Terrestrial radiation prediction method and computer device

Abstract

The present application provides a terrestrial radiation prediction method and a computer device, which can be applied to the field of new energy. The method comprises: determining the total transmittance of solar radiation within a preset area range on the basis of first-type data and second-type data; determining first terrestrial radiation on the basis of the total transmittance; and predicting second terrestrial radiation of a target area (e.g., a power station) on the basis of the first terrestrial radiation, meteorological element data, target climate state data, and target radiation (e.g., zenith radiation or clear-sky radiation). In the present application, on the basis of two types of data, quantification is performed on the absorption, attenuation, refraction and the like of cloud and atmosphere on solar radiation during radiation transmission, to calculate more realistic terrestrial radiation. On this basis and on the basis of multi-scale, multi-source heterogeneous data, the terrestrial radiation of the target area is predicted. Since the calculated first terrestrial radiation is within the preset area range, the preset area range can be defined by a user, thereby satisfying the requirements of power stations or station areas, and the introduction of multi-scale data improves the prediction capability for the terrestrial radiation of the target area.

Description

A method for predicting Earth's surface radiation and computer equipment

[0001] This application claims priority to Chinese Patent Application No. 202510391107.1, filed on March 28, 2025, entitled "A Method for Predicting Surface Radiation and a Computer Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of new energy, and in particular to a method for predicting surface radiation and a computer device. Background Technology

[0003] Weather forecasting, also known as meteorological forecasting, refers to the prediction of the state of the Earth's atmosphere at a specific location in the future using modern science and technology. It is mainly based on a large amount of collected meteorological data (such as temperature, humidity, wind direction, wind speed, and air pressure) and uses knowledge of atmospheric processes (such as meteorology) to predict changes in future meteorological data. For example, weather forecasts can predict air pressure, wind speed, temperature, and surface radiation over a period of time in the future.

[0004] Traditional meteorological forecasting of surface radiation involves the following steps: First, cloud cover characteristics are extracted from satellite cloud images to predict future cloud cover features. Then, based on numerical weather prediction (NWP) data from the stations under test, meteorological elements with high correlation to surface radiation are selected. Next, a time-series artificial intelligence (AI) model is established. Using the selected meteorological element data and the predicted cloud cover characteristics, the theoretical clear-sky irradiance (theoretical clear-sky irradiance refers to the solar radiation theoretically reaching the Earth's surface under clear sky conditions with little or no cloud cover and very good air quality, which can be calculated using physical formulas) is corrected to obtain the predicted future surface radiation. In this forecasting method, the relevant data used are satellite cloud images and NWP data. The satellite cloud images are infrared cloud images, which only describe the extent of cloud cover. The NWP data consists of data on certain meteorological elements related to irradiance, such as temperature, humidity, precipitation, shortwave radiation, and thermal flux. By using satellite cloud images / cloud image features and NWP data as model inputs, an AI model can predict future surface radiation.

[0005] The prediction error of the above-mentioned implementation method is very large when the sky is not clear: because satellite cloud images only describe the coverage of the surface by clouds, and only visually represent the coverage of clouds. The actual solar radiation transmission process includes complex processes such as attenuation, reflection, and absorption. Judging the influence of clouds solely from their shading characteristics and coverage area is inaccurate in the description of the solar radiation transmission process to the ground under cloudy and complex weather conditions, resulting in a large error in the predicted surface radiation. In addition, the existing spatial scale based on NWP data and irradiance is about 25 kilometers, which cannot meet the needs of power plant or site areas, as many power plant or site areas exceed 25 kilometers. Summary of the Invention

[0006] This application provides a method and computer equipment for predicting surface radiation. Based on two types of data (e.g., satellite observation data of type one and atmospheric reanalysis data of type two), it quantifies the effects of cloud and atmospheric absorption, attenuation, and refraction on solar radiation during radiative transmission (i.e., the quantification result is characterized by calculated total transmittance), calculating a more realistic surface radiation (i.e., first surface radiation). Based on this, it combines multi-scale, multi-source heterogeneous data (i.e., first surface radiation, meteorological data, target climatological data, zenith radiation / clear-sky radiation, etc.) to predict the surface radiation of the target area (i.e., second surface radiation). Since the calculated first surface radiation is within a preset area (the target area belongs to this preset area), and this preset area can be user-defined (to predict the surface radiation of a certain area, the actual surface radiation within the preset area greater than or equal to that area can be calculated first), it can meet the needs of power plants or site areas. Furthermore, the introduction of multi-scale data improves the predictive ability of surface radiation in the target area, thereby further improving the photovoltaic power prediction capability.

[0007] Based on this, the embodiments of this application provide the following technical solutions:

[0008] Firstly, this application provides a method for predicting surface radiation, which specifically includes: firstly, calculating the total transmittance of solar radiation within a preset area (which can be denoted as T) based on a first type of data (e.g., satellite observation data) and a second type of data (e.g., atmospheric reanalysis data). allThe total transmittance is used to characterize the total solar radiation transmittance under all-day conditions, and the total solar radiation transmittance characterizes the proportion of solar radiation that reaches the Earth's surface after passing through the medium. It is important to note that the preset area range can be customized. To calculate the first surface radiation for a given area, first-type and second-type data for that area are obtained, and the total solar transmittance for that area is calculated accordingly. After calculating the total transmittance within the preset area range, the first surface radiation (which can be denoted as R1) can be determined based on this total transmittance. Surface radiation characterizes the amount of solar radiation reaching the Earth's surface. Finally, based on the first surface radiation calculated above, the data of at least one meteorological element (e.g., wind speed, temperature, humidity, pressure, etc.), the target climatological data, and the target radiation, the surface radiation of the target area is predicted. This surface radiation of the target area can be referred to as the second surface radiation (denoted as R2). This target area belongs to the aforementioned preset area range. The target climatological data is climatological data encompassing the area of ​​the target region, which can be obtained through monitored meteorological data. The target radiation is calculated in advance and can be either zenith radiation or clear-sky radiation; this application does not limit this. It should be noted that in this embodiment, since there are multiple meteorological elements, one or more meteorological elements with a significant impact on surface radiation can be selected from the total number of meteorological elements as at least one meteorological element described in this application. The selected meteorological element can also be referred to as a basic meteorological element or a key meteorological element.

[0009] In the above embodiments of this application, based on two types of data (e.g., satellite observation data of the first type and atmospheric reanalysis data of the second type), the effects of attenuation, reflection, and refraction of solar radiation during atmospheric transmission are quantified, thereby converting direct satellite observation information into near real-time total transmittance related to solar radiation, and calculating the true irradiance reaching the Earth's surface (i.e., the first surface radiation). Based on this, multi-scale, multi-source heterogeneous data (i.e., the first surface radiation, meteorological data, target climatological data, zenith radiation / clear-sky radiation, etc.) are combined to predict the surface radiation of the target area (i.e., the second surface radiation). Since the calculated first surface radiation is within a preset area (the target area belongs to this preset area), and this preset area can be user-defined, it can meet the needs of power plant or site areas and improve the accuracy of surface radiation forecasting.

[0010] In one possible implementation of the first aspect, determining the total transmittance of solar radiation within a preset area based on the first type of data and the second type of data can be achieved by: firstly, determining the clear-sky transmittance of solar radiation within the preset area (which can be denoted as T) based on the first type of data and the second type of data. clr) and cloud and sky transmittance (which can be denoted as T) c The transmittance under clear weather conditions is used to characterize the total transmittance of solar radiation under clear weather conditions, and the transmittance under cloudy weather conditions is used to characterize the total transmittance of solar radiation under cloudy weather conditions. Then, based on the calculated transmittance under clear weather conditions and the transmittance under cloudy weather conditions, the total transmittance of solar radiation within a preset area is determined.

[0011] In the above embodiments of this application, the attenuation of solar radiation during its transmission in atmospheric space is physically parameterized by clear sky transmittance and cloud sky transmittance.

[0012] In one possible implementation of the first aspect, where the first type of data includes cloud phase, aerosol optical parameters (also known as aerosol optical thickness (AOT)), and cloud optical parameters, and the second type of data includes atmospheric composition data, one way to determine the clear-sky transmittance and cloud-sky transmittance of solar radiation within a preset area based on the first type of data and the second type of data is as follows: determine the clear-sky transmittance of solar radiation within a preset area based on AOT and atmospheric composition data, and determine the cloud-sky transmittance of solar radiation within a preset area based on cloud phase and cloud optical parameters.

[0013] In the above embodiments of this application, the clear sky transmittance and cloud sky transmittance are calculated by acquiring cloud phase, AOT, cloud optical parameters, atmospheric composition data, etc., thereby quantifying the complex propagation and absorption process of solar radiation in the atmosphere.

[0014] In one possible implementation of the first aspect, since the cloud phase includes the ice cloud phase (which can be denoted as CP) i ) and water-cloud phase (which can be denoted as CP) w The optical parameters of clouds include the first optical parameter of water clouds (which can be denoted as CLOT). w ) and the second optical parameter of the ice cloud (which can be denoted as CLOT) i Therefore, one way to determine the cloud-sky transmittance of solar radiation within a preset area based on the cloud phase and the cloud's optical parameters is to: determine the water-cloud-sky transmittance of solar radiation within the preset area based on the water-cloud phase and the first optical parameter (which can be denoted as T). wc Water cloud transmittance is used to characterize the total solar radiation transmittance under water cloud conditions. Based on the ice cloud phase and the second optical parameter, the ice cloud transmittance (which can be denoted as T) of solar radiation within a preset area is determined. ic The ice cloud transmittance is used to characterize the total solar radiation transmittance under ice cloud conditions. Finally, based on the water cloud transmittance and the ice cloud transmittance, the cloud transmittance of solar radiation within the preset area is determined.

[0015] In the above embodiments of this application, the solar radiation transmission process under water cloud sky conditions and ice cloud sky conditions is parameterized respectively, so that the parameterized scenario is more in line with the actual application scenario and has wide applicability.

[0016] In one possible implementation of the first aspect, the method of determining the cloud-sky transmittance of solar radiation within a preset area based on the transmittance of water-cloud and ice-cloud can be as follows: based on the ratio of water-cloud phase to ice-cloud phase within the preset area, determine the first weighting coefficients of water-cloud transmittance and ice-cloud transmittance respectively, and then perform a weighted summation of water-cloud transmittance and ice-cloud transmittance based on their respective first weighting coefficients to obtain the cloud-sky transmittance of solar radiation within the preset area.

[0017] In the above embodiments of this application, it is specifically explained that the first weighting coefficients of the water cloud-sky transmittance and the ice cloud-sky transmittance are determined according to the ratio of the water cloud phase to the ice cloud phase, and the cloud-sky transmittance is obtained by weighted summation. This is in line with the actual application scenario and is feasible.

[0018] In one possible implementation of the first aspect, the types of the aforementioned atmospheric component data include at least one of the following: precipitable water (i.e., H2O) and ozone (i.e., O3).

[0019] In the above embodiments of this application, several atmospheric components that have a significant impact on solar radiation were selected for parameterization, thereby indirectly improving the accuracy of subsequent surface radiation forecasts.

[0020] In one possible implementation of the first aspect, determining the total transmittance of solar radiation within a preset area based on clear sky transmittance and cloud sky transmittance can be achieved as follows: First, based on the cloud cover within the preset area, determine the second weighting coefficients for clear sky transmittance and cloud sky transmittance respectively, assuming they are x and y respectively, where x and y represent the proportions of cloudless coverage and cloud cover respectively. Then, perform a weighted summation of clear sky transmittance and cloud sky transmittance based on their respective second weighting coefficients to obtain the total transmittance of solar radiation within the preset area.

[0021] In the above embodiments of this application, it is specifically described that the second weighting coefficients of clear sky transmittance and cloud sky transmittance are determined according to cloud coverage, and the total transmittance is obtained by weighted summation based on these coefficients. This is in line with actual application scenarios and is feasible.

[0022] In one possible implementation of the first aspect, determining the first surface radiation based on the total transmittance can be achieved by multiplying the total transmittance by the target radiation to obtain the first surface radiation.

[0023] In the above embodiments of this application, a specific method for calculating the first surface radiation is described, which achieves accurate calculation of the true value of surface radiation.

[0024] In one possible implementation of the first aspect, one way to predict the second surface radiation of a target area based on the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation is to input the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation into a target model to obtain the second surface radiation of the target area in the forecast period output by the target model.

[0025] In the above embodiments of this application, multi-scale, multi-source heterogeneous data are used as input data for the constructed target model, thereby realizing the prediction of surface radiation in the target area, which is feasible.

[0026] In one possible implementation of the first aspect, when the forecast period belongs to the first future period, the target model is input with the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation to obtain the second surface radiation of the target area within the forecast period output by the target model. One implementation is to input the first surface radiation, data of at least one meteorological element acquired at the current time, target climatological data, and the predicted target radiation for the first future period into the target model to obtain the second surface radiation of the target area for the first future period output by the target model. That is, if the forecast period is the first future period (i.e., short-term, such as 1-4 hours in the future), the target model is in extrapolation mode, the meteorological element input into the target model is measured at the current time (i.e., time T), and the target radiation is predicted for the first future period. The duration of the first future period is less than a preset duration (e.g., 4 hours, 6 hours, etc.), and the preset duration can be customized; this application does not limit it.

[0027] In the above embodiments of this application, it is specifically described that the operating mode of the target model can be determined to be extrapolation mode based on the forecast duration. The time period of the input data is also different in different modes, thereby achieving targeted and accurate prediction. Furthermore, the target model incorporates the physical constraints of target radiation at future times, enhancing the forecast capability.

[0028] In one possible implementation of the first aspect, when the forecast period belongs to the second future period, the target model is input with the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation to obtain the second surface radiation of the target area in the forecast period output by the target model. One implementation is to input the first surface radiation, data of at least one meteorological element predicted for the second future period, target climatological data, and target radiation predicted for the second future period into the target model to obtain the second surface radiation of the target area in the second future period output by the target model. That is, if the forecast period is the second future period (i.e., medium to long term, such as the next 24h, 48h, 72h, 240h, etc.), the target model is in diagnostic mode, the meteorological element input into the model is predicted for the second future period, and the target radiation is also predicted for the second future period. The duration of the second future period is greater than or equal to a preset duration (e.g., 24h, 48h, 72h, 240h, etc.), and the preset duration can be customized. This application does not limit this.

[0029] In the above embodiments of this application, it is specifically described that the operating mode of the target model can be determined as a diagnostic mode based on the forecast duration. The time period of the input data is also different in different modes, thereby achieving targeted and accurate prediction. Furthermore, the target model incorporates the physical constraints of target radiation at future times, enhancing the forecast capability.

[0030] In one possible implementation of the first aspect, after predicting the second surface radiation of the target area, the method may further include: determining at least one correction parameter based on observation data within the target area (e.g., real-time satellite observation data and / or user equipment observation data of the target area) and the second surface radiation, and correcting the second surface radiation based on the at least one correction parameter to obtain the corrected second surface radiation.

[0031] In the above embodiments of this application, the predicted second surface radiation can be further corrected based on observational data within the target area to achieve a more stable and locally accurate forecast of surface radiation in the medium to long term. This is because the correction parameters may differ depending on the target area; therefore, different correction parameters can be determined for different target areas to achieve regionalized and targeted correction of the second surface radiation.

[0032] In one possible implementation of the first aspect, the method may further include: predicting the power of photovoltaic power generation equipment deployed in the target area based on second surface radiation or modified second surface radiation.

[0033] In the above embodiments of this application, the second surface radiation or the modified second surface radiation can be used to predict the power of photovoltaic power generation equipment deployed in the target area, so as to achieve functions such as ensuring grid stability, meeting grid connection requirements, optimizing power trading and economic benefits, and improving energy utilization efficiency.

[0034] A second aspect of this application provides a computer device having the function of implementing the method of the first aspect or any possible implementation thereof. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function.

[0035] A third aspect of this application provides a computer device that may include a memory, a processor, and a bus system. The memory is used to store a computer program (also referred to as a program or computer-readable instructions), and the processor is used to invoke the program stored in the memory to execute the method of the first aspect of the embodiments of this application or any possible implementation of the first aspect.

[0036] A fourth aspect of this application provides a computer-readable storage medium storing instructions that, when executed on a computer, enable the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0037] The fifth aspect of this application provides a computer program or a computer program product containing instructions that, when the computer program or computer program product is run on a computer, causes the computer to perform the method described in the first aspect or any possible implementation of the first aspect.

[0038] A sixth aspect of this application provides a chip including at least one processor and at least one interface circuit coupled to the processor. The interface circuit performs transceiver functions and sends instructions to the at least one processor. The at least one processor runs a computer program or instructions, having the functionality to implement the methods described in the first aspect or any possible implementation of the first aspect. This functionality can be implemented in hardware, software, or a combination of hardware and software, including one or more modules corresponding to the described functions. Furthermore, the interface circuit is used to communicate with other modules outside the chip.

[0039] In some implementations of this application, some of the one or more processors may implement some steps of the above method through dedicated hardware. For example, the processing involving neural network models may be implemented by a dedicated neural network processor or graphics processor.

[0040] The method provided in this application embodiment can be implemented by a single chip or by multiple chips working together. Attached Figure Description

[0041] Figure 1 is a schematic diagram of the system architecture provided in an embodiment of this application;

[0042] Figure 2 is a schematic diagram of solar radiation being absorbed or scattered during its passage through the atmosphere, as provided in an embodiment of this application.

[0043] Figure 3 is a flowchart illustrating a method for predicting surface radiation provided in an embodiment of this application;

[0044] Figure 4 is a schematic diagram of an example of obtaining the first surface radiation based on zenith radiation and total transmittance according to an embodiment of this application.

[0045] Figure 5 is a schematic diagram of an application of the target model provided in an embodiment of this application;

[0046] Figure 6 is a schematic diagram illustrating the extrapolation mode of the target model provided in an embodiment of this application;

[0047] Figure 7 is a schematic diagram illustrating the diagnostic mode of the target model provided in an embodiment of this application;

[0048] Figure 8 is a comparative schematic diagram of the extrapolation mode and the diagnostic mode of the target model provided in the embodiments of this application;

[0049] Figure 9 is a schematic diagram of self-iterative reasoning and correction of the predicted second surface radiation provided in an embodiment of this application;

[0050] Figure 10 is a schematic diagram of a computer device provided in an embodiment of this application;

[0051] Figure 11 is a schematic diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0052] This application provides a method and computer equipment for predicting surface radiation. Based on two types of data (e.g., satellite observation data of the first type and atmospheric reanalysis data of the second type), it quantifies the effects of cloud and atmospheric absorption, attenuation, and refraction on solar radiation during radiative transmission (i.e., the quantification result is characterized by calculated total transmittance), calculating a more realistic surface radiation (i.e., the first surface radiation). Based on this, it combines multi-scale, multi-source heterogeneous data (i.e., the first surface radiation, meteorological element data, target climatological data, zenith radiation / clear-sky radiation, etc.) to predict the surface radiation of the target area (i.e., the second surface radiation). Since the calculated first surface radiation is within a preset area (the target area belongs to this preset area), which can be user-defined, it can meet the needs of power plants or site areas. Furthermore, the introduction of multi-scale data improves the predictive ability of surface radiation in the target area, thereby further enhancing the photovoltaic power prediction capability.

[0053] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0054] To better understand the solutions of the embodiments of this application, the relevant terms and concepts that may be involved in the embodiments of this application will be introduced below. It should be understood that the explanation of the relevant concepts may be limited due to the specific circumstances of the embodiments of this application, but it does not mean that this application can only be limited to that specific situation. The specific circumstances of different embodiments may also differ, and no specific limitation is made here.

[0055] (1) NWP

[0056] It is a numerical model used to predict weather and related variables such as temperature, humidity, and wind speed over time. The NWP system uses mathematical equations to describe the physical processes of the atmosphere, ocean, and Earth systems. These equations are based on physical laws such as conservation of mass, conservation of momentum, and thermodynamic principles, and are solved using initial observational data.

[0057] (2) Meteorological elements

[0058] These are the various elements that indicate the physical state and phenomena of the atmosphere. They mainly include, but are not limited to: irradiance, temperature, air pressure, wind, humidity, clouds, and precipitation.

[0059] (3) Satellite cloud image

[0060] Images of cloud cover and surface features on Earth, observed from above by meteorological satellites. Satellite cloud images mainly include: infrared cloud images, visible light cloud images, and water vapor images.

[0061] (4) Climate

[0062] Climate states are generally represented in various forms, such as average climate state and standard climate state, and the relevant data are climate state data.

[0063] Mean climatology: refers to the climatic characteristics and distribution patterns represented by the average values ​​of meteorological elements within a specific region during a period of relatively stable climate.

[0064] Standard climate state: According to the definition of the World Meteorological Organization, it uses the 30-year average value of a certain meteorological element as a climate baseline to characterize the general climate characteristics and distribution patterns of a specific region.

[0065] (5) Zenith radiation

[0066] Zenith radiation refers to the amount of solar radiation received by the Earth's atmosphere or atmospheric surface. It can also be called total solar radiation or overall solar radiation. It is the sum of direct radiation, scattered radiation, and reflected radiation, i.e., zenith radiation = direct radiation + scattered radiation + reflected radiation.

[0067] (6) Clear-sky radiation

[0068] Clear-sky radiation is a theoretical value of surface radiation calculated by taking into account the influence of atmospheric components other than clouds on radiation transmission. It can measure the amount of solar radiation reaching the Earth's surface under clear sky conditions without clouds.

[0069] (7) Cloud coverage

[0070] Cloud cover is used to characterize the degree to which the sky is covered by clouds. It can be represented by the percentage of cloud-covered pixels out of the total effective pixels in the covered area of ​​satellite remote sensing data. Here, 0 represents that all pixels in the area are clear, and 100 represents that all pixels in the area are covered by clouds. The unit is ( ).

[0071] (8) Clear-Sky Condition

[0072] Clear weather conditions refer to conditions where cloud cover is 0, meaning there are no clouds in the atmosphere. At this time, only atmospheric components such as aerosols and water vapor affect radiation transmission.

[0073] (9) Cloudy-Sky Condition

[0074] Cloud cover conditions refer to conditions where cloud coverage is 100%, at which point clouds are the primary factor affecting radiation transmission in the atmosphere.

[0075] In this embodiment, cloud conditions can be further divided into water cloud conditions and ice cloud conditions, based on cloud phase. Clouds composed of water droplets are called water cloud phases, or simply water clouds, while clouds composed of ice crystals are called ice cloud phases, or simply ice clouds. Clouds composed of both water droplets and ice crystals are called mixed clouds. When the cloud phase is water cloud, the cloud conditions are water cloud conditions; when the cloud phase is ice cloud, the cloud conditions are ice cloud conditions.

[0076] (10) All-Sky Condition

[0077] All-day conditions refer to cloud cover conditions that are greater than 0 and less than 100%. This is because, in reality, clouds do not cover the atmosphere 100%, and the impact of clear and cloudy conditions on solar radiation transmission often needs to be weighted according to the actual cloud cover. At this time, atmospheric components such as aerosols and water vapor affect radiation transmission, as do clouds.

[0078] (11) Total solar radiation transmittance

[0079] Total solar radiation transmittance, also known as solar radiation transmittance, measures the effect of different atmospheric components (such as clouds, aerosols, water vapor, etc.) on the transmission of solar radiation. 0 means that solar radiation will be completely absorbed or scattered by atmospheric components and cannot pass through; 100 means that atmospheric components have no effect on radiation transmission and solar radiation can pass through completely without attenuation. The unit is _____.

[0080] (12) Surface albedo

[0081] Surface albedo is used to measure the ratio of reflected radiance to incident radiance on the Earth's surface, that is, the ratio of the total radiant energy emitted in all directions per unit time and per unit area (represented by M) to the total incident radiant energy (represented by E).

[0082] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0083] First, the system architecture and overall process of the method used in the embodiments of this application will be described. Please refer to Figure 1 for details. Figure 1 is a schematic diagram of the system architecture provided in the embodiments of this application. The system architecture includes at least: a near-real-time remote sensing satellite surface radiation parameterization inversion module 101 and a regional high-resolution prediction model 102.

[0084] The near-real-time remote sensing satellite surface radiation parameterization inversion module 101 is used to implement a parameterization scheme for solar radiation retrieval based on satellites, converting near-real-time satellite observation data into relevant information about solar radiation. Specifically, solar radiation passes through the atmosphere and is absorbed and scattered by extinction components in the atmosphere, such as clouds, aerosols, and water vapor, resulting in a reduction in the intensity of solar radiation reaching the ground (as shown in Figure 2). The basic principle of solar radiation satellite inversion is to use satellite observation information on components such as clouds and aerosols in the Earth's atmosphere to quantify their absorption, transmission, and scattering effects on solar radiation, calculate the attenuation of solar radiation transmission in the atmosphere, and finally obtain the solar radiation reaching the Earth's surface.

[0085] The regional high-resolution prediction model 102 is a multi-source heterogeneous data assimilation prediction model used to fuse meteorological grid data and station time series data of different resolutions to achieve a regional high-resolution surface radiation prediction method constrained by target radiation (e.g., zenith radiation, clear sky radiation). Specifically, it can include extrapolation mode and diagnostic mode to achieve different forecast time steps.

[0086] Finally, the model output can be revised based on observational data and climate information to achieve high-precision predictions for ultra-short-term, short-term, and medium-to-long-term forecasts, with stable and reliable forecast performance, providing key inputs for downstream photovoltaic power prediction.

[0087] It should be noted that, in the embodiments of this application, the system architecture in Figure 1 is only for illustration, and there are no limitations on the deployment method of each unit / module, nor on the data type and data category of the input unit / module.

[0088] Based on the above system architecture, the method for predicting surface radiation provided in this application embodiment will be described below. Please refer to Figure 3 for details. Figure 3 is a flowchart of the method for predicting surface radiation provided in this application embodiment, which includes the following steps:

[0089] 301. Based on the first type of data and the second type of data, determine the total transmittance of solar radiation within the preset area. The total transmittance is used to characterize the total transmittance of solar radiation under all-day conditions. The total transmittance of solar radiation is used to characterize the proportion of solar radiation that can reach the Earth's surface after passing through the medium.

[0090] First, based on the first type of data (e.g., satellite observation data) and the second type of data (e.g., atmospheric reanalysis data), calculate the total transmittance of solar radiation within the preset area (which can be denoted as T). all ), where the total transmittance T all Total solar radiation transmittance is used to characterize the proportion of solar radiation that reaches the Earth's surface after passing through a medium, under all-day conditions.

[0091] It is important to note that the preset area range can be customized. To calculate the first surface radiation of specific areas (e.g., area A with a diameter of 80 kilometers centered on the latitude and longitude of the power station), the first and second type data for that area A are obtained. Based on this, the total solar transmittance T within area A is calculated. all .

[0092] Specifically, in some embodiments of this application, the clear-sky transmittance of solar radiation within a preset area (which can be denoted as T) can be determined first based on the first type of data and the second type of data, respectively. clr ) and cloud and sky transmittance (which can be denoted as T) c ), of which, the transmittance T on a sunny day clr The total solar radiation transmittance (T) under clear weather conditions represents the transmittance under cloudy weather conditions. c Used to characterize the total solar radiation transmittance under cloud conditions; then, based on the clear-sky transmittance T... clr and cloud and sky transmittance T c Determine the total solar transmittance T within the preset area. all .

[0093] It should be noted that in some embodiments of this application, the clear day transmittance T is calculated. clr and cloud and sky transmittance T c The methods may include, but are not limited to:

[0094] A. Sunny day transmittance T clr The calculation method.

[0095] If the first type of data includes AOT (Air-to-Oxygen) and the second type of data includes atmospheric component data (e.g., steady-state data of atmospheric components), then the clear-sky transmittance T of solar radiation within the preset area can be determined based on the AOT and atmospheric component data (e.g., steady-state data of atmospheric components such as precipitable water (H2O) and ozone (O3)). clr .

[0096] As an example, assuming the atmospheric composition data includes steady-state data for precipitable water (H2O) and ozone (O3), then the clear-sky transmittance T of solar radiation within the preset area is... clr It can be expressed as shown in the following formula (1):

[0097] Sunny day conditions: T clr =f1(AOT,O3,H2O) (1)

[0098] Specifically, under clear weather conditions, considering the attenuation effect of solar radiation transmission through atmospheric components such as aerosols, water vapor, and ozone, the influence of each component can be parameterized as solar radiation transmittance (ranging from 0 to 1). The product of the transmittances of all atmospheric components is the total solar radiation transmittance under clear weather conditions, i.e., the clear weather transmittance T. clr .

[0099] Therefore, in practical applications, the clear-sky transmittance T of solar radiation within the preset area is used as the reference. clr It can also be further expressed as shown in the following equation (2):

[0100] Sunny conditions:

[0101] Among them, T oz , T g T r T a T represents the transmittance caused by ozone absorption, water vapor absorption, permanent gas absorption, Rayleigh scattering, and aerosol attenuation, respectively. d1 T is the transmittance of Rayleigh single scattering downwards. d2 It is the transmittance of aerosols in a single downward scattering. The transmittance of each component is related to the concentration of the corresponding component.

[0102] B. Cloud and sky transmittance T c The calculation method.

[0103] When the first type of data includes cloud phase (CP) and cloud optical parameters (also known as cloud optical thickness (CLOT)), the cloud-sky transmittance T of solar radiation within a preset area can be determined based on the cloud phase and cloud optical parameters. c The cloud's transmittance T c The calculation method can be expressed as shown in the following formula (3):

[0104] Cloud conditions: T c =f2(CLOT,CP) (3)

[0105] It should be noted that, in this embodiment of the application, since cloud phases include ice cloud phases and water cloud phases, it is assumed that the water cloud phase is represented as CP. w The phase state of ice clouds is represented as CP. i The optical parameters of water clouds are represented as CLOT.w (i.e., the first optical parameter), the optical parameters of ice clouds are represented as CLOT. i (i.e., the second optical parameter) allows for parameterization of the attenuation of solar radiation in water clouds and ice clouds under cloudy conditions. The total solar transmittance under cloudy conditions is then obtained by weighting the parameters according to the proportions of different cloud phases, i.e., the cloud transmittance T. c .

[0106] Specifically, we can first determine the phase CP of water and clouds. w And the optical parameters CLOT of water clouds w Determine the water cloud transmittance T of solar radiation within the preset area. wc Water and cloud transmittance T wc The total solar radiation transmittance T is used to characterize the total solar radiation transmittance under water cloud conditions. wc It can be expressed as shown in the following formula (4):

[0107] Water and Cloud Conditions: T wc =f 21 (CLOT w ,CP w (4)

[0108] In practical applications, the water cloud transmittance T of solar radiation within a preset area is used as the reference value. wc It can also be further expressed as shown in the following equation (5):

[0109] Water and Cloud Conditions:

[0110] Among them, the calculation of equation (5) is related to cloud optical thickness (τ) and ozone concentration. It is related to the cosine of the solar zenith angle (μ), where a is a specific function.

[0111] Similarly, this can be based on the ice cloud phase CP. i And the optical parameters CLOT of ice clouds i Determine the transmittance T of solar radiation over ice clouds within a preset area. ic Ice Cloud Sky Transmittance T ic The water cloud transmittance T is used to characterize the total solar radiation transmittance under ice cloud conditions. ic It can be expressed as shown in the following formula (6):

[0112] Ice Cloud Sky Conditions: T ic =f 22 (CLOT i ,CP i (6)

[0113] In practical applications, the transmittance of solar radiation over ice clouds within a preset area is T.ic It can also be further expressed as shown in the following equation (7):

[0114] Ice Cloud Sky Conditions:

[0115] Among them, the calculation of equation (7) is related to cloud optical thickness (τ) and ozone concentration. It is related to the cosine (μ) of the solar zenith angle, a w and b w For specific functions.

[0116] Finally, based on the water cloud sky transmittance T wc And the transmittance of the ice cloud sky T ic Determine the cloud transmittance T of solar radiation within the preset area. c Specifically, we can first determine the phase CP of water and clouds within a preset area. w CP with Bingyun i The proportions were used to determine the water cloud transmittance T. wc And the transmittance of the ice cloud sky T ic Let their respective first weight coefficients be C. w and C i The C w and C i These represent the coverage ratios of water cloud components and ice cloud components, respectively. Then, based on these two first weighting coefficients C... w and C i The transmittance T of water and clouds was compared separately. wc And the transmittance of the ice cloud sky T ic By performing a weighted summation, the cloud transmittance T of solar radiation within the preset area is obtained. c The cloud's transmittance T c Specifically, it can be expressed as shown in the following formula (8):

[0117] Cloud conditions: T c =C w T wc +C i T ic (8)

[0118] The solar transmittance T on a clear day within the preset area was calculated. clr And the cloud transmittance T of solar radiation within the designated area. c Then, the total transmittance T of solar radiation within the preset area can be calculated. all One possible implementation is as follows: First, determine the clear day transmittance T based on the cloud cover within a preset area. clr and cloud and sky transmittance T cTheir respective second weighting coefficients, assuming to be x and y, represent the proportions of cloudless coverage and cloud cover, respectively. Then, based on their respective second weighting coefficients x and y, the clear sky transmittance T is calculated. clr And cloud sky transmittance T c By performing a weighted summation, the total solar transmittance T within the preset area is obtained. all The total transmittance T all Specifically, it can be expressed as shown in the following formula (9):

[0119] All-day conditions: T all =x*T clr +y*T c =(1-C w -C i )T clr +C w T wc +C i T ic (9)

[0120] 302. Determine the first surface radiation based on the total transmittance. Surface radiation is used to characterize the amount of solar radiation reaching the Earth's surface.

[0121] The total transmittance T within the preset area is calculated. all Then, based on the total transmittance T all Determine the first surface radiation (which can be denoted as R1), which characterizes the amount of solar radiation reaching the Earth's surface. Specifically, it can be based on the total transmittance T. all With target radiation R o The first surface radiation R1 is calculated and can be specifically expressed as shown in the following formula (10): R1 = T all *R o =μS0E0 T all (10)

[0122] Where μ is the cosine of the solar zenith angle, and S0 is the solar constant. R is the eccentricity correction coefficient for Earth's orbit, and r and r0 are the Earth-Sun distance and the mean Earth-Sun distance, respectively. The first surface radiation R1 is a spatiotemporal series data, representing the surface radiance data for a predetermined duration (i.e., a predetermined time) within a predetermined area (i.e., spatially defined).

[0123] It should be noted that, in the embodiments of this application, the target radiation R o It can be zenith radiation or clear-sky radiation; this application does not specify which. The target radiation R... o Taking zenith radiation as an example (as shown in Figure 4), the near-real-time total transmittance T is obtained based on satellite inversion calculations.all By combining the zenith radiation data obtained from physical calculations, we can obtain the surface radiation data (i.e., the first surface radiation R1).

[0124] 303. Based on the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation, predict the second surface radiation of the target area. The target area belongs to a preset area range. The target climatological data is obtained through monitored meteorological data. The target radiation is calculated in advance. The target radiation includes zenith radiation or clear sky radiation.

[0125] Finally, based on the first surface radiation R1 calculated above, data of at least one meteorological element (e.g., wind speed, temperature, humidity, pressure, etc.), target climatological data, and target radiation, the surface radiation of the target area is predicted. This surface radiation of the target area can be referred to as the second surface radiation, denoted as R2. The target area belongs to a preset area range. The target climatological data is climatological data encompassing the area of ​​the target region, which can be obtained through monitored meteorological data. This target climatological data is irradiance time-series data of a certain coordinate location processed by an algorithm, reflecting the long-term climate characteristics of a certain location, and is used as prior information to supplement it. The target radiation is calculated in advance. This target radiation can be zenith radiation or clear-sky radiation; this application does not limit it to either. It should be noted that, in this embodiment of the application, since there are multiple meteorological elements, one or more meteorological elements with a greater impact on surface radiation can be selected from the full range of multiple meteorological elements as at least one meteorological element mentioned in this application. The selected meteorological element can also be referred to as a basic meteorological element or a key meteorological element.

[0126] Specifically, in some embodiments of this application, the first surface radiation R1 obtained above, data of at least one meteorological element, target climatological data, and target radiation can be input into a target model (e.g., the regional high-resolution prediction model 102 shown in Figure 1) to obtain the second surface radiation R2 of the target area in the forecast period output by the target model. See Figure 5 for details. In Figure 5, the input data of the target model (also referred to as a physically constrained irradiance model) includes at least one key meteorological element, the first surface radiation obtained through near-real-time inversion calculation, target climatological data reflecting the long-term climate characteristics of the target coordinates, and embedded target radiation (e.g., zenith radiation or clear-sky radiation). Based on this multi-scale data, the target model is trained, and the trained target model can be directly used to predict the regional irradiance (i.e., the second surface radiation of the target area) at future times.

[0127] It is important to note that in this embodiment, the embedding of target radiation is asynchronous. It requires the target radiation at the predicted time as guiding information; that is, the target radiation (which can be predicted and calculated) for the predicted second surface radiation time period is used as the input data for the target model. Furthermore, physical constraints are reflected in the loss function of the target model. This involves setting upper and lower limits for the output data to exclude cases where the predicted output data exceeds the upper limit of the target radiation or does not conform to reality. For example, if the target model predicts a second surface radiation greater than zero at night, this is unrealistic because solar radiation should be zero at night; this situation can be eliminated through physical constraints.

[0128] It should also be noted that in some embodiments of this application, the forecasting capability of the target area can be improved by embedding latitude and longitude coordinates into the location encoding of the target model. This process can be called hierarchical rotational location encoding. Its core idea is to implicitly encode the location information into the patch by rotating the vector, thereby capturing the sequential relationship of the sequence in the self-attention mechanism. Rotational location encoding integrates the location information into the vector space through geometric rotation, which solves the problems of poor extrapolation capability and parameter redundancy of traditional location encoding while maintaining computational efficiency. At the same time, it also considers that the meteorological grid is a regular feature point, but the latitude and longitude coordinates of the station data often do not coincide with the coordinates of the grid points. Through hierarchical rotational location encoding, the climate state and station observation data are accurately correlated with the satellite inverted irradiance data.

[0129] It should be noted that, in some embodiments of this application, different operating modes of the target model can be determined based on the forecast duration, including but not limited to:

[0130] A. Extrapolation mode.

[0131] When the forecast period falls within the first future period, the target model is considered to be in extrapolation mode. The duration of the first future period is less than the preset duration (e.g., 4h, 6h, etc.). The preset duration can be customized, and this application does not limit it.

[0132] In this embodiment of the application, when the target model is in extrapolation mode, one way to obtain the second surface radiation of the target area in the forecast period by inputting the first surface radiation, data of at least one meteorological element, target climatological data and target radiation into the target model is as follows: input the first surface radiation, data of at least one meteorological element at the current time, target climatological data and the predicted target radiation of the first future period into the target model to obtain the second surface radiation of the target area in the first future period output by the target model.

[0133] To facilitate understanding of this process, a specific example is used below to illustrate the extrapolation model. In this example, the target radiation is taken as zenith radiation. Please refer to Figure 6 for details. T is the current time, and T+△t is the future △t time. In Figure 6, the data input to the target model are the basic meteorological elements at time T (such as wind, temperature, humidity, pressure, and pressure layer), the first surface radiation at time T obtained based on the initial field of remote sensing satellites at time T, the target climatological data, and the zenith radiation at time T+△t (predicted). Then, the predicted second surface radiation of the target area at time T+△t is obtained based on this. At each predicted moment in the first future time period (e.g., the predicted moment is determined periodically), the second surface radiation at each predicted moment can be calculated based on this process. For example, assuming that the first future time period includes 6 predicted moments, namely T+Δt1, T+Δt2, T+Δt3, T+Δt4, T+Δt5, and T+Δt6, then the time series data composed of the predicted second surface radiation at these 6 moments is the second surface radiation of the target area in the first future time period.

[0134] B. Diagnostic Mode.

[0135] When the forecast period falls within the second future period, the target model is considered to be in diagnostic mode. The duration of the second future period is greater than or equal to a preset duration (e.g., 24h, 48h, 72h, 240h, etc.). The preset duration can be customized, and this application does not limit it.

[0136] In this embodiment of the application, when the target model is in diagnostic mode, the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation are input into the target model to obtain the second surface radiation of the target area in the forecast period output by the target model. One way to obtain the second surface radiation of the target area in the forecast period is to input the first surface radiation, data of at least one meteorological element in the predicted second future period, target climatological data, and target radiation in the predicted second future period into the target model to obtain the second surface radiation of the target area in the second future period output by the target model.

[0137] To facilitate understanding of this process, a specific example is used below to illustrate the diagnostic model. In this example, the target radiation is zenith radiation, as shown in Figure 7. Here, T is the current time, and T+△t is the future △t time. In Figure 7, the data input to the target model are the basic meteorological elements at time T+△t (such as wind, temperature, humidity, pressure, and pressure layer, which can be predicted), the first surface radiation at time T obtained based on the initial field of the remote sensing satellite at time T, the target climatological data, and the zenith radiation at time T+△t (predicted). Then, the predicted second surface radiation of the target area at time T+△t is obtained based on this. At each predicted moment of the second future time period (e.g., the predicted moment is determined periodically), the second surface radiation at each predicted moment can be calculated based on this process. For example, assuming that the second future time period includes 100 predicted moments, assuming that they are T+Δt1, T+Δt2, ..., T+Δt100, then the time series data composed of the second surface radiation at these 100 predicted moments is the second surface radiation of the target area in the second future time period.

[0138] In summary, this application can determine the operating mode of the selected radiation forecast model based on the forecast duration, as shown in Figure 8. Assuming the target model is the regional high-resolution prediction model Solar-ViT, it can be mainly divided into extrapolation mode (e.g., ultra-short extrapolation mode within 1-6 hours) and diagnostic mode. Different operating modes can be selected based on different needs.

[0139] It should be noted that, in some embodiments of this application, after predicting the second surface radiation of the target area, the predicted second surface radiation can be further corrected based on observational data (e.g., real-time satellite observation data and / or user equipment observation data of the target area) and climatological information within the target area, in order to achieve a more accurate and stable medium- to long-term local surface radiation forecast (because the correction parameters may differ for different target areas, different correction parameters can be determined for different target areas to achieve regionalized and targeted correction of the second surface radiation). Specifically, at least one correction parameter (α in Figure 9) can be determined based on the observational data within the target area and the second surface radiation. i and β i Finally, based on at least one correction parameter, the second surface radiation is corrected to obtain the corrected second surface radiation.

[0140] It should also be noted that in some other embodiments of this application, the second surface radiation (or the modified second surface radiation) can be used to predict the power of photovoltaic power generation equipment deployed in the target area, so as to achieve functions such as ensuring grid stability, meeting grid connection requirements, optimizing power trading and economic benefits, and improving energy utilization efficiency.

[0141] Based on the above embodiments, in order to better implement the above solutions of the embodiments of this application, related equipment for implementing the above solutions is also provided below. Referring specifically to Figure 10, which is a schematic diagram of a computer device provided in an embodiment of this application, the computer device 1000 may specifically include: a first determining module 1001, a second determining module 1002, and a prediction module 1003. The first determining module 1001 is used to determine the total transmittance of solar radiation within a preset area based on first type data and second type data. This total transmittance characterizes the total transmittance of solar radiation under all-day conditions and represents the proportion of solar radiation that reaches the Earth's surface after passing through a medium. The second determining module 1002 is used to determine the first surface radiation based on the total transmittance. Surface radiation characterizes the amount of solar radiation reaching the Earth's surface. The prediction module 1003 is used to predict the second surface radiation of a target area based on the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation. The target area belongs to the preset area. The target climatological data is obtained through monitored meteorological data, and the target radiation is calculated in advance. The target radiation includes zenith radiation or clear-sky radiation.

[0142] In one possible design, the first determining module 1001 is specifically used to: determine the clear sky transmittance and cloud sky transmittance of solar radiation within a preset area based on the first type of data and the second type of data, respectively. The clear sky transmittance is used to characterize the total transmittance of solar radiation under clear sky conditions, and the cloud sky transmittance is used to characterize the total transmittance of solar radiation under cloud sky conditions; and determine the total transmittance of solar radiation within the preset area based on the clear sky transmittance and the cloud sky transmittance.

[0143] In one possible design, the first type of data includes cloud phase, optical parameters of aerosols, and optical parameters of clouds; the second type of data includes atmospheric composition data; and the first determining module 1001 is further used to: determine the clear-sky transmittance of solar radiation within a preset area based on the optical parameters of the aerosols and the atmospheric composition data; and determine the cloud-sky transmittance of solar radiation within the preset area based on the cloud phase and the optical parameters of the clouds.

[0144] In one possible design, the cloud phase includes a water cloud phase and an ice cloud phase, and the cloud's optical parameters include a first optical parameter for the water cloud and a second optical parameter for the ice cloud. The first determining module 1001 is further configured to: determine the water cloud-sky transmittance of solar radiation within the preset area based on the water cloud phase and the first optical parameter, wherein the water cloud-sky transmittance is used to characterize the total solar radiation transmittance under water cloud conditions; determine the ice cloud-sky transmittance of solar radiation within the preset area based on the ice cloud phase and the second optical parameter, wherein the ice cloud-sky transmittance is used to characterize the total solar radiation transmittance under ice cloud conditions; and determine the cloud-sky transmittance of solar radiation within the preset area based on the water cloud-sky transmittance and the ice cloud-sky transmittance.

[0145] In one possible design, the first determining module 1001 is further configured to: determine the first weighting coefficients of the water cloud sky transmittance and the ice cloud sky transmittance respectively based on the ratio of water cloud phase to ice cloud phase within the preset area; and perform a weighted summation of the water cloud sky transmittance and the ice cloud sky transmittance based on the first weighting coefficients to obtain the cloud sky transmittance of solar radiation within the preset area.

[0146] In one possible design, the type of atmospheric component data includes at least one of the following: precipitable water and ozone.

[0147] In one possible design, the first determining module 1001 is further configured to: determine the second weighting coefficients of the clear sky transmittance and the cloud sky transmittance respectively based on the cloud coverage within the preset area; and perform a weighted summation of the clear sky transmittance and the cloud sky transmittance based on the second weighting coefficients to obtain the total transmittance of solar radiation within the preset area.

[0148] In one possible design, the second determining module 1002 is specifically used to: multiply the total transmittance by the target radiation to obtain the first surface radiation.

[0149] In one possible design, the prediction module 1003 is specifically used to: input the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation into the target model to obtain the second surface radiation of the target area in the forecast period output by the target model.

[0150] In one possible design, the prediction module 1003 is further configured to: when the forecast period belongs to a first future period, input the first surface radiation, the data of at least one meteorological element acquired at the current time, the target climate data, and the predicted target radiation of the first future period into the target model to obtain the second surface radiation of the target area output by the target model in the first future period, wherein the duration of the first future period is less than a preset duration.

[0151] In one possible design, the prediction module 1003 is further configured to: when the forecast period belongs to a second future period, input the first surface radiation, the data of at least one meteorological element of the predicted second future period, the target climatological data, and the target radiation of the predicted second future period into the target model to obtain the second surface radiation of the target area of ​​the target area output by the target model in the second future period, wherein the duration of the second future period is greater than or equal to a preset duration.

[0152] In one possible design, the prediction module 1003 is further configured to: after predicting the second surface radiation of the target area, determine at least one correction parameter based on the observation data of the target area and the second surface radiation; and correct the second surface radiation based on the correction parameter to obtain the corrected second surface radiation.

[0153] In one possible design, the prediction module 1003 is also used to: predict the power of photovoltaic power generation equipment deployed in the target area based on the second surface radiation or the modified second surface radiation.

[0154] It should be noted that the information interaction and execution process between the modules / units in the computer device 1000 are based on the same concept as the method embodiments described above in this application. For details, please refer to the description in the method embodiments shown above in this application, which will not be repeated here.

[0155] Next, we will introduce another computer device provided in the embodiments of this application. Please refer to Figure 11. Figure 11 is a schematic diagram of the structure of a computer device provided in the embodiments of this application. The computer device 1100 may be deployed with the modules described in the embodiment corresponding to Figure 10, used to implement the functions of the computer device 1000 in the embodiment corresponding to Figure 10. Specifically, the computer device 1100 is implemented by one or more servers. The computer device 1100 may vary considerably due to different configurations or performance. It may include one or more central processing units (CPUs) 1122 and memory 1132, and one or more storage media 1130 (e.g., one or more mass storage devices) for storing application programs 1142 or data 1144. The memory 1132 and storage media 1130 may be temporary storage or persistent storage. The program stored in the storage media 1130 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the computer device 1100. Furthermore, the central processing unit 1122 can be configured to communicate with the storage medium 1130 and execute a series of instruction operations in the storage medium 1130 on the computer device 1100.

[0156] Computer device 1100 may also include one or more power supplies 1126, one or more wired or wireless network interfaces 1150, one or more input / output interfaces 1158, and / or one or more operating systems 1141, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0157] In this embodiment, the central processing unit 1122 is used to execute the steps performed by the computer device in the embodiment corresponding to FIG3. For example, the central processing unit 1122 may be used to: firstly, calculate the total transmittance T of solar radiation within a preset area based on a first type of data (e.g., satellite observation data) and a second type of data (e.g., atmospheric reanalysis data). all Among them, the total transmittance T all Total solar transmittance is used to characterize the proportion of solar radiation that reaches the Earth's surface after passing through a medium, under all-day conditions. The total transmittance T within a predetermined area is calculated. all Then, based on the total transmittance T all A first surface radiation R1 is determined, which characterizes the amount of solar radiation reaching the Earth's surface. Finally, based on the first surface radiation R1 calculated above, data of at least one meteorological element (e.g., wind speed, temperature, humidity, pressure, etc.), target climatological data, and target radiation, a second surface radiation R2 for the target area is predicted. This target area belongs to a preset area range. The target climatological data is climatological data covering the area of ​​the target region, which can be obtained through monitored meteorological data. This target climatological data is irradiance time-series data of a certain coordinate location processed by an algorithm, reflecting the long-term climatic characteristics of a certain location, and is used as a supplement to prior information. The target radiation is calculated in advance, and this target radiation can be zenith radiation or clear-sky radiation; this application does not limit it to either.

[0158] It should be noted that the specific way in which the central processing unit 1122 executes the above steps is based on the same concept as the method embodiment corresponding to Figure 3 in this application, and the resulting technical effects are also the same as those in the above embodiments of this application. For details, please refer to the description in the method embodiment shown above in this application, which will not be repeated here.

[0159] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0160] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0161] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0162] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. A method for predicting surface radiation, characterized in that, include: Based on the first type of data and the second type of data, the total transmittance of solar radiation within a preset area is determined. The total transmittance is used to characterize the total transmittance of solar radiation under all-day conditions. The total transmittance of solar radiation is used to characterize the proportion of solar radiation that can reach the Earth's surface after passing through the medium. The first surface radiation is determined based on the total transmittance, and the surface radiation is used to characterize the amount of solar radiation reaching the surface. Based on the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation, predict the second surface radiation of the target area, wherein the target area belongs to the preset area range, the target climatological data is obtained through monitored meteorological data, and the target radiation is calculated in advance, wherein the target radiation includes zenith radiation or clear-sky radiation.

2. The method according to claim 1, characterized in that, The step of determining the total transmittance of solar radiation within a preset area based on the first type of data and the second type of data includes: Based on the first type of data and the second type of data, the clear sky transmittance and cloud sky transmittance of solar radiation within the preset area are determined respectively. The clear sky transmittance is used to characterize the total solar radiation transmittance under clear sky conditions, and the cloud sky transmittance is used to characterize the total solar radiation transmittance under cloud sky conditions. Based on the clear sky transmittance and the cloud cover transmittance, the total transmittance of solar radiation within the preset area is determined.

3. The method according to claim 2, characterized in that, The first type of data includes cloud phase, optical parameters of aerosols, and optical parameters of clouds; the second type of data includes atmospheric composition data. Determining the clear-sky transmittance and cloud-sky transmittance of solar radiation within the preset area based on the first type of data and the second type of data includes: Based on the optical parameters of the aerosol and the atmospheric composition data, the clear-day transmittance of solar radiation within the preset area is determined. Based on the cloud phase and the cloud's optical parameters, determine the cloud transmittance of solar radiation within the preset area.

4. The method according to claim 3, characterized in that, The cloud phases include water cloud phases and ice cloud phases, and the optical parameters of the clouds include first optical parameters for water clouds and second optical parameters for ice clouds. Determining the cloud transmittance of solar radiation within the preset area based on the cloud phases and the cloud optical parameters includes: Based on the water cloud phase and the first optical parameter, the water cloud transmittance of solar radiation within the preset area is determined, and the water cloud transmittance is used to characterize the total transmittance of solar radiation under water cloud conditions. Based on the ice cloud phase and the second optical parameter, the ice cloud transmittance of solar radiation within the preset area is determined, and the ice cloud transmittance is used to characterize the total transmittance of solar radiation under ice cloud conditions. Based on the water cloud transmittance and the ice cloud transmittance, the cloud transmittance of solar radiation within the preset area is determined.

5. The method according to claim 4, characterized in that, The step of determining the cloud transmittance of solar radiation within the preset area based on the water cloud transmittance and the ice cloud transmittance includes: Based on the ratio of water cloud phase to ice cloud phase within the preset area, the first weighting coefficients of the water cloud sky transmittance and the ice cloud sky transmittance are determined respectively. The cloud transmittance of solar radiation within the preset area is obtained by weighting and summing the water cloud transmittance and the ice cloud transmittance according to the first weighting coefficient.

6. The method according to any one of claims 3-5, characterized in that, The types of atmospheric component data include at least one of the following: Precipitation and ozone.

7. The method according to any one of claims 2-6, characterized in that, Determining the total transmittance of solar radiation within the preset area based on the clear sky transmittance and the cloud cover transmittance includes: Based on the cloud coverage within the preset area, the second weighting coefficients for the clear sky transmittance and the cloud sky transmittance are determined respectively. The total transmittance of solar radiation within the preset area is obtained by weighting and summing the transmittance under clear skies and cloud cover using the second weighting coefficient.

8. The method according to any one of claims 1-7, characterized in that, The determination of the first surface radiation based on the total transmittance includes: Multiplying the total transmittance by the target radiation yields the first surface radiation.

9. The method according to any one of claims 1-8, characterized in that, The step of predicting the second surface radiation of the target area based on the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation includes: The first surface radiation, data of at least one meteorological element, target climatological data, and target radiation are input into the target model to obtain the second surface radiation of the target area during the forecast period, which is output by the target model.

10. The method according to claim 9, characterized in that, When the forecast period falls within a first future period, the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation are input into the target model to obtain the second surface radiation of the target area within the forecast period, as output by the target model, including: The first surface radiation, data of at least one meteorological element acquired at the current time, target climatological data, and the predicted target radiation for the first future time period are input into the target model to obtain the second surface radiation of the target area in the first future time period output by the target model, wherein the duration of the first future time period is less than a preset duration.

11. The method according to claim 9, characterized in that, When the forecast period falls within a second future period, the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation are input into the target model to obtain the second surface radiation of the target area within the forecast period, as output by the target model. The target model is input with the first surface radiation, data of at least one meteorological element predicted for the second future period, target climatological data, and the target radiation predicted for the second future period, to obtain the second surface radiation of the target area in the second future period output by the target model, wherein the duration of the second future period is greater than or equal to a preset duration.

12. The method according to any one of claims 1-11, characterized in that, Following the second surface radiation in the predicted target area, the method further includes: Based on the observation data within the target area and the second surface radiation, at least one correction parameter is determined; The second surface radiation is corrected according to the correction parameters to obtain the corrected second surface radiation.

13. The method according to any one of claims 1-12, characterized in that, The method further includes: The power output of photovoltaic power generation equipment deployed in the target area is predicted based on the second surface radiation or the modified second surface radiation.

14. A computer device, characterized in that, include: The first determining module is used to determine the total transmittance of solar radiation within a preset area based on the first type of data and the second type of data. The total transmittance is used to characterize the total transmittance of solar radiation under all-day conditions. The total transmittance of solar radiation is used to characterize the proportion of solar radiation that can reach the Earth's surface after passing through the medium. The second determining module is used to determine the first surface radiation based on the total transmittance, and the surface radiation is used to characterize the amount of solar radiation reaching the surface. The prediction module is used to predict the second surface radiation of a target area based on the first surface radiation, data of at least one meteorological element, target climatological data, and target radiation. The target area belongs to the preset area range. The target climatological data is obtained through monitored meteorological data. The target radiation is calculated in advance. The target radiation includes zenith radiation or clear-sky radiation.

15. The device according to claim 14, characterized in that, The first determining module is specifically used for: Based on the first type of data and the second type of data, the clear sky transmittance and cloud sky transmittance of solar radiation within the preset area are determined respectively. The clear sky transmittance is used to characterize the total solar radiation transmittance under clear sky conditions, and the cloud sky transmittance is used to characterize the total solar radiation transmittance under cloud sky conditions. Based on the clear sky transmittance and the cloud cover transmittance, the total transmittance of solar radiation within the preset area is determined.

16. The device according to claim 15, characterized in that, The first type of data includes cloud phase, optical parameters of aerosols, and optical parameters of clouds; the second type of data includes atmospheric component data; and the first determining module is further used for: Based on the optical parameters of the aerosol and the atmospheric composition data, the clear-day transmittance of solar radiation within the preset area is determined. Based on the cloud phase and the cloud's optical parameters, determine the cloud transmittance of solar radiation within the preset area.

17. The device according to claim 16, characterized in that, The cloud phase includes water cloud phase and ice cloud phase, and the cloud optical parameters include first optical parameters of water cloud and second optical parameters of ice cloud. The first determining module is further used for: Based on the water cloud phase and the first optical parameter, the water cloud transmittance of solar radiation within the preset area is determined, and the water cloud transmittance is used to characterize the total transmittance of solar radiation under water cloud conditions. Based on the ice cloud phase and the second optical parameter, the ice cloud transmittance of solar radiation within the preset area is determined, and the ice cloud transmittance is used to characterize the total transmittance of solar radiation under ice cloud conditions. Based on the water cloud transmittance and the ice cloud transmittance, the cloud transmittance of solar radiation within the preset area is determined.

18. The device according to claim 17, characterized in that, The first determining module is further configured to: Based on the ratio of water cloud phase to ice cloud phase within the preset area, the first weighting coefficients of the water cloud sky transmittance and the ice cloud sky transmittance are determined respectively. The cloud transmittance of solar radiation within the preset area is obtained by weighting and summing the water cloud transmittance and the ice cloud transmittance according to the first weighting coefficient.

19. The device according to any one of claims 16-18, characterized in that, The types of atmospheric component data include at least one of the following: Precipitation and ozone.

20. The device according to any one of claims 15-19, characterized in that, The first determining module is further configured to: Based on the cloud coverage within the preset area, the second weighting coefficients for the clear sky transmittance and the cloud sky transmittance are determined respectively. The total transmittance of solar radiation within the preset area is obtained by weighting and summing the transmittance under clear skies and cloud cover using the second weighting coefficient.

21. The device according to any one of claims 14-20, characterized in that, The second determining module is specifically used for: Multiplying the total transmittance by the target radiation yields the first surface radiation.

22. The device according to any one of claims 14-21, characterized in that, The prediction module is specifically used for: The first surface radiation, data of at least one meteorological element, target climatological data, and target radiation are input into the target model to obtain the second surface radiation of the target area during the forecast period, which is output by the target model.

23. The device according to claim 22, characterized in that, The prediction module is further used for: If the forecast period falls within a first future period, the first surface radiation, data of at least one meteorological element acquired at the current time, target climatological data, and the predicted target radiation for the first future period are input into the target model to obtain the second surface radiation of the target area in the first future period output by the target model. The duration of the first future period is less than a preset duration.

24. The device according to claim 22, characterized in that, The prediction module is further used for: If the forecast period falls within the second future period, the first surface radiation, data of at least one meteorological element of the predicted second future period, target climatological data, and the predicted target radiation of the second future period are input into the target model to obtain the second surface radiation of the target area in the second future period output by the target model, wherein the duration of the second future period is greater than or equal to a preset duration.

25. The device according to any one of claims 14-24, characterized in that, The prediction module is also used for: After predicting the second surface radiation in the target area, at least one correction parameter is determined based on the observation data within the target area and the second surface radiation. The second surface radiation is corrected according to the correction parameters to obtain the corrected second surface radiation.

26. The device according to any one of claims 14-25, characterized in that, The prediction module is also used for: The power output of photovoltaic power generation equipment deployed in the target area is predicted based on the second surface radiation or the modified second surface radiation.

27. A computer device comprising a processor and a memory, the processor being coupled to the memory, characterized in that, The memory is used to store programs; The processor is configured to execute a program in the memory, causing the computer device to perform the method as described in any one of claims 1-13.

28. A computer storage medium, characterized in that, The device stores computer-readable instructions, which, when executed by a processor, implement the method as described in any one of claims 1-13.

29. A computer program product, characterized in that, The computer program product includes computer-readable instructions that, when executed by a processor, implement the method as described in any one of claims 1-13.

30. A chip, the chip comprising a processor and a data interface, characterized in that, The processor reads instructions stored in the memory through the data interface and executes the method as described in any one of claims 1-13.

Images