Solar irradiance prediction method, device, equipment, medium and product

Abstract

The invention provides a solar irradiance prediction method and device, equipment, a medium and a product. The method comprises the following steps: acquiring historical data in a freezing and thawing process of a high-altitude area within a preset time period; wherein the historical data comprises cloud cover, soil temperature, soil humidity, soil type and solar irradiance; preprocessing the historical data to obtain preprocessed historical data; training an initial model by using the preprocessed historical data to obtain a solar irradiance prediction model; and obtaining new data, performing solar irradiance prediction on the new data by using the solar irradiance prediction model, and generating a visual prediction result. By considering the plateau land surface freezing and thawing process, land surface process memorability and earth-gas energy balance, the prediction capability of the high-altitude cross-seasonal solar irradiance is improved to a certain extent, and the prediction accuracy of the solar irradiance of the high-altitude photovoltaic field is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological forecasting, and in particular to a solar irradiance forecasting method, device, equipment, medium and product. Background Art

[0002] The freeze-thaw process is a very unique climate phenomenon at high altitudes, in which soil moisture and soil temperature play an important role in the land-atmosphere water cycle and heat exchange. It has a memory effect of more than half a year, which can continue the abnormal conditions of soil water and heat in the previous period, and have an important impact on long-term weather forecasts through land-air feedback. Soil moisture can affect surface solar radiation through evaporation and energy regulation. On the one hand, soil moisture transports water vapor to the atmosphere, affects local cloud cover by regulating water vapor, and then affects solar radiation. On the other hand, soil moisture / temperature can also regulate the ground-air energy exchange to affect the atmospheric thermal conditions. Excessive soil moisture will cause the atmospheric temperature to drop, further increase the relative humidity and promote the formation of cloud cover. Therefore, the soil temperature / humidity that characterizes the freeze-thaw process can regulate the subsequent water and energy exchange between the land surface and the atmosphere through its "memory" characteristics, and is the source of predictability for predicting high-altitude surface solar irradiance.

[0003] At present, traditional prediction methods mainly consider precursor signals such as sea temperature and sea ice to predict solar irradiance. However, due to the complex weather at high altitudes, the timeliness and accuracy of solar irradiance prediction are not high. Therefore, an effective solar irradiance prediction method is urgently needed to solve the above problems. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide a solar irradiance prediction method, device, equipment, medium and product that overcome the above problems or at least partially solve the above problems.

[0005] To achieve the above object and other related objects, the present invention provides a solar irradiance prediction method, the method comprising:

[0006] Collect historical data of freeze-thaw process in high altitude areas within a preset time period; wherein the historical data includes cloud cover, soil temperature, soil moisture, soil type and solar irradiance;

[0007] Preprocessing the historical data to obtain preprocessed historical data;

[0008] Using the preprocessed historical data, the pre-built initial model is trained to obtain a solar irradiance prediction model;

[0009] New data is acquired, and the solar irradiance prediction model is used to predict the solar irradiance of the new data, so as to generate a visual prediction result.

[0010] Optionally, preprocessing the historical data to obtain preprocessed historical data includes:

[0011] Eliminate duplicate and erroneous record data in the historical data to obtain cleaned historical data, and fill in missing values ​​in the cleaned historical data to obtain filled historical data;

[0012] Performing smoothing filtering on the padded historical data to obtain filtered historical data, and removing abnormal values ​​in the filtered historical data to obtain historical data to be processed;

[0013] The historical data to be processed is standardized to obtain pre-processed historical data.

[0014] Optionally, the using the pre-processed historical data to train the initial model to obtain a solar irradiance prediction model includes:

[0015] Obtaining a calculation equation for soil enthalpy, and calculating the soil enthalpy value using the preprocessed historical data and the calculation equation;

[0016] According to the soil enthalpy value, calculating the lead-lag correlation coefficient of the soil enthalpy value;

[0017] Extracting the solar irradiance from the preprocessed historical data, and constructing a time series data set using the soil enthalpy value, the lead-lag correlation coefficient, and the solar irradiance;

[0018] Dividing the time series data set into a training set and a test set, and using the training set to train the initial model to obtain an initial solar irradiance prediction model;

[0019] The initial solar irradiance prediction model is evaluated using the test set to obtain an evaluation result, and the physical parameters of the initial solar irradiance prediction model are adjusted according to the evaluation result to obtain a solar irradiance prediction model.

[0020] Optionally, the calculating soil enthalpy using the pre-processed historical data and the calculation equation includes:

[0021] Extracting soil moisture and soil temperature from the pre-processed historical data; wherein the soil moisture includes solid water content, liquid water content and soil dry matter content;

[0022] The soil enthalpy is calculated according to the solid water content, the liquid water content, the soil dry matter content, the soil temperature and the calculation equation.

[0023] Optionally, after the step of constructing a time series data set using the soil enthalpy value, the lead-lag correlation coefficient and the solar irradiance, the method further includes:

[0024] Using the soil enthalpy value and the lead-lag correlation coefficient, a soil enthalpy value persistence model is constructed to verify the persistence of the soil enthalpy value in a time series through the soil enthalpy value persistence model;

[0025] When determining that the persistence of the soil enthalpy value is effective, the correlation between the soil enthalpy value and the solar irradiance is analyzed to determine that there is a significant correlation between the soil enthalpy value and the solar irradiance.

[0026] Optionally, the using the solar irradiance prediction model to perform solar irradiance prediction on the new data to generate a visualized prediction result includes:

[0027] Preprocessing the new data to obtain preprocessed new data; wherein the new data includes cloud cover, soil temperature, soil moisture and soil type;

[0028] The new data is input into the solar irradiance prediction model to perform solar irradiance prediction, and the prediction results are visualized to obtain visualized prediction results.

[0029] In a second aspect, the present invention further provides a solar irradiance prediction device, the device comprising:

[0030] A collection module, used to collect historical data of freeze-thaw process in high altitude areas within a preset time period; wherein the historical data includes cloud cover, soil temperature, soil moisture, soil type and solar irradiance;

[0031] A preprocessing module, used for preprocessing the historical data to obtain preprocessed historical data;

[0032] A training module, used to train the initial model using the preprocessed historical data to obtain a solar irradiance prediction model;

[0033] The prediction module is used to obtain new data, use the solar irradiance prediction model to predict the solar irradiance of the new data, and generate a visual prediction result.

[0034] In a third aspect, the present invention provides an electronic device, comprising: a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory, so that the electronic device performs the steps of the solar irradiance prediction method as described above.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the steps of the solar irradiance prediction method as described above.

[0036] In a fifth aspect, the present invention provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer implements the steps of the solar irradiance prediction method as described above.

[0037] The above one or more technical solutions provided by the present invention may have the following advantages or at least achieve the following technical effects:

[0038] The solar irradiance prediction method, system, equipment, medium and product of the present invention include: collecting historical data of freeze-thaw process in high altitude areas within a preset time period; wherein the historical data include cloud cover, soil temperature, soil moisture, soil type and solar irradiance; preprocessing the historical data to obtain preprocessed historical data; using the preprocessed historical data to train a pre-built initial model to obtain a solar irradiance prediction model; acquiring new data, and using the solar irradiance prediction model to predict the solar irradiance of the new data to generate a visualized prediction result.

[0039] Therefore, the present invention improves the prediction capability of high-altitude cross-seasonal solar irradiance to a certain extent by considering the plateau land surface freeze-thaw process, land surface process memory and ground-atmosphere energy balance, and enhances the prediction accuracy of solar irradiance of high-altitude photovoltaic fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 Shown is a schematic flow chart of a solar irradiance prediction method according to an embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram showing the lead-lag correlation coefficients of the soil enthalpy in winter and the soil enthalpy at different soil depths in the following spring (March-May) and summer (June-July) in one embodiment of the present invention;

[0042] Figure 3 It shows a schematic diagram of the lead-lag correlation coefficients of winter soil enthalpy and subsequent summer surface solar radiation in one embodiment of the present invention;

[0043] Figure 4 Shown is a schematic diagram of the functional modules of a solar irradiance prediction device according to an embodiment of the present invention;

[0044] Figure 5 Shown is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0046] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0047] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0048] The terms "first", "second", etc. in the specification and claims of the disclosed embodiments and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the disclosed embodiments described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0049] Unless otherwise stated, the term "plurality" means two or more.

[0050] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0051] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0052] For ease of understanding, the following first explains the relevant nouns or terms used in the embodiments of the present invention:

[0053] <1> Solar irradiance refers to the solar radiation flux per unit area. It represents the amount of radiation energy received per unit area per unit time on the surface irradiated by the radiation energy, that is, the radiation flux density on the irradiated surface. Its unit is watt per square meter (W / m 2 ).

[0054] <2> , soil enthalpy (SE) refers to the heat stored or released by soil per unit volume during temperature changes; it can be expressed as the total enthalpy of soil particles, soil liquid water and soil air, reflecting the changes in land surface water and thermal energy.

[0055] Soil enthalpy is related to factors such as soil temperature, soil specific heat capacity, soil water content and soil density, and can be calculated by soil temperature change and soil specific heat capacity.

[0056] <3> , the lead-lag correlation coefficient of soil enthalpy, which is used to analyze the correlation between soil enthalpy values ​​and themselves at different time lags. In time series analysis, the lead-lag correlation coefficient (r) is used to identify periodicity and trends in time series.

[0057] Among them, positive correlation: If the correlation coefficient is positive, it means that the soil enthalpy has a similar change trend when it is lagging or leading.

[0058] Negative correlation: If the correlation coefficient is negative, it indicates that the soil enthalpy values ​​show opposite trends when lagging or leading.

[0059] <4> Confidence Level is a concept in statistics that indicates the degree of confidence in the results of statistical inference. When constructing a confidence interval or conducting a hypothesis test, the confidence level is an important parameter that indicates how confident we are that the true value of the parameter is within a certain interval, or how confident we are in rejecting the null hypothesis.

[0060] A 95% confidence level means that if you draw samples repeatedly from the same population and construct confidence intervals, there is a 95% probability that those confidence intervals will contain the true value of the population parameter.

[0061] The technical solutions in the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0062] See also Figure 1 An embodiment of the present invention provides a solar irradiance prediction method, which may include the following steps S10 to S40:

[0063] Step S10, collecting historical data of freeze-thaw processes in high altitude areas within a preset time period; wherein the historical data includes cloud cover, soil temperature, soil moisture, soil type, and solar irradiance.

[0064] Among them, the preset time period can be set by the user according to research needs.

[0065] In this embodiment, the preset time period is from 1979 to 2014, and a systematic study is conducted on the possible climate effects caused by soil enthalpy (SE) anomalies during the freeze-thaw process on the Qinghai-Tibet Plateau: ① Explore the thermal impact of winter soil enthalpy (SE) on the Qinghai-Tibet Plateau on the subsequent seasons and its incentive research; ② The role of soil enthalpy (SE) in the connection between climate anomalies.

[0066] Historical data refers to meteorological observation data and soil type data recorded in chronological order; it includes but is not limited to: cloud cover, soil temperature, soil moisture, soil type and solar irradiance.

[0067] As an example, historical data may be meteorological observation data and soil type data collected during the freeze-thaw process of the Qinghai-Tibet Plateau from 1979 to 2014, such as cloud cover, soil temperature, soil moisture, soil type, and solar irradiance.

[0068] In a specific implementation, historical data of freeze-thaw processes in high altitude areas within a preset time period are collected; the historical data may include cloud cover, soil temperature, soil moisture, soil type, and solar irradiance.

[0069] Step S20, preprocessing the historical data to obtain preprocessed historical data.

[0070] The preprocessed historical data refers to data obtained after preprocessing the historical data, wherein the preprocessing includes but is not limited to filling missing values ​​and / or abnormal values ​​in the historical data, and performing normalization or standardization.

[0071] In a specific implementation, historical data may contain missing values ​​and outliers, and the historical data can be processed by filling and / or interpolation. It may also be necessary to normalize or standardize the historical data to obtain preprocessed historical data to improve the efficiency and effectiveness of model training.

[0072] Step S30, using the preprocessed historical data to train the pre-built initial model to obtain a solar irradiance prediction model.

[0073] The initial model may be a pre-built machine learning model, which may select a suitable algorithm, such as a linear regression, a decision tree, or a LTSM (long short-term memory network) to build the initial model.

[0074] In the specific implementation, the soil enthalpy value can be calculated using the preprocessed historical data, and the lead-lag correlation coefficient of the soil enthalpy value at different times can be calculated; before training the model, the soil enthalpy value and the lead-lag correlation coefficient need to be used to verify the seasonal changes in the soil enthalpy value in the time series, and to verify whether there is a significant correlation between the soil enthalpy value and the solar irradiance; and after determining the persistence of the soil enthalpy value and the significant correlation between the soil enthalpy and the solar irradiance, the soil enthalpy value and the lead-lag correlation coefficient can be used to train the pre-constructed initial model to obtain a solar irradiance prediction model.

[0075] Step S40, acquiring new data, and using the solar irradiance prediction model to perform solar irradiance prediction on the new data, to generate a visualized prediction result.

[0076] The new data may be meteorological observation data of the solar irradiance to be predicted and soil type data, etc., which may include but are not limited to: cloud cover, soil temperature, soil moisture and soil type.

[0077] The visual prediction results can be used to graphically display the prediction results of the solar irradiance prediction model; it can also be used to show the relationship between the actual value and the predicted value.

[0078] In the specific implementation, first, new data is obtained; the new data may contain missing values ​​and outliers, and the new data can be processed by filling and / or interpolation, and the new data can be normalized or standardized; then the preprocessed new data can be input into the solar irradiance prediction model to predict the solar irradiance and generate a visual prediction result.

[0079] In this embodiment, historical data of the freeze-thaw process in high-altitude areas within a preset time period are collected; wherein the historical data include cloud cover, soil temperature, soil moisture, soil type, and solar irradiance; the historical data are preprocessed to obtain preprocessed historical data; the pre-constructed initial model is trained using the preprocessed historical data to obtain a solar irradiance prediction model; new data are acquired, and the solar irradiance prediction model is used to predict the solar irradiance of the new data to generate a visualized prediction result. The present invention improves the prediction capability of high-altitude cross-seasonal solar irradiance to a certain extent by considering the plateau land surface freeze-thaw process, land surface process memory, and ground-atmosphere energy balance, thereby enhancing the prediction accuracy of solar irradiance of high-altitude photovoltaic fields.

[0080] Based on the above embodiments, a second embodiment of the solar irradiance prediction method of the present invention is proposed. In this embodiment, step S20 may include the following sub-steps S201 to S203:

[0081] Sub-step S201, removes duplicate and erroneous record data in the historical data to obtain cleaned historical data, and fills in missing values ​​in the cleaned historical data to obtain filled historical data.

[0082] The cleaned historical data may be data obtained after removing duplicate and erroneous record data in the historical data.

[0083] The filled historical data may be data obtained by filling missing values ​​in the cleaned historical data.

[0084] In a specific implementation, duplicate and erroneous record data in the historical data can be eliminated to obtain cleaned historical data; then the missing values ​​in the cleaned historical data can be filled by using the mean or linear interpolation method to obtain filled historical data.

[0085] Sub-step S202, performing smoothing filtering on the padded historical data to obtain filtered historical data, and removing abnormal values ​​in the filtered historical data to obtain historical data to be processed.

[0086] The filtered historical data may be data obtained by performing smoothing filtering on the padded historical data.

[0087] The historical data to be processed may be data obtained after removing abnormal values ​​from the filtered historical data.

[0088] In a specific implementation, the padded historical data can be smoothed and filtered (e.g., averaging or Gaussian filtering) to eliminate noise in the data and obtain filtered historical data; then, the standard score method (Z-Score) or box plot method can be used to remove outliers in the filtered historical data to obtain the historical data to be processed, which can improve data quality and ensure the accuracy of model training.

[0089] Sub-step S203, performing standardization processing on the historical data to be processed to obtain pre-processed historical data.

[0090] In a specific implementation, the historical data to be processed can be standardized to obtain preprocessed historical data; through standardization, the efficiency and performance of model training can be improved.

[0091] In this embodiment, the historical data after cleaning is obtained by eliminating duplicate and erroneous record data in the historical data, and the missing values ​​in the historical data after cleaning are filled to obtain the filled historical data; the filled historical data is smoothed and filtered to obtain the filtered historical data, and the abnormal values ​​in the filtered historical data are removed to obtain the historical data to be processed; the historical data to be processed is standardized to obtain the pre-processed historical data. Thus, by pre-processing the historical data, the efficiency and performance of the model training can be improved.

[0092] Based on the above embodiments, a third embodiment of the solar irradiance prediction method of the present invention is proposed. In this embodiment, step S30 may include the following sub-steps S301 to S305:

[0093] Sub-step S301, obtaining a calculation equation for soil enthalpy, and calculating the soil enthalpy value using the pre-processed historical data and the calculation equation.

[0094] Among them, the calculation equation of soil enthalpy (SE) can be expressed as:

[0095] SE=(c i λ i +c l λ l +c d λ d )(TT f )-L i,l ρ i λ i (1)

[0096] The subscripts i, l, and d represent soil solid water, liquid water, and soil dry matter, respectively; c is the volume heat capacity (in J·m -3 ·K -1 ); λ is volume percentage (unit: m 3 ·m -3 ); T is soil temperature (unit K); T f is the freezing point temperature (in K, usually 273.16); L i,l is the melting latent heat of solid water in soil (unit: J·kg -1 , usually takes the value of 3.337×10 5 );ρ i is the latent heat of soil solid water density (in kg·m -3 , usually taken as 917); the volumetric hot melt of solid water in soil c i The value is usually 1.942×10 6 ; Volumetric heat of liquid water in soil c l The value is usually 4.188×106 ; The volumetric melt of soil dry matter is calculated from the soil organic matter density, sand and clay percentages.

[0097] In a specific implementation, a calculation equation for soil enthalpy can be obtained; and then the soil enthalpy value can be calculated using the calculation equation and preprocessed historical data.

[0098] Sub-step S302: calculating the lead-lag correlation coefficient of the soil enthalpy value according to the soil enthalpy value.

[0099] Among them, the lead-lag correlation coefficient (r) reflects the time delay effect of soil temperature and humidity changes on atmospheric heat and water vapor transport. This coefficient can quantify the impact of soil enthalpy on atmospheric processes at different time scales, thereby predicting cloud changes and solar irradiance.

[0100] The high lead-lag correlation coefficient indicates that the change of soil enthalpy has a significant predictive effect on solar irradiance. By calculating and analyzing this coefficient, the accuracy of the solar irradiance prediction model can be improved. Combining the soil enthalpy lead-lag correlation coefficient with other meteorological data can more comprehensively understand and predict the dynamic changes of solar irradiance.

[0101] To calculate the lead-lag correlation coefficient (r) of soil enthalpy, the formula can be used:

[0102]

[0103] Where n is the number of samples; X i and Y i represents the i-th value of the leading and lagging elements respectively; X and Y represent the means of the leading and lagging elements respectively.

[0104] When the lead-lag correlation coefficient (r) approaches 1, there is a complete positive correlation, and there is a complete positive linear relationship between the lead and lag elements, indicating good memory;

[0105] When the lead-lag correlation coefficient (r) approaches -1, there is a complete negative correlation, and there is a completely negative linear relationship between the lead and lag elements, indicating that the memory is broken by other signals;

[0106] When the lead-lag correlation coefficient (r) approaches 0, there is no correlation and no linear relationship between the two variables, indicating no memory.

[0107] It should be noted that, in this embodiment, by calculating the lead-lag correlation coefficient between winter soil enthalpy and lagging month soil enthalpy, the value range is (-1,1), and the correlation coefficient passes the 95% significance test, indicating that the lagging month soil enthalpy has the ability to remember the winter soil enthalpy.

[0108] In the specific implementation, the soil enthalpy value can be used to calculate the lead-lag correlation coefficient of the soil enthalpy value; then the lead-lag correlation coefficient can be used to verify the persistence of the soil enthalpy value in the time series, which can be used as a verification step in the model construction process to ensure the reliability of the model.

[0109] Sub-step S303, extracting the solar irradiance from the pre-processed historical data, and constructing a time series data set using the soil enthalpy value, the lead-lag correlation coefficient and the solar irradiance.

[0110] The time series data set may be a data set that records soil enthalpy, lead-lag correlation coefficient, and solar irradiance in chronological order.

[0111] In the specific implementation, solar irradiance is extracted from the preprocessed historical data, and the soil enthalpy, lead-lag correlation coefficient and solar irradiance are recorded in chronological order to construct a time series dataset.

[0112] Sub-step S304, dividing the time series data set into a training set and a test set, and using the training set to train the initial model to obtain an initial solar irradiance prediction model.

[0113] In the specific implementation, the time series data set can be divided into a training set and a test set in a certain ratio; then the soil enthalpy value and lead-lag correlation coefficient in the training set are used as the input of the initial model, and the solar irradiance in the training set is used as the output of the initial model. The initial model is iteratively trained, and the model parameters (such as accuracy) are optimized by cross-validation. The training is stopped when the accuracy of the initial model reaches a stable level after iterative training, and the initial solar irradiance prediction model is obtained.

[0114] As an example, the ratio of the training set to the test set may be 7:3 (8:2 or 9:1).

[0115] Sub-step S305, using the test set to evaluate the initial solar irradiance prediction model to obtain an evaluation result, and adjusting the physical parameters of the initial solar irradiance prediction model according to the evaluation result to obtain a solar irradiance prediction model.

[0116] The evaluation results can be evaluation indicators for evaluating the prediction performance of the initial solar irradiance prediction model using the test set, which may include but are not limited to: root mean square error (RESE), mean absolute error (MAE), determination coefficient (R 2 ) and explained variance (EVS) and other evaluation indicators.

[0117] In the specific implementation, the test set can be used to evaluate the initial solar irradiance prediction model to obtain the evaluation results; then the evaluation results can be used to adjust the physical parameters in the initial solar irradiance prediction model (such as state quantity, land surface depth and other parameters), and finally a solar irradiance prediction model that can effectively predict solar irradiance is obtained.

[0118] Further, in one embodiment, sub-step S301 may include the following sub-steps A10 to A20:

[0119] Sub-step A10, extracting soil moisture, soil temperature and soil type from the pre-processed historical data; wherein the soil moisture includes solid water content, liquid water content and soil dry matter content;

[0120] Sub-step A20, calculating soil enthalpy according to the soil type, the solid water content, the liquid water content, the soil dry matter content, the soil temperature and the calculation equation.

[0121] Soil moisture may include solid water content, liquid water content and soil dry matter content.

[0122] In a specific implementation, soil moisture, soil temperature and soil type can be extracted from the preprocessed historical data; wherein soil moisture includes solid water content, liquid water content and soil dry matter content; and then the soil enthalpy value is calculated according to the soil type, solid water content, liquid water content, soil dry matter content, soil temperature and the calculation equation (see formula (1) in the above sub-step S301); and then the soil enthalpy value can be used to calculate the lead-lag correlation coefficient (see formula (2) in the above sub-step S302), so as to use the lead-lag correlation coefficient to verify the persistence of the soil enthalpy value in the time series.

[0123] Furthermore, in one embodiment, after sub-step S303, the method may further include the following sub-steps S306 to S307:

[0124] Sub-step S306, constructing a soil enthalpy persistence model using the soil enthalpy value and the lead-lag correlation coefficient, so as to verify the persistence of the soil enthalpy value in the time series through the soil enthalpy persistence model;

[0125] Sub-step S307, when determining that the persistence of the soil enthalpy value is valid, analyzing the correlation between the soil enthalpy value and the solar irradiance to determine that there is a significant correlation between the soil enthalpy value and the solar irradiance.

[0126] Among them, the soil enthalpy persistence model is a time series model that can be used to verify the persistence characteristics of soil enthalpy in time series. Generally, the better the persistence, the longer the time scale of land surface thermal anomaly maintenance, and thus the greater the impact on solar radiation.

[0127] It should be noted that soil enthalpy has a certain memory, which is particularly evident during the freeze-thaw process. During the freezing period (winter), when the soil is frozen, heat is stored in the soil; during the thawing period (summer), heat is released through water heat exchange, affecting the temperature and humidity of the surrounding atmosphere. This heat exchange process will cause changes in atmospheric clouds, which will further affect the distribution and intensity of solar radiation. This dynamic change characteristic of soil enthalpy makes it play an important role in meteorological models, which can help predict and analyze the temporal and spatial changes of solar radiation and provide support for precise climate and energy management.

[0128] In the specific implementation, the soil enthalpy value and the lead-lag correlation coefficient can be used to construct a soil enthalpy value persistence model to verify the persistence of soil enthalpy value in the time series through the soil enthalpy value persistence model; and then when determining that the persistence of soil enthalpy value is valid, it is possible to analyze whether there is a correlation between soil enthalpy value and solar irradiance to determine whether there is a significant correlation between soil enthalpy value and solar irradiance. Therefore, the changes in moisture and heat in the soil can be simulated by calculating soil enthalpy to simulate the influence of solar irradiance on the freeze-thaw process from winter to summer.

[0129] As an example, see Figure 2 , Figure 2 is the soil enthalpy in winter and the soil enthalpy at different soil depths in spring (March-May, see Figure 2 (a1-a4)) and summer (June-August, see Figure 2 Schematic diagram of the lead-lag correlation coefficient of (b1-b4)). Figure 2 (a1-a4, b1-b4) show the lead-lag correlation coefficient (r) of different soil depths (0-10cm, 10-40cm, 40-100cm and 100-200cm) of the same soil. Figure 2 The middle diagonal line area indicates that the lead-lag correlation coefficient passes the 95% confidence level test.

[0130] Figure 2 The correlation between the current winter soil enthalpy and the subsequent spring and summer soil enthalpy is shown in Figure 2. In spring, the winter soil enthalpy signal can still be clearly detected from the shallow to the deeper soil depths, indicating that the winter soil enthalpy has good persistence (see Figure 2 (a1-a4)). In addition, from Figure 2It can be seen from (b1-b4) that the winter soil enthalpy signal preserved in the deep soil in summer is significantly weakened compared with that in spring, which means that the abnormal soil enthalpy may be released into the atmosphere.

[0131] See also Figure 3 , Figure 3 Schematic diagram of the correlation coefficient between winter soil enthalpy and subsequent summer (June-August) surface solar radiation from 1979 to 2014. Figure 3 The middle diagonal line area indicates that the lead-lag correlation coefficient passes the 95% confidence level test.

[0132] From a seasonal perspective, it was found that the connection between the winter and summer climate of the Qinghai-Tibet Plateau is mainly affected by soil enthalpy (i.e. the combined effect of soil moisture and soil temperature). The soil enthalpy signal can persist until the following summer due to its own memory, indicating that the land surface freeze-thaw process is a key "land surface bridge" connecting the winter and summer climate anomalies of the Qinghai-Tibet Plateau.

[0133] In this embodiment, the soil enthalpy value and its lead-lag correlation coefficient are calculated by using the preprocessed historical data, so as to verify the persistence of the soil enthalpy value through the lead-lag correlation coefficient; the solar irradiance in the preprocessed historical data is extracted, and then the soil enthalpy value and its lead-lag correlation coefficient and the solar irradiance can be used to construct a time series data set; the time series data set is divided into a training set and a test set, and the initial model is trained using the training set to obtain an initial solar irradiance prediction model; the initial solar irradiance prediction model is evaluated using the test set to obtain an evaluation result, and the physical parameters of the initial solar irradiance prediction model are adjusted according to the evaluation result to obtain a solar irradiance prediction model. Thus, by using soil enthalpy to simulate the changes in moisture and heat in the soil, the influence of the freeze-thaw process on the solar irradiance can be predicted.

[0134] Based on the above embodiments, a fourth embodiment of the solar irradiance prediction method of the present invention is proposed. In this embodiment, step S40 may include the following sub-steps S401 to S402:

[0135] Sub-step S401, preprocessing the new data to obtain preprocessed new data; wherein the new data includes cloud cover, soil temperature, soil moisture and soil type.

[0136] Among them, new data can include cloud cover, soil temperature, soil moisture and soil type.

[0137] In a specific implementation, the new data may contain missing values ​​and outliers. The missing values ​​in the new data can be processed by averaging or linear interpolation. Then, the new data is smoothed by averaging or Gaussian filtering to reduce random noise, and the standard score method (Z-Score) or box plot method is used to detect and remove outliers. Finally, the data is standardized or normalized to obtain the preprocessed new data. The new data includes cloud cover, soil temperature, soil moisture and soil type.

[0138] Sub-step S402, inputting the pre-processed new data into the solar irradiance prediction model to perform solar irradiance prediction, visually displaying the prediction results, and obtaining visualized prediction results.

[0139] In a specific implementation, the preprocessed new data can be input into the solar irradiance prediction model to perform solar irradiance prediction, and the prediction results can be visualized to generate visualized prediction results.

[0140] In this embodiment, the new data is preprocessed to obtain the preprocessed new data; wherein the new data includes cloud cover, soil temperature, soil moisture and soil type; the new data is input into the solar irradiance prediction model to predict the solar irradiance, and the prediction results are visualized to obtain visualized prediction results. Therefore, the relationship between the actual value and the predicted value can be compared and analyzed through the visualized prediction results, which is also helpful to observe the performance and prediction effect of the prediction model.

[0141] Based on the same inventive concept, the fifth embodiment of the present invention also provides a solar irradiance prediction device corresponding to the solar irradiance prediction method of the previous embodiment. Since the principle of solving the problem by the device in the fifth embodiment of the present invention is similar to the solar irradiance prediction method of the previous embodiment of the present invention, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated. Figure 4 , the solar irradiance prediction device of the present invention may include:

[0142] The acquisition module 10 is used to collect historical data of the freeze-thaw process in high altitude areas within a preset time period; wherein the historical data includes cloud cover, soil temperature, soil moisture, soil type and solar irradiance;

[0143] A preprocessing module 20, used for preprocessing the historical data to obtain preprocessed historical data;

[0144] A training module 30 is used to train the initial model using the preprocessed historical data to obtain a solar irradiance prediction model;

[0145] The prediction module 40 is used to obtain new data, use the solar irradiance prediction model to perform solar irradiance prediction on the new data, and generate a visualized prediction result.

[0146] In addition, the present invention also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned solar irradiance prediction method is implemented.

[0147] Figure 5 is a schematic block diagram of an electronic device provided in an embodiment of the present application. Figure 5 As shown, the electronic device includes: at least one processor 401, a memory 402, at least one network interface 403 and a user interface 405. The various components in the electronic device are coupled together through a bus system 404. It can be understood that the bus system 404 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 404 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 5 In the specification, various buses are labeled as bus systems.

[0148] The user interface 405 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0149] It is understood that the memory 402 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable categories of memory.

[0150] The memory 402 in the embodiment of the present invention is used to store various categories of data to support the operation of the electronic device 400. Examples of these data include: any executable program for operating on the electronic device 400, such as an operating system 4021 and an application 4022; the operating system 4021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 4022 may include various applications, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The solar irradiance prediction method provided in the embodiment of the present invention may be included in the application 4022.

[0151] The method disclosed in the above embodiment of the present invention can be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 401 or the instruction in the form of software. The above processor 401 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 401 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general processor 401 can be a microprocessor or any conventional processor, etc. In combination with the steps of the method for determining the real height of a web page provided in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to perform, or it can be performed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0152] In an exemplary embodiment, the electronic device 400 may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD) to execute the aforementioned method.

[0153] In summary, the present invention improves the prediction capability of high-altitude cross-seasonal solar irradiance to a certain extent by considering the plateau land surface freeze-thaw process, land surface process memory and ground-atmosphere energy balance, and enhances the prediction accuracy of solar irradiance of high-altitude photovoltaic fields.

[0154] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A solar irradiance prediction method, characterized in that: The method comprises: Collect historical data of freeze-thaw process in high altitude areas within a preset time period; wherein the historical data includes cloud cover, soil temperature, soil moisture, soil type and solar irradiance; Preprocessing the historical data to obtain preprocessed historical data; Using the preprocessed historical data, the pre-built initial model is trained to obtain a solar irradiance prediction model; New data is acquired, and the solar irradiance prediction model is used to predict the solar irradiance of the new data, so as to generate a visual prediction result.

2. The method according to claim 1, characterized in that: The preprocessing of the historical data to obtain the preprocessed historical data includes: Eliminate duplicate and erroneous record data in the historical data to obtain cleaned historical data, and fill in missing values ​​in the cleaned historical data to obtain filled historical data; Performing smoothing filtering on the padded historical data to obtain filtered historical data, and removing abnormal values ​​in the filtered historical data to obtain historical data to be processed; The historical data to be processed is standardized to obtain pre-processed historical data.

3. The method according to claim 1, characterized in that The method of using the pre-processed historical data to train the initial model to obtain a solar irradiance prediction model includes: Obtaining a calculation equation for soil enthalpy, and calculating the soil enthalpy value using the preprocessed historical data and the calculation equation; According to the soil enthalpy value, calculating the lead-lag correlation coefficient of the soil enthalpy value; Extracting the solar irradiance from the preprocessed historical data, and constructing a time series data set using the soil enthalpy value, the lead-lag correlation coefficient, and the solar irradiance; Dividing the time series data set into a training set and a test set, and using the training set to train the initial model to obtain an initial solar irradiance prediction model; The initial solar irradiance prediction model is evaluated using the test set to obtain an evaluation result, and the physical parameters of the initial solar irradiance prediction model are adjusted according to the evaluation result to obtain a solar irradiance prediction model.

4. The method according to claim 3, characterized in that The method of calculating the soil enthalpy value by using the pre-processed historical data and the calculation equation includes: Extracting soil moisture, soil temperature and soil type from the pre-processed historical data; wherein the soil moisture includes solid water content, liquid water content and soil dry matter content; The soil enthalpy is calculated according to the soil type, the solid water content, the liquid water content, the soil dry matter content, the soil temperature and the calculation equation.

5. The method according to claim 3, characterized in that: After the step of constructing a time series data set using the soil enthalpy value, the lead-lag correlation coefficient and the solar irradiance, the method further includes: Using the soil enthalpy value and the lead-lag correlation coefficient, a soil enthalpy value persistence model is constructed to verify the persistence of the soil enthalpy value in a time series through the soil enthalpy value persistence model; When determining that the persistence of the soil enthalpy value is effective, the correlation between the soil enthalpy value and the solar irradiance is analyzed to determine that there is a significant correlation between the soil enthalpy value and the solar irradiance.

6. The method according to claim 1, characterized in that The using the solar irradiance prediction model to perform solar irradiance prediction on the new data to generate a visualized prediction result includes: Preprocessing the new data to obtain preprocessed new data; wherein the new data includes cloud cover, soil temperature, soil moisture and soil type; The preprocessed new data is input into the solar irradiance prediction model to perform solar irradiance prediction, and the prediction results are visualized to obtain visualized prediction results.

7. A solar irradiance prediction device, characterized in that: The device comprises: A collection module, used to collect historical data of freeze-thaw process in high altitude areas within a preset time period; wherein the historical data includes cloud cover, soil temperature, soil moisture, soil type and solar irradiance; A preprocessing module, used for preprocessing the historical data to obtain preprocessed historical data; A training module, used to train the initial model using the preprocessed historical data to obtain a solar irradiance prediction model; The prediction module is used to obtain new data, use the solar irradiance prediction model to predict the solar irradiance of the new data, and generate a visual prediction result.

8. An electronic device, characterized in that: The electronic device comprises: a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the steps of the method as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, and when the program is run, it is used to implement the steps of the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes computer program codes, and when the computer program codes are executed on a computer, the computer is enabled to implement the steps of the method according to any one of claims 1 to 6.

Images