Curved surface photovoltaic power prediction method and system

Abstract

The invention relates to a curved-surface photovoltaic power prediction method and system, and belongs to the technical field of photovoltaic power prediction.The method comprises the steps that three-dimensional modeling is conducted on curved-surface photovoltaic power on the basis of installation parameters of a photovoltaic module to obtain a curved-surface photovoltaic model; fitting the total irradiance received by the curved surface photovoltaic model in a preset time period by using the solar radiation data; establishing a mapping model of the total irradiance received by the curved-surface photovoltaic and the actual output power of the curved-surface photovoltaic, and obtaining a curved-surface photovoltaic power output calculation model; and inputting the curved surface photovoltaic output power and the screened meteorological factors into a neural network for training to obtain a parameter optimal model, and completing prediction of the curved surface photovoltaic output power by using the model. According to the method, the curved surface photovoltaic and solar radiation models are modeled, so that the prediction model not only can better reflect the geometrical shape and the installation angle of the photovoltaic module in practical application, but also can more accurately calculate the radiation quantity received by the photovoltaic module, and the reliability of power prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power prediction, and in particular to a method and system for predicting curved photovoltaic power. Background Art

[0002] As the global demand for renewable energy continues to increase, photovoltaic (PV) power generation, as a clean and sustainable form of energy, has become an important part of the global energy structure transformation. Especially in the context of accelerated urbanization, the rapid development of BIPV (building integrated photovoltaic) technology has enabled photovoltaic systems to not only generate electricity, but also play an aesthetic and structural role in buildings. The performance of these systems directly affects their economic benefits and feasibility, and accurate photovoltaic power prediction is the basis for efficient management and optimized configuration.

[0003] The commonly used data-driven photovoltaic power prediction technology mines the correspondence between power generation and historical meteorological data through training, selects similar input parameters after predicting future meteorological data, and uses a black box system model to estimate the photovoltaic output power. Since this process does not involve the effective extraction and analysis of physical information unique to curved photovoltaics (such as the complex and changeable radiation reception angle that affects the total radiation), the prediction accuracy is poor. The photovoltaic power prediction technology based on physics-driven physical modeling is based on the principles of photovoltaic power generation systems. The prediction model has a single applicable scenario, poor generalization ability, and the solution process has a large amount of computation and high operating costs. Summary of the invention

[0004] To solve the above problems, an object of the embodiments of the present invention is to provide a method and system for predicting curved photovoltaic power.

[0005] A curved photovoltaic power prediction method, comprising:

[0006] Step 1: Collect historical PV output power data, meteorological factor data, and PV module installation parameters;

[0007] Step 2: Calculate the correlation between each meteorological factor and the historical photovoltaic output power data, and extract the meteorological factors with correlation greater than the preset threshold as the screened meteorological factors;

[0008] Step 3: Perform three-dimensional modeling of the curved photovoltaic system based on the installation parameters of the photovoltaic modules to obtain a curved photovoltaic model;

[0009] Step 4: construct a solar radiation model using the solar trajectory data and meteorological factor data, and determine the solar radiation data within a preset time period based on the solar radiation model;

[0010] Step 5: Use solar radiation data to fit the total irradiance received by the curved photovoltaic model within a preset time period;

[0011] Step 6: Establish a mapping model between the total irradiance received by the curved photovoltaic system and the actual output power of the curved photovoltaic system, and obtain a calculation model for the power output of the curved photovoltaic system;

[0012] Step 7: Use the curved photovoltaic power output calculation model to calculate the curved photovoltaic output power under the corresponding meteorological factor data;

[0013] Step 8: Input the curved surface photovoltaic output power and the screened meteorological factors as data sets into a neural network for training to obtain an optimal parameter model, and use the optimal parameter model to complete the prediction of the target curved surface photovoltaic output power.

[0014] Preferably, the step 3: performing three-dimensional modeling of the curved photovoltaic based on the installation parameters of the photovoltaic module to obtain a curved photovoltaic model includes:

[0015] The position, number and change amplitude of the control points on the surface fitting model are changed to adjust the surface shape until the surface fitting model is fitted with the actual curved photovoltaic surface to obtain a curved photovoltaic model; wherein the surface fitting model is:

[0016]

[0017] Among them, W pq is the characteristic grid control point sequence on the rectangular area, W(a,b) is the point on the surface, ρ pq is the control point weight, Y p,W(a) is the first spline basis function, Y q,W(b) is the second spline basis function; x is the total number of control points in the A direction; y is the total number of control points in the B direction; p is the A unit vector; q is the B unit vector.

[0018] Preferably, the step 4: constructing a solar radiation model using solar trajectory data and meteorological factor data, and determining solar radiation data within a preset time period based on the solar radiation model, includes:

[0019] Step 4.1: Calculate the solar trajectory data using the solar declination angle, azimuth angle, and altitude angle calculation formula;

[0020] Step 4.2: Calculate the total solar radiation using the direct radiation and diffuse radiation calculation formulas;

[0021] Step 4.3: Determine the solar radiation data under different meteorological conditions within a preset time period based on the solar trajectory data, the total solar radiation and the meteorological factor data.

[0022] Preferably, in step 4.1, the solar declination angle calculation formula is:

[0023] δ=0.3723+23.2567·sin(ω0t)+0.1149sin(2ω0t)-0.1727sin(3ω0t)-

[0024] 0.7580cos(ω0t)+0.3656cos(2ω0t)+0.0201cos(3ω0t)

[0025] Wherein, δ represents the solar declination angle, ω0 = 2π / 365.2422, t = n-1-n0, n is the date, n0 = 79.6764 + [0.2422 (year-1985)] - int (0.25 (year-1985)), year is the year;

[0026] The formula for calculating the solar altitude angle is:

[0027] α=90°-|β-γ|

[0028] Among them, α represents the solar altitude angle, β represents the latitude of the target, and γ is the latitude of the direct solar angle;

[0029] The formula for calculating the solar azimuth angle is:

[0030] cosγ=(sinδsinβ-sinα) / (cosδcosβ)

[0031] Where cosγ represents the solar azimuth.

[0032] Preferably, in step 4.2, the direct radiation calculation formula is:

[0033] I DN =I0Pm

[0034] Among them, I DN is direct radiation, I0 is the solar constant, P is the atmospheric transparency, and m is the atmospheric mass

[0035] The diffuse radiation calculation formula is:

[0036] I d =I0(1-P)(1+cosα) / 2

[0037] Among them, I d For diffuse radiation.

[0038] Preferably, in step 6, the curved photovoltaic power output calculation model is:

[0039] W PV =ηS PV X

[0040] Among them, W PVis the surface photovoltaic power output, η is the photovoltaic conversion efficiency, S PV X is the total solar radiation received by the curved photovoltaic system.

[0041] The present invention also provides a curved photovoltaic power prediction system, comprising:

[0042] Data collection module, used to collect historical photovoltaic output power data, meteorological factor data and installation parameters of photovoltaic modules;

[0043] A screening module is used to calculate the correlation between each meteorological factor and the historical photovoltaic output power data, and extract meteorological factors with correlation greater than a preset threshold as the screened meteorological factors;

[0044] A curved photovoltaic model building module is used to perform three-dimensional modeling of curved photovoltaics based on the installation parameters of photovoltaic modules to obtain a curved photovoltaic model;

[0045] A solar radiation model building module is used to build a solar radiation model using solar trajectory data and meteorological factor data, and determine solar radiation data within a preset time period based on the solar radiation model;

[0046] The total irradiance fitting module is used to fit the total irradiance received by the curved photovoltaic model within a preset time period using solar radiation data;

[0047] The curved photovoltaic power output model building module is used to establish a mapping model between the total irradiance received by the curved photovoltaic and the actual output power of the curved photovoltaic, and obtain a curved photovoltaic power output calculation model;

[0048] A curved photovoltaic output power calculation module is used to calculate the curved photovoltaic output power under corresponding meteorological factor data using a curved photovoltaic power output calculation model;

[0049] The curved surface photovoltaic output power prediction module is used to input the curved surface photovoltaic output power and the screened meteorological factors as data sets into the neural network for training to obtain the optimal parameter model, and use the optimal parameter model to complete the prediction of the target curved surface photovoltaic output power.

[0050] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for predicting curved photovoltaic power.

[0051] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in the above-mentioned curved photovoltaic power prediction method when executed by a processor.

[0052] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0053] The present invention relates to a method for predicting curved surface photovoltaic power. Compared with the prior art, the present invention models curved surface photovoltaic and solar radiation models so that the prediction model can not only better reflect the geometric shape and installation angle of photovoltaic modules in practical applications, but also more accurately calculate the amount of radiation received by the photovoltaic modules, thereby improving the reliability of power prediction.

[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 A flow chart of a curved photovoltaic power prediction method provided by the present invention;

[0057] Figure 2 A flow chart for establishing a physical basis model of curved photovoltaic solar radiation provided by the present invention. DETAILED DESCRIPTION

[0058] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0059] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0060] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0061] See also Figure 1-2 , a curved photovoltaic power prediction method, comprising:

[0062] Step 1: Collect historical PV output power data, meteorological factor data, and PV module installation parameters;

[0063] In step 1, the present invention can collect historical photovoltaic power data, meteorological factor data (including but not limited to temperature, humidity, wind speed, clouds, etc.), and installation parameters of photovoltaic modules (including but not limited to inclination, azimuth, surface shape, etc.) from the official website of the Meteorological Bureau.

[0064] Step 2: Calculate the correlation between each meteorological factor and the historical photovoltaic output power data, and extract the meteorological factors with correlation greater than the preset threshold as the screened meteorological factors;

[0065] Step 3: Perform three-dimensional modeling of the curved photovoltaic system based on the installation parameters of the photovoltaic modules to obtain a curved photovoltaic model;

[0066] In practical applications, the present invention utilizes curved surface generation technology to adjust the curved surface shape by changing the position, number and variation amplitude of control points, thereby improving the degree of fit with the actual curved photovoltaic epidermis.

[0067] The surface fitting model is:

[0068]

[0069] Among them, W pq is the characteristic grid control point sequence on the rectangular area, W(a,b) is the point on the surface, ρ pq is the control point weight, Y p,W(a) is the first spline basis function, Y q,W(b)is the second spline basis function; x is the total number of control points in the A direction; y is the total number of control points in the B direction; p is the A unit vector; q is the B unit vector.

[0070] Step 4: construct a solar radiation model using the solar trajectory data and meteorological factor data, and determine the solar radiation data within a preset time period based on the solar radiation model;

[0071] In step 4, the present invention can use calculation formulas such as the solar declination angle, azimuth angle, altitude angle, etc. to calculate the solar trajectory at a specific time and region, import solar trajectory data and meteorological factor data, and combine the direct radiation and diffuse radiation calculation formulas to calculate the total solar radiation, analyze the solar radiation under specific meteorological conditions, generate solar trajectory diagrams for the whole day and the whole year, and obtain a solar radiation model based on the solar trajectory and meteorological conditions.

[0072] The formula for calculating the solar declination angle is:

[0073] δ=0.3723+23.2567·sin(ω0t)+0.1149sin(2ω0t)-0.1727sin(3ω0t)-0.7580cos(ω0t)+0.3656cos(2ω0t)+0.0201cos(3ω0t)

[0074] The formula for calculating the solar altitude angle is:

[0075] α=90°-|β-γ|

[0076] The formula for calculating the solar azimuth angle is:

[0077] cosγ=(sinδsinβ-sinα) / (cosδcosβ)

[0078] The direct radiation calculation formula is:

[0079] I DN =I0Pm

[0080] The diffuse radiation calculation formula is:

[0081] I d =I0(1-P)(1+cosα) / 2

[0082] Where δ represents the solar declination angle, ω0 = 2π / 365.2422, t = n-1-n0, n is the date, n0 = 79.6764 + [0.2422 (year-1985)] - int (0.25 (year-1985)), year is the year, I DN is direct radiation, I0 is the solar constant, P is the atmospheric transparency, and m is the atmospheric mass.

[0083] Step 5: Use solar radiation data to fit the total irradiance received by the curved photovoltaic model within a preset time period;

[0084] In step 5, the present invention first inputs the radiation calculation matrix into the solar radiation model, and the time period data to be analyzed, to obtain the solar radiation matrix of the specific time period, which contains the solar radiation data of each hour in the specific time period. The solar radiation matrix of the specific time period and the curved surface photovoltaic model are input, the model is divided into small curved surface units, and the solar radiation amount of each small curved surface unit in the specific time period is determined to obtain the total irradiance of each time period received by the curved surface photovoltaic.

[0085] Step 6: Establish a mapping model between the total irradiance received by the curved photovoltaic system and the actual output power of the curved photovoltaic system, and obtain a calculation model for the power output of the curved photovoltaic system;

[0086] The photovoltaic output power formula is as follows:

[0087] W PV =ηS PV X

[0088] Where η is the photovoltaic conversion efficiency, %; S PV X is the total solar radiation received by the curved photovoltaic system.

[0089] Step 7: Use the curved photovoltaic power output calculation model to calculate the curved photovoltaic output power under the corresponding meteorological factor data;

[0090] Step 8: Input the curved surface photovoltaic output power and the screened meteorological factors as data sets into a neural network for training to obtain an optimal parameter model, and use the optimal parameter model to complete the prediction of the target curved surface photovoltaic output power.

[0091] It should be noted that the training process of the present invention includes:

[0092] ① Data preprocessing: The collected meteorological factors with a high correlation with the output power, the total solar radiation based on the meteorological factors, and the power output values ​​predicted by the curved photovoltaic physical model are used as data sets, and standardized processing is performed to unify the data dimension.

[0093] ② Set the number of data sets with similar meteorological conditions to X, select X data sets closest to the forecast day conditions as sample inputs of the artificial neural network, and use X possible photovoltaic power values ​​constrained by the physical characteristics of curved photovoltaic surfaces as outputs to train the hybrid prediction model.

[0094] ③Model optimization: Use the output power results of the physical model to enhance the learning of the data-driven model. At the same time, according to the actual power output of curved photovoltaics, use the least squares method to find the optimal parameters by minimizing the MSE to achieve parameter adjustment and iteration of the model and obtain a model with optimal parameters.

[0095] ④ Prediction of curved photovoltaic output power: The power values ​​predicted by meteorological factors and the physical model of total solar radiation are used as data sets and standardized. Based on the optimal parameter model obtained through training, the data set closest to the predicted day conditions is selected as input, and the power is used as output to realize the prediction of curved photovoltaic power output.

[0096] According to the specific embodiments of the present invention, the present invention provides the following technical effects:

[0097] The present invention uses the sun's trajectory model to count the radiation data of curved photovoltaics in each time period, establishes a mapping relationship between the total solar radiation received by the curved photovoltaics and the actual output power, and uses it as a constraint and guide for the data model, providing more reliable physical information for the data-driven method, enhancing the understanding of the neural network, and greatly improving the accuracy of curved photovoltaic power output prediction.

[0098] The present invention also provides a curved photovoltaic power prediction system, comprising:

[0099] Data collection module, used to collect historical photovoltaic output power data, meteorological factor data and installation parameters of photovoltaic modules;

[0100] A screening module is used to calculate the correlation between each meteorological factor and the historical photovoltaic output power data, and extract meteorological factors with correlation greater than a preset threshold as the screened meteorological factors;

[0101] A curved photovoltaic model building module is used to perform three-dimensional modeling of curved photovoltaics based on the installation parameters of photovoltaic modules to obtain a curved photovoltaic model;

[0102] A solar radiation model building module is used to build a solar radiation model using solar trajectory data and meteorological factor data, and determine solar radiation data within a preset time period based on the solar radiation model;

[0103] The total irradiance fitting module is used to fit the total irradiance received by the curved photovoltaic model within a preset time period using solar radiation data;

[0104] The curved photovoltaic power output model building module is used to establish a mapping model between the total irradiance received by the curved photovoltaic and the actual output power of the curved photovoltaic, and obtain a curved photovoltaic power output calculation model;

[0105] A curved photovoltaic output power calculation module is used to calculate the curved photovoltaic output power under corresponding meteorological factor data using a curved photovoltaic power output calculation model;

[0106] The curved surface photovoltaic output power prediction module is used to input the curved surface photovoltaic output power and the screened meteorological factors as data sets into the neural network for training to obtain the optimal parameter model, and use the optimal parameter model to complete the prediction of the target curved surface photovoltaic output power.

[0107] Compared with the prior art, the beneficial effects of a curved surface photovoltaic power prediction system provided by the present invention are the same as the beneficial effects of a curved surface photovoltaic power prediction method described in the above technical solution, which will not be elaborated here.

[0108] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for predicting the power of a curved photovoltaic device. Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for predicting the power of a curved photovoltaic device described in the above-mentioned technical solution, and are not elaborated herein.

[0109] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned curved surface photovoltaic power prediction method are implemented. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the curved surface photovoltaic power prediction method described in the above-mentioned technical solution, which will not be repeated here.

[0110] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for predicting curved photovoltaic power, characterized in that: include: Step 1: Collect historical PV output power data, meteorological factor data, and PV module installation parameters; Step 2: Calculate the correlation between each meteorological factor and the historical photovoltaic output power data, and extract the meteorological factors with correlation greater than the preset threshold as the screened meteorological factors; Step 3: Perform three-dimensional modeling of the curved photovoltaic system based on the installation parameters of the photovoltaic modules to obtain a curved photovoltaic model; Step 4: construct a solar radiation model using the solar trajectory data and meteorological factor data, and determine the solar radiation data within a preset time period based on the solar radiation model; Step 5: Use solar radiation data to fit the total irradiance received by the curved photovoltaic model within a preset time period; Step 6: Establish a mapping model between the total irradiance received by the curved photovoltaic system and the actual output power of the curved photovoltaic system, and obtain a calculation model for the power output of the curved photovoltaic system; Step 7: Use the curved photovoltaic power output calculation model to calculate the curved photovoltaic output power under the corresponding meteorological factor data; Step 8: Input the curved surface photovoltaic output power and the screened meteorological factors as data sets into a neural network for training to obtain an optimal parameter model, and use the optimal parameter model to complete the prediction of the target curved surface photovoltaic output power.

2. A curved photovoltaic power prediction method according to claim 1, characterized in that: The step 3: performing three-dimensional modeling of the curved photovoltaic based on the installation parameters of the photovoltaic module to obtain a curved photovoltaic model, including: The position, number and change amplitude of the control points on the surface fitting model are changed to adjust the surface shape until the surface fitting model is fitted with the actual curved photovoltaic surface to obtain a curved photovoltaic model; wherein the surface fitting model is: Among them, W pq is the characteristic grid control point sequence on the rectangular area, W(a,b) is the point on the surface, ρ pq is the control point weight, Y p,W(a) is the first spline basis function, Y q,W(b) is the second spline basis function; x is the total number of control points in the A direction; y is the total number of control points in the B direction; p is the A unit vector; q is the B unit vector.

3. A curved photovoltaic power prediction method according to claim 2, characterized in that: The step 4: constructing a solar radiation model using the solar trajectory data and the meteorological factor data, and determining the solar radiation data within a preset time period based on the solar radiation model, includes: Step 4.1: Calculate the solar trajectory data using the solar declination angle, azimuth angle, and altitude angle calculation formula; Step 4.2: Calculate the total solar radiation using the direct radiation and diffuse radiation calculation formulas; Step 4.3: Determine the solar radiation data under different meteorological conditions within a preset time period based on the solar trajectory data, the total solar radiation and the meteorological factor data.

4. A curved photovoltaic power prediction method according to claim 3, characterized in that: In step 4.1, the solar declination angle is calculated as: δ=0.3723+23.2567·sin(ω0t)+0.1149sin(2ω0t)-0.1727sin(3ω0t)- 0.7580cos(ω0t)+0.3656cos(2ω0t)+0.0201cos(3ω0t) Wherein, δ represents the solar declination angle, ω0 = 2π / 365.2422, t = n-1-n0, n is the date, n0 = 79.6764 + [0.2422 (year-1985)] - int (0.25 (year-1985)), year is the year; The formula for calculating the solar altitude angle is: α=90o-|β-γ| Among them, α represents the solar altitude angle, β represents the latitude of the target, and γ is the latitude of the direct solar angle; The formula for calculating the solar azimuth angle is: cosγ=(sinδsinβ-sinα) / (cosδcosβ) Where cosγ represents the solar azimuth.

5. A curved photovoltaic power prediction method according to claim 4, characterized in that: In step 4.2, the direct radiation calculation formula is: I DN =I0Pm Among them, I DN is direct radiation, I0 is the solar constant, P is the atmospheric transparency, and m is the atmospheric mass The diffuse radiation calculation formula is: I d =I0(1-P)(1+cosα) / 2 Among them, I d For diffuse radiation.

6. A curved photovoltaic power prediction method according to claim 5, characterized in that: In step 6, the curved photovoltaic power output calculation model is: W PV =ηS PV X Among them, W PV is the surface photovoltaic power output, η is the photovoltaic conversion efficiency, S PV X is the total solar radiation received by the curved photovoltaic system.

7. A curved photovoltaic power prediction system, characterized in that: include: Data collection module, used to collect historical photovoltaic output power data, meteorological factor data and installation parameters of photovoltaic modules; A screening module is used to calculate the correlation between each meteorological factor and the historical photovoltaic output power data, and extract meteorological factors with correlation greater than a preset threshold as the screened meteorological factors; A curved photovoltaic model building module is used to perform three-dimensional modeling of curved photovoltaics based on the installation parameters of photovoltaic modules to obtain a curved photovoltaic model; A solar radiation model building module is used to build a solar radiation model using solar trajectory data and meteorological factor data, and determine solar radiation data within a preset time period based on the solar radiation model; The total irradiance fitting module is used to fit the total irradiance received by the curved photovoltaic model within a preset time period using solar radiation data; The curved photovoltaic power output model building module is used to establish a mapping model between the total irradiance received by the curved photovoltaic and the actual output power of the curved photovoltaic, and obtain a curved photovoltaic power output calculation model; A curved photovoltaic output power calculation module is used to calculate the curved photovoltaic output power under corresponding meteorological factor data using a curved photovoltaic power output calculation model; The curved surface photovoltaic output power prediction module is used to input the curved surface photovoltaic output power and the screened meteorological factors as data sets into the neural network for training to obtain the optimal parameter model, and use the optimal parameter model to complete the prediction of the target curved surface photovoltaic output power.

8. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the curved photovoltaic power prediction method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in a curved photovoltaic power prediction method as described in any one of claims 1 to 6 are implemented.

Images