Wind and solar energy prediction method, device and electronic equipment

By optimizing the radiation feedback effect mechanism and ensemble forecasting technology, the initial meteorological chemical coupled online mode was created, which solved the problem of unconsidered aerosol impact in the numerical mode, improved the forecast accuracy of solar and wind energy resources, and provided higher quality forecast data .

CN118822111BActive Publication Date: 2024-12-06BEIJING CHIYUAN TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411304018.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-12-06
Estimated Expiration
2044-09-19

AI Technical Summary

Technical Problem

The existing numerical model is difficult to accurately predict solar energy and wind resources when there is insufficient observation data for high-quality solar radiation and wind, and the impact of aerosols on radiation is not fully considered, resulting in a decrease in prediction accuracy.

Method used

By optimizing the radiation feedback effect mechanism, introducing ensemble forecasting technology, creating an initial meteorological chemical coupled online mode, using multiple sets of meteorological prediction field data, topography and land use data and emission source lists, improving the photochemical parameter scheme FAST-J, and performing optimal integration Solution selection, determine the optimal physical parameterized solution combination for wind and light energy prediction.

Benefits of technology

It improves the forecast accuracy of solar and wind energy resources, provides higher quality basic forecast data, and enhances the accuracy of forecasting of meteorological elements and pollutants.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118822111B_ABST
    Figure CN118822111B_ABST
Patent Text Reader

Abstract

The present application provides a method, device and electronic equipment for wind and solar energy prediction, which involves wind and solar energy prediction, including: creating an initial meteorological and chemical coupling online model according to multiple sets of meteorological prediction field data, land and terrain data and emission source lists corresponding to the target area; improving the photochemical parameter scheme FAST‑J in the initial meteorological and chemical coupling online model to obtain an optimized meteorological and chemical coupling online model; selecting the optimal integral scheme for the optimized meteorological and chemical coupling online model, determining the optimal physical parameterization scheme combination and determining it as a wind and solar energy prediction model; using the wind and solar energy prediction model, determining the corresponding wind and solar energy prediction results at each moment in the prediction time period. The present application predicts solar energy and wind energy resources by optimizing the radiation feedback effect mechanism and introducing ensemble forecasting technology in conventional numerical simulations, thereby improving the forecast accuracy of renewable resources.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of wind and solar energy prediction, and in particular to a wind and solar energy prediction method, device and electronic equipment. Background Art

[0002] In the absence of high-quality solar radiation and wind observation data, the use of numerical models for prediction and evaluation has become the most important method for solar energy resource assessment at home and abroad. Numerical models represented by WRF can calculate meteorological conditions and pollution concentrations, and output products such as solar irradiance and wind resources for renewable energy assessment. However, geographical factors, atmospheric pollution environment and other factors are the main factors affecting ground solar radiation, wind, etc. The interaction and influence of various factors will cause the numerical simulation of solar radiation and wind field results to result in large errors and low reliability, and the results need to be corrected before use.

[0003] The direct radiation effect of aerosols can reduce the amount of solar radiation on the ground, causing changes in surface temperature, which in turn affects the development of the tropospheric boundary layer and changes the meteorological conditions that affect the diffusion and dilution of pollutants. In the context of continuous improvement in air quality, the concentration of aerosols continues to decrease, and the seasonal and spatial variations are large. In the current numerical models, the impact of aerosols on radiation is not fully considered, and the effect of air quality on meteorological conditions through radiation feedback is not transmitted in real time, resulting in high total radiation and direct radiation values ​​simulated by the model, low scattered radiation values, and low wind speed simulation, resulting in a reduction in the accuracy of solar and wind energy forecasts. At the same time, the initial conditions of the numerical forecast model or the slight errors in the model will cause uncertainty in the forecast results of a single model. Ensemble forecasting is an effective scientific means to solve this problem. By perturbing the initial conditions and physical processes of the model and optimizing the forecast results of multiple models by ensemble optimization, the accuracy of meteorological elements and pollutant forecasts can be effectively improved, providing higher quality basic forecast data for solar and wind energy forecasts. Summary of the invention

[0004] In view of this, the purpose of this application is to at least provide a wind and solar energy prediction method, device and electronic equipment. Therefore, this application optimizes the radiation feedback effect mechanism in conventional numerical simulations, introduces ensemble forecasting technology, predicts solar energy and wind energy resources, and improves the forecast accuracy of renewable resources.

[0005] This application mainly includes the following aspects:

[0006] In the first aspect, an embodiment of the present application provides a method for predicting wind and solar energy, including: collecting historical meteorological and pollution source data generated in a target area within a preset historical time period before the prediction start time, multiple sets of meteorological forecast field data on a global scale, terrain and land use data, and emission source lists, the historical meteorological and pollution source data include the observation values ​​corresponding to the target monitoring elements at each collection time within the preset historical time period, the multiple sets of meteorological forecast field data include a set of global meteorological forecast field data corresponding to the European Center for Medium-Term Weather Forecasts Integrated Forecast System during the prediction time period, and the GFS of the National Environmental Prediction Center NECP of the United States. The corresponding 1 set of global meteorological forecast field data and 16 sets of global meteorological forecast field data corresponding to the China Meteorological Administration's Global Ensemble Forecast System, the target monitoring elements include preset meteorological field elements and preset pollutant concentration distribution elements; based on multiple sets of meteorological forecast field data, land and terrain data and emission source lists, an initial meteorological-chemical coupling online model is created. The initial meteorological-chemical coupling online model includes multiple physical parameterization scheme combinations, each physical parameterization scheme combination includes multiple different physical parameterization schemes, and different physical parameterization schemes reflect different meteorological physical processes; multiple optical parameters corresponding to aerosols are used to improve the photochemical parameter scheme FAS in the initial meteorological-chemical coupling online model. T-J, obtain an optimized meteorological-chemical coupling online model; select the optimal integral scheme for the optimized meteorological-chemical coupling online model to select the optimal physical parameterization scheme combination from multiple physical parameterization scheme combinations; apply the optimal physical parameterization scheme combination to the initial meteorological-chemical coupling online model to obtain the target meteorological-chemical coupling online model; determine the target meteorological-chemical coupling online model as a wind-solar energy prediction model; use multiple groups of meteorological prediction field data, the terrain and land use data and the emission source list, use the wind-solar energy prediction model to perform wind-solar meteorological field and pollutant ensemble forecasts, and optimize the forecast results to determine the wind-solar energy prediction results at each moment in the target prediction time period.

[0007] In one possible implementation, the initial meteorological-chemical coupling online mode also includes multiple chemical parameterization schemes, different chemical parameterization schemes reflect different meteorological chemical processes, and the multiple chemical parameterization schemes include a photochemical parameter scheme FAST-J, wherein the optimized meteorological-chemical coupling online mode is obtained by: using Mie scattering theory to calculate multiple target optical parameters corresponding to aerosols, where the target optical parameters are optical parameters that affect the photolysis rate calculation; and transferring the multiple target optical parameters to the photolysis rate calculation module in the photochemical parameter scheme FAST-J to obtain the optimized meteorological-chemical coupling online mode.

[0008] In one possible implementation, the initial meteorological-chemical coupled online model includes initial meteorological conditions, boundary meteorological conditions, and emission source distribution corresponding to each set of meteorological forecast field data, and the multiple chemical parameterization schemes also include a gas phase chemistry scheme CBM-Z and an aerosol chemistry scheme MOSAIC. Among them, the optimal physical parameterization scheme combination is determined in the following way: in the meteorological and chemical coupling online mode, the following processing is performed: the initial meteorological conditions, boundary meteorological conditions and emission source distribution corresponding to the target meteorological prediction field data are enabled; the gas phase chemistry scheme CBM-Z, the aerosol chemistry scheme MOSAIC and the photochemical parameter scheme FAST-J are selected, and the aerosol radiation direct feedback mechanism switch is turned on; single perturbation integration experiments are performed on multiple physical parameterization scheme combinations respectively, and the single perturbation integration results corresponding to each physical parameterization scheme combination are obtained, and the single perturbation integration results include the first prediction data within the preset historical time period corresponding to the wind and solar energy prediction area, and the first prediction data include the simulation value corresponding to the target monitoring element at each collection time within the preset historical time period; based on the historical meteorological and pollution source data and the first prediction data, the single perturbation integration results corresponding to each physical parameterization scheme combination are evaluated and analyzed respectively, and the evaluation and analysis results corresponding to each physical parameterization scheme combination are obtained; according to the evaluation and analysis results corresponding to each physical parameterization scheme combination, the optimal physical parameterization scheme combination is determined.

[0009] In one possible implementation, the step of determining the optimal physical parameterization scheme combination according to the evaluation and analysis results corresponding to each physical parameterization scheme combination includes: performing the following processing for the single disturbance integration result corresponding to each physical parameterization scheme combination: calculating the correlation coefficient, standard mean deviation and standard mean error corresponding to the physical parameterization scheme combination according to the observation value and simulation value corresponding to each acquisition moment in a preset historical time period of the target monitoring element indicated by the single disturbance integration result; if there is a correlation coefficient greater than the first threshold, the second threshold ≤ standard mean deviation ≤ third threshold and the standard mean error ≤ fourth threshold, then determining the physical parameterization scheme combination as a candidate physical parameterization scheme combination; from multiple candidate physical parameterization scheme combinations, comprehensively selecting the optimal physical parameterization scheme combination according to the preset selection strategy.

[0010] In one possible implementation, the correlation coefficient is determined by the following formula:

[0011]

[0012] In this formula, represents the correlation coefficient, N represents the number of observations or simulations corresponding to the target monitoring element collected within the preset historical time period, represents the simulated value of the target monitoring element, represents the observed value of the target monitoring element, It represents the average value of N simulation values ​​corresponding to the target monitoring element. Represents the average value among the N observation values ​​corresponding to the target monitoring element;

[0013] The standard mean deviation is determined by the following formula :

[0014]

[0015] The standard mean error is determined by the following formula :

[0016]

[0017] In one possible implementation, the wind and solar energy prediction results at each moment in the target prediction time period are determined in the following manner: multiple groups of meteorological prediction field data, terrain and land use data, and emission source lists are input into the wind and solar energy prediction model to perform integral calculations using the optimal physical parameterization scheme combination to determine the second prediction data corresponding to each group of meteorological prediction field data, the second prediction data including the simulation value corresponding to the target monitoring element at each collection moment in the target prediction time period; based on the second prediction data corresponding to each group of meteorological prediction field data and a preset regression equation, the optimal simulation value corresponding to each target monitoring element at each collection moment in the prediction time period is determined, the preset regression equation describes the mapping relationship between multiple simulation values ​​of the target monitoring element at each collection moment and the optimal simulation value; using the optimal simulation value corresponding to the target meteorological element at each collection moment in the prediction time period, the corresponding wind and solar energy prediction results at each moment in the prediction time period are determined.

[0018] In a possible implementation, the preset regression equation is:

[0019]

[0020] in, Indicates the number of The optimal simulation value corresponding to the target monitoring element at each collection time, Indicates The weighted regression coefficient corresponding to the group of meteorological forecast field data, Indicated in In the group of meteorological forecast field data, the simulated value of the target monitoring element at the nth collection time from the start time of the forecast, and b represents the regression constant.

[0021] In a possible implementation, the wind and solar energy forecast results include photovoltaic power generation potential, working efficiency of photovoltaic modules, actual temperature of photovoltaic modules and wind power density, and meteorological elements include downward shortwave radiation and wind speed at 100 meters. The corresponding wind and solar energy forecast results at each moment in the forecast time period are determined by the following formula:

[0022]

[0023] in, Represents the photovoltaic power generation potential, Indicates the working efficiency of photovoltaic modules. Represents the shortwave flux of photovoltaic modules under standard conditions, Indicates downward shortwave radiation and wind speed at 100 meters.

[0024]

[0025] The actual temperature of the PV panels, Represents the test temperature of PV modules under standard conditions;

[0026]

[0027] Indicates the ambient temperature, Indicates the wind speed at 100 meters.

[0028]

[0029] represents the wind power density, represents the number of meteorological elements collected during the forecast period, Vm represents the simulated value of the wind speed at the mth 100-meter point during the forecast period, Indicates the air density.

[0030] In a second aspect, the embodiment of the present application further provides a wind and solar energy prediction device, the device comprising:

[0031] The data collection module is used to collect historical meteorological and pollution source data generated in the target area within the preset historical time period before the forecast start time, multiple sets of global meteorological forecast field data, terrain and land use data and emission source lists. The historical meteorological and pollution source data include the corresponding observation values ​​of the target monitoring elements at each collection time within the preset historical time period. The multiple sets of meteorological forecast field data include a set of global meteorological forecast field data corresponding to the European Center for Medium-Term Weather Forecasts Integrated Forecast System during the forecast period, and the GFS of the National Environmental Prediction Center NECP of the United States The target monitoring elements include preset meteorological field elements and preset pollutant concentration distribution elements; a creation module is used to create an initial meteorological-chemical coupling online model based on multiple sets of meteorological prediction field data, land and terrain data and emission source lists. The initial meteorological-chemical coupling online model includes multiple physical parameterization scheme combinations, each physical parameterization scheme combination includes multiple different physical parameterization schemes, and different physical parameterization schemes reflect different meteorological physical processes; an improvement module is used to use multiple optical parameters corresponding to aerosols to improve the photochemical parameter scheme FAST-J in the initial meteorological-chemical coupling online model, and obtain An optimized meteorological-chemical coupling online model; a scheme selection module, used to select the optimal integral scheme for the optimized meteorological-chemical coupling online model, so as to select the optimal physical parameterization scheme combination from multiple physical parameterization scheme combinations; an application module, used to apply the optimal physical parameterization scheme combination to the initial meteorological-chemical coupling online model, so as to obtain the target meteorological-chemical coupling online model; a determination module, used to determine the target meteorological-chemical coupling online model as a wind-solar energy prediction model; a prediction module, used to use multiple sets of meteorological prediction field data, terrain and land use data and emission source lists, use the wind-solar energy prediction model to perform ensemble forecasts of wind-solar meteorological fields and pollutants, and optimize the forecast results to determine the wind-solar energy prediction results at each moment in the target prediction time period.

[0032] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the wind and solar energy prediction method provided in any of the above embodiments.

[0033] The embodiment of the present application provides a method, device and electronic device for forecasting wind and solar energy, including: creating an initial meteorological and chemical coupling online model according to multiple sets of meteorological forecast field data, land and terrain data and emission source lists corresponding to the target area; improving the photochemical parameter scheme FAST-J in the initial meteorological and chemical coupling online model to obtain an optimized meteorological and chemical coupling online model; selecting the optimal integral scheme for the optimized meteorological and chemical coupling online model, determining the optimal physical parameterization scheme combination and determining it as a wind and solar energy forecast model; using the wind and solar energy forecast model, multiple sets of meteorological forecast field data, terrain and land use data and emission source lists, determining the corresponding wind and solar energy forecast results at each moment in the forecast time period. The present application predicts solar energy and wind energy resources by optimizing the radiation feedback effect mechanism and introducing ensemble forecasting technology in conventional numerical simulations, thereby improving the forecast accuracy of renewable resources.

[0034] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A flow chart of a wind and solar energy prediction method provided in an embodiment of the present application is shown;

[0037] Figure 2 A flowchart showing the steps of determining a wind and solar energy prediction result provided by an embodiment of the present application is shown;

[0038] Figure 3 A functional module diagram of a wind and solar energy prediction device provided in an embodiment of the present application is shown;

[0039] Figure 4 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0040] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0041] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0042] Solar energy and wind energy are considered to be renewable energy sources that can be used on a large scale. Reasonable and accurate assessment of solar energy and wind energy resources is a key step in the development and utilization of renewable resources. Solar energy and wind energy resources are significantly affected by meteorological conditions and geographical factors, resulting in large discontinuity and instability in the efficiency of photovoltaic and wind power generation. In order to meet the demand for renewable energy generation, accurate photovoltaic and wind power generation prediction and assessment has become a key issue in the stable conversion of renewable energy.

[0043] The main methods for forecasting solar energy and wind energy include statistical methods based on real-time and historical data from observation sites, and methods based on numerical simulation prediction. Due to the high cost of installation and maintenance of measuring instruments, the distribution density of meteorological observation stations is relatively sparse, especially in some remote areas (such as the Gobi region in the northwest), where the sunshine time is long and the wind speed is high, and the solar energy and wind energy resources are generally abundant. However, the distribution of observation meteorological stations in these areas is very sparse. It is not reasonable to directly use observation data to predict and evaluate the renewable energy resources in these areas, and the accuracy is low. In the absence of high-quality solar radiation and wind observation data, the use of numerical models for prediction and evaluation has become the most important solar energy resource assessment method at home and abroad. Numerical models can calculate and output solar irradiance and wind resource products for the assessment of renewable resources. Numerical models have become an important means of research and management in the field of air pollution control and climate change response.

[0044] Numerical models are based on the numerical solution of mathematical and physical equations such as atmospheric dynamics, atmospheric physics, atmospheric chemistry and land surface processes. Numerical models represented by WRF can calculate meteorological conditions and pollution concentrations, and output products such as solar irradiance and wind resources for the assessment of renewable energy. However, geographical factors, atmospheric pollution environment and other factors are the main factors affecting ground solar radiation, wind, etc. The interaction and influence of various factors will cause the numerical simulation of solar radiation and wind field results to result in large errors and low reliability, and the results need to be corrected before use.

[0045] The direct radiation effect of aerosols can reduce the amount of solar radiation on the ground, causing changes in surface temperature, which in turn affects the development of the tropospheric boundary layer and changes the meteorological conditions that affect the diffusion and dilution of pollutants. When the aerosol concentration continues to decrease and the seasonal and spatial variations are large, if the radiation feedback effect is not considered in the numerical model, it will have a great impact on the accuracy of solar and wind energy forecasts. However, the current numerical models do not fully consider the impact of aerosols on radiation, and do not transmit the effect of air quality on meteorological conditions through radiation feedback in real time, resulting in high total radiation and direct radiation values ​​simulated by the model, low scattered radiation values, and low wind speed simulation. At the same time, the initial conditions of the numerical forecast model or the slight errors in the model will make the forecast results of a single model uncertain. Ensemble forecasting is an effective scientific means to solve this problem. By perturbing the initial conditions and physical processes of the model and optimizing the multi-model forecast results of the ensemble, the forecast accuracy of meteorological elements and pollutants can be effectively improved, providing higher quality basic forecast data for solar and wind energy forecasts.

[0046] Based on this, the embodiments of the present application provide a wind and solar energy prediction method, device and electronic device, which optimizes the radiation feedback effect mechanism in conventional numerical simulations and introduces ensemble prediction technology to predict solar energy and wind energy resources, thereby improving the prediction accuracy of renewable resources, as follows:

[0047] See also Figure 1 , Figure 1 A flow chart of a wind and solar energy prediction method provided in an embodiment of the present application is shown. Figure 1 As shown, the method provided in the embodiment of the present application comprises the following steps:

[0048] S100, collecting historical meteorological and pollution source data generated in the target area within a preset historical time period before the forecast start time, multiple sets of meteorological forecast field data, terrain and land use data and emission source lists on a global scale.

[0049] Historical meteorological and pollution source data include the observation values ​​of the target monitoring elements at each collection time within a preset historical time period. The target monitoring elements include preset meteorological field elements and preset pollutant concentration distribution elements.

[0050] S200, creating an initial meteorological-chemical coupling online model based on multiple sets of meteorological forecast field data, land and terrain data, and emission source inventories.

[0051] The initial meteorological-chemical coupled online model includes a plurality of physical parameterization scheme combinations, each of which includes a plurality of different physical parameterization schemes, and different physical parameterization schemes reflect different meteorological physical processes.

[0052] S300, using multiple optical parameters corresponding to aerosols, improve the photochemical parameter scheme FAST-J in the initial meteorological-chemical coupling online model to obtain the optimized meteorological-chemical coupling online model.

[0053] S400, selecting the best integral scheme for the optimized meteorological-chemical coupled online model, so as to select the best physical parameterization scheme combination from multiple physical parameterization scheme combinations.

[0054] S500, applying the optimal physical parameterization scheme combination to the initial meteorological-chemical coupled online model to obtain the target meteorological-chemical coupled online model.

[0055] S600: determine the target meteorological-chemical coupling online model as a wind-solar energy prediction model.

[0056] S700, using multiple sets of meteorological forecast field data, terrain and land use data and emission source lists, using wind and solar energy forecast models to perform wind and solar meteorological field and pollutant ensemble forecasts, and perform optimization of forecast results to determine the wind and solar energy forecast results at each moment in the target forecast time period.

[0057] Specifically, in step S100, the target area for wind and solar energy forecasting and the forecast time period for wind and solar energy forecasting are first determined. The forecast time period includes a forecast start time and a forecast end time. The preset historical time period before the forecast start time can be 1 year before the forecast start time. The preset historical time period can be set according to actual needs. The meteorological and pollution source data include meteorological station observation data (including but not limited to at least one of the following items: temperature, humidity, precipitation, wind speed, boundary layer height, WS10, GHI) and air quality monitoring network data (including but not limited to at least one of the following items: PM2.5, PM10, ozone, SO2, NOx, CO).

[0058] Multiple groups of meteorological forecast field data include the forecast field data corresponding to the European Centre for Medium-Range Weather Forecasts (ECMWF) Integrated Forecast System IFS during the forecast period (1 member, including 1 group of global meteorological forecast field data), the GFS (Global Forecast System) forecast field data of the National Center for Environmental Prediction NECP of the United States (1 member, including 1 group of global meteorological forecast field data) and the China Meteorological Administration Global Ensemble Forecast System CMA_GEPS forecast field data (16 members, including 16 groups of global meteorological forecast field data). In other words, this application collects a total of 18 groups of global meteorological forecast field data, and also collects the latest terrain and land use data in the wind and solar energy forecast area.

[0059] Directly collect the domestic mainstream MEIC pollution source list as the emission source list, or combine the environmental statistical data, pollution source census data and statistical yearbook information in the wind and solar energy forecast area, apply the emission factor method to calculate the emission source intensity of atmospheric pollution sources in the wind and solar energy forecast area, and establish an emission source list, where the emission source list includes but is not limited to at least one of the following items: longitude and latitude, type of emission source and emission amount.

[0060] In a preferred embodiment, step S200 includes:

[0061] Download and install the source code corresponding to the meteorological-chemical coupling online mode, obtain the meteorological-chemical coupling online mode, and initialize the meteorological-chemical coupling online mode: write the prediction time parameters, the simulation range parameters corresponding to the wind and solar energy prediction area, the grid processing parameters, multiple sets of meteorological prediction field data, terrain and land use data, and the emission source list into the meteorological-chemical coupling online mode, start the data interpolation processing module in the meteorological-chemical coupling online mode, so that the data interpolation processing module interpolates the multiple sets of meteorological prediction field data, terrain and land use data, and the emission source list according to the grid processing parameters and the simulation range parameters, generates the initial meteorological conditions, boundary meteorological conditions and emission source distribution corresponding to each set of meteorological prediction field data, and determines the initialized meteorological-chemical coupling online mode as the initial meteorological-chemical coupling online mode.

[0062] The numerical model is coupled with the Chem module on the basis of the conventional WRF (Weather Research and Forecasting model). WRF is used to simulate meteorological conditions to provide a more accurate meteorological field for air quality simulation, and the Chem module realizes the simulation of chemical processes in the atmosphere, including the emission, transmission and deposition of pollutants, as well as the interaction and influence mechanism between meteorological fields and pollutants. Through the compilation and selection of chemical mechanisms, mutual feedback between pollutants and meteorological elements is realized in the time step integral, reducing the loss of atmospheric information caused by meteorological data interpolation in the offline mode and improving the simulation accuracy.

[0063] Specifically, the installation and compilation of the source code corresponding to the meteorological-chemical coupling online mode is achieved through the following methods: select Unix or Linux system, use FORTRAN or INTEL compiler for compilation preparation, install MPI software and NETCDF library, set key environment variables, mainly set OBJECT_MODE=64, WRF_CHEM=1, WRF_EM_CORE=1, WRFIO_NCD_LARGE_FILE_SUPPORT=1, execute the configure file, compile WRF, ensure that WRF_CHEM in the compilation output file information is 1, and output real.exe, wrf.exe, ndown.exe, nup.exe execution files, execute the configure file to compile the WPS module, determine the current directory to generate geogrid.exe, ungrib.exe, metgrid.exe files, and complete the installation and construction of the meteorological-chemical coupling online mode.

[0064] Then the meteorological-chemical coupling online mode WRF-chem is initialized. During the initialization process, the prediction time parameters are first determined. The prediction time parameters include the prediction start time and prediction end time corresponding to the prediction time period (for example, the prediction start time is 7:30 on July 30, 2024, and the prediction end time is 7:30 on August 5) and the historical start time and historical end time corresponding to the preset historical time period (for example, the historical start time is 7:30 on July 30, 2023 to 6:30 on July 30, 2024).

[0065] According to the target area determined in step S100, the simulation range parameters are set, and the simulation range parameters include the target area, the preset range around the target area, the longitude and latitude corresponding to the center of the target area, and the corresponding number of grids in the east-west and north-south directions of the target area. The grid processing parameters include a double-layer nested resolution, with an outer layer of 9 km resolution and an inner layer of 3 km resolution. After determining the simulation range parameters, grid processing parameters, multiple sets of meteorological forecast field data, terrain and land use data, and emission source lists, the data interpolation module provided by the meteorological-chemical coupling online mode WRF-chem is used to generate 18 sets of initial meteorological conditions and 18 sets of boundary meteorological conditions.

[0066] The emission source inventory is interpolated into 9KM resolution and 3KM resolution, and produced into Netcdf format inventory data.

[0067] In the present application, the meteorological-chemical coupling online mode WRF-chem includes multiple chemical parameterization schemes. Different chemical parameterization schemes reflect different meteorological chemical processes. The multiple chemical parameterization schemes include the photochemical parameter scheme FAST-J. After the initial meteorological-chemical coupling online mode WRF-chem is built, the initial meteorological-chemical coupling online mode WRF-chem is further optimized. Specifically, it is necessary to first improve the photochemical parameter scheme FAST-J in the meteorological-chemical coupling online mode WRF-chem.

[0068] In a preferred embodiment, step S300 includes:

[0069] The Mie scattering theory is used to calculate multiple target optical parameters corresponding to aerosols. The target optical parameters are optical parameters that affect the photolysis rate calculation. The multiple target optical parameters are transferred to the photolysis rate calculation module in the photochemical parameter scheme FAST-J to obtain the optimized meteorological and chemical coupled online mode.

[0070] In one example, the multiple target optical parameters include but are not limited to at least one of the following items: optical thickness (AOD), single scattering albedo (SSA) and asymmetry factor (g). The present application updates the multiple target optical parameters in the photolysis rate calculation module through real-time calculation, so that the photolysis rate calculation module uses the multiple target optical parameters updated in real time to complete the photolysis rate calculation, thereby improving the accuracy of the photolysis rate calculation, so as to achieve the simulation function of optimizing the impact of aerosol feedback effect on regional solar radiation.

[0071] In order to realize the feedback response of atmospheric pollution changes on solar radiation and wind energy, simulate the direct radiation effect of aerosols, and improve the prediction accuracy of solar energy and wind energy resources, it is necessary to select and optimize the optimal integration scheme of the optimized meteorological and chemical coupling online model, so as to select the optimal physical parameterization scheme combination that makes the integration result most accurate from multiple physical parameterization scheme combinations.

[0072] In a specific embodiment, the initial meteorological-chemical coupling online model includes initial meteorological conditions, boundary meteorological conditions and emission source distribution corresponding to each set of meteorological forecast field data, and the multiple chemical parameterization schemes also include a gas phase chemistry scheme CBM-Z and an aerosol chemistry scheme MOSAIC. Specifically, step S400 includes:

[0073] In the optimized meteorological-chemical coupling online mode, the following processing is performed:

[0074] The initial meteorological conditions, boundary meteorological conditions and emission source distribution corresponding to the target meteorological forecast field data are enabled, the gas phase chemistry scheme CBM-Z, the aerosol chemistry scheme MOSAIC and the photochemical parameter scheme FAST-J are selected, and the aerosol radiation direct feedback mechanism switch is turned on. Single perturbation integration experiments are carried out on multiple physical parameterization scheme combinations to obtain the single perturbation integration results corresponding to each physical parameterization scheme combination. The single perturbation integration results include the first prediction data within the preset historical time period corresponding to the target area. The first prediction data include the simulation values ​​corresponding to the target monitoring elements at each collection time within the preset historical time period. Based on the historical meteorological and pollution source data and the first prediction data, the single perturbation integration results corresponding to each physical parameterization scheme combination are evaluated and analyzed to obtain the evaluation and analysis results corresponding to each physical parameterization scheme combination. According to the evaluation and analysis results corresponding to each physical parameterization scheme combination, the optimal physical parameterization scheme combination is determined.

[0075] In a specific example, the target meteorological forecast field data is the GFS meteorological forecast field data. In this application, the initial meteorological conditions and boundary meteorological conditions corresponding to the GFS meteorological forecast field data are used to simulate the meteorological and atmospheric pollution processes in a preset historical time period. The multiple chemical parameterization schemes selected in this application are predetermined, and the gas phase chemistry scheme CBM-Z, the aerosol chemistry scheme MOSAIC and the photochemical parameter scheme Fast-J are selected. After setting, turn on the aerosol radiation direct feedback mechanism switch.

[0076] In the present application, multiple physical parameterization scheme combinations are divided into multiple different disturbance groups in the WRF-Chem model. The different disturbance groups include a radiation process disturbance group, a cumulus process disturbance group, a boundary layer disturbance group, a land surface process disturbance group, and an urban canopy disturbance group. Each disturbance group includes multiple physical parameterization scheme combinations. According to different disturbance groups, single perturbation integration experiments are performed on multiple physical parameterization scheme combinations respectively. The following Table 1 shows a single perturbation scheme table provided in the present application:

[0077] Table 1

[0078]

[0079] As shown in Table 1, Table 1 provides a total of 24 physical parameterization scheme combinations, among which the radiation process perturbation group includes 2 physical parameterization scheme combinations, the cumulus process perturbation group includes 2 physical parameterization scheme combinations, the boundary layer perturbation group includes 8 physical parameterization scheme combinations, the land surface process perturbation group includes 8 physical parameterization scheme combinations and the urban canopy perturbation group includes 4 physical parameterization scheme combinations. Taking the radiation process perturbation group as an example, one of the physical parameterization scheme combinations in the radiation process perturbation group includes multiple physical parameterization schemes such as LIN, Goddard, RRTM, GD, YUS, Noah, and SLAB.

[0080] After single-integral perturbations are performed on the radiation process, cumulus process, boundary layer process, land surface process and urban canopy process, the 24 physical parameterization scheme combinations in Table 1 are subjected to model simulation integral calculation experiments, and a total of 24 single-perturbation integral results can be obtained. The 24 single-perturbation integral results are evaluated and analyzed using historical meteorological and pollution source data, and the optimal physical parameterization scheme combination can be obtained based on the evaluation and analysis results.

[0081] In another preferred embodiment, the step of determining the optimal physical parameterization scheme combination according to the evaluation analysis results corresponding to each physical parameterization scheme combination includes:

[0082] For the single perturbation integration results corresponding to each physical parameterization scheme combination, the following processing is performed:

[0083] According to the observed values ​​and simulated values ​​corresponding to each collection moment in the preset historical time period of the target monitoring element indicated by the single disturbance integration result, the correlation coefficient, standard mean deviation and standard mean error corresponding to the physical parameterization scheme combination are calculated. If there is a correlation coefficient greater than the first threshold, the second threshold ≤ standard mean deviation ≤ the third threshold and the standard mean error ≤ the fourth threshold, then the physical parameterization scheme combination is determined as a candidate physical parameterization scheme combination. From multiple candidate physical parameterization scheme combinations, the optimal physical parameterization scheme combination is comprehensively selected according to the preset selection strategy.

[0084] Specifically, the first threshold, the second threshold, the third threshold and the fourth threshold can be set according to user needs. In a specific implementation, the first threshold = 0.5, the second threshold = -0.6, the third threshold = 0.6, and the fourth threshold = 0.7. Specifically, the correlation coefficient R reflects the degree of agreement between the simulation results and the observation results corresponding to the meteorological elements, and the standard mean deviation NMB and the standard mean error NME represent the degree of deviation between the simulation results and the observation results. When R>0.5, -0.6≤NMB≤0.6, and NME≤0.7, it is considered that the simulation results of the meteorological-chemical coupling online mode under the physical parameterization scheme combination are reasonable, and the physical parameterization scheme combination is used as a candidate physical parameterization scheme combination. If -0.3≤NMB≤0.3 and NME≤0.5, it is considered that the simulation results of the meteorological-chemical coupling online mode are relatively ideal. If R≤0.5, NMB<-0.6 or NMB>0.6, or NME>0.7 exists, it is determined that the physical parameterization scheme combination does not meet the selection requirements and the physical parameterization scheme combination is discarded.

[0085] In a preferred embodiment, the correlation coefficient is determined by the following formula:

[0086]

[0087] In this formula, represents the correlation coefficient, N represents the number of observations or simulations corresponding to the target monitoring element collected within the preset historical time period, represents the simulated value of the target monitoring element, represents the observed value of the target monitoring element, It represents the average value of N simulation values ​​corresponding to the target monitoring element. Represents the average value among N observation values ​​corresponding to the target monitoring element.

[0088] The standard mean deviation is determined by the following formula :

[0089]

[0090] The standard mean error is determined by the following formula :

[0091]

[0092] In the present application, the target monitoring elements include but are not limited to at least one of the following items: PM2.5 concentration and component concentration, output shortwave radiation SWDOWN, wind speed WS10 at 100 meters, ground two-meter temperature T2 and air density.

[0093] After determining multiple candidate physical parameterization scheme combinations, this application needs to further select the optimal physical parameterization scheme combination according to the preset selection strategy. Specifically, the preset selection strategy includes: comparing the correlation coefficient R, standard mean deviation NMB and standard mean error NME corresponding to each climate element under multiple candidate physical parameterization scheme combinations, and selecting the candidate physical parameterization scheme combination with the largest R, the smallest NMB and the smallest NME for each climate element from multiple candidate physical parameterization scheme combinations as the optimal physical parameterization scheme combination.

[0094] After determining the optimal physical parameterization scheme combination, the optimal physical parameterization scheme combination is applied in the optimized meteorological-chemical coupling online model for integral calculation to obtain the target meteorological-chemical coupling online model, and the target meteorological-chemical coupling online model is determined as the wind-solar energy prediction model.

[0095] In a preferred embodiment, see Figure 2 , Figure 2 A flowchart of the steps for determining the wind and solar energy prediction results provided by an embodiment of the present application is shown. Figure 2 As shown, step S700 includes:

[0096] S7001. Input multiple sets of meteorological forecast field data, terrain and land use data and emission source lists into the wind and solar energy forecast model, and use the optimal physical parameterization scheme combination for integral calculation to determine the second prediction data corresponding to each set of meteorological forecast field data.

[0097] The second prediction data includes the simulation value corresponding to the target monitoring element at each collection time within the prediction time period.

[0098] S7002. Determine the optimal simulation value corresponding to each target monitoring element at each collection time within the forecast time period based on the second prediction data corresponding to each set of meteorological forecast field data and the preset regression equation.

[0099] The preset regression equation describes the mapping relationship between multiple simulation values ​​of the target monitoring element at each collection time and the optimal simulation value.

[0100] S7003. Using the optimal simulation value corresponding to each acquisition moment in the forecast time period of the target meteorological element, determine the corresponding wind and solar energy forecast result at each moment in the target forecast time period.

[0101] In the present application, in step S7001, after executing step S600, the present application inputs multiple groups of meteorological forecast field data, terrain and land use data and emission source lists into the built wind and solar energy forecast model, and outputs the simulation value corresponding to each collection moment in the forecast time period of the target monitoring element under each group of meteorological forecast field data. That is, since the present application provides 18 groups of different meteorological forecast field data, each target monitoring element has a total of 18 simulation values ​​at each collection moment in the forecast time period.

[0102] In step S7002 of the present application, an optimal simulation value can be determined from 18 simulation values ​​corresponding to the target monitoring element at each collection time within the prediction time period by using a preset regression equation.

[0103] In a preferred embodiment, before executing step S7002, 18 sets of meteorological forecast field data, terrain and land use data, and a list of emission sources corresponding to a preset historical time period (a list of months corresponding to the preset historical time period) are input into the wind and solar energy prediction model, and integral calculations are performed through the optimal physical parameterization scheme combination to obtain 18 sets of simulation values ​​corresponding to the target monitoring elements at each collection moment within the preset historical time period, and then the multivariate linear regression method is used to perform regression calculations on the 18 sets of simulation values ​​and observation values ​​corresponding to each target monitoring element to build a regression equation.

[0104] The regression equation is constructed using the following formula:

[0105]

[0106] In this formula, Indicates the time from the beginning of the back calculation period. The observation value corresponding to the target monitoring element at each collection time, Indicates The weighted regression coefficient corresponding to the group of meteorological forecast field data, Indicated in In the group of meteorological forecast field data, the target monitoring element is the simulated value at the i-th collection time starting from the starting time of the back-calculation period, b represents the regression constant, and in this application, the back-calculation period is the period formed from m moments before the forecast time.

[0107] Thus, for each collection time in the preset historical time period, a training regression sample is formed by the observation value corresponding to the target monitoring element at the collection time and the multiple simulation values ​​corresponding to the collection time of the target monitoring element in the preset historical time period. The regression equation is trained using multiple training regression samples to obtain the regression weight coefficient corresponding to each set of meteorological forecast field data. And regression constant b, thus the target regression equation is obtained:

[0108]

[0109] In this formula, Indicates the number of The optimal simulation value corresponding to the target monitoring element at each collection time, Indicates The weighted regression coefficient corresponding to the group of meteorological forecast field data, Indicated in In the group of meteorological forecast field data, the simulated value of the target monitoring element at the nth collection time from the start time of the forecast, and b represents the regression constant.

[0110] In another preferred embodiment, the wind and solar energy prediction results include photovoltaic power generation potential, working efficiency of photovoltaic modules, actual temperature of photovoltaic modules and wind power density, and the meteorological elements include downward shortwave radiation and wind speed at 100 meters. Step S7003 includes:

[0111]

[0112] in, Represents the photovoltaic power generation potential, Indicates the working efficiency of photovoltaic modules. Represents the shortwave flux of photovoltaic modules under standard conditions, Indicates downward shortwave radiation and wind speed at 100 meters.

[0113]

[0114] The actual temperature of the PV panels, Represents the test temperature of photovoltaic modules under standard conditions. In this application, Generally take 25℃.

[0115]

[0116] Indicates the ambient temperature, Indicates the wind speed at 100 meters.

[0117]

[0118] represents the wind power density, represents the number of target monitoring elements collected during the forecast period, Vm represents the simulated value of the wind speed at the mth 100-meter point during the forecast period, Indicates the air density.

[0119] This application achieves simultaneous prediction of solar and wind energy resources through statistical analysis, numerical simulation, and ensemble forecasting methods, thereby improving the accuracy of renewable energy prediction.

[0120] Based on the same application concept, the embodiments of the present application also provide a wind and solar energy prediction device corresponding to the wind and solar energy prediction method provided in the above embodiments. Since the principle of solving the problem by the device in the embodiments of the present application is similar to the wind and solar energy prediction method in the above embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0121] See also Figure 3 , Figure 3 FIG. 1 shows a functional module diagram of a wind and solar energy prediction device provided in an embodiment of the present application. Figure 3 As shown, the wind and solar energy prediction device includes:

[0122] The data collection module 800 is used to collect historical meteorological and pollution source data generated in the target area within a preset historical time period before the prediction start time, multiple sets of global meteorological forecast field data, terrain and land use data and emission source lists, the historical meteorological and pollution source data include the corresponding observation values ​​of the target monitoring elements at each collection time within the preset historical time period, the multiple sets of meteorological forecast field data include 1 set of global meteorological forecast field data corresponding to the European Center for Medium-Term Weather Forecasts Integrated Forecast System during the prediction period, 1 set of global meteorological forecast field data corresponding to the GFS of the National Environmental Prediction Center NECP of the United States, and 16 sets of global meteorological forecast field data corresponding to the Global Ensemble Forecast System of the China Meteorological Administration, and the target monitoring elements include preset meteorological field elements and preset pollutant concentration distribution elements;

[0123] A creation module 810 is used to create an initial meteorological-chemical coupling online model according to multiple sets of meteorological forecast field data, land and terrain data, and emission source lists, wherein the initial meteorological-chemical coupling online model includes multiple physical parameterization scheme combinations, each physical parameterization scheme combination includes multiple different physical parameterization schemes, and different physical parameterization schemes reflect different meteorological physical processes;

[0124] The improvement module 820 is used to improve the photochemical parameter scheme FAST-J in the initial meteorological-chemical coupled online model using multiple optical parameters corresponding to the aerosol, so as to obtain an optimized meteorological-chemical coupled online model;

[0125] A scheme selection module 830 is used to select the best integral scheme for the optimized meteorological-chemical coupled online model, so as to select the best physical parameterization scheme combination from multiple physical parameterization scheme combinations;

[0126] An application module 840 is used to apply the optimal physical parameterization scheme combination to the initial meteorological-chemical coupled online model to obtain a target meteorological-chemical coupled online model;

[0127] A determination module 850 is used to determine the target meteorological-chemical coupled online model as a wind-solar energy prediction model;

[0128] The prediction module 860 is used to use multiple sets of meteorological forecast field data, terrain and land use data and emission source lists, use wind and solar energy prediction models to make ensemble forecasts of wind and solar meteorological fields and pollutants, and optimize the forecast results to determine the wind and solar energy prediction results at each moment in the target prediction time period.

[0129] Based on the same application idea, please refer to Figure 4 , Figure 4 FIG. 1 is a schematic diagram showing the structure of an electronic device provided by an embodiment of the present application. Figure 4 As shown, the electronic device 900 includes: a processor 910, a memory 920 and a bus 930. The memory 920 stores machine-readable instructions executable by the processor 910. When the electronic device 900 is running, the processor 910 and the memory 920 communicate through the bus 930. The machine-readable instructions are executed by the processor 910 when it is running, such as the steps of the wind and solar energy prediction method provided in any of the above embodiments.

[0130] Based on the same application concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the wind and solar energy prediction method provided in the above embodiment are executed.

[0131] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0134] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0135] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A wind and solar energy prediction method, characterized in that: The method comprises: Collect historical meteorological and pollution source data generated in the target area within a preset historical time period before the forecast start time, multiple sets of global meteorological forecast field data, terrain and land use data and emission source lists, the historical meteorological and pollution source data include the observation values ​​corresponding to the target monitoring elements at each collection time within the preset historical time period, the multiple sets of meteorological forecast field data include 1 set of global meteorological forecast field data corresponding to the European Center for Medium-Term Weather Forecasts Integrated Forecast System during the forecast period, 1 set of global meteorological forecast field data corresponding to the GFS of the National Environmental Prediction Center NECP of the United States, and 16 sets of global meteorological forecast field data corresponding to the Global Ensemble Forecast System of the China Meteorological Administration, the target monitoring elements include preset meteorological field elements and preset pollutant concentration distribution elements; Creating an initial meteorological-chemical coupling online model according to the multiple sets of meteorological forecast field data, the land and terrain data and the emission source list, wherein the initial meteorological-chemical coupling online model includes a plurality of physical parameterization scheme combinations, each physical parameterization scheme combination includes a plurality of different physical parameterization schemes, and different physical parameterization schemes reflect different meteorological physical processes; Using multiple optical parameters corresponding to aerosols, the photochemical parameter scheme FAST-J in the initial meteorological-chemical coupled online model is improved to obtain an optimized meteorological-chemical coupled online model; Performing single integral perturbation on multiple physical parameterization schemes in the optimized meteorological-chemical coupled online model to select an optimal physical parameterization scheme combination from the multiple physical parameterization scheme combinations; Applying the optimal physical parameterization scheme combination to the initial meteorological-chemical coupled online model to obtain a target meteorological-chemical coupled online model; Determine the target meteorological-chemical coupling online model as a wind-solar energy prediction model; Utilizing multiple sets of meteorological forecast field data, the terrain and land use data and the emission source list, using the wind and solar energy forecast model to perform wind and solar meteorological field and pollutant ensemble forecasts, and optimizing the forecast results to determine the wind and solar energy forecast results at each moment within the target forecast time period; The initial meteorological-chemical coupled online model also includes a plurality of chemical parameterization schemes, and different chemical parameterization schemes reflect different meteorological-chemical processes. The plurality of chemical parameterization schemes include a photochemical parameter scheme FAST-J, Among them, the optimized meteorological-chemical coupling online model is obtained by the following methods: Calculating multiple target optical parameters corresponding to the aerosol using Mie scattering theory, wherein the target optical parameters are optical parameters that affect the calculation of the photolysis rate; The plurality of target optical parameters are transferred to the photolysis rate calculation module in the photochemical parameter scheme FAST-J to obtain an optimized meteorological-chemical coupled online model; The initial meteorological-chemical coupled online model includes initial meteorological conditions, boundary meteorological conditions and emission source distribution corresponding to each set of meteorological forecast field data, and the multiple chemical parameterization schemes also include a gas phase chemistry scheme CBM-Z and an aerosol chemistry scheme MOSAIC. Among them, the optimal physical parameterization scheme combination is determined by the following methods: In the optimized meteorological-chemical coupling online mode, the following processing is performed: Enable the initial meteorological conditions, boundary meteorological conditions and emission source distribution corresponding to the target meteorological forecast field data; The gas phase chemistry scheme CBM-Z, the aerosol chemistry scheme MOSAIC and the photochemical parameter scheme FAST-J were selected, and the aerosol radiation direct feedback mechanism switch was turned on; For the multiple physical parameterization scheme combinations, single perturbation integration experiments are respectively performed to obtain a single perturbation integration result corresponding to each physical parameterization scheme combination, wherein the single perturbation integration result includes first prediction data within a preset historical time period corresponding to the target area, and the first prediction data includes a simulation value corresponding to the target monitoring element at each collection time within the preset historical time period; Based on the historical meteorological and pollution source data and the first prediction data, respectively evaluate and analyze the single disturbance integral results corresponding to each physical parameterization scheme combination to obtain the evaluation and analysis results corresponding to each physical parameterization scheme combination; According to the evaluation and analysis results corresponding to each physical parameterization scheme combination, the optimal physical parameterization scheme combination is determined.

2. The method according to claim 1, characterized in that According to the evaluation and analysis results corresponding to each physical parameterization scheme combination, the steps of determining the optimal physical parameterization scheme combination include: For the single perturbation integration results corresponding to each physical parameterization scheme combination, the following processing is performed: According to the observed value and simulated value corresponding to each acquisition moment of the target monitoring element indicated by the single disturbance integral result in the preset historical time period, the correlation coefficient, standard mean deviation and standard mean error corresponding to the physical parameterization scheme combination are calculated; If the correlation coefficient is greater than the first threshold, the second threshold is less than or equal to the standard mean deviation and the third threshold is less than or equal to the standard mean error, the physical parameterization scheme combination is determined as a candidate physical parameterization scheme combination; From multiple candidate physical parameterization scheme combinations, the optimal physical parameterization scheme combination is comprehensively selected according to the preset selection strategy.

3. The method according to claim 2, characterized in that The correlation coefficient is determined by the following formula: In this formula, represents the correlation coefficient, N represents the number of observations or simulations corresponding to the target monitoring element collected within the preset historical time period, represents the simulated value of the target monitoring element, represents the observed value of the target monitoring element, It represents the average value of N simulation values ​​corresponding to the target monitoring element. Represents the average value among the N observation values ​​corresponding to the target monitoring element; The standard mean deviation is determined by the following formula : ; The standard mean error is determined by the following formula : 。 4. The method according to claim 1, characterized in that: The wind and solar energy forecast results at each moment in the target forecast period are determined by the following methods: Input the multiple groups of meteorological forecast field data, the terrain and land use data and the emission source list into the wind and solar energy forecast model, and use the optimal physical parameterization scheme combination to perform integral calculation to determine the second forecast data corresponding to each group of meteorological forecast field data, the second forecast data including the simulation value corresponding to the target monitoring element at each collection time within the forecast time period; Determine the optimal simulation value corresponding to each target monitoring element at each collection time within the forecast time period according to the second prediction data corresponding to each set of meteorological forecast field data and the preset regression equation, wherein the preset regression equation describes the mapping relationship between multiple simulation values ​​of the target monitoring element at each collection time and the optimal simulation value; The optimal simulation value corresponding to the target meteorological element at each collection moment within the forecast time period is used to determine the corresponding wind and solar energy forecast results at each moment within the forecast time period.

5. The method according to claim 4, characterized in that The preset regression equation is: in, Indicates the number of The optimal simulation value corresponding to the target monitoring element at each collection time, Indicates The weighted regression coefficient corresponding to the group of meteorological forecast field data, Indicated in In the group of meteorological forecast field data, the simulated value of the target monitoring element at the nth collection time from the start time of the forecast, and b represents the regression constant.

6. The method according to claim 1, characterized in that The wind and solar energy forecast results include photovoltaic power generation potential, photovoltaic module working efficiency, photovoltaic module actual temperature and wind power density, and meteorological elements include downward shortwave radiation and wind speed at 100 meters. The corresponding wind and solar energy forecast results at each moment in the forecast period are determined by the following formula: in, Represents the photovoltaic power generation potential, Indicates the working efficiency of photovoltaic modules. Represents the shortwave flux of photovoltaic modules under standard conditions, Indicates downward shortwave radiation and wind speed at 100 meters, The actual temperature of the PV panels, Represents the test temperature of PV modules under standard conditions; Indicates the ambient temperature, Indicates the wind speed at 100 meters. represents the wind power density, represents the number of target monitoring elements collected during the forecast period, Vm represents the simulated value of the wind speed at the mth 100-meter point during the forecast period, Indicates the air density.

7. A wind and solar energy prediction device, characterized in that: The device comprises: A data collection module is used to collect historical meteorological and pollution source data generated in the target area within a preset historical time period before the prediction start time, multiple sets of global meteorological forecast field data, terrain and land use data and emission source lists, wherein the historical meteorological and pollution source data include the observation values ​​corresponding to the target monitoring elements at each collection time within the preset historical time period, the multiple sets of meteorological forecast field data include 1 set of global meteorological forecast field data corresponding to the European Center for Medium-Term Weather Forecasts Integrated Forecast System during the prediction period, 1 set of global meteorological forecast field data corresponding to the GFS of the National Environmental Prediction Center NECP of the United States, and 16 sets of global meteorological forecast field data corresponding to the China Meteorological Administration Global Ensemble Forecast System, and the target monitoring elements include preset meteorological field elements and preset pollutant concentration distribution elements; A creation module, used to create an initial meteorological-chemical coupling online model according to the multiple groups of meteorological forecast field data, the land and terrain data and the emission source list, wherein the initial meteorological-chemical coupling online model includes a plurality of physical parameterization scheme combinations, each physical parameterization scheme combination includes a plurality of different physical parameterization schemes, and different physical parameterization schemes reflect different meteorological physical processes; A perfecting module is used to improve the photochemical parameter scheme FAST-J in the initial meteorological-chemical coupled online model by using a plurality of optical parameters corresponding to aerosols, so as to obtain an optimized meteorological-chemical coupled online model; A scheme selection module is used to perform single integral perturbation on multiple physical parameterization schemes in the optimized meteorological-chemical coupled online mode to select an optimal physical parameterization scheme combination from multiple physical parameterization scheme combinations; An application module, for applying the optimal physical parameterization scheme combination to the initial meteorological-chemical coupled online model to obtain a target meteorological-chemical coupled online model; A determination module, used to determine the target meteorological-chemical coupling online model as a wind-solar energy prediction model; A prediction module, for using multiple sets of meteorological forecast field data, the terrain and land use data and the emission source list, using the wind and solar energy forecast model to perform wind and solar meteorological field and pollutant ensemble forecasts, and performing optimal selection of forecast results to determine the wind and solar energy forecast results at each moment within the target forecast time period; The initial meteorological-chemical coupled online model also includes a plurality of chemical parameterization schemes, and different chemical parameterization schemes reflect different meteorological-chemical processes. The plurality of chemical parameterization schemes include a photochemical parameter scheme FAST-J, The improvement module is further used to: calculate multiple target optical parameters corresponding to the aerosol using Mie scattering theory, wherein the target optical parameters are optical parameters that affect the calculation of the photolysis rate; The plurality of target optical parameters are transferred to the photolysis rate calculation module in the photochemical parameter scheme FAST-J to obtain an optimized meteorological-chemical coupled online model; The scheme selection module is also used to perform the following processing in the optimized meteorological-chemical coupling online mode: Enable the initial meteorological conditions, boundary meteorological conditions and emission source distribution corresponding to the target meteorological forecast field data; The gas phase chemistry scheme CBM-Z, the aerosol chemistry scheme MOSAIC and the photochemical parameter scheme FAST-J were selected, and the aerosol radiation direct feedback mechanism switch was turned on; For the multiple physical parameterization scheme combinations, single perturbation integration experiments are respectively performed to obtain a single perturbation integration result corresponding to each physical parameterization scheme combination, wherein the single perturbation integration result includes first prediction data within a preset historical time period corresponding to the target area, and the first prediction data includes a simulation value corresponding to the target monitoring element at each collection time within the preset historical time period; Based on the historical meteorological and pollution source data and the first prediction data, respectively evaluate and analyze the single disturbance integral results corresponding to each physical parameterization scheme combination to obtain the evaluation and analysis results corresponding to each physical parameterization scheme combination; According to the evaluation and analysis results corresponding to each physical parameterization scheme combination, the optimal physical parameterization scheme combination is determined.

8. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the wind and solar energy prediction method as described in any one of claims 1 to 6.