Method and system for correcting total solar radiation data of photovoltaic power station

Abstract

The application relates to the technical field of photovoltaic power station evaluation, and particularly discloses a photovoltaic power station total solar radiation data correction method and system. The method uses high-precision ground surface radiation observation sequence data of a solar radiation in a certain range of the power station, corrects a weather scale radiation component, namely a low-frequency component, of meteorological satellite radiation sequence data at a position of the power station according to spatial similarity and randomness of total solar radiation through a wavelet analysis method, reduces deviation caused by an optical thickness related parameter model inversion, and improves evaluation accuracy of satellite radiation data.

Description

Technical Field

[0001] This application relates to the field of photovoltaic power plant assessment technology, specifically to a method and system for correcting total solar radiation data of a photovoltaic power plant. Background Technology

[0002] my country has a vast territory, but ground-based solar radiation observation stations are scarce and unevenly distributed. Currently, my country's meteorological department has 110 meteorological observation stations that observe solar radiation-related parameters, but this number is far from meeting the needs of high-precision solar energy utilization. Most photovoltaic power plants typically install ground-based radiometers to assist in the operation and maintenance management of the power plant. However, these radiometers are of low quality, the data reliability is not high, and they lack regular calibration and maintenance. Directly using the power plant's radiometer observation results to assess the power plant's production and operation status would introduce significant uncertainty.

[0003] Using satellite remote sensing to estimate solar radiation parameters can overcome the problem of scarce ground-based observation data. Satellite inversion technology can obtain high spatiotemporal resolution surface solar radiation data over long time series over a region or even the globe. However, the process of calculating total solar radiation by satellite inversion is relatively complex, requires a large number of meteorological and physical quantities, and current technology still has shortcomings in handling the radiation effects of clouds and aerosols, leading to certain errors in the calculation results. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a method and system for correcting total solar radiation data of photovoltaic power plants, which solves the technical problem that the process of estimating solar radiation data at the location of photovoltaic power plants by existing satellite remote sensing methods is complicated and has estimation errors.

[0005] To achieve the above and other related objectives, this application provides a method for correcting total solar radiation data of a photovoltaic power plant, comprising:

[0006] Acquire solar irradiance observation sequence data of at least one irradiator within a preset range of the evaluation power station, as well as meteorological satellite irradiance sequence data of the locations of the evaluation power station and the irradiator;

[0007] The irradiation observation sequence data of the irradiation instrument, the meteorological satellite irradiation sequence data of the evaluation power station and the location of the irradiation instrument are decomposed into high-frequency sequence components and low-frequency sequence components using wavelet analysis.

[0008] The regression model is trained using the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of irradiation observation sequence data of the irradiator, so as to obtain a satellite radiation low-frequency sequence component correction model.

[0009] The low-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station is input into the satellite radiation low-frequency sequence component correction model to obtain the corrected low-frequency sequence component.

[0010] The corrected low-frequency sequence component is superimposed with the high-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station being evaluated to obtain the total solar radiation data of the power station being evaluated.

[0011] In one optional embodiment of this application, the wavelet analysis method includes the Haar wavelet analysis method, the db wavelet analysis method, the bior wavelet analysis method, or the sym wavelet analysis method.

[0012] In an optional embodiment of this application, the regression model includes a linear model or a machine learning model.

[0013] In an optional embodiment of this application, the machine learning model includes a recursive backpropagation network model.

[0014] In an optional embodiment of this application, the regression model is trained using the low-frequency sequence components of meteorological satellite irradiance sequence data at the location of the irradiator and the low-frequency sequence components of the irradiance observation sequence data of the irradiator, to obtain a satellite radiation low-frequency sequence component correction model, specifically including:

[0015] The low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiator are used as input parameters of the regression model, and the low-frequency sequence components of the irradiation observation sequence data of the irradiator are used as output parameters of the regression model to train the regression model, so as to obtain the satellite radiation low-frequency sequence component correction model.

[0016] In an optional embodiment of this application, the regression model is trained using the low-frequency sequence components of meteorological satellite irradiance sequence data at the location of the irradiator and the low-frequency sequence components of the irradiance observation sequence data of the irradiator, to obtain a satellite radiation low-frequency sequence component correction model, specifically including:

[0017] The low-frequency sequence components of the meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of the irradiation observation sequence data of the irradiator are normalized.

[0018] The regression model is trained using the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiator after normalization and the low-frequency sequence components of the irradiation observation sequence data of the irradiator, so as to obtain the satellite radiation low-frequency sequence component correction model.

[0019] In an optional embodiment of this application, when the preset range of the evaluation power station includes multiple irradiators, the regression model is trained using the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiators and the low-frequency sequence components of irradiation observation sequence data of the irradiators, to obtain a satellite radiation low-frequency sequence component correction model, specifically including...

[0020] The regression model is trained using the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of each irradiator and the low-frequency sequence components of the corresponding irradiation observation sequence data of the irradiator, so as to obtain multiple satellite radiation low-frequency sequence component correction models.

[0021] In an optional embodiment of this application, the low-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station is input into the satellite radiation low-frequency sequence component correction model to obtain the corrected low-frequency sequence component, specifically including:

[0022] The low-frequency sequence components of the meteorological satellite irradiance sequence data at the location of the power station are respectively input into each of the satellite radiation low-frequency sequence component correction models to obtain multiple corrected low-frequency sequence components before fusion.

[0023] Multiple corrected low-frequency sequence components before fusion are fused to obtain the corrected low-frequency sequence components.

[0024] In an optional embodiment of this application, multiple modified low-frequency sequence components before fusion are fused to obtain the modified low-frequency sequence components, specifically including:

[0025] The inverse distance weighting method is used to fuse multiple corrected low-frequency sequence components before fusion to obtain the corrected low-frequency sequence components.

[0026] To achieve the above and other related objectives, this application also provides a power plant total solar radiation data acquisition system, comprising:

[0027] The data acquisition module is used to acquire solar irradiance observation sequence data of at least one irradiator within a preset range of the evaluation power station, as well as meteorological satellite irradiance sequence data of the locations of the evaluation power station and the irradiator.

[0028] The data decomposition module is used to decompose the irradiation observation sequence data of the irradiator, the irradiation sequence data of the evaluation power station and the meteorological satellite at the location of the irradiator into high-frequency sequence components and low-frequency sequence components respectively using wavelet analysis method;

[0029] The model training module is used to train the regression model using the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of irradiation observation sequence data of the irradiator, so as to obtain a satellite radiation low-frequency sequence component correction model.

[0030] The low-frequency component acquisition module is used to input the low-frequency sequence components of the meteorological satellite irradiance sequence data of the location of the power station into the satellite radiation low-frequency sequence component correction model to obtain the corrected low-frequency sequence components.

[0031] The irradiance data acquisition module is used to superimpose the corrected low-frequency sequence component with the high-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the assessment power station to obtain the total solar radiation data of the assessment power station.

[0032] The photovoltaic power station solar total radiation data correction method and system of this application utilizes solar radiation observation sequence data from a high-precision surface irradiance instrument within a certain range of the power station. Based on the spatial similarity and randomness of total solar radiation, wavelet analysis is used to correct the synoptic-scale irradiance component, i.e. the low-frequency component, of the meteorological satellite irradiance sequence data at the location of the power station. This reduces the deviation caused by the inversion of optical thickness-related parameter models and improves the accuracy of satellite radiation data assessment. Attached Figure Description

[0033] Figure 1 This is a flowchart illustrating a method for correcting total solar radiation data of a photovoltaic power plant in one embodiment of this application.

[0034] Figure 2 The graph shows the total daily solar radiation data and its high and low frequency components after wavelet decomposition, where the horizontal axis represents time and the vertical axis represents the total daily solar radiation.

[0035] Figure 3 This is a block diagram of a photovoltaic power plant total solar radiation data correction system according to one embodiment of this application. Detailed Implementation

[0036] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application.

[0037] Please see Figures 1-3It should be noted that the illustrations provided in this embodiment are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0038] To address the technical problem of complex estimation processes and estimation errors in existing satellite remote sensing methods for determining solar radiation data at the location of photovoltaic power plants, embodiments of this application disclose a method for correcting total solar radiation data for photovoltaic power plants. Figure 1 A method for correcting total solar radiation data of a photovoltaic power plant according to an embodiment of this application is provided.

[0039] like Figure 1 As shown, the method for correcting the total solar radiation data of the photovoltaic power station includes at least the following steps:

[0040] Step S10: Obtain solar irradiance observation sequence data of at least one irradiator within a preset range of the evaluation power station, and meteorological satellite irradiance sequence data of the locations of the evaluation power station and the irradiator;

[0041] Step S20: Using wavelet analysis, the irradiation observation sequence data of the irradiation instrument, the irradiation sequence data of the evaluation power station and the meteorological satellite at the location of the irradiation instrument are decomposed into high-frequency sequence components and low-frequency sequence components respectively.

[0042] Step S30: Use the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of irradiation observation sequence data of the irradiator to train the regression model, so as to obtain the satellite radiation low-frequency sequence component correction model.

[0043] Step S40: Input the low-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station into the satellite radiation low-frequency sequence component correction model to obtain the corrected low-frequency sequence component;

[0044] Step S50: The corrected low-frequency sequence component is superimposed with the high-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station being evaluated, in order to obtain the total solar radiation data of the power station being evaluated.

[0045] The technical solution of this application utilizes high-precision surface irradiance data within a certain range of a photovoltaic power station. Based on the spatial similarity and randomness of total solar radiation, wavelet analysis is used to correct the synoptic-scale irradiance component, i.e. the low-frequency component, of meteorological satellite remote sensing data. This reduces the bias caused by the inversion of optical thickness-related parameter models and improves the accuracy of satellite data evaluation.

[0046] The method for correcting the total solar radiation data of a photovoltaic power station in this embodiment will be described in detail below.

[0047] First, perform step S10: acquire solar irradiance observation sequence data of at least one irradiator within a preset range of the evaluation power station, and meteorological satellite irradiance sequence data of the locations of the evaluation power station and the irradiator.

[0048] It should be noted that the preset range refers to the area enclosed by a circle with the power station to be evaluated as the center and the preset range value as the radius. The preset range can be adjusted according to the terrain of the area where the photovoltaic power station to be evaluated (hereinafter referred to as the evaluated power station) is located. The simpler the terrain, the larger the preset range; conversely, the more complex the terrain, the smaller the preset range. For example, the preset range is 300 kilometers.

[0049] The assessment of a power plant typically includes multiple irradiance meters distributed across different locations within the predetermined area. These meters collect solar irradiance data at their respective locations. To obtain accurate solar irradiance data, high-precision irradiance meters are required, which can more accurately correct for meteorological satellite irradiance data at the location of the photovoltaic power plant.

[0050] In this embodiment, the total daily solar radiation data observed by one or more irradiators within a preset range of the evaluation power station for a preset time period is obtained as solar radiation observation sequence data; the total daily solar radiation data calculated based on satellite inversion technology at the location of the evaluation power station and each of the irradiators is obtained as meteorological satellite radiation sequence data. As an example, the meteorological satellite can be any satellite such as Fengyun-4 or Japan's Himawari-8 satellite, and the preset time period is, for example, half a year, one year, two years, or longer.

[0051] Next, step S20 is executed: using wavelet analysis, the irradiation observation sequence data of the irradiator, the irradiation sequence data of the evaluation power station and the meteorological satellite at the location of the irradiator are decomposed into high-frequency sequence components and low-frequency sequence components.

[0052] Because the calculation of total solar radiation data based on satellite inversion technology is affected by weather, factors such as cloud cover, aerosols, water vapor, and various gas components can cause certain deviations. These factors are mainly reflected in the low-frequency components of meteorological satellite irradiance sequence data. Therefore, this application only corrects the low-frequency components of meteorological satellite irradiance sequence data, and does not correct the high-frequency components of meteorological satellite irradiance sequence data.

[0053] To obtain the low-frequency and high-frequency components of the sequence data, this application utilizes wavelet analysis to decompose the irradiation observation sequence data of the irradiator, the meteorological satellite irradiation sequence data of the evaluation power station and the location of the irradiator into high-frequency and low-frequency sequence components, respectively. The wavelet analysis method can be, for example, the Haar wavelet analysis method, the db wavelet analysis method, the bior wavelet analysis method, the sym wavelet analysis method, or other existing wavelet analysis methods.

[0054] It should be noted that wavelet analysis is a signal processing technique that decomposes a signal into high-frequency and low-frequency components within different frequency ranges to better understand the signal's characteristics. For example... Figure 2 As shown, the data is processed using db7 to perform three-scale Mallat pyramid wavelet decomposition on the total daily radiation data of the irradiance instrument with a length of 250. Figure 2 In the diagram, curve 1 represents the original time series of total daily radiation data at 250°C, curve 2 represents the decomposed low-frequency sequence, i.e., the low-frequency component, and curve 3 represents the decomposed high-frequency sequence, i.e., the high-frequency component.

[0055] Next, step S30 is executed: the regression model is trained using the low-frequency sequence components of the meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of the irradiation observation sequence data of the irradiator, so as to obtain the satellite radiation low-frequency sequence component correction model.

[0056] During training, the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiator are used as input parameters of the regression model, and the low-frequency sequence components of the irradiation observation sequence data of the irradiator are used as output parameters of the regression model to train the regression model, so as to obtain the satellite radiation low-frequency sequence component correction model.

[0057] In this embodiment, the regression model includes a linear model or a machine learning model. The machine learning model may be, for example, a recursive backpropagation network model or a recursive backpropagation network model.

[0058] It should be noted that, in order to accelerate model training and improve model accuracy, when using the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of the irradiation observation sequence data of the irradiator to train the regression model and obtain the satellite radiation low-frequency sequence component correction model:

[0059] First, the low-frequency sequence components of the meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of the irradiation observation sequence data of the irradiator need to be normalized. Then, the regression model is trained using the normalized low-frequency sequence components of the meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of the irradiation observation sequence data of the irradiator to obtain the satellite radiation low-frequency sequence component correction model.

[0060] It should be noted that when the preset range of the power station includes multiple irradiators, the low-frequency sequence components of the meteorological satellite irradiation sequence data at the location of each irradiator and the low-frequency sequence components of the irradiation observation sequence data of the corresponding irradiator can be used to train the regression model to obtain multiple satellite radiation low-frequency sequence component correction models, and each satellite radiation low-frequency sequence component correction model corresponds to one irradiator.

[0061] Step S40: Input the low-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station into the satellite radiation low-frequency sequence component correction model to obtain the corrected low-frequency sequence component.

[0062] It should be noted that when multiple satellite radiation low-frequency sequence component correction models are obtained in step S30, the low-frequency sequence components of meteorological satellite irradiance sequence data at the location of the power station need to be input into each of the satellite radiation low-frequency sequence component correction models to obtain multiple pre-fusion low-frequency sequence components. The multiple corrected pre-fusion low-frequency sequence components are then fused to obtain the corrected low-frequency sequence components.

[0063] Specifically, when fusing multiple corrected low-frequency sequence components before fusion to obtain the corrected low-frequency sequence components, the inverse distance weighting method can be used. The inverse distance weighting method is based on the principle of proximity: the closer two objects are, the more similar their properties are; conversely, the farther apart they are, the less similar they are. It uses the distance between the interpolation point and the sample point as the weight for a weighted average, assigning greater weight to sample points closer to the interpolation point.

[0064] By employing the inverse distance weighting method to fuse multiple corrected low-frequency sequence components before fusion to obtain the corrected low-frequency sequence components, random biases caused by terrain factors can be effectively corrected, and the application scenarios can be expanded to an effective range of 300 kilometers or more. Furthermore, this application only corrects low-frequency components, thus avoiding over-correction of random biases caused by terrain.

[0065] Step S 50: The corrected low-frequency sequence component is superimposed with the high-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station to obtain the total solar radiation data of the power station.

[0066] As can be seen from the above, this application can utilize high-precision surface irradiance data within a certain range of photovoltaic power stations, and based on the spatial similarity and randomness of total solar radiation, use wavelet analysis to correct the synoptic-scale irradiance component, i.e. the low-frequency component, of meteorological satellite remote sensing data. This effectively corrects the deviations caused by the parameterization process of influencing factors such as cloud cover, aerosols, water vapor, and various gas components, thereby reducing the deviations caused by the inversion of optical thickness-related parameter models, while avoiding over-correction of random deviations caused by terrain, and improving the accuracy of satellite data evaluation.

[0067] Figure 3 This is a functional block diagram of a photovoltaic power plant total solar radiation data correction system provided in an embodiment of this application. Please refer to... Figure 3 As shown, the photovoltaic power station solar total radiation data correction system 11 includes a data acquisition module 111, a data decomposition module 112, a model training module 113, a low-frequency component acquisition module 114, and an irradiation data acquisition module 115.

[0068] The data acquisition module 111 is used to acquire solar irradiance observation sequence data of at least one irradiator within a preset range of the evaluation power station, as well as meteorological satellite irradiance sequence data of the location of the evaluation power station and the irradiator.

[0069] Data decomposition module 112 is used to decompose the irradiation observation sequence data of the irradiator, the irradiation sequence data of the evaluation power station and the meteorological satellite at the location of the irradiator into high-frequency sequence components and low-frequency sequence components respectively using wavelet analysis method;

[0070] The model training module 113 is used to train the regression model using the low-frequency sequence components of the meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of the irradiation observation sequence data of the irradiator, so as to obtain the satellite radiation low-frequency sequence component correction model.

[0071] The low-frequency component acquisition module 114 is used to input the low-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station into the satellite radiation low-frequency sequence component correction model to obtain the corrected low-frequency sequence component.

[0072] The irradiance data acquisition module 115 is used to superimpose the corrected low-frequency sequence component with the high-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the assessment power station to obtain the total solar radiation data of the assessment power station.

[0073] It should be noted that the photovoltaic power plant total solar radiation data correction system 11 in this embodiment is a device corresponding to the photovoltaic power plant total solar radiation data correction method described above. The functional modules in the photovoltaic power plant total solar radiation data correction system 11 correspond to the corresponding steps in the photovoltaic power plant total solar radiation data correction method. The photovoltaic power plant total solar radiation data correction system of this embodiment can be implemented in conjunction with the photovoltaic power plant total solar radiation data correction method. Accordingly, the relevant technical details mentioned in the photovoltaic power plant total solar radiation data correction system of this embodiment can also be applied to the aforementioned photovoltaic power plant total solar radiation data correction method.

[0074] It should be noted that the aforementioned functional modules can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. Additionally, these modules can be fully or partially integrated together, or implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, some or all of the steps of the above method, or the aforementioned functional modules, can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0075] Throughout this description, numerous specific details, such as examples of components and / or methods, are provided to provide a complete understanding of embodiments of this application. However, those skilled in the art will recognize that embodiments of this application may be practiced without one or more of these specific details or by other devices, systems, components, methods, parts, materials, components, etc.

[0076] It should also be understood that one or more of the elements shown in the figures may be implemented in a more separate or more integrated manner, or may even be removed because they are inoperable in certain circumstances or provided because they may be useful for a particular application.

[0077] Furthermore, unless otherwise expressly stated, any arrows or symbols in the accompanying drawings should be considered illustrative only and not limiting. Additionally, unless otherwise stated, the terms "or" as used herein are generally intended to mean "and / or". Where a term is anticipated to provide a separation or combination capability that is unclear, a combination of components or steps will also be considered as indicated.

[0078] The above description of the embodiments shown in this application (including the content set forth in the abstract of the specification) is not intended to be an exhaustive enumeration or to limit this application to the precise forms disclosed herein. Although specific embodiments and examples of this application have been described herein for illustrative purposes only, various equivalent modifications are possible within the spirit and scope of this application, as will be recognized and understood by those skilled in the art. As indicated, these modifications can be made to this application in accordance with the above description of the embodiments described herein, and such modifications will be within the spirit and scope of this application.

[0079] This document has generally described the systems and methods in detail to aid in understanding the present application. Furthermore, various specific details have been provided to offer a general understanding of the embodiments of this application. However, those skilled in the art will recognize that embodiments of this application can be practiced without one or more specific details, or using other means, systems, accessories, methods, components, materials, parts, etc. In other instances, well-known structures, materials, and / or operations have not been specifically shown or described in detail to avoid obscuring various aspects of the embodiments of this application.

[0080] Therefore, although this application has been described herein with reference to specific embodiments thereof, freedom of modification, various changes and substitutions are also within the scope of the above disclosure, and it should be understood that in some cases, certain features of this application may be adopted without departing from the scope and spirit of the invention and without corresponding use of other features. Thus, many modifications can be made to adapt a particular environment or material to the essential scope and spirit of this application. This application is not intended to be limited to the specific terminology used in the following claims and / or the specific embodiments disclosed as the best mode of carrying out this application, but this application will include any and all embodiments and equivalents falling within the scope of the appended claims. Therefore, the scope of this application will be determined only by the appended claims.

Claims

1. A method for correcting total solar radiation data of a photovoltaic power station, characterized in that, include: Acquire solar irradiance observation sequence data of at least one irradiator within a preset range of the evaluation power station, as well as meteorological satellite irradiance sequence data of the locations of the evaluation power station and the irradiator; The solar irradiation observation sequence data of the irradiation instrument, the meteorological satellite irradiation sequence data of the evaluation power station and the location of the irradiation instrument are decomposed into high-frequency sequence components and low-frequency sequence components using wavelet analysis methods. The wavelet analysis methods include Har wavelet analysis method, db wavelet analysis method, bior wavelet analysis method or sym wavelet analysis method. The regression model is trained using the low-frequency sequence components of meteorological satellite irradiance sequence data at the location of the irradiator and the low-frequency sequence components of solar irradiance observation sequence data of the irradiator, so as to obtain a satellite radiation low-frequency sequence component correction model. The low-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station is input into the satellite radiation low-frequency sequence component correction model to obtain the corrected low-frequency sequence component. The corrected low-frequency sequence component is superimposed with the high-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the power station being evaluated to obtain the total solar radiation data of the power station being evaluated.

2. The method for correcting total solar radiation data of a photovoltaic power station according to claim 1, characterized in that, The regression model includes a linear model or a machine learning model.

3. The method for correcting total solar radiation data of a photovoltaic power station according to claim 2, characterized in that, The machine learning model includes a recursive backpropagation network model.

4. The method for correcting total solar radiation data of a photovoltaic power station according to claim 1, characterized in that, The regression model is trained using the low-frequency sequence components of meteorological satellite irradiance sequence data at the location of the irradiator and the low-frequency sequence components of solar irradiance observation sequence data from the irradiator, to obtain a satellite radiation low-frequency sequence component correction model, specifically including: The low-frequency sequence component of the meteorological satellite irradiance sequence data at the location of the irradiator is used as the input parameter of the regression model, and the low-frequency sequence component of the solar irradiance observation sequence data of the irradiator is used as the output parameter of the regression model to train the regression model, so as to obtain the satellite radiation low-frequency sequence component correction model.

5. The method for correcting total solar radiation data of a photovoltaic power station according to claim 1, characterized in that, The regression model is trained using the low-frequency sequence components of meteorological satellite irradiance sequence data at the location of the irradiator and the low-frequency sequence components of solar irradiance observation sequence data from the irradiator, to obtain a satellite radiation low-frequency sequence component correction model, specifically including: The low-frequency sequence components of the meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of the solar irradiation observation sequence data of the irradiator are normalized. The regression model is trained using the low-frequency sequence components of meteorological satellite irradiance sequence data at the location of the irradiator after normalization and the low-frequency sequence components of solar irradiance observation sequence data of the irradiator, so as to obtain the satellite radiation low-frequency sequence component correction model.

6. The method for correcting total solar radiation data of a photovoltaic power station according to any one of claims 1-5, characterized in that, When the preset range of the power station includes multiple irradiators, the regression model is trained using the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiators and the low-frequency sequence components of solar irradiation observation sequence data of the irradiators, to obtain a satellite radiation low-frequency sequence component correction model, specifically including... The regression model is trained using the low-frequency sequence components of meteorological satellite irradiance sequence data at the location of each irradiator and the low-frequency sequence components of the corresponding solar irradiance observation sequence data of the irradiator, so as to obtain multiple satellite radiation low-frequency sequence component correction models.

7. The method for correcting total solar radiation data of a photovoltaic power station according to claim 6, characterized in that, The low-frequency sequence components of the meteorological satellite irradiance sequence data at the location of the power station are input into the satellite radiation low-frequency sequence component correction model to obtain the corrected low-frequency sequence components, specifically including: The low-frequency sequence components of the meteorological satellite irradiance sequence data at the location of the power station are respectively input into each of the satellite radiation low-frequency sequence component correction models to obtain multiple corrected low-frequency sequence components before fusion. Multiple corrected low-frequency sequence components before fusion are fused to obtain the corrected low-frequency sequence components.

8. The method for correcting total solar radiation data of a photovoltaic power station according to claim 7, characterized in that, The process of fusing multiple corrected low-frequency sequence components before fusion to obtain the corrected low-frequency sequence components specifically includes: The inverse distance weighting method is used to fuse multiple corrected low-frequency sequence components before fusion to obtain the corrected low-frequency sequence components.

9. A system for correcting total solar radiation data in a photovoltaic power station, characterized in that, include: The data acquisition module is used to acquire solar irradiance observation sequence data of at least one irradiator within a preset range of the evaluation power station, as well as meteorological satellite irradiance sequence data of the location of the evaluation power station and the irradiator. The data decomposition module is used to decompose the solar irradiation observation sequence data of the irradiation instrument, the meteorological satellite irradiation sequence data of the evaluation power station and the location of the irradiation instrument into high-frequency sequence components and low-frequency sequence components using wavelet analysis methods. The wavelet analysis methods include the Har wavelet analysis method, the db wavelet analysis method, the bior wavelet analysis method or the sym wavelet analysis method. The model training module is used to train the regression model using the low-frequency sequence components of meteorological satellite irradiation sequence data at the location of the irradiator and the low-frequency sequence components of solar irradiation observation sequence data of the irradiator, so as to obtain a satellite radiation low-frequency sequence component correction model. The low-frequency component acquisition module is used to input the low-frequency sequence components of the meteorological satellite irradiance sequence data of the location of the power station into the satellite radiation low-frequency sequence component correction model to obtain the corrected low-frequency sequence components. The irradiance data acquisition module is used to superimpose the corrected low-frequency sequence component with the high-frequency sequence component of the meteorological satellite irradiance sequence data of the location of the assessment power station to obtain the total solar radiation data of the assessment power station.

Images