CN111865203A - Photovoltaic power generation method, device, computer equipment and storage medium - Google Patents

Abstract

The invention relates to the field of photovoltaic power generation, and discloses a photovoltaic power generation method, a photovoltaic power generation device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring a sky image through a preset shooting device; inputting the sky image into a preset image processing model, and acquiring ambient light data output by the preset image processing model; processing position data and ambient light data of the solar panel array by a preset Hay-Davies model to generate predicted light energy data; and processing the predicted light energy data according to a preset AI calculation model, and outputting the adjustment angle of the solar panel array. The intelligent weather recognition system can intelligently recognize the weather condition of the photovoltaic power station and improve the generating capacity of the solar panel array.

Description

Photovoltaic power generation method, device, computer equipment and storage medium

technical field

The present invention relates to the field of photovoltaic power generation, and in particular, to a photovoltaic power generation method, device, computer equipment and storage medium.

Background technique

As a device that can absorb solar thermal radiant energy, solar panels convert radiant energy directly or indirectly into electrical energy through the photoelectric effect or photochemical effect. At present, most solar panels are placed at a fixed angle, or the rotation is controlled by adding a light sensor and a motor in cooperation. However, due to the randomness of the sky scene, light sensors do not have the ability to accurately identify and track the sun, and these two traditional methods have limitations on the efficiency of solar energy harvesting.

SUMMARY OF THE INVENTION

Based on this, it is necessary to provide a photovoltaic power generation method, device, computer equipment and storage medium for the above technical problems, so as to intelligently identify the weather conditions of the photovoltaic power station and increase the power generation of the solar panel array.

A photovoltaic power generation method, comprising:

Obtain the sky image through the preset shooting device;

Inputting the sky image into a preset image processing model, and obtaining ambient light data output by the preset image processing model;

The position data of the solar panel array and the ambient light data are processed by a preset Hay-Davies model to generate predicted light energy data;

The predicted light energy data is processed according to the preset AI calculation model, and the adjustment angle of the solar panel array is output.

A photovoltaic power generation device, comprising:

an image acquisition module for acquiring sky images through a preset shooting device;

an image processing module, configured to input the sky image into a preset image processing model, and obtain ambient light data output by the preset image processing model;

A light energy prediction module, configured to process the position data of the solar panel array and the ambient light data through a preset Hay-Davies model to generate predicted light energy data;

The angle output module is used to process the predicted light energy data according to the preset AI calculation model, and output the adjustment angle of the solar panel array.

A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, the processor implementing the photovoltaic power generation method described above when the processor executes the computer-readable instructions.

A computer-readable storage medium storing computer-readable instructions, the computer-readable instructions implementing the above photovoltaic power generation method when executed by a processor.

In the above photovoltaic power generation method, device, computer equipment and storage medium, a sky image is acquired by a preset photographing device, so as to predict weather conditions according to the sky image. Input the sky image into a preset image processing model, and obtain ambient light data output by the preset image processing model. Here, the preset image processing model is obtained by training based on historical sky image data, and the prediction accuracy is relatively high. high. The position data of the solar panel array and the ambient light data are processed by a preset Hay-Davies model to generate predicted light energy data, where the predicted light energy data may refer to the radiation intensity of the inclined surface of the solar panel array. The predicted light energy data is processed according to the preset AI calculation model, and the adjustment angle of the solar panel array is output. Here, the preset AI calculation model is obtained by training based on historical data, and the optimal adjustment angle of the solar panel array can be determined. The invention can intelligently identify the weather conditions of the photovoltaic power station, and increase the power generation of the solar panel array.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the drawings that are used in the description of the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention. , for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative labor.

1 is a schematic diagram of an application environment of a photovoltaic power generation method in an embodiment of the present invention;

2 is a schematic flowchart of a photovoltaic power generation method in an embodiment of the present invention;

3 is a schematic flowchart of a photovoltaic power generation method in an embodiment of the present invention;

4 is a schematic flowchart of a photovoltaic power generation method in an embodiment of the present invention;

5 is a schematic flowchart of a photovoltaic power generation method in an embodiment of the present invention;

6 is a schematic flowchart of a photovoltaic power generation method in an embodiment of the present invention;

7 is a schematic structural diagram of a photovoltaic power generation device in an embodiment of the present invention;

FIG. 8 is a schematic diagram of a computer device in an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

The photovoltaic method provided in this embodiment can be applied in the application environment as shown in FIG. 1 , in which the client and the server communicate. Among them, clients include but are not limited to various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers.

In one embodiment, as shown in FIG. 2 , a photovoltaic power generation method is provided, and the method is applied to the server in FIG. 1 as an example for description, including the following steps:

S10, acquiring a sky image through a preset shooting device;

S20. Input the sky image into a preset image processing model, and obtain ambient light data output by the preset image processing model;

S30. Process the position data of the solar panel array and the ambient light data by using a preset Hay-Davies model to generate predicted light energy data;

S40. Process the predicted light energy data according to a preset AI calculation model, and output the adjustment angle of the solar panel array.

Illustratively, 600 solar panels are deployed on a flat ground with a radius of 5 kilometers to form a solar panel array. Set up a LoRa (a wireless networking standard) gateway in the center of the flat. The LoRa gateway can connect with the cloud platform through a wireless network. The server is provided with an AI (artificial intelligence) computing chip. The AI computing chip can be set up on the cloud platform or locally in the photovoltaic power station. The LoRa gateway is connected to the server.

In this embodiment, the preset photographing device may be set according to actual needs. The preset camera can acquire sky images of the entire sky (or most of the sky). Illustratively, five cameras may be set, wherein the shooting orientations of the four cameras are perpendicular to each other (for example, it may be east, west, north, south), and the shooting orientation of the other camera is vertically upward. An ND mirror (light reduction mirror) can be set on the camera as required to reduce damage to the camera by external light. The sky image obtained by the preset photographing device may be transmitted to the server through a network (which may be a wired network or a wireless network). The shooting frequency of sky images can be set as required, such as 10 images/min. If the sky image is captured with an ND mirror, when processing the sky image, it is necessary to perform light enhancement processing on the sky image, that is, fill light for each pixel of the image according to the transmittance of the ND mirror.

On the server side, the preset settings have multiple preset image processing models for calculating different ambient light data. In the early stage of operation of photovoltaic power plants, the amount of data of sky images is small. At this time, the preset image processing model may be a computational model constructed by a machine learning algorithm. Take multiple eigenvalues of multiple sky images to obtain predicted values. For example, the predicted value can be the sun particle, which can be set as the feature value through a series of features such as the shape of the sun and the brightness value. These data are trained through machine learning, and a preset image processing model is obtained after the training is completed. Similarly, if the predicted value is a cloud, a cloud trajectory or a sun trajectory, the corresponding feature value can also be extracted, and then trained through a suitable training set to obtain a preset image processing model. Thus, it is possible to input the current sky image into the preset image processing model, and obtain the corresponding prediction result (here, the prediction result refers to the predicted light energy data).

In the middle and later stages of the operation of photovoltaic power plants, the amount of data of sky images is large. At this time, the preset image processing model is obtained after training sky image samples based on a deep learning algorithm. In the process of deep learning, the sky image data set and the result data set are input, and feature values are automatically obtained through a multi-layer neural network, and a preset image processing model is obtained after training on a large number of data sets. Similarly, the preset image processing model can output the position of the image of each cloud and the sun at any point in time. According to statistics, in the case of enough samples, the accuracy of the results obtained by deep learning will be better than that of machine learning.

By processing the sky image by the preset image processing model, the ambient light data of one day can be obtained. Ambient light data includes weather data related to the amount of electricity produced by the solar panel array. Specifically, the ambient light data includes, but is not limited to, the sun's trajectory (including the sun's altitude and sun's azimuth), the cloud's trajectory, the amount of cloud, and the transparency of the atmosphere.

The default Hay-Davies model is a practical calculation model for solar irradiance on inclined planes. The Hay-Davies model can calculate the total radiation intensity I _θ of the inclined plane. Here, the radiation intensity of the solar panel array can be calculated based on the ambient light data output by the preset image processing model, that is, the altitude and azimuth of the sun, and atmospheric transparency, combined with the altitude and azimuth of the solar panel array. . Further, the amount of electricity generated can be calculated in combination with the light energy conversion rate of the solar panel array.

The preset AI calculation model is an analysis model constructed based on historical solar panel array operation record data and historical sky image data. The preset AI calculation model can be used to determine the adjustment angle of the current solar panel array, so that the solar panel array is at the best tilt angle. Here, when the solar panel array is at the optimal tilt angle, the solar panel array is not necessarily facing the sun, but may be at a certain angle (that is, the line connecting the center of the sun and the solar panel is not perpendicular to the plane where the solar panel is located). ). This is because adjusting the inclination angle of the solar panel array needs to consume a certain amount of energy. If the increment of power generation after adjusting the angle is smaller than the energy consumed by adjusting the angle, the angle adjustment is not performed. Here, adjustment angle=optimum tilt angle (ie, optimum angle)-current tilt angle. When the preset AI calculation model determines that no angle deflection is currently required, the adjustment angle is zero.

In steps S10-S40, a sky image is acquired by a preset photographing device, so as to predict weather conditions according to the sky image. Input the sky image into a preset image processing model, and obtain ambient light data output by the preset image processing model. Here, the preset image processing model is obtained by training based on historical sky image data, and the prediction accuracy is relatively high. high. The position data of the solar panel array and the ambient light data are processed by a preset Hay-Davies model to generate predicted light energy data, where the predicted light energy data may refer to the radiation intensity of the inclined surface of the solar panel array. The predicted light energy data is processed according to the preset AI calculation model, and the adjustment angle of the solar panel array is output. Here, the preset AI calculation model is obtained by training based on historical data, and the optimal adjustment angle of the solar panel array can be determined.

Optionally, as shown in FIG. 3 , step S40, that is, processing the predicted light energy data according to the preset AI calculation model, and outputting the adjustment angle of the solar panel array, including:

S401. Obtain an optimal angle and an optimal power generation amount according to the predicted light energy data;

S402. Obtain the current power generation amount, and calculate the difference between the optimal power generation amount and the current power generation amount;

S403. When the difference is greater than a preset threshold, calculate the angle difference between the optimal angle and the current angle of the solar panel array, where the angle difference is the adjustment angle.

In this embodiment, if the predicted light energy data includes the optimal angle and the optimal power generation amount, the optimal angle and the optimal power generation amount are directly extracted from the predicted light energy data. If the predicted light energy data does not include the optimal angle and the optimal power generation amount, the optimal angle and the optimal power generation amount can be calculated based on the predicted light energy data. The sun's altitude and azimuth are included in the predicted light energy data. The optimal angle refers to the vertical sunlight on the solar panel array. At this time, the azimuth angle of the solar panel array is the same as the azimuth angle of the sun, and the tilt angle is the height angle of the sun plus 90 degrees.

Optimum power generation refers to the power generation when the solar panel array is at the optimum angle. Optimal power generation = radiation intensity * photovoltaic panel conversion rate. The radiant intensity may refer to the total radiant intensity of the inclined plane. The total radiation intensity I _θ of the inclined surface = the direct radiation intensity of the inclined surface I _Dθ + the scattered radiation intensity of the inclined surface I _dθ + the ground reflected radiation intensity of the inclined surface I _Rθ .

Wherein, the direct radiation intensity of the inclined plane I _Dθ = I _DN cosi. i is the incident angle of the sun, that is, the angle between the incident ray of the sun and the plane normal. I _DN refers to the intensity of radiation to the sun. The normal solar radiation intensity I _DN can be calculated by the following formula:

I _DN =I ₀ P ^m .

In the formula, I ₀ is the solar constant, which refers to the solar radiation energy received per unit area and unit time on the surface of the earth's upper boundary perpendicular to the sun's rays when the earth is at the average annual distance between the sun and the earth, and its value is 1367±7W /m ² . Since the change of solar radiation intensity caused by the change of the distance between the sun and the earth does not exceed 3.4%, I ₀ can be regarded as a constant here. P refers to atmospheric transparency. The solar mass m refers to the ratio of the distance the sun's rays travel through the Earth's atmosphere to the distance the sun's rays travel through the Earth's atmosphere when the sun is at the zenith.

其中，θ为太阳能板摆放的太阳高度角，I_dH为水平面散射辐射强度。

式中，h为太阳高度角。Inclined plane scattered radiation intensity

Among them, θ is the altitude angle of the sun where the solar panel is placed, and I _dH is the scattered radiation intensity on the horizontal plane.

In the formula, h is the altitude angle of the sun.

Radiation intensity I _Rθ =ρ _G I _H (1-sinθ) reflected from the sloped surface. Among them, ρ _G is the reflectivity of natural surface to solar radiation, which is generally 0.2. I _H is the total radiation intensity on the horizontal plane, and its value is:

After calculating the optimum power generation amount, the difference between the optimum power generation amount and the current power generation amount can be obtained. When the difference is greater than the preset threshold, the angle difference between the optimal angle and the current angle of the solar panel array is calculated, and the difference is the adjustment angle. That is, it is necessary to adjust the inclination angle of the solar panel array to the optimum angle. Here, the preset threshold can be set according to actual needs. In some cases, the preset threshold is related to the energy required to adjust the tilt angle of the solar panel array. For example, the energy required to adjust the tilt angle of the solar panel array is Q, and the preset threshold can be set to 1.2Q.

Optionally, as shown in FIG. 4 , after step S20, that is, after the sky image is input into the preset image processing model, the method further includes:

S21, obtaining disaster alarm data output by the preset image processing model;

S22. When the disaster alarm data includes a threatening disaster, adjust the angle of the solar panel array to a preset safe angle.

In this embodiment, the preset image processing model can be trained on some images that can predict disaster weather, so that it has the capability of disaster warning. That is to say, the preset image processing model can simultaneously output disaster warning data when processing sky images. The disaster warning data can be blank, that is, no disaster occurs. Disaster alert data can include threatening disasters such as strong winds, hail. When there is such a threatening disaster, it is necessary to adjust the angle of the solar panel array to a preset safe angle and give a safety warning. The staff can take corresponding preventive measures according to the safety warning to ensure the safety of the solar panel array.

Optionally, the ambient light data includes atmospheric transparency, the altitude angle and the azimuth angle of the sun.

Here, atmospheric transparency, the altitude and azimuth of the sun are important environmental data that determine the radiation intensity of the inclined plane of the solar panel array. Based on these ambient light data and the azimuth and elevation angles of the solar panel array, the radiation intensity of the inclined surface of the solar panel array can be accurately calculated.

Optionally, as shown in FIG. 5 , after step S30, after obtaining the predicted light energy data output by the preset image processing model, the method further includes:

S301. Acquire all-day predicted light energy data;

S302, processing the predicted light energy data by an enumeration method to generate a plurality of all-day power generation data;

S303, determining the all-day power generation data with the highest power generation as the optimal data;

S304, acquiring angle adjustment information of the solar panel array corresponding to the optimal data;

S305. Optimize the preset AI calculation model according to the angle adjustment information.

Through the calculation in the previous embodiment, the solar radiation intensity and power generation of the inclined plane obtained at each time point are the predicted light energy data for the whole day. The power consumption of the motor rotating at different angles is taken as a known quantity, the sky image, and the solar azimuth that is provided to the electronic control system after the model is calculated, that is, the sun altitude angle and the sun azimuth angle. The electronic control system rotates the motor according to the sun azimuth information to face the sun. Effect. Enumerate multiple time points when the motor needs to rotate or not rotate, and add the different power generation obtained by the altitude angle and azimuth angle of the enumerated different state result time points, by calculating the different time points of the motor Rotate to the sun's altitude and azimuth and continue to compare, and the whole-day power generation data can be obtained in all the enumeration time points when the motor rotates or does not rotate.

In an example, a day is set as 12 time points, and there are 2 ¹² possibilities for the state of motor rotation and non-rotation at each time point, that is, the total number of digits is 12-bit 000000000000–111111111111 enumeration state, and the Nth bit is 1 That means the motor rotates at the Nth time point, and 0 means no rotation. By adding up the power obtained at each time point in each possible state, the power generation data for the whole day can be obtained. From this, ²¹² all-day power generation data can be calculated, that is, 4096 all-day power generation data. Here, the whole-day power generation data refers to the power generation after subtracting the energy consumed by the rotation of the motor. Then, the whole-day power generation data with the highest output power is selected as the optimal data. In this way, the angle adjustment information of the solar panel array corresponding to the optimal data can be obtained. For example, the angle adjustment information of the solar panel array corresponding to the optimal data may be 001011110100. The angle adjustment information can be used to further optimize the preset AI calculation model. For example, for the currently calculated predicted light energy data, similar historical predicted light energy data records can be searched for, and corresponding angle adjustment information can be obtained. If there are multiple historically predicted light energy data records and the angle adjustment information is different, the final angle adjustment information may be selected by voting.

Optionally, as shown in FIG. 6 , after step S30, that is, after obtaining the predicted light energy data output by the preset image processing model, the method further includes:

S31. Calculate and estimate power generation data according to the predicted light energy data;

S32 , verifying the actual power generation data according to the estimated power generation data to generate a verification result.

In this embodiment, after the predicted light energy data is obtained, the estimated power generation data can be calculated. The estimated power generation data may refer to estimated power generation data within one cycle. Here, the period can be set as required, such as days, months, or weeks. The actual power generation data refers to the actual power generation data within the same time period as the estimated power generation data. Usually, there is a certain deviation between the estimated power generation data and the actual power generation data, but there is a reasonable deviation range. For example, the actual power generation data may be within ±10% of the estimated power generation data. The actual power generation data is verified according to the estimated power generation data, in order to verify the authenticity of the actual power generation data. If the actual power generation data is much larger than the estimated power generation data, there is a problem of photovoltaic power theft (referring to the use of forged power generation data to defraud subsidies). If the actual power generation data is less than the lower limit of the estimated power generation data, there may be a fault in the line, causing the power of the photovoltaic power station to fail to connect to the grid normally. That is to say, after verification, there may be three verification results, one is normal, and the other two are abnormal.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

In one embodiment, a photovoltaic power generation device is provided, and the photovoltaic power generation device corresponds one-to-one with the photovoltaic power generation method in the above-mentioned embodiment. As shown in FIG. 7 , the photovoltaic power generation device includes an image acquisition module 10 , an image processing module 20 , a light energy prediction module 30 and an angle output module 40 . The detailed description of each functional module is as follows:

an image acquisition module 10, configured to acquire a sky image through a preset photographing device;

An image processing module 20, configured to input the sky image into a preset image processing model, and obtain ambient light data output by the preset image processing model;

A light energy prediction module 30, configured to process the position data of the solar panel array and the ambient light data by using a preset Hay-Davies model to generate predicted light energy data;

The angle output module 40 is configured to process the predicted light energy data according to the preset AI calculation model, and output the adjustment angle of the solar panel array.

Optionally, the angle output module 40 includes:

calculating an optimal data unit for obtaining an optimal angle and an optimal power generation amount according to the predicted light energy data;

a difference calculating unit, configured to obtain the current power generation amount, and calculate the difference between the optimal power generation amount and the current power generation amount;

A calculating and adjusting angle unit for calculating the angle difference between the optimal angle and the current angle of the solar panel array when the difference is greater than a preset threshold, and the angle difference is the adjustment angle.

Optionally, the photovoltaic power generation device further includes:

an obtaining disaster data module for obtaining disaster warning data output by the preset image processing model;

The safety adjustment module is used to adjust the angle of the solar panel array to a preset safety angle when the disaster alarm data includes a threatening disaster.

Optionally, the ambient light data includes atmospheric transparency, the altitude angle and the azimuth angle of the sun.

Optionally, the photovoltaic power generation device further includes:

The acquisition data module is used to acquire the predicted light energy data of the whole day;

a data processing module, configured to process the predicted light energy data through an enumeration method to generate a plurality of all-day power generation data;

Determine the optimal data module, which is used to determine the all-day power generation data with the highest power generation as the optimal data;

an angle adjustment information acquisition module, configured to acquire angle adjustment information of the solar panel array corresponding to the optimal data;

A model optimization module, configured to optimize the preset AI computing model according to the angle adjustment information.

Optionally, the photovoltaic power generation device further includes:

an estimated power generation module, configured to calculate and estimate power generation data according to the predicted light energy data;

A verification module, configured to verify the actual power generation data according to the estimated power generation data, and generate a verification result.

For the specific limitation of the photovoltaic power generation device, reference may be made to the definition of the photovoltaic power generation method above, which will not be repeated here. Each module in the above photovoltaic power generation device can be implemented in whole or in part by software, hardware and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided, and the computer device may be a server, and its internal structure diagram may be as shown in FIG. 8 . The computer device includes a processor, memory, a network interface, and a database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, computer readable instructions and a database. The internal memory provides an environment for the execution of the operating system and computer-readable instructions in the non-volatile storage medium. The database of the computer equipment is used to store the data involved in the above photovoltaic power generation method. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer readable instructions, when executed by a processor, implement a photovoltaic power generation method.

In one embodiment, a computer device is provided, comprising a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor, and the processor implements the following steps when executing the computer-readable instructions:

Obtain the sky image through the preset shooting device;

Inputting the sky image into a preset image processing model, and obtaining ambient light data output by the preset image processing model;

The position data of the solar panel array and the ambient light data are processed by a preset Hay-Davies model to generate predicted light energy data;

The predicted light energy data is processed according to the preset AI calculation model, and the adjustment angle of the solar panel array is output.

In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided, and the readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media storage medium. Computer-readable instructions are stored on the readable storage medium, and when the computer-readable instructions are executed by one or more processors, implement the following steps:

Obtain the sky image through the preset shooting device;

Inputting the sky image into a preset image processing model, and obtaining ambient light data output by the preset image processing model;

The position data of the solar panel array and the ambient light data are processed by a preset Hay-Davies model to generate predicted light energy data;

The predicted light energy data is processed according to the preset AI calculation model, and the adjustment angle of the solar panel array is output.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile computer. In the readable storage medium, the computer-readable instructions, when executed, may include the processes of the foregoing method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be used for the foregoing implementations. The technical solutions described in the examples are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the within the protection scope of the present invention.

Claims (10)

1. A photovoltaic power generation method, characterized in that, comprising: Obtain the sky image through the preset shooting device; Inputting the sky image into a preset image processing model, and obtaining ambient light data output by the preset image processing model; The position data of the solar panel array and the ambient light data are processed by a preset Hay-Davies model to generate predicted light energy data; The predicted light energy data is processed according to the preset AI calculation model, and the adjustment angle of the solar panel array is output. 2 . The photovoltaic power generation method according to claim 1 , wherein processing the predicted light energy data according to a preset AI calculation model and outputting the adjustment angle of the solar panel array, comprising: 2 . Obtain the optimal angle and optimal power generation according to the predicted light energy data; obtaining the current power generation amount, and calculating the difference between the optimal power generation amount and the current power generation amount; When the difference is greater than a preset threshold, an angle difference between the optimum angle and the current angle of the solar panel array is calculated, and the angle difference is the adjustment angle. 3. The photovoltaic power generation method according to claim 1, wherein after inputting the sky image into a preset image processing model, the method further comprises: obtaining the disaster alarm data output by the preset image processing model; When the disaster warning data includes a threatening disaster, the angle of the solar panel array is adjusted to a preset safe angle. 4. The photovoltaic power generation method according to claim 1, wherein the ambient light data includes atmospheric transparency, altitude and azimuth of the sun. 5 . The photovoltaic power generation method according to claim 1 , wherein the processing of the position data of the solar panel array and the ambient light data by using a preset Hay-Davies model, and after generating the predicted light energy data, further comprises: 6 . Obtain forecasted light energy data throughout the day; Process the predicted light energy data by an enumeration method to generate a plurality of all-day power generation data; Determine the all-day power generation data with the highest power generation as the optimal data; acquiring angle adjustment information of the solar panel array corresponding to the optimal data; The preset AI calculation model is optimized according to the angle adjustment information. 6 . The photovoltaic power generation method according to claim 1 , wherein after acquiring the predicted light energy data output by the preset image processing model, the method further comprises: 7 . Calculate and estimate power generation data according to the predicted light energy data; The actual power generation data is verified according to the estimated power generation data, and a verification result is generated. 7. A photovoltaic power generation device, comprising: an image acquisition module for acquiring sky images through a preset shooting device; an image processing module, configured to input the sky image into a preset image processing model, and obtain ambient light data output by the preset image processing model; A light energy prediction module for processing the position data of the solar panel array and the ambient light data through a preset Hay-Davies model to generate predicted light energy data; The angle output module is used to process the predicted light energy data according to the preset AI calculation model, and output the adjustment angle of the solar panel array. 8. The photovoltaic power generation device of claim 7, further comprising: The acquisition data module is used to acquire the predicted light energy data of the whole day; a data processing module, configured to process the predicted light energy data through an enumeration method to generate a plurality of all-day power generation data; Determine the optimal data module, which is used to determine the all-day power generation data with the highest power generation as the optimal data; an angle adjustment information acquisition module, configured to acquire angle adjustment information of the solar panel array corresponding to the optimal data; A model optimization module, configured to optimize the preset AI computing model according to the angle adjustment information. 9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein when the processor executes the computer-readable instructions A photovoltaic power generation method as claimed in any one of claims 1 to 6 is realized. 10. One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the operations of claims 1 to 6 The photovoltaic power generation method of any one.

Images