Photovoltaic-assembly modeling method and apparatus based on knowledge and data dual-driven artificial intelligence, and device and storage medium

Abstract

Provided in the embodiments of the present invention are a photovoltaic-assembly modeling method and apparatus, and a device and a storage medium. The method comprises: collecting first operating condition data corresponding to a photovoltaic assembly, wherein the first operating condition data comprises environment information corresponding to the photovoltaic assembly and an output power corresponding to the photovoltaic assembly; determining a photovoltaic-assembly physical model, wherein the photovoltaic-assembly physical model is used for representing the output power corresponding to the photovoltaic assembly under different environment conditions; on the basis of the first operating condition data, performing parameter identification on a plurality of photovoltaic assembly parameters in the photovoltaic-assembly physical model, so as to obtain target parameter values respectively corresponding to the plurality of photovoltaic assembly parameters; and on the basis of the target parameter values respectively corresponding to the plurality of photovoltaic assembly parameters, and the photovoltaic-assembly physical model, establishing a photovoltaic-assembly simulation model. In this way, a more accurate photovoltaic-assembly simulation model can be constructed.

Description

Photovoltaic module modeling method, device, equipment and storage medium Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a photovoltaic module modeling method, device, equipment and storage medium. Background Art

[0002] Photovoltaic modules are widely used in various applications. They are the core components of solar power generation, using the photovoltaic cells within the module to convert solar energy into electricity. The conversion efficiency of the multiple photovoltaic cells within a module is a direct factor influencing the conversion of solar energy into electricity. The output power of multiple photovoltaic cells exhibits a nonlinear relationship with factors such as the operating environment's irradiance and the module's temperature. Therefore, changes in environmental factors such as irradiance can significantly shift the maximum power point of the module, affecting its performance.

[0003] To understand the performance of photovoltaic modules under various operating conditions, we can model them. This simulation model can be used to predict the module's operating status. This allows us to track the module's maximum power point, detect faults, and adjust the power generation system accordingly. Therefore, there is an urgent need to develop an accurate, efficient, and reliable photovoltaic module simulation model.

[0004] Summary of the Invention

[0005] The embodiments of the present invention provide a photovoltaic module modeling method, apparatus, device, and storage medium for constructing an accurate photovoltaic module simulation model so that the photovoltaic module simulation model can better reflect the actual working performance of the photovoltaic module. Specifically:

[0006] In a first aspect, an embodiment of the present invention provides a photovoltaic module modeling method, the method comprising:

[0007] Collecting first operating condition data corresponding to the photovoltaic assembly, where the first operating condition data includes environmental information corresponding to the photovoltaic assembly and output power corresponding to the photovoltaic assembly;

[0008] Determining a photovoltaic module physical model, wherein the photovoltaic module physical model is used to characterize the output power corresponding to the photovoltaic module under different environmental conditions;

[0009] performing parameter identification on a plurality of photovoltaic module parameters in the photovoltaic module physical model according to the first operating condition data to obtain target parameter values ​​corresponding to each of the plurality of photovoltaic module parameters, wherein the photovoltaic module parameters are used to describe the operating state of the photovoltaic module under each operating condition;

[0010] A photovoltaic module simulation model is constructed based on the target parameter values ​​corresponding to each of the multiple photovoltaic module parameters and the photovoltaic module physical model. The input of the photovoltaic module simulation model is the environmental information corresponding to the photovoltaic module under the current working conditions, and the output of the photovoltaic module simulation model is the output power of the photovoltaic module under the current working conditions.

[0011] In a second aspect, an embodiment of the present invention provides a photovoltaic module modeling device, the device comprising:

[0012] a data acquisition module, configured to acquire first operating condition data corresponding to the photovoltaic assembly, wherein the first operating condition data includes environmental information corresponding to the photovoltaic assembly and output power corresponding to the photovoltaic assembly, wherein the environmental information includes a plurality of environmental characteristic data;

[0013] A physical model determination module is used to determine a physical model of a photovoltaic module, wherein the physical model of the photovoltaic module is used to characterize the output power corresponding to the photovoltaic module under different environmental conditions;

[0014] a parameter determination module, configured to perform parameter identification on a plurality of photovoltaic module parameters in the photovoltaic module physical model according to the first operating condition data, so as to obtain target parameter values ​​corresponding to each of the plurality of photovoltaic module parameters, wherein the photovoltaic module parameters are used to describe the operating state of the photovoltaic module under various operating conditions;

[0015] A simulation model construction module is used to construct a photovoltaic module simulation model based on the target parameter values ​​corresponding to the multiple photovoltaic module parameters and the photovoltaic module physical model. The input of the photovoltaic module simulation model is the environmental information corresponding to the photovoltaic module under the current working conditions, and the output of the photovoltaic module simulation model is the output power of the photovoltaic module under the current working conditions.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device comprising: a memory and a processor; the memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement each step in the photovoltaic module modeling method provided in an embodiment of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the steps of the photovoltaic module modeling method provided by the embodiment of the present invention.

[0018] The photovoltaic module modeling solution provided by an embodiment of the present invention constructs a photovoltaic module simulation model by determining a photovoltaic module physical model that matches the photovoltaic module and using the photovoltaic module physical model as the model structure of a photovoltaic module simulation model. The model takes environmental information corresponding to the photovoltaic module under the current operating condition as input and the output power of the photovoltaic module under the current operating condition as output. Specifically, first operating condition data corresponding to the photovoltaic module is collected. The first operating condition data includes the environmental information corresponding to the photovoltaic module and the output power corresponding to the photovoltaic module. Next, a photovoltaic module physical model is determined, which is used to characterize the output power of the photovoltaic module under different environmental conditions. Then, based on the first operating condition data, parameter identification is performed on multiple photovoltaic module parameters in the photovoltaic module physical model to obtain target parameter values ​​corresponding to each of the multiple photovoltaic module parameters. The photovoltaic module parameters are used to describe the operating state of the photovoltaic module under various operating conditions. Finally, a photovoltaic module simulation model is constructed based on the target parameter values ​​corresponding to each of the multiple photovoltaic module parameters and the photovoltaic module physical model. The input of the photovoltaic module simulation model is the environmental information corresponding to the photovoltaic module under the current operating condition, and the output of the photovoltaic module simulation model is the output power of the photovoltaic module under the current operating condition.

[0019] In the above scheme, according to the first operating condition data, parameter identification is performed on multiple photovoltaic module parameters in the photovoltaic module physical model to obtain target parameter values ​​corresponding to each of the multiple photovoltaic module parameters. Not only can the target parameter values ​​corresponding to the multiple photovoltaic module parameters be quickly determined, but the target parameter values ​​corresponding to the determined multiple photovoltaic module parameters can also be made more consistent with the actual operating conditions. Based on the target parameter values ​​corresponding to the multiple photovoltaic module parameters and the photovoltaic module physical model, a more accurate photovoltaic module simulation model can be constructed, so that the constructed photovoltaic module simulation model can better simulate the maximum output power corresponding to the photovoltaic module under various environmental conditions, so as to optimize the power generation efficiency of the photovoltaic power station by utilizing the maximum output power. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] FIG1 is a schematic diagram of a process of a photovoltaic module modeling method provided by an embodiment of the present invention;

[0022] FIG2 is a schematic diagram of a process for determining target parameter values ​​corresponding to multiple photovoltaic modules according to an embodiment of the present invention;

[0023] FIG3 is a schematic diagram of a process for determining target parameter values ​​corresponding to multiple photovoltaic module parameters using a genetic algorithm according to an embodiment of the present invention;

[0024] FIG4 is a schematic flow chart of another photovoltaic module modeling method provided by an embodiment of the present invention;

[0025] FIG5 is a schematic structural diagram of a photovoltaic module simulation model provided by an embodiment of the present invention;

[0026] FIG6 is a schematic diagram of an application of a photovoltaic module modeling method provided by an embodiment of the present invention;

[0027] FIG7 is a schematic structural diagram of a photovoltaic module modeling device provided by an embodiment of the present invention;

[0028] FIG8 is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0030] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," "the," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0031] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0032] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0033] In order to facilitate understanding of the technical solution of the present invention, the following is a brief description of the relevant technologies:

[0034] Photovoltaic modules are widely used in various applications. They are the core components of solar power generation, using the photovoltaic cells in the modules to convert solar energy into electricity. Accurate modeling of PV modules is crucial for optimizing the power generation efficiency of PV power plants. PV modules often operate in harsh outdoor environments, where they are susceptible to various environmental factors, including thermal cycling, humidity, UV rays, and wind-induced vibrations. These environmental factors can also cause localized material aging, performance degradation, and cracking, significantly impacting the electrical characteristics of the modules and, in turn, the power generation efficiency of the PV power plant.

[0035] Therefore, accurate modeling of photovoltaic modules plays an important role in optimizing the power generation efficiency of photovoltaic power stations, tracking the maximum power point of photovoltaic modules, and fault detection.

[0036] Traditional photovoltaic module modeling technology provides the following implementation methods:

[0037] Implementation method 1 is to determine the equivalent circuit corresponding to the photovoltaic module and establish a photovoltaic module simulation model based on a white box model of the equivalent circuit.

[0038] Specifically, the photovoltaic module is equivalent to a single / double diode model. The single / double diode model determines the equivalent circuit equation corresponding to the photovoltaic module through the IV characteristic curve. When the root mean square error between the fitting curve and the measured curve is minimized based on the equivalent circuit equation, the optimal parameters corresponding to the internal parameters are determined, and then the obtained optimal parameters are substituted to obtain its accurate photovoltaic model.

[0039] However, this method solves the unknown parameters of the maximum power point based on the factory output characteristics of photovoltaic modules. However, the engineering application environment may not necessarily meet the standard test conditions required by the factory characteristics. Therefore, the constructed photovoltaic module simulation model cannot well meet the needs of actual engineering applications. In addition, the accuracy of the model is highly dependent on the numerical values ​​of the parameters within the formula, and these parameters are easily affected by environmental factors. Therefore, in order to obtain an accurate model under various operating conditions, it is necessary to extract parameters from the IV characteristic curve under various operating conditions, which makes photovoltaic modeling cumbersome and inefficient. In addition, complex models are established for different operating conditions in actual use. The data collected by the abundant sensors in the photovoltaic system introduces more parameters into the white box model. The overly complex model increases the complexity of online calculations and loses the robustness of the model.

[0040] The second implementation method is to establish a photovoltaic module simulation model based on data-driven photovoltaic module black box modeling technology.

[0041] By using a neural network model, the maximum power point tracking problem for photovoltaic modules under non-uniform illumination is abstracted into a multi-peak function approximation problem, thereby determining the voltage corresponding to the maximum power point. However, PV module models constructed based on neural network models require a large amount of data from actual operating conditions to train the model. Moreover, the performance of PV module models obtained by PV module black-box modeling methods is significantly affected by the training data, requiring not only high-quality training data but also a large amount of data to train the model. Furthermore, PV module black-box modeling methods lack the support of physical theory, resulting in poor model interpretability and difficulty in balancing accuracy and generalization.

[0042] In order to solve the above technical problems, a new photovoltaic module modeling method is provided in an embodiment of the present invention. The photovoltaic module physical model is determined, and the photovoltaic module physical model is used as the model structure of the photovoltaic module simulation model. According to the actual first operating condition data of the photovoltaic module, parameter identification is performed on multiple photovoltaic module parameters in the photovoltaic module physical model to determine the optimal parameter values ​​corresponding to the multiple photovoltaic module parameters. In this way, not only can the obtained photovoltaic module simulation model be interpretable, but also a photovoltaic module simulation model with higher accuracy can be obtained. In addition, according to the actual first operating condition data of the photovoltaic module, parameter identification is performed on multiple photovoltaic module parameters in the photovoltaic module physical model. Not only can the target parameter values ​​corresponding to the multiple photovoltaic module parameters be quickly determined, but the target parameter values ​​corresponding to the determined multiple photovoltaic module parameters can also be made more consistent with the actual operating conditions, thereby improving the practicality of the photovoltaic module simulation model.

[0043] The following embodiments of the present invention are described in detail with reference to the accompanying drawings. In the absence of conflicts between the embodiments, the following embodiments and features therein may be combined with each other.

[0044] FIG1 is a flow chart of a photovoltaic module modeling method according to an embodiment of the present invention. Referring to FIG1 , the method may be performed by a photovoltaic module modeling device. It is understood that the control device may be implemented as software or a combination of software and hardware. Specifically, the photovoltaic module modeling method may include the following steps:

[0045] 101. Collect first operating condition data corresponding to a photovoltaic module, where the first operating condition data includes environmental information corresponding to the photovoltaic module and output power corresponding to the photovoltaic module.

[0046] 102. Determine the physical model of the photovoltaic module. The physical model of the photovoltaic module is used to characterize the output power corresponding to the photovoltaic module under different environmental conditions.

[0047] 103. Perform parameter identification on multiple photovoltaic module parameters in the photovoltaic module physical model according to the first operating condition data to obtain target parameter values ​​corresponding to each of the multiple photovoltaic module parameters. The photovoltaic module parameters are used to describe the working state of the photovoltaic module under various operating conditions.

[0048] 104. Construct a photovoltaic module simulation model based on the target parameter values ​​corresponding to the multiple photovoltaic module parameters and the photovoltaic module physical model. The input of the photovoltaic module simulation model is the environmental information corresponding to the photovoltaic module under the current working condition, and the output of the photovoltaic module simulation model is the output power of the photovoltaic module under the current working condition.

[0049] When constructing a photovoltaic module simulation model, the first operating condition data corresponding to the photovoltaic module can be collected first. The first operating condition data refers to the historical data obtained by the photovoltaic module under various actual operating conditions. Specifically, the first operating condition data may include environmental information corresponding to the photovoltaic module and the output power corresponding to the photovoltaic module. The environmental information includes a plurality of environmental characteristic data, which are used to characterize the working environment of the photovoltaic module. For example, the environmental characteristic data includes the sunlight irradiance, wind speed, temperature of the photovoltaic module, etc. in the working environment of the photovoltaic module. In the embodiment of the present invention, there is no limitation on the type of data and the amount of data included in the first operating condition data, and they can be set according to actual conditions.

[0050] Next, a photovoltaic module physical model corresponding to the photovoltaic module is determined. The photovoltaic module physical model is used to characterize the output power of the photovoltaic module under different environmental conditions. Environmental information corresponding to the photovoltaic module's operating environment can be used as input, and the output power of the photovoltaic module under the current operating environment can be used as the output of the photovoltaic module physical model to determine the output power of the photovoltaic module under different environmental conditions. In other words, in this embodiment of the present invention, the current operating state or performance of the photovoltaic module can be predicted based on the output power of the photovoltaic module under different environmental conditions.

[0051] The photovoltaic module physical model can be a single diode circuit, a double diode circuit, an empirical formula, and other physical models. The single diode circuit model is divided into a single diode three-parameter model, a single diode four-parameter model, a single diode five-parameter model, and the like. The empirical formula in the empirical formula physical model can be P pv =G t Aη PV η loss η inv [1-γ(T m -25)]. Among them, P pv Refers to the output power of photovoltaic modules, G t It refers to the sunlight irradiance in the working environment of the photovoltaic module, A is the area of ​​the photovoltaic module, η pvis the photovoltaic power generation efficiency of the photovoltaic module's cells, η loss is the loss efficiency of photovoltaic power generation caused by various factors in the environment such as dust, η MPPT is the conversion efficiency of the inverter, γ is the maximum power coefficient of the cell in the photovoltaic module related to temperature, T m It is the module temperature of the photovoltaic component. Other empirical formulas can also be used. It can be set according to actual needs and there is no limitation on this.

[0052] In an optional embodiment, the photovoltaic module physical model corresponding to the photovoltaic module may be determined based on the collected first operating condition data, or based on the physical parameters corresponding to the photovoltaic module.

[0053] After determining the PV module physical model, parameter identification can then be performed on multiple PV module parameters in the PV module physical model based on the first operating condition data to obtain target parameter values ​​corresponding to each of the multiple PV module parameters. The PV module parameters are used to describe the operating state of the PV module under various operating conditions. For example, the PV module parameters may include the area of ​​the PV module, the photovoltaic power generation efficiency of the PV module's cells, the photovoltaic power generation loss efficiency, the inverter's conversion efficiency, and the temperature-dependent maximum power coefficient of the cells in the PV module. The target parameter values ​​are the optimal parameter values ​​corresponding to the PV module parameters under various operating conditions.

[0054] Parameter identification involves determining the values ​​of the multiple PV module parameters based on the collected first operating condition data corresponding to each PV module under various operating conditions, given the known input and output data of the PV module physical model and the structure of the PV module physical model (physical model formula). In embodiments of the present invention, an optimization algorithm can be used to perform parameter identification on the multiple PV module parameters to obtain more precise target parameter values, thereby improving the accuracy of the constructed PV module simulation model.

[0055] Specifically, an optimization algorithm can be used to perform parameter identification on multiple photovoltaic module parameters in the photovoltaic module physical model based on the first operating condition data corresponding to the photovoltaic module under various operating conditions, thereby obtaining target parameter values ​​corresponding to each of the multiple photovoltaic module parameters. The optimization algorithm can be a genetic algorithm, a least squares method, a linear programming algorithm, a particle swarm optimization algorithm, or other optimization algorithm for performing parameter identification on the photovoltaic module parameters. In the embodiments of the present invention, the type of optimization algorithm is not limited, and a corresponding optimization algorithm can be selected based on actual needs.

[0056] In addition, in actual applications, when using sensors to collect the first operating condition data corresponding to the photovoltaic components under various operating conditions, sensor failure, data transmission loss, register read and write errors, etc. may occur when using sensors to collect data, so that the collected first operating condition data may contain abnormal data values. Then, when performing parameter identification on multiple photovoltaic component parameters based on the first operating condition data, the target parameter values ​​corresponding to the determined multiple photovoltaic component parameters may have certain deviations, thereby affecting the accuracy of the constructed photovoltaic component simulation model. Therefore, in an optional embodiment, the collected first operating condition data can be cleaned first to ensure that the collected first operating condition data is close to the actual state. Then, based on the cleaned first operating condition data, parameter identification is performed on multiple photovoltaic component parameters to obtain the first parameter values ​​corresponding to each of the multiple photovoltaic component parameters.

[0057] In the embodiments of the present invention, the data cleaning method is not limited. Data cleaning methods such as median filtering can be used to clean the collected first operating condition data corresponding to the photovoltaic modules to accurately remove abnormal first operating condition data. It should also be noted that when identifying multiple photovoltaic module parameters, whether to clean the first operating condition data can be determined based on actual needs, and this is not limited in the embodiments of the present invention.

[0058] Preferably, in an embodiment of the present invention, a genetic algorithm can be used to perform parameter identification on multiple photovoltaic module parameters in a photovoltaic module physical model based on the first operating condition data to obtain target parameter values ​​corresponding to each of the multiple photovoltaic module parameters. Subsequently, a photovoltaic module simulation model is constructed based on the target parameter values ​​corresponding to each of the multiple photovoltaic module parameters and the photovoltaic module physical model. The input of the photovoltaic module simulation model is the environmental information corresponding to the photovoltaic module under the current operating condition, and the output of the photovoltaic module simulation model is the output power of the photovoltaic module under the current operating condition.

[0059] In an optional embodiment, based on the target parameter values ​​corresponding to each of the multiple photovoltaic module parameters and the photovoltaic module physical model, the specific implementation method of constructing the photovoltaic module simulation model can be: substituting the target parameter values ​​corresponding to each of the multiple photovoltaic module parameters into the photovoltaic module physical model, and using the photovoltaic module physical model as the model structure of the photovoltaic module simulation model, using the environmental information corresponding to the working environment under the current working condition of the photovoltaic module as the input of the photovoltaic module simulation model, and using the output power corresponding to the current working condition of the photovoltaic module as the output of the photovoltaic module simulation model, so as to construct the photovoltaic module simulation model.

[0060] In an embodiment of the present invention, parameter identification is performed on multiple photovoltaic module parameters in the photovoltaic module physical model according to the first operating condition data to obtain target parameter values ​​corresponding to each of the multiple photovoltaic module parameters. This not only allows the target parameter values ​​corresponding to the multiple photovoltaic module parameters to be quickly determined, but also allows the target parameter values ​​corresponding to the determined multiple photovoltaic module parameters to be more consistent with actual operating conditions. Furthermore, based on the target parameter values ​​corresponding to the multiple photovoltaic module parameters and the photovoltaic module physical model, a more accurate photovoltaic module simulation model can be constructed, so that the constructed photovoltaic module simulation model can better simulate the maximum output power corresponding to the photovoltaic module under various environmental conditions, so as to optimize the power generation efficiency of the photovoltaic power station using the maximum output power.

[0061] The above embodiment describes the specific implementation process of constructing a photovoltaic module simulation model based on target parameter values ​​corresponding to multiple photovoltaic module parameters and a photovoltaic module physical model. To facilitate understanding of the specific implementation process of determining the target parameter values ​​corresponding to multiple photovoltaic module parameters in the above embodiment, an exemplary implementation method of determining the target parameter values ​​corresponding to multiple photovoltaic modules using a genetic algorithm is provided in conjunction with Figure 2.

[0062] FIG2 is a schematic diagram of a process for determining target parameter values ​​corresponding to multiple photovoltaic modules according to an embodiment of the present invention. Referring to FIG2 , a method for performing parameter identification on multiple photovoltaic module parameters in a photovoltaic module physical model based on first operating condition data to obtain target parameter values ​​corresponding to the multiple photovoltaic module parameters is provided. Specifically, the method may include the following steps:

[0063] 201. Convert the photovoltaic module physical model into an objective function to be optimized, where the coefficients of the objective function are multiple photovoltaic module parameters in the photovoltaic module physical model, and the function value of the objective function is the output power of the photovoltaic module.

[0064] 202. Determine, using a genetic algorithm, first parameter values ​​corresponding to each of the plurality of photovoltaic module parameters under the objective function and the first operating condition data.

[0065] 203. Determine target parameter values ​​corresponding to each of the plurality of photovoltaic module parameters according to the first parameter value.

[0066] When determining target parameter values ​​corresponding to various PV module parameters in a PV module physical model, the PV module physical model can be first converted into an objective function to be optimized. The coefficients of the objective function are the multiple PV module parameters in the PV module physical model, and the function value of the objective function is the output power of the PV module. Next, a genetic algorithm is used to determine the first parameter values ​​corresponding to each of the multiple PV module parameters under the objective function under the first operating condition data.

[0067] Among them, the specific implementation process of using a genetic algorithm to determine the first parameter values ​​corresponding to each of the multiple photovoltaic component parameters under the first operating condition data of the objective function may include: taking the multiple photovoltaic component parameters as individuals of the genetic algorithm, and taking the objective function as the fitness function of the genetic algorithm, adopting a crossover mutation strategy, and determining the optimal individual in the final population based on the fitness function and the output power in the first operating condition data; and determining the optimal individual as the first parameter value corresponding to each of the multiple photovoltaic component parameters.

[0068] In an optional embodiment, a crossover mutation strategy is employed to determine the optimal individual in the final population based on the fitness function and the output power in the first operating condition data. The specific implementation process may include: randomly selecting parameter values ​​corresponding to each of multiple photovoltaic module parameters in the fitness function; determining a function value corresponding to the fitness function based on the parameter values ​​and multiple environmental characteristic data; performing a fitness calculation on the function value and the output power in the first operating condition data to determine performance index parameters corresponding to the photovoltaic module, the performance index parameters being used to reflect the operating performance of the photovoltaic module; and if the performance index parameters do not meet preset index parameters, adjusting the multiple photovoltaic module parameters in the fitness function using a crossover mutation strategy to determine the optimal individual in the final population. If the performance index parameters meet the preset index parameters, the individual corresponding to the current population is determined as the optimal individual. In other words, the parameter values ​​corresponding to each of the multiple photovoltaic module parameters are determined as the target parameter values ​​corresponding to each of the multiple photovoltaic module parameters. The corresponding preset index parameters can be set according to actual needs.

[0069] In conjunction with FIG3 , the implementation process of using genetic algorithm to determine the target parameter values ​​corresponding to multiple photovoltaic module parameters is shown. In the specific implementation, it is assumed that the first working condition data corresponding to the photovoltaic module includes the output power, the sunlight irradiance in the working environment of the photovoltaic module, and the module temperature of the photovoltaic module. The empirical formula of the photovoltaic module physical model is P pv =G t Aη PV η loss η inv [1-γ(T m -25)]. P pv is the output power of the photovoltaic module, G t is the sunlight irradiance in the working environment of the photovoltaic module, A is the area of ​​the photovoltaic module, η pv is the photovoltaic power generation efficiency of the photovoltaic module cells, η loss is the loss efficiency of photovoltaic power generation caused by various factors in the environment such as dust, η inv is the conversion efficiency of the inverter, γ is the maximum power coefficient of the cell in the photovoltaic module related to temperature, T m is the module temperature of the photovoltaic module. In addition, multiple photovoltaic module parameters are A, ηpv ,η loss ,η inv , γ, the input of the photovoltaic module physical model is G t 、T m , the output of the PV module physical model is P pv The physical model is converted into a fitness function, and its multiple photovoltaic module parameters are the fitness function coefficients.

[0070] First, parameter values ​​corresponding to multiple photovoltaic module parameters in a fitness function are randomly created, and these randomly created parameter values ​​are determined as the initial population. Next, the parameter values ​​corresponding to the randomly created photovoltaic module parameters, as well as the sunlight irradiance and module temperature of the photovoltaic module's operating environment in first operating condition data, are substituted into the fitness function to output a function value corresponding to the fitness function. A fitness calculation is then performed on the function value and the output power of the photovoltaic module corresponding to the current environmental conditions in the first operating condition data to determine a performance index parameter corresponding to the photovoltaic module. If the performance index parameter satisfies a termination condition, the parameter value corresponding to the current multiple photovoltaic module parameters is directly output and determined as the target parameter value corresponding to the multiple photovoltaic module parameters. If the performance index parameter does not meet the termination condition, a selection operation is continued to identify new individuals in the population. Crossover and mutation operations are then performed on the new individuals to reselect parameter values ​​corresponding to the multiple photovoltaic module parameters. The parameter values ​​corresponding to the multiple photovoltaic module parameters are then continuously optimized in a cycle to find the target parameter value corresponding to the multiple photovoltaic module parameters.

[0071] From the above description, it can be seen that: a group of multiple photovoltaic module parameters are regarded as population individuals, and the optimal solutions corresponding to multiple photovoltaic module parameters are searched by simulating the natural evolution process of the population individuals, so as to obtain the optimal parameter values ​​(target parameter values) corresponding to the multiple photovoltaic module parameters in the photovoltaic module physical model. The target parameter values ​​corresponding to the multiple photovoltaic module parameters determined in this way can better characterize the corresponding actual parameter values ​​under various working conditions, and thus improve the accuracy of the photovoltaic module simulation model, so that the photovoltaic module simulation model can predict the actual working status corresponding to the photovoltaic module under various working conditions.

[0072] In an embodiment of the present invention, a photovoltaic module physical model is converted into an objective function to be optimized, where the coefficients of the objective function are multiple photovoltaic module parameters in the photovoltaic module physical model, and the function value of the objective function is the output power of the photovoltaic module. A genetic algorithm is used to determine first parameter values ​​corresponding to each of the multiple photovoltaic module parameters under first operating conditions. Based on the first parameter values, target parameter values ​​corresponding to each of the multiple photovoltaic module parameters are determined. The target parameter values ​​determined in this way are more reliable and stable, and can effectively characterize the operating performance of the photovoltaic module under various environmental conditions, thereby improving the accuracy, reliability, stability, and generalization capability of the photovoltaic module simulation model.

[0073] After determining target parameter values ​​corresponding to each of the plurality of photovoltaic module parameters in the photovoltaic module physical model, a photovoltaic module simulation model is constructed based on the target parameter values ​​corresponding to each of the plurality of photovoltaic module parameters and the photovoltaic module physical model. Specifically, the target parameter values ​​corresponding to each of the plurality of photovoltaic module parameters can be substituted into the photovoltaic module physical model to obtain the photovoltaic module simulation model.

[0074] In other words, if the photovoltaic module physical model is used as the model structure of the photovoltaic module simulation model, then the model performance of the established photovoltaic module simulation model will be directly determined by the target parameter values ​​corresponding to the multiple photovoltaic module parameters determined in the photovoltaic module physical model. Therefore, in an embodiment of the present invention, in order to obtain more optimal target parameter values ​​corresponding to the multiple photovoltaic module parameters, a neural network model, a bilinear model, an autoregressive moving average model, fuzzy logic, or other general nonlinear function approximator can be combined to further determine the optimal parameter values ​​corresponding to the photovoltaic module parameters, so that the determined parameter values ​​can better represent the corresponding operating performance of the photovoltaic module under the current operating conditions.

[0075] However, in practical applications, the number of photovoltaic module parameters in the photovoltaic module physical model is relatively large. To obtain an accurate photovoltaic module simulation model under various operating conditions, parameter extraction must be performed under each operating condition. If a nonlinear function approximator is used to determine the target parameter values ​​corresponding to the photovoltaic module parameters, photovoltaic modeling will be cumbersome and inefficient, and the complexity of online calculations will also be increased. In an embodiment of the present invention, the principal component parameters (target photovoltaic module parameters) can be first determined from multiple photovoltaic module parameters, and then the optimal parameter values ​​corresponding to the principal component parameters can be further determined. The parameter values ​​corresponding to the remaining photovoltaic module parameters are used as the target parameter values ​​obtained by the optimization algorithm and substituted into the photovoltaic module physical model to obtain the final photovoltaic module simulation model.

[0076] In conjunction with the following embodiments, the specific implementation process of determining target photovoltaic module parameters and constructing a photovoltaic module simulation model based on parameter values ​​corresponding to the target photovoltaic module parameters is exemplified.

[0077] FIG4 is a flow chart of another photovoltaic module modeling method provided by an embodiment of the present invention. Based on the above embodiment, referring to FIG4 , specifically, the method may include the following steps:

[0078] 401. Collect first operating condition data corresponding to a photovoltaic component, where the first operating condition data includes environmental information corresponding to the photovoltaic component and output power corresponding to the photovoltaic component.

[0079] 402. Determine a photovoltaic module physical model, where the photovoltaic module physical model is used to characterize the output power corresponding to the photovoltaic module under different environmental conditions.

[0080] 403. Using an optimization algorithm, perform parameter identification on multiple photovoltaic module parameters in the photovoltaic module physical model according to the first operating condition data to obtain target parameter values ​​corresponding to each of the multiple photovoltaic module parameters, where the photovoltaic module parameters are used to describe the working state of the photovoltaic module under various operating conditions.

[0081] 404. Filter target photovoltaic module parameters from multiple photovoltaic module parameters.

[0082] 405. According to the first operating condition data, environmental information is used as input and target photovoltaic module parameters are used as output to obtain a trained photovoltaic module parameter model, where the photovoltaic module parameter model is used to determine parameter values ​​corresponding to the target photovoltaic module parameters.

[0083] 406. Construct a photovoltaic module simulation model according to target parameter values ​​corresponding to the plurality of photovoltaic module parameters, a photovoltaic module physical model, and a photovoltaic module parameter model.

[0084] When constructing a PV module simulation model, the first step is to collect first operating condition data corresponding to the PV module. This first operating condition data includes environmental information corresponding to the PV module and the output power corresponding to the PV module. A physical model of the PV module is then determined. This physical model characterizes the output power corresponding to the PV module under different environmental conditions and serves as the model structure for the PV module simulation model. Next, an optimization algorithm is used to perform parameter identification on multiple PV module parameters in the physical model based on the first operating condition data to obtain target parameter values ​​corresponding to each of the multiple PV module parameters. The PV module parameters are used to describe the operating state of the PV module under various operating conditions.

[0085] Then, a target photovoltaic module parameter is selected from the multiple photovoltaic module parameters, where the target photovoltaic module parameter is a principal component parameter among the multiple photovoltaic module parameters. Specifically, the process for selecting the target photovoltaic module parameter may include: collecting second operating condition data corresponding to the photovoltaic module, where the second operating condition data and the first operating condition data are operating condition data corresponding to the photovoltaic module within the same time period; using a genetic algorithm to determine the second parameter value corresponding to each of the multiple photovoltaic module parameters under the objective function under the second operating condition data; and selecting the target photovoltaic module parameter from the multiple photovoltaic module parameters based on the first parameter value and the second parameter value. The difference between the first parameter value corresponding to the target photovoltaic module parameter and the second parameter value corresponding to the target photovoltaic module parameter is the photovoltaic module parameter with the largest difference among the multiple photovoltaic module parameters.

[0086] It can be seen from this that by comparing the differences between the first parameter values ​​corresponding to the multiple photovoltaic module parameters obtained based on the first operating condition data and the second parameter values ​​corresponding to the multiple photovoltaic module parameters obtained based on the second operating condition data, the photovoltaic module parameter with the larger difference is determined as the target photovoltaic module parameter.

[0087] Among them, in the embodiment of the present invention, the data cleaning method is not limited and a data cleaning method such as median filtering can be used to perform data cleaning processing on the collected first operating condition data corresponding to the photovoltaic component to accurately clean out abnormal first operating condition data.

[0088] After determining the target photovoltaic module parameters, a photovoltaic module parameter model is constructed to determine a second parameter value corresponding to the target photovoltaic module parameters using the photovoltaic module parameter model. Specifically, based on the first operating condition data, environmental information is used as input, and the target photovoltaic module parameters are used as output to obtain a trained photovoltaic module parameter model. The photovoltaic module parameter model is used to determine the parameter value corresponding to the target photovoltaic module parameters.

[0089] In addition, a PV module parameter model can be generated by training a neural network. Specifically, the neural network is trained using the environmental information in the preset first operating condition data and reference values ​​of target PV module parameters corresponding to the environmental information, thereby obtaining a PV module parameter model. Training can also be performed using the second operating condition data, or using the first operating condition data and the second operating condition data, to obtain PV module parameters. This embodiment of the present invention is merely an example.

[0090] After establishing the PV module parameter model, the PV module parameter model can be used to analyze and process the environmental information of the PV module under the current operating conditions, thereby obtaining the parameter values ​​of the target PV parameters corresponding to the environmental information under the operating conditions. The PV module parameter model can also be generated by training a bilinear model, an autoregressive moving average model, fuzzy logic, or other general nonlinear function approximator.

[0091] In practice, because environmental information includes multiple environmental characteristic data, analyzing and processing these multiple environmental characteristic data using a photovoltaic module parameter model requires complex training and inference processes, resulting in high computational costs. Therefore, in an embodiment of the present invention, the multiple environmental characteristic data in the environmental information can be filtered and processed before constructing a photovoltaic module parameter model based on the filtered multiple environmental characteristic data. This simplifies the training and inference processes for the photovoltaic module parameter model, reducing computational costs, while also enabling more accurate parameter values ​​to be obtained.

[0092] Specifically, in an optional embodiment, based on the first operating condition data, with environmental information as input and target photovoltaic module parameters as output, a specific implementation process for obtaining a trained photovoltaic module parameter model may include: performing sensitivity analysis on multiple environmental feature data to determine the sensitivity relationship between each environmental feature data and the output power; based on the sensitivity relationship between each environmental feature data and the output power, screening out target environmental feature data from multiple environmental feature data; based on the first operating condition data, with target environmental feature data as input and target photovoltaic module parameters as output, training a neural network to obtain a trained photovoltaic module parameter model.

[0093] After obtaining the trained PV module parameter model, a PV module simulation model is constructed based on the target parameter values ​​corresponding to the multiple PV module parameters, the PV module physical model, and the PV module parameter model. Specifically, the target parameter values ​​corresponding to the multiple PV module parameters are substituted into the PV module physical model to obtain an updated PV module physical model. The PV module simulation model is then constructed based on the updated PV module physical model and the PV module parameter model.

[0094] As can be seen from the above description, the PV module simulation model includes a PV module physical model and a PV module parameter model, as shown in Figure 5. The PV module parameters are primarily used to determine the second parameter value corresponding to the target PV module parameter, and these second parameter values ​​are then input into the PV module physical model. The PV module physical model is primarily used to determine the output power of the PV module based on received environmental information and the second parameter value corresponding to the target PV module parameter.

[0095] After constructing a PV module simulation model, it can be used to predict the output power of the PV module under various operating conditions. For example, as shown in Figure 6, environmental information about the PV module under the current operating conditions is first obtained. This environmental information includes target environmental characteristic data. The target environmental characteristic data is input into the PV module parameter model within the PV module simulation model to obtain a third parameter value corresponding to the target PV module parameter. The third parameter value and the environmental information are then input into the PV module physical model within the PV simulation model to obtain the output power of the PV module under the current operating conditions.

[0096] In an embodiment of the present invention, a target photovoltaic module parameter is screened out from a plurality of photovoltaic module parameters, and a trained photovoltaic module parameter model is obtained based on the first operating condition data. The photovoltaic module parameter model is used to determine the parameter value corresponding to the target photovoltaic module parameter, and then a photovoltaic module simulation model is constructed based on the target parameter values ​​corresponding to the plurality of photovoltaic module parameters, the photovoltaic module physical model, and the photovoltaic module parameter model. The photovoltaic module simulation model obtained in this way has high accuracy, and the photovoltaic module simulation model has good a priori and interpretability, so as to better characterize the working status of the photovoltaic module under various operating conditions.

[0097] The detailed implementation and beneficial effects of each step in the photovoltaic module modeling method provided by the embodiment of the present invention have been described in detail in the above embodiments and will not be elaborated on here. For specific details, please refer to the above detailed description.

[0098] The photovoltaic module modeling device of one or more embodiments of the present invention will be described in detail below. Those skilled in the art will understand that these devices can be constructed using commercially available hardware components and configured according to the steps taught in this solution.

[0099] FIG7 is a schematic structural diagram of a photovoltaic module modeling device provided by an embodiment of the present invention. As shown in FIG7 , the device includes: a data acquisition module 11 , a physical model determination module 12 , a parameter determination module 13 , and a simulation model construction module 14 .

[0100] The data acquisition module 11 is used to acquire first operating condition data corresponding to the photovoltaic assembly, where the first operating condition data includes environmental information corresponding to the photovoltaic assembly and output power corresponding to the photovoltaic assembly, and the environmental information includes a plurality of environmental characteristic data.

[0101] The physical model determination module 12 is used to determine a physical model of a photovoltaic module, where the physical model of the photovoltaic module is used to characterize the output power of the photovoltaic module under different environmental conditions.

[0102] The parameter determination module 13 is used to perform parameter identification on multiple photovoltaic module parameters in the photovoltaic module physical model based on the first operating condition data to obtain target parameter values ​​corresponding to each of the multiple photovoltaic module parameters, and the photovoltaic module parameters are used to describe the working status of the photovoltaic module under various operating conditions.

[0103] The simulation model construction module 14 is used to construct a photovoltaic module simulation model based on the target parameter values ​​corresponding to the multiple photovoltaic module parameters and the photovoltaic module physical model. The input of the photovoltaic module simulation model is the environmental information corresponding to the photovoltaic module under the current working conditions, and the output of the photovoltaic module simulation model is the output power of the photovoltaic module under the current working conditions.

[0104] In an optional embodiment, the parameter determination module 13 can be specifically used to: convert the photovoltaic module physical model into an objective function to be optimized, the coefficients of the objective function are multiple photovoltaic module parameters in the photovoltaic module physical model, and the function value of the objective function is the output power of the photovoltaic module; use a genetic algorithm to determine the first parameter value corresponding to each of the multiple photovoltaic module parameters under the first operating condition data of the objective function; and determine the target parameter value corresponding to each of the multiple photovoltaic module parameters based on the first parameter value.

[0105] In an optional embodiment, the parameter determination module 13 can be specifically used to: use the multiple photovoltaic component parameters as individuals of the genetic algorithm; use the objective function as the fitness function of the genetic algorithm; adopt a crossover mutation strategy to determine the optimal individual in the final population based on the fitness function and the output power in the first operating condition data; and determine the optimal individual as the first parameter value corresponding to each of the multiple photovoltaic component parameters.

[0106] In an optional embodiment, the environmental information in the first operating condition data includes multiple environmental characteristic data, and the environmental characteristic data is used to characterize the working environment of the photovoltaic module; the parameter determination module 13 can be specifically used to: randomly select the parameter values ​​corresponding to the multiple photovoltaic module parameters in the fitness function; determine the function value corresponding to the fitness function according to the parameter value and the multiple environmental characteristic data; perform fitness calculation on the function value and the output power in the first operating condition data to determine the performance index parameter corresponding to the photovoltaic module, and the performance index parameter is used to reflect the working performance of the photovoltaic module; if the performance index parameter does not meet the preset index parameter, a crossover mutation strategy is adopted to adjust the multiple photovoltaic module parameters in the fitness function to determine the optimal individual in the final population.

[0107] In an optional embodiment, the simulation model construction module 14 is specifically used to: collect second operating condition data corresponding to the photovoltaic component, the second operating condition data and the first operating condition data are operating condition data corresponding to the photovoltaic component within the same time period; use a genetic algorithm to determine the second parameter value corresponding to each of the multiple photovoltaic component parameters under the second operating condition data of the objective function; based on the first parameter value and the second parameter value, filter out the target photovoltaic component parameter from the multiple photovoltaic component parameters, wherein the difference between the first parameter value corresponding to the target photovoltaic component parameter and the second parameter value corresponding to the target photovoltaic component parameter is the photovoltaic component parameter with the largest difference among the multiple photovoltaic component parameters; based on the first operating condition data, use the environmental information as input and the target photovoltaic component parameter as output to obtain a trained photovoltaic component parameter model, the photovoltaic component parameter model being used to determine the parameter value corresponding to the target photovoltaic component parameter; and construct a photovoltaic component simulation model based on the target parameter values ​​corresponding to each of the multiple photovoltaic component parameters, the photovoltaic component physical model and the photovoltaic component parameter model.

[0108] In an optional embodiment, the environmental information includes the multiple environmental characteristic data, and the simulation model construction module 14 is specifically used to: perform sensitivity analysis on the multiple environmental characteristic data to determine the sensitivity relationship between each environmental characteristic data and the output power; based on the sensitivity relationship between each environmental characteristic data and the output power, filter out target environmental characteristic data from the multiple environmental characteristic data; based on the first operating condition data, use the target environmental characteristic data as input and the target photovoltaic component parameters as output to train a neural network to obtain a trained photovoltaic component parameter model.

[0109] In an optional embodiment, the device may also include an application module, which is specifically used to: obtain environmental information of the photovoltaic component under the current working conditions, the environmental information including target environmental characteristic data; input the target environmental characteristic data into the photovoltaic component parameter model in the photovoltaic simulation model to obtain a third parameter value corresponding to the target photovoltaic component parameter; input the third parameter value and the environmental information into the photovoltaic component physical model in the photovoltaic simulation model to obtain the output power of the photovoltaic component under the current working conditions.

[0110] The device shown in FIG7 can execute the steps introduced in the aforementioned embodiments. For detailed execution process and technical effects, please refer to the description in the aforementioned embodiments and will not be repeated here.

[0111] In one possible design, the structure of the photovoltaic module modeling device shown in FIG. 7 can be implemented as an electronic device, as shown in FIG. 8 . The electronic device may include a memory 21, a processor 22, and a communication interface 23. Memory 21 stores executable code, which, when executed by processor 22, enables processor 22 to at least implement the photovoltaic module modeling method provided in the aforementioned embodiments.

[0112] In addition, an embodiment of the present invention provides a non-transitory machine-readable storage medium, on which executable code is stored. When the executable code is executed by a processor of an electronic device, the processor can at least implement the photovoltaic component modeling method provided in the aforementioned embodiment.

[0113] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Those skilled in the art can understand and implement the present invention without inventive effort.

[0114] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by a combination of hardware and software. Based on this understanding, the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a computer product. The present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A photovoltaic module modeling method, characterized in that, Including: Collecting first operating condition data corresponding to a photovoltaic module, where the first operating condition data includes environmental information corresponding to the photovoltaic module and output power corresponding to the photovoltaic module; Determining a physical model of the photovoltaic module, where the physical model of the photovoltaic module is used to characterize the output power corresponding to the photovoltaic module under different environmental conditions; According to the first operating condition data, performing parameter identification on multiple photovoltaic module parameters in the physical model of the photovoltaic module to obtain target parameter values corresponding to the multiple photovoltaic module parameters respectively, where the photovoltaic module parameters are used to describe the operating state of the photovoltaic module under various operating conditions; According to the target parameter values corresponding to the multiple photovoltaic module parameters respectively and the physical model of the photovoltaic module, constructing a simulation model of the photovoltaic module, where the input of the simulation model of the photovoltaic module is the environmental information corresponding to the photovoltaic module under the current operating condition, and the output of the simulation model of the photovoltaic module is the output power of the photovoltaic module under the current operating condition.

2. The method according to claim 1, wherein The performing parameter identification on multiple photovoltaic module parameters in the physical model of the photovoltaic module according to the first operating condition data to obtain target parameter values corresponding to the multiple photovoltaic module parameters respectively includes: Converting the physical model of the photovoltaic module into an objective function to be optimized, where the coefficients of the objective function are multiple photovoltaic module parameters in the physical model of the photovoltaic module, and the function value of the objective function is the output power of the photovoltaic module; Using a genetic algorithm to determine first parameter values corresponding to the multiple photovoltaic module parameters respectively under the first operating condition data for the objective function; According to the first parameter values, determining target parameter values corresponding to the multiple photovoltaic module parameters respectively.

3. The method according to claim 2, wherein The using a genetic algorithm to determine first parameter values corresponding to the multiple photovoltaic module parameters respectively under the first operating condition data for the objective function includes: Taking the multiple photovoltaic module parameters as individuals of the genetic algorithm; Taking the objective function as the fitness function of the genetic algorithm; Adopting a crossover and mutation strategy, and according to the fitness function and the output power in the first operating condition data, determining the optimal individual in the final population; Determining the optimal individual as the first parameter values corresponding to the multiple photovoltaic module parameters respectively.

4. The method according to claim 3, characterized in that The environmental information in the first operating condition data includes multiple environmental characteristic data, and the environmental characteristic data is used to characterize the working environment of the photovoltaic module; the adopting a crossover and mutation strategy, and according to the fitness function and the output power in the first operating condition data, determining the optimal individual in the final population includes: Randomly selecting parameter values corresponding to the multiple photovoltaic module parameters respectively in the fitness function; According to the parameter values and the multiple environmental characteristic data, determining the function value corresponding to the fitness function; Performing fitness calculation on the function value and the output power in the first operating condition data to determine performance index parameters corresponding to the photovoltaic module, where the performance index parameters are used to reflect the working performance of the photovoltaic module. If the performance index parameters do not meet the preset index parameters, a crossover and mutation strategy is adopted to adjust multiple photovoltaic module parameters in the fitness function to determine the optimal individual in the final population.

5. The method according to claim 2, characterized in that, Constructing a photovoltaic module simulation model according to the target parameter values corresponding to the multiple photovoltaic module parameters and the photovoltaic module physical model includes: Collecting second operating condition data corresponding to the photovoltaic module, where the second operating condition data and the first operating condition data are operating condition data corresponding to the photovoltaic module within the same time period; Using a genetic algorithm to determine second parameter values corresponding to the multiple photovoltaic module parameters under the second operating condition data of the objective function; Screening out target photovoltaic module parameters from the multiple photovoltaic module parameters according to the first parameter values and the second parameter values, where the difference between the first parameter value corresponding to the target photovoltaic module parameter and the second parameter value corresponding to the target photovoltaic module parameter is the photovoltaic module parameter with the largest difference among the multiple photovoltaic module parameters; Using the first operating condition data, taking the environmental information as the input and the target photovoltaic module parameters as the output to obtain a trained photovoltaic module parameter model, where the photovoltaic module parameter model is used to determine the parameter values corresponding to the target photovoltaic module parameters; Constructing a photovoltaic module simulation model according to the target parameter values corresponding to the multiple photovoltaic module parameters, the photovoltaic module physical model, and the photovoltaic module parameter model.

6. The method according to claim 5, characterized in that The environmental information includes the multiple environmental characteristic data. Using the first operating condition data, taking the environmental information as the input and the target photovoltaic module parameters as the output to obtain a trained photovoltaic module parameter model includes: Performing a sensitivity analysis on the multiple environmental characteristic data to determine the sensitivity relationship between each environmental characteristic data and the output power; Screening out target environmental characteristic data from the multiple environmental characteristic data according to the sensitivity relationship between each environmental characteristic data and the output power; Using the first operating condition data, taking the target environmental characteristic data as the input and the target photovoltaic module parameters as the output to train a neural network to obtain a trained photovoltaic module parameter model.

7. The method according to claim 6, wherein The method further includes: Obtaining the environmental information of the photovoltaic module under the current operating condition, where the environmental information includes target environmental characteristic data; Inputting the target environmental characteristic data into the photovoltaic module parameter model in the photovoltaic simulation model to obtain a third parameter value corresponding to the target photovoltaic module parameter; Inputting the third parameter value and the environmental information into the photovoltaic module physical model in the photovoltaic module simulation model to obtain the output power of the photovoltaic module under the current operating condition.

8. A photovoltaic module modeling device, characterized in that, The device includes: A data acquisition module for collecting first operating condition data corresponding to the photovoltaic module, where the first operating condition data includes the environmental information corresponding to the photovoltaic module and the output power corresponding to the photovoltaic module, and the environmental information includes multiple environmental characteristic data; A physical model determination module, configured to determine a physical model of a photovoltaic module, where the physical model of the photovoltaic module is used to characterize the output power of the photovoltaic module corresponding to different environmental conditions; A parameter determination module, configured to perform parameter identification on a plurality of photovoltaic module parameters in the physical model of the photovoltaic module according to the first operating condition data, so as to obtain target parameter values corresponding to the plurality of photovoltaic module parameters respectively, where the photovoltaic module parameters are used to describe the operating state of the photovoltaic module under each operating condition; A simulation model construction module, configured to construct a photovoltaic module simulation model according to the target parameter values corresponding to the plurality of photovoltaic module parameters respectively and the physical model of the photovoltaic module, where the input of the photovoltaic module simulation model is the environmental information corresponding to the photovoltaic module under the current operating condition, and the output of the photovoltaic module simulation model is the output power of the photovoltaic module under the current operating condition.

9. An electronic device, characterized in that, Comprising: A memory, a processor, and a communication interface; wherein, executable code is stored on the memory, and when the executable code is executed by the processor, the processor executes the photovoltaic module modeling method according to any one of claims 1 to 7.

10. A non-transitory machine-readable storage medium, characterized in that, Executable code is stored on the non-transitory machine-readable storage medium, and when the executable code is executed by the processor of the electronic device, the processor executes the photovoltaic module modeling method according to any one of claims 1 to 7.

Images