or other types. The photovoltaic panel power specification can be 250W, 270W, 310W, or other power specifications. The photovoltaic panel material can be amorphous silicon, monocrystalline silicon, polycrystalline silicon, or other materials.

[0105] For example, the photovoltaic panel parameters are obtained by acquiring the photovoltaic panel type and / or photovoltaic panel power specifications and / or photovoltaic panel material.

[0106] Step S12: Based on the photovoltaic panel parameters, simulate the photovoltaic panel arrangement state using the photovoltaic panel arrangement simulation model to obtain photovoltaic panel arrangement information;

[0107] In this embodiment, it should be noted that the photovoltaic panel arrangement information refers to the arrangement information between individual photovoltaic panels, and the photovoltaic panel arrangement information includes at least one of the following: horizontal spacing distance between photovoltaic panels, vertical spacing distance between photovoltaic panels, and minimum spacing distance between photovoltaic panels.

[0108] As one feasible implementation method, refer to Figure 3 , Figure 3 This is a top view example of a photovoltaic panel installation area arrangement according to an embodiment of the present invention. Figure 3 The photovoltaic panels (small white squares in the illustration) are used to represent the arrangement information of the photovoltaic panels through the distance between each small white square.

[0109] Step S13: Based on the photovoltaic panel arrangement information and the target environment simulation parameter values, simulate the photovoltaic panel illumination coverage when the adjustable bracket is controlled at various preset control angles using the photovoltaic panel illumination coverage simulation model.

[0110] The adjustable scaffold control model training method further includes:

[0111] The inverter simulation model corresponding to the photovoltaic panel is generated based on the photovoltaic panel simulation model.

[0112] Specifically, based on the photovoltaic panel simulation model, the power, efficiency, circuit topology, and inverter type of the inverter are selected, and the inverter simulation model is generated based on the power, efficiency, circuit topology, and inverter type.

[0113] As a feasible implementation, if the inverter type is a grid-connected inverter, the inverter simulation model also includes a grid model; if the inverter type is an off-grid inverter, the inverter simulation model does not include a grid model.

[0114] Step S20: Based on the solar panel illumination coverage, select a control angle from the various preset control angles that makes the preset power generation parameters of the solar panel meet the preset conditions, and use it as the selected control angle corresponding to the target environment simulation parameter value. The preset power generation parameters include power generation.

[0115] In this embodiment, it should be noted that the preset power generation parameters are the pre-set power generation efficiency parameters of the photovoltaic panel.

[0116] For example, based on the photovoltaic panel illumination coverage conditions corresponding to the various preset control angles, a control angle that makes the preset power generation parameters of the photovoltaic panel meet the preset conditions is selected from the various preset control angles and used as the selected control angle corresponding to the target environment simulation parameter value.

[0117] In one feasible implementation, the photovoltaic panel illumination coverage status includes the photovoltaic panel illumination coverage area. Based on the photovoltaic panel illumination coverage area corresponding to each of the various preset control angles, a control angle is selected from the various preset control angles so that the preset power generation parameters of the photovoltaic panel meet the preset conditions, and this angle is used as the selected control angle corresponding to the target environment simulation parameter value.

[0118] As another feasible implementation, the photovoltaic panel illumination coverage status includes the photovoltaic panel illumination coverage position. Based on the photovoltaic panel illumination coverage positions corresponding to various preset control angles, a control angle is selected from the various preset control angles so that the preset power generation parameters of the photovoltaic panel meet the preset conditions, and this angle is used as the selected control angle corresponding to the target environment simulation parameter value.

[0119] As another feasible implementation, the adjustable support is simulated under the control of various preset control angles by using an adjustable support simulation model.

[0120] Step S20 includes:

[0121] Step S21: If the preset power generation parameters include power generation efficiency and power generation, then based on the photovoltaic panel illumination coverage, select a control angle from the various preset control angles that makes the power generation efficiency greater than a preset efficiency threshold and the power generation greater than a first preset power generation threshold.

[0122] In this embodiment, it should be noted that the preset efficiency threshold is a pre-set critical value for determining whether the power generation efficiency meets the user's needs, and the first preset power generation threshold is a pre-set minimum value of power generation of the photovoltaic panel that needs to be met under the condition of satisfying the power generation efficiency of the photovoltaic panel.

[0123] Step S22: If the preset power generation parameters include the number of angle adjustments of the adjustable bracket and the power generation, then based on the photovoltaic panel's illumination coverage, select a control angle from the various preset control angles such that the number of angle adjustments is less than a preset threshold and the power generation is greater than a second preset power generation threshold.

[0124] In this embodiment, it should be noted that the preset number threshold is a pre-set critical value for determining that the number of angle adjustments of the adjustable bracket meets the user's requirements, and the second preset power generation threshold is a pre-set minimum value of power generation of the photovoltaic panel that needs to be met under the condition of satisfying the number of angle adjustments of the adjustable bracket.

[0125] Step S30: Use the target environment simulation parameter value as the input feature data in the training sample, and use the selected control angle corresponding to the target environment simulation parameter value as the training label in the training sample to generate a training sample.

[0126] Step S40: Based on multiple training samples generated from the various environmental simulation parameter values, the adjustable stent control model is iteratively optimized to obtain the target adjustable stent control model.

[0127] For example, the various environmental simulation parameter values ​​are used as input feature data in the training samples, and the control angles corresponding to the various environmental simulation parameter values ​​are used as training labels in the training samples to generate multiple training samples. Based on the multiple training samples, the adjustable stent control model is iteratively optimized to obtain the target adjustable stent control model.

[0128] Specifically, by inputting the input feature data of the training samples into the adjustable stent control model, output labels are obtained, and the difference between the output labels and the training labels is determined. Based on the difference, the model loss corresponding to the adjustable stent control model is calculated, and then it is determined whether the model loss has converged. If the model loss has converged, the adjustable stent control model is used as the target adjustable stent control model. If the model loss has not converged, the adjustable stent control model is updated based on the gradient calculated by the model loss using a preset model update method, wherein the preset model update method includes gradient descent and gradient ascent, etc.

[0129] In this invention, various environmental simulation parameter values ​​are obtained, and a photovoltaic panel simulation model is used to simulate the photovoltaic panel's illumination coverage under various preset control angles within a simulated environment using an adjustable support. The adjustable support is a support connected to the photovoltaic panel, and the simulated environment is defined by the target environment simulation parameter values, which are any one of the various environmental simulation parameter values. Based on the photovoltaic panel's illumination coverage, a control angle is selected from the various preset control angles that ensures the preset power generation parameters of the photovoltaic panel meet preset conditions. This selected angle corresponds to the target environment simulation parameter value, where the preset power generation parameters include power generation. The target environment... Simulated parameter values ​​are used as input feature data in training samples. The selected control angle corresponding to the simulated parameter values ​​of the target environment is used as the training label in the training sample to generate a training sample. Based on multiple training samples generated from the simulated parameter values ​​of various environments, the adjustable support control model is iteratively optimized to obtain the target adjustable support control model. The photovoltaic panel simulation model is used to simulate the photovoltaic panel illumination coverage under various environmental influences, which greatly shortens the time for collecting training samples for the adjustable support control model. Furthermore, by selecting the control angle of the adjustable support based on the photovoltaic panel illumination coverage, the training labels for the training samples are automatically generated, thereby improving the training efficiency of the adjustable support control model.

[0130] Furthermore, based on the first embodiment described above, a second embodiment of the adjustable support control model training algorithm of the present invention is proposed. In this embodiment, the multiple training samples generated based on the various environmental simulation parameter values ​​include a first type of training samples and a second type of training samples. The input feature data in the first type of training samples also includes conventional operating condition parameter values.

[0131] The target environment simulation parameter value and the normal operating condition parameter value are used as input feature data in the training sample, and the selected control angle corresponding to the target environment simulation parameter value is used as the training label in the training sample to generate a training sample.

[0132] The adjustable scaffold control model training method further includes:

[0133] Step A10: Obtain the parameter values ​​for special operating conditions;

[0134] Step A10 includes:

[0135] Step A11: Obtain the first state of the inverter in the photovoltaic panel, the second state of the adjustable bracket, the simulation parameter value of the installation position of the photovoltaic panel, and / or the climate simulation parameter value, wherein the first state is used to characterize the working condition of the inverter, and the second state is used to characterize the control stability of the adjustable bracket.

[0136] For example, the first state simulated by the inverter simulation model, the second state simulated by the adjustable bracket simulation model, the installation location condition simulation parameter values ​​simulated by the installation location condition simulation model, and / or the climate simulation parameter values ​​simulated by the climate simulation model are obtained.

[0137] Step A12: Determine whether the adjustable bracket is in a special working condition based on the first state, the second state, the installation position condition simulation parameter value and / or the climate simulation parameter value.

[0138] Step A12 includes:

[0139] Step A121: If the first state is the running state, then it is determined that the adjustable bracket is not in a special working condition.

[0140] Understandably, when the inverter is in a stopped state, since the inverter is a device used to convert the DC power from the photovoltaic panel into AC power, the photovoltaic panel cannot operate at this time. Therefore, any adjustments to the adjustable bracket are futile, and the power generation efficiency of the photovoltaic panel remains at 0.

[0141] For example, if the first state is the running state, it is determined that the adjustable bracket is not in a special working condition, and the first state is used as the normal working condition parameter value.

[0142] Step A122: If the first state is a stopped state, then the adjustable bracket is determined to be in a special working condition.

[0143] For example, if the first state is a stopped state, the adjustable bracket is determined to be in a special working condition, and the first state is used as the parameter value of the special working condition.

[0144] By assessing the operational stability of the inverter, unstable operating conditions can be identified as special conditions, allowing for timely maintenance of the inverter.

[0145] Step A12 includes:

[0146] Step A123: If the second state is a stable control state, then it is determined that the adjustable support is not in a special working condition.

[0147] It is understandable that when the adjustable support is not under stable control, that is, when the adjustable support cannot respond in time when an angle control command is issued, it is easy for the adjustable support to fail to respond in time even when an angle control command is issued, resulting in the photovoltaic panel not being driven to rotate in time, and thus the photovoltaic panel's power generation efficiency is poor.

[0148] For example, if the second state is a stable control state, it is determined that the adjustable support is not in a special working condition, and the second state is used as the normal working condition parameter value.

[0149] Step A124: If the second state is an unstable control state, then the adjustable support is determined to be in a special working condition.

[0150] For example, if the second state is a stable control state, then the adjustable support is determined to be in a special working condition, and the second state is used as the parameter value of the special working condition.

[0151] By assessing the control stability of the adjustable support, unstable operating conditions can be identified as special conditions, allowing for timely maintenance of the adjustable support.

[0152] Step A12 includes:

[0153] Step A125: Based on the simulated parameter values ​​of the installation location and / or the simulated climate parameter values, determine whether the photovoltaic panel has a risk of being blocked;

[0154] It is understandable that when there is a risk of objects blocking the photovoltaic panel and / or a risk of sunlight blocking the panel, the subsequent sunlight conditions of the photovoltaic panel may not be ideal. If this situation is not addressed, even if the sunlight conditions are good (direct sunlight on the photovoltaic panel), the power generation effect of the photovoltaic panel will still be poor due to the risk of objects blocking the photovoltaic panel and / or sunlight blocking the panel.

[0155] Step A126: If it exists, then determine that the adjustable bracket is in a special working condition;

[0156] For example, if the photovoltaic panel is at risk of being blocked, the adjustable bracket is determined to be in a special working condition, and the simulated parameter value of the installation position and / or the simulated parameter value of the climate are used as the parameter value of the special working condition.

[0157] Step A127: If it does not exist, then it is determined that the adjustable bracket is not in a special working condition.

[0158] For example, if the photovoltaic panel does not pose a risk of shading, it is determined that the adjustable bracket is not in a special operating condition, and the simulated parameter value of the installation location and / or the simulated parameter value of the climate are used as the parameter value of the normal operating condition.

[0159] By assessing the shading risk of photovoltaic panels, a special angle setting can be implemented when shading risk exists, i.e., when the adjustable support is in a special operating condition. This avoids the technical defect that even under good lighting conditions (direct sunlight on the photovoltaic panels), the power generation effect of the photovoltaic panels may still be poor due to the presence of objects on the photovoltaic panels and / or the risk of light obstruction. This improves the accuracy of the training label selection for the training samples of the adjustable support control model, thereby improving the training accuracy of the adjustable support control model.

[0160] Step A13: If the condition is met, then the first state, the second state, the simulation parameter value of the installation location condition, and / or the climate simulation parameter value shall be used as the special working condition parameter value.

[0161] Step A14: If not in the state, then the first state, the second state, the installation location condition simulation parameter value and / or the climate simulation parameter value shall be used as the normal operating condition parameter value.

[0162] Step A20: Use the target environment simulation parameter value and the special working condition parameter value as input feature data in the training sample of the second type, and use the special control angle corresponding to the special working condition parameter value as the training label in the training sample of the second type to generate a training sample of the second type.

[0163] For example, the target environment simulation parameter value and the special working condition parameter value are concatenated to obtain the input feature data in the second type of training sample, and the special control angle corresponding to the special working condition parameter value is used as the training label in the second type of training sample to generate a training sample of the second type.

[0164] In this invention, special working condition parameter values ​​are obtained; the target environment simulation parameter values ​​and the special working condition parameter values ​​are used as input feature data in the second type of training samples, and the special control angle corresponding to the special working condition parameter values ​​is used as the training label in the second type of training samples to generate a second type of training sample. By identifying the special working conditions of the adjustable support, the generated training samples are more comprehensive, thereby improving the training accuracy of the adjustable support control model.

[0165] Furthermore, based on the first and / or second embodiments described above, a third embodiment of the adjustable support control model training algorithm of the present invention is proposed. In this embodiment, after step S40, the algorithm further includes:

[0166] Step S50: Obtain the real-time environmental parameter values ​​of the environment where the photovoltaic panel is located and the real-time operating condition parameter values ​​of the photovoltaic panel;

[0167] For example, the real-time environmental parameters of the environment where the photovoltaic panel is located and the real-time operating condition parameters of the photovoltaic panel are obtained.

[0168] Step S60: Based on the real-time environmental parameter values ​​and the real-time operating condition parameter values, predict the real-time control angle of the adjustable support using the target adjustable support control model.

[0169] For example, the real-time environmental parameter values ​​and the real-time operating condition parameter values ​​are mapped to the real-time control angle of the adjustable support through the target adjustable support control model.

[0170] In this invention, real-time environmental parameter values ​​of the environment in which the photovoltaic panel is located and real-time operating condition parameter values ​​of the photovoltaic panel are obtained. Based on the real-time environmental parameter values ​​and the real-time operating condition parameter values, the real-time control angle of the adjustable bracket is predicted by the target adjustable bracket control model. The control angle of the adjustable bracket is predicted by the target adjustable bracket control model trained with various environmental simulation parameter values. Since the decision basis of the target adjustable bracket control model is obtained by the joint decision of various environmental simulation parameters, the angle control accuracy of the adjustable bracket is high, thereby ensuring that the power generation efficiency of the photovoltaic panel driven by the adjustable bracket is high.

[0171] Furthermore, this invention also proposes an adjustable scaffold control model training device, referring to... Figure 4 The adjustable scaffold control model training device includes:

[0172] The acquisition module 10 is used to acquire various environmental simulation parameter values ​​and simulate the photovoltaic panel's light coverage under various preset control angles in a simulated environment using a photovoltaic panel simulation model. The adjustable support is a support connected to the photovoltaic panel, and the simulated environment is defined by target environmental simulation parameter values, which are any one of the various environmental simulation parameter values.

[0173] The selection module is used to select a control angle from various preset control angles based on the photovoltaic panel's light coverage, such that the preset power generation parameters of the photovoltaic panel meet preset conditions, as the selected control angle corresponding to the target environment simulation parameter value, wherein the preset power generation parameters include power generation.

[0174] The generation module is used to take the target environment simulation parameter value as the input feature data in the training sample, and take the selected control angle corresponding to the target environment simulation parameter value as the training label in the training sample to generate a training sample.

[0175] The iteration module is used to iteratively optimize the adjustable stent control model based on multiple training samples generated from the various environmental simulation parameter values, so as to obtain the target adjustable stent control model.

[0176] Furthermore, the photovoltaic panel simulation model includes a photovoltaic panel arrangement simulation model and a photovoltaic panel illumination coverage simulation model, and the acquisition module 10 is also used for:

[0177] Obtain the photovoltaic panel parameters;

[0178] Based on the photovoltaic panel parameters, the photovoltaic panel arrangement state is simulated using the photovoltaic panel arrangement simulation model to obtain photovoltaic panel arrangement information;

[0179] Based on the photovoltaic panel arrangement information and the target environment simulation parameter values, the photovoltaic panel illumination coverage is simulated using the photovoltaic panel illumination coverage simulation model when the adjustable support is controlled at various preset control angles.

[0180] Furthermore, the multiple training samples generated based on the various environmental simulation parameter values ​​include a first type of training samples and a second type of training samples. The input feature data in the first type of training samples also includes conventional operating condition parameter values. The adjustable support control model training device is also used for:

[0181] Obtain parameter values ​​for special operating conditions;

[0182] The target environment simulation parameter value and the special working condition parameter value are used as input feature data in the training sample of the second type, and the special control angle corresponding to the special working condition parameter value is used as the training label in the training sample of the second type to generate a training sample of the second type.

[0183] Furthermore, the adjustable scaffold control model training device is also used for:

[0184] The first state of the inverter in the photovoltaic panel, the second state of the adjustable bracket, the simulated parameter value of the installation position of the photovoltaic panel and / or the simulated parameter value of the climate are obtained, wherein the first state is used to characterize the working condition of the inverter, and the second state is used to characterize the control stability of the adjustable bracket.

[0185] Based on the first state, the second state, the simulated parameter value of the installation position, and / or the simulated parameter value of the climate, it is determined whether the adjustable bracket is in a special working condition;

[0186] If it is in the state, then the first state, the second state, the simulation parameter value of the installation location condition and / or the climate simulation parameter value shall be used as the special working condition parameter value.

[0187] If not, the first state, the second state, the simulated parameter value of the installation location, and / or the simulated parameter value of the climate will be used as the normal operating condition parameter value.

[0188] Furthermore, the adjustable scaffold control model training device is also used for:

[0189] If the first state is the running state, then it is determined that the adjustable bracket is not in a special working condition;

[0190] If the first state is a stopped state, then the adjustable bracket is determined to be in a special working condition.

[0191] Furthermore, the adjustable scaffold control model training device is also used for:

[0192] If the second state is a stable control state, then it is determined that the adjustable support is not in a special working condition;

[0193] If the second state is an unstable control state, then the adjustable support is determined to be in a special working condition.

[0194] Furthermore, the adjustable scaffold control model training device is also used for:

[0195] Based on the simulated parameter values ​​of the installation location and / or the simulated climate parameter values, determine whether the photovoltaic panel poses a risk of shading.

[0196] If it exists, the adjustable bracket is determined to be in a special working condition;

[0197] If it does not exist, it is determined that the adjustable bracket is not in a special working condition.

[0198] Furthermore, after the step of iteratively optimizing the adjustable stent control model based on multiple training samples generated from the various environmental simulation parameter values ​​to obtain the target adjustable stent control model, the adjustable stent control model training device is further used for:

[0199] Obtain the real-time environmental parameter values ​​of the environment where the photovoltaic panel is located and the real-time operating condition parameter values ​​of the photovoltaic panel;

[0200] Based on the real-time environmental parameter values ​​and the real-time operating condition parameter values, the real-time control angle of the adjustable support is predicted by the target adjustable support control model.

[0201] Furthermore, the selection module 20 is also used for:

[0202] If the preset power generation parameters include power generation efficiency and power generation, then based on the photovoltaic panel's light coverage, a selected control angle is chosen from the various preset control angles such that the power generation efficiency is greater than a preset efficiency threshold and the power generation is greater than a first preset power generation threshold.

[0203] If the preset power generation parameters include the number of angle adjustments of the adjustable bracket and the power generation, then based on the photovoltaic panel's illumination coverage, a selected control angle is chosen from the various preset control angles such that the number of angle adjustments is less than a preset threshold and the power generation is greater than a second preset power generation threshold.

[0204] All embodiments of the adjustable scaffold control model training device of the present invention can refer to the various embodiments of the adjustable scaffold control model training method of the present invention, and will not be described again here.

[0205] Furthermore, this embodiment of the invention also proposes a computer-readable storage medium storing an adjustable scaffold control model training program, which, when executed by a processor, implements the steps of the adjustable scaffold control model training method described below.

[0206] The various embodiments of the adjustable scaffold control model training device and computer-readable storage medium of the present invention can all refer to the various embodiments of the adjustable scaffold control model training method of the present invention, and will not be repeated here.

[0207] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0208] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0209] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0210] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for training an adjustable stent control model, characterized in that, The adjustable scaffold control model training method includes the following steps: Various environmental simulation parameter values ​​are obtained, and the photovoltaic panel illumination coverage is simulated in the simulated environment when the adjustable bracket is controlled at various preset control angles. The adjustable bracket is a bracket connected to the photovoltaic panel, and the simulated environment is an environment defined by target environmental simulation parameter values, which are any one of the various environmental simulation parameter values. Based on the solar irradiance coverage of the photovoltaic panel, a control angle is selected from the various preset control angles so that the preset power generation parameters of the photovoltaic panel meet the preset conditions, and this angle is used as the selected control angle corresponding to the target environment simulation parameter value. The preset power generation parameters include power generation. The target environment simulation parameter value is used as the input feature data in the training sample, and the selected control angle corresponding to the target environment simulation parameter value is used as the training label in the training sample to generate a training sample. Based on multiple training samples generated from the various environmental simulation parameter values, the adjustable stent control model is iteratively optimized to obtain the target adjustable stent control model. The training samples generated based on the various environmental simulation parameter values ​​include a first type of training sample and a second type of training sample. The input feature data in the first type of training sample also includes conventional operating condition parameter values, and the input feature data in the second type of training sample also includes special operating condition parameter values.

2. The adjustable scaffold control model training method as described in claim 1, characterized in that, The photovoltaic panel simulation model includes a photovoltaic panel arrangement simulation model and a photovoltaic panel illumination coverage simulation model. The steps of simulating the photovoltaic panel illumination coverage under various preset control angles using a photovoltaic panel simulation model include: Obtain the photovoltaic panel parameters of the photovoltaic panel; Based on the photovoltaic panel parameters, the photovoltaic panel arrangement state is simulated using the photovoltaic panel arrangement simulation model to obtain photovoltaic panel arrangement information; Based on the photovoltaic panel arrangement information and the target environment simulation parameter values, the photovoltaic panel illumination coverage is simulated using the photovoltaic panel illumination coverage simulation model when the adjustable support is controlled at various preset control angles.

3. The adjustable scaffold control model training method as described in claim 1, characterized in that, The adjustable scaffold control model training method further includes: Obtain parameter values ​​for special operating conditions; The target environment simulation parameter value and the special working condition parameter value are used as input feature data in the training sample of the second type, and the special control angle corresponding to the special working condition parameter value is used as the training label in the training sample of the second type to generate a training sample of the second type.

4. The adjustable scaffold control model training method as described in claim 3, characterized in that, The steps for obtaining the parameter values ​​for special operating conditions include: The first state of the inverter in the photovoltaic panel, the second state of the adjustable bracket, the simulated parameter value of the installation position of the photovoltaic panel and / or the simulated parameter value of the climate are obtained, wherein the first state is used to characterize the working condition of the inverter, and the second state is used to characterize the control stability of the adjustable bracket. Based on the first state, the second state, the simulated parameter value of the installation position, and / or the simulated parameter value of the climate, it is determined whether the adjustable bracket is in a special working condition; If it is in the state, then the first state, the second state, the simulation parameter value of the installation location condition and / or the climate simulation parameter value shall be used as the special working condition parameter value. If not, the first state, the second state, the simulated parameter value of the installation location, and / or the simulated parameter value of the climate will be used as the normal operating condition parameter value.

5. The adjustable scaffold control model training method as described in claim 4, characterized in that, The step of determining whether the adjustable bracket is in a special working condition based on the first state includes: If the first state is the running state, then it is determined that the adjustable bracket is not in a special working condition; If the first state is a stopped state, then the adjustable bracket is determined to be in a special working condition.

6. The adjustable scaffold control model training method as described in claim 4, characterized in that, The step of determining whether the adjustable bracket is in a special working condition based on the second state includes: If the second state is a stable control state, then it is determined that the adjustable support is not in a special working condition; If the second state is an unstable control state, then the adjustable support is determined to be in a special working condition.

7. The adjustable scaffold control model training method as described in claim 4, characterized in that, The step of determining whether the adjustable bracket is under special working conditions based on the simulated parameter values ​​of the installation location and / or the simulated climate parameter values ​​includes: Based on the simulated parameter values ​​of the installation location and / or the simulated climate parameter values, determine whether the photovoltaic panel poses a risk of shading. If it exists, the adjustable bracket is determined to be in a special working condition; If it does not exist, it is determined that the adjustable bracket is not in a special working condition.

8. The adjustable scaffold control model training method as described in claim 3, characterized in that, After the step of iteratively optimizing the adjustable stent control model based on multiple training samples generated from the various environmental simulation parameter values ​​to obtain the target adjustable stent control model, the method further includes: Obtain the real-time environmental parameter values ​​of the environment where the photovoltaic panel is located and the real-time operating condition parameter values ​​of the photovoltaic panel; Based on the real-time environmental parameter values ​​and the real-time operating condition parameter values, the real-time control angle of the adjustable support is predicted by the target adjustable support control model.

9. The adjustable scaffold control model training method according to any one of claims 1 to 8, characterized in that, The step of selecting, based on the photovoltaic panel's illumination coverage, a control angle from various preset control angles that makes the preset power generation parameters of the photovoltaic panel meet preset conditions, and using this angle as the selected control angle corresponding to the target environment simulation parameter value, includes: If the preset power generation parameters include power generation efficiency and power generation, then based on the photovoltaic panel's illumination coverage, a selected control angle is chosen from the various preset control angles such that the power generation efficiency is greater than a preset efficiency threshold and the power generation is greater than a first preset power generation threshold. If the preset power generation parameters include the number of angle adjustments of the adjustable bracket and the power generation, then based on the photovoltaic panel's illumination coverage, a selected control angle is chosen from the various preset control angles such that the number of angle adjustments is less than a preset threshold and the power generation is greater than a second preset power generation threshold.

10. An adjustable scaffold control model training device, characterized in that, The adjustable scaffold control model training device includes: The acquisition module is used to acquire various environmental simulation parameter values ​​and simulate the photovoltaic panel's light coverage under various preset control angles in a simulated environment using a photovoltaic panel simulation model. The adjustable support is a support connected to the photovoltaic panel, and the simulated environment is defined by target environmental simulation parameter values, which are any one of the various environmental simulation parameter values. The selection module is used to select a control angle from various preset control angles based on the photovoltaic panel's light coverage, such that the preset power generation parameters of the photovoltaic panel meet preset conditions, as the selected control angle corresponding to the target environment simulation parameter value, wherein the preset power generation parameters include power generation. The generation module is used to take the target environment simulation parameter value as the input feature data in the training sample, and take the selected control angle corresponding to the target environment simulation parameter value as the training label in the training sample to generate a training sample. The iteration module is used to iteratively optimize the adjustable stent control model based on multiple training samples generated from the various environmental simulation parameter values ​​to obtain the target adjustable stent control model. The training samples generated based on the various environmental simulation parameter values ​​include a first type of training sample and a second type of training sample. The input feature data in the first type of training sample also includes conventional operating condition parameter values, and the input feature data in the second type of training sample also includes special operating condition parameter values.

11. An adjustable scaffold control model training device, characterized in that, The adjustable stent control model training device includes: a memory, a processor, and an adjustable stent control model training program stored in the memory and executable on the processor. When the adjustable stent control model training program is executed by the processor, it implements the steps of the adjustable stent control model training method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an adjustable scaffold control model training program, which, when executed by a processor, implements the steps of the adjustable scaffold control model training method as described in any one of claims 1 to 9.

Images