Weather forecast wind element data correction method and device based on data decomposition

Abstract

The invention provides a weather forecast wind element data correction method and device based on data decomposition. According to the method, a weather forecast wind element data correction model based on data decomposition trained by the method is used for processing wind element sub-data related to the wind speed in the weather forecast wind element data of the to-be-corrected point in the future time period to obtain corrected wind speed, for example, the wind speed of the to-be-corrected point is corrected. The weather forecast wind element data correction model based on data decomposition comprises a plurality of wind element data correction sub-models, and each wind element data correction sub-model processes wind element sub-data related to wind speed in weather forecast wind element data of a to-be-corrected point location in a future time period. Then, according to the wind speed correction components which are respectively output, the corrected wind speed of the to-be-corrected point position in the future time period is obtained; therefore, the wind speed correction accuracy can be improved through the wind speed correction method and device.

Description

Technical Field

[0001] The present application relates to the field of wind energy technology, and in particular to a method and device for correcting meteorological forecast wind element data based on data decomposition. Background Art

[0002] As wind power generation technology matures, the capacity of wind turbines and the scale of grid-connected wind farms continue to expand, the proportion of wind power generation in the total power generation of the power system increases year by year, and the penetration power of wind farms continues to increase. A series of problems brought to the power system are becoming increasingly prominent, seriously threatening the normal operation of the power system. Therefore, the need for timely and accurate prediction of wind power generation has been proposed, which can significantly enhance the safety, stability, economy and controllability of the power system.

[0003] Among them, wind data is the key input for wind power prediction, and wind data is obtained based on weather forecast data. Summary of the invention

[0004] The present application shows a method and device for correcting wind element data of weather forecast based on data decomposition.

[0005] In a first aspect, the present application shows a method for training a meteorological forecast wind factor data correction model based on data decomposition, the method comprising: Acquire first wind element data of a weather forecast for a first historical time period at a sample point, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; Calculate the wind speed difference between the wind speed in the first wind element data and a preset reference wind speed error; the preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast of multiple second historical time periods of the sample point and the historical measured wind speed of each second historical time period of the sample point; the second historical time period is earlier than the first historical time period; The wind speed in the first wind element data is replaced by the calculated wind speed difference to obtain the second wind element data of the meteorological forecast for the first historical time period of the sample point; Based on the random forest algorithm, in the second wind element data, wind element sub-data related to the wind speed is determined; Obtain the historical measured wind speed of the first historical time period of the sample point; The fully adaptive noise ensemble empirical mode decomposition (CEEMDAN) algorithm is used to decompose the historical measured wind speed of the first historical time period of the sample point to obtain multiple intrinsic mode function (IMF) wind speed components and a residual component. For any one of the multiple IMF wind speed components and a residual component, using wind element sub-data related to the wind speed as sample data and the component as labeled data, training a wind element data correction sub-model corresponding to the component; At least according to the wind element data correction sub-models respectively corresponding to the various components, a meteorological forecast wind element data correction model based on data decomposition is obtained.

[0006] In a second aspect, the present application shows a method for correcting wind element data of a meteorological forecast based on data decomposition, the method comprising: Acquire first wind element data of a weather forecast for a first time period of a point to be corrected, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; Calculate the wind speed difference between the wind speed in the first wind element data and a preset reference wind speed error; the preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast for multiple second time periods of the point to be corrected and the historical measured wind speed of each second time period of the point to be corrected; the second time period is earlier than the first time period; The wind speed in the first wind element data is replaced by the calculated wind speed difference to obtain the second wind element data of the weather forecast for the first time period of the point to be corrected; Based on the random forest algorithm, in the second wind element data, wind element sub-data related to the wind speed is determined; Inputting the wind element sub-data related to the wind speed into the meteorological forecast wind element data correction model based on data decomposition, wherein the meteorological forecast wind element data correction model based on data decomposition includes a plurality of wind element data correction sub-models, each wind element data correction sub-model processes the wind element sub-data related to the wind speed respectively to obtain a respective output wind speed correction component, and then obtaining the corrected wind speed of the first time period of the point to be corrected according to the respective output wind speed correction components; Among them, the meteorological forecast wind element data correction model based on data decomposition is trained by any one of the methods described in the first aspect.

[0007] In a third aspect, the present application shows a device for training a weather forecast wind element data correction model based on data decomposition, the device comprising: A first acquisition module is used to acquire first wind element data of a meteorological forecast for a first historical time period at a sample point, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; The first calculation module is used to calculate the wind speed difference between the wind speed in the first wind element data and the preset reference wind speed error; the preset reference wind speed error includes: the first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast of multiple second historical time periods of the sample point and the historical measured wind speed of each second historical time period of the sample point; the second historical time period is earlier than the first historical time period; A first replacement module is used to replace the wind speed in the first wind element data with the calculated wind speed difference to obtain the second wind element data of the meteorological forecast for the first historical time period of the sample point; A first determination module is used to determine wind element sub-data related to wind speed in the second wind element data based on a random forest algorithm; The second acquisition module is used to obtain the historical measured wind speed of the sample point in the first historical time period; A decomposition module is used to decompose the historical measured wind speed of the first historical time period of the sample point by using a fully adaptive noise ensemble empirical mode decomposition (CEEMDAN) algorithm to obtain multiple intrinsic mode function (IMF) wind speed components and a residual component; A training module, for training a wind element data correction sub-model corresponding to any one of a plurality of IMF wind speed components and a residual component, using wind element sub-data related to the wind speed as sample data and the component as labeled data; The third acquisition module is used to obtain a meteorological forecast wind element data correction model based on data decomposition at least according to the wind element data correction sub-model corresponding to each component.

[0008] In a fourth aspect, the present application shows a device for correcting wind element data of a meteorological forecast based on data decomposition, the device comprising: a fifth acquisition module, configured to acquire first wind element data of a weather forecast for a first time period of a point to be corrected, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; The second calculation module is used to calculate the wind speed difference between the wind speed in the first wind element data and a preset reference wind speed error; the preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast for multiple second time periods of the point to be corrected and the historical measured wind speed of each second time period of the point to be corrected; the second time period is earlier than the first time period; A second replacement module is used to replace the wind speed in the first wind element data with the calculated wind speed difference to obtain the second wind element data of the weather forecast for the first time period of the point to be corrected; A second determination module is used to determine wind element sub-data related to wind speed in the second wind element data based on a random forest algorithm; A processing module, used for inputting wind element sub-data related to wind speed into a meteorological forecast wind element data correction model based on data decomposition, wherein the meteorological forecast wind element data correction model based on data decomposition includes a plurality of wind element data correction sub-models, each wind element data correction sub-model processes the wind element sub-data related to wind speed respectively to obtain a respective output wind speed correction component, and then obtains a corrected wind speed of a first time period of a point to be corrected according to the respective output wind speed correction components; Among them, the meteorological forecast wind element data correction model based on data decomposition is trained by any one of the methods described in the first aspect.

[0009] Alternatively, the weather forecast wind element data correction model based on data decomposition is obtained by training through any one of the devices described in the third aspect.

[0010] In a fifth aspect, the present application illustrates an electronic device, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the method described in any of the above aspects.

[0011] In a sixth aspect, the present application illustrates a non-temporary computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute a method as described in any of the above aspects.

[0012] In a seventh aspect, the present application illustrates a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the method described in any of the above aspects.

[0013] The technical solution provided by this application may have the following beneficial effects: When training a meteorological forecast wind element data correction model based on data decomposition, wind element sub-data related to wind speed determined in the second wind element data are used. The second wind element data is obtained by replacing the "wind speed in the first wind element data" with the "wind speed difference between the wind speed in the first wind element data and the preset benchmark wind speed error". In the second wind element data, the wind speed difference can be regarded as the wind speed, which is close to the historical measured wind speed, narrowing the gap between the wind speed in the sample data and the historical measured wind speed, which is conducive to improving the accuracy of wind speed correction of the trained meteorological forecast wind element data correction model based on data decomposition.

[0014] In this way, when correcting the wind speed of the future time period of the point to be corrected, the meteorological forecast wind element data correction model based on data decomposition trained in the present application can be used to process the wind element sub-data related to the wind speed in the meteorological forecast wind element data of the future time period of the point to be corrected to obtain the corrected wind speed. For example, the meteorological forecast wind element data correction model based on data decomposition includes multiple wind element data correction sub-models, and each wind element data correction sub-model processes the wind element sub-data related to the wind speed in the meteorological forecast wind element data of the future time period of the point to be corrected respectively to obtain the wind speed correction component outputted by each, and then the corrected wind speed of the future time period of the point to be corrected is obtained according to the wind speed correction component outputted by each; in this way, through the present application, the accuracy of wind speed correction can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of the steps of a method for training a weather forecast wind element data correction model based on data decomposition in the present application.

[0016] Figure 2 It is a flowchart of the processing process of a random forest algorithm of the present application.

[0017] Figure 3 It is a schematic diagram of the network structure of a model of the present application.

[0018] Figure 4 It is a schematic diagram of the network structure of a model of the present application.

[0019] Figure 5 It is a flowchart of the steps of a method for testing a weather forecast wind element data correction model based on data decomposition in the present application.

[0020] Figure 6 This is a flowchart of the steps of a method for correcting wind element data of a weather forecast based on data decomposition in the present application.

[0021] Figure 7 It is a structural block diagram of a device for training a weather forecast wind element data correction model based on data decomposition in the present application.

[0022] Figure 8 This is a structural block diagram of a weather forecast wind element data correction device based on data decomposition in the present application.

[0023] Fig. 9 It is a block diagram of an electronic device of the present application.

[0024] Fig.10 It is a block diagram of an electronic device of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] Current weather forecast data is usually obtained by simulating the WRF (Weather Research and Forecasting Model) model. However, there is usually a certain deviation between the wind data in the simulated weather forecast data and the actual wind data. That is, the accuracy of the obtained wind data is poor, which may lead to low accuracy in wind power generation prediction.

[0027] To this end, it is necessary to correct the wind data simulated by WRF so that the corrected wind data is as close to the actual wind data as possible. In this way, the accuracy of wind power generation prediction can be improved, which is of great significance to enhancing the safety, stability and economy of the operation of a high-proportion renewable energy power system.

[0028] The wind data that needs to be corrected currently involves wind speed. The wind speed correction is usually based on a machine learning model. However, according to statistics, the accuracy of the wind speed corrected based on the machine learning model is still very low.

[0029] Therefore, in order to improve the accuracy of wind speed correction, this application is proposed.

[0030] Reference Figure 1 , shows a flowchart of the steps of a method for training a meteorological forecast wind factor data correction model based on data decomposition of the present application, the method can be applied to an electronic device, the electronic device can include a terminal or a server, etc., wherein the method can specifically include the following steps: In step S101, the first wind element data of the weather forecast for the first historical time period of the sample point is obtained, the first wind element data includes a plurality of wind element sub-data, the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure and light intensity.

[0031] The wind element sub-data may be wind element sub-data of each altitude layer of the sample point, and the altitude layer may be 100 meters, 90 meters, 80 meters, 70 meters, 60 meters, and other altitude layers.

[0032] The sample points can be a grid, for example, weather forecast data is given with a grid as the minimum resolution. The grid can be a rectangle, square, triangle, pentagon or hexagon, etc.

[0033] The wind element data of meteorological forecast can be the wind element data of the weather forecast model (WRF model). The weather forecast model (WRF model) represents a new generation of non-hydrostatic equilibrium, high-resolution mesoscale meteorological research and forecasting numerical model, which mainly considers the forecast of important weather from cloud scale to weather scale.

[0034] The wind element data of weather forecast can be understood as: the wind element data given by the weather forecast model (WRF model) in the historical process.

[0035] In step S102, the wind speed difference between the wind speed in the first wind element data and the preset reference wind speed error is calculated. The preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast of multiple second historical time periods of the sample point and the historical measured wind speed of each second historical time period of the sample point. The second historical time period is earlier than the first historical time period.

[0036] The multiple second historical time periods are all time periods earlier than the first historical time period, any two second historical time periods do not overlap, and the multiple second historical time periods may be sequentially adjacent time periods.

[0037] For any second historical time period, the wind speed difference between the wind speed in the wind element data of the meteorological forecast for the second historical time period at the sample point and the historical measured wind speed for the second historical time period at the sample point can be calculated. The same is true for each other second historical time period, thereby obtaining the wind speed differences corresponding to multiple second historical time periods. Then, the average value between the wind speed differences corresponding to multiple second historical time periods can be calculated and used as the preset benchmark wind speed error.

[0038] The wind speed difference between the two wind speeds may be the difference between the two wind speeds or the absolute value of the difference, etc. For example, when calculating the wind speed difference between the wind speed in the first wind element data and the preset reference wind speed error, the difference between the wind speed in the first wind element data and the preset reference wind speed error may be calculated.

[0039] In step S103, the calculated wind speed difference is used to replace the wind speed in the first wind element data, so as to obtain the second wind element data of the weather forecast for the first historical time period of the sample point.

[0040] In the second wind element data, the wind speed difference can be regarded as the wind speed, which is close to the historical measured wind speed. It narrows the gap between the wind speed in the sample data and the historical measured wind speed, which is conducive to improving the accuracy of wind speed correction of the trained meteorological forecast wind element data correction model based on data decomposition.

[0041] In step S104, based on the random forest algorithm, wind element sub-data related to wind speed is determined from the second wind element data.

[0042] The wind element sub-data related to wind speed includes at least wind speed, etc.

[0043] In an embodiment of the present application, based on the random forest algorithm, the correlation degree between each wind element sub-data in the second wind element data and wind speed can be determined, and the top-N wind element sub-data with the highest correlation degree with wind speed are selected. N is a positive integer.

[0044] In this step, using the random forest algorithm can extract wind element sub-data with a high correlation degree with wind speed from each wind element sub-data in the second wind element data.

[0045] The random forest algorithm is an algorithm that integrates multiple trees through the idea of ensemble learning.

[0046] Among them, referring to Figure 2 , the processing process of the random forest algorithm includes: First, generate a random forest, for i = 1 to i = n tree (n tree is the number of decision trees).

[0047] (1) Assume that the sample feature dimension is M, and a constant m << M. Randomly select m feature subsets from the M features as the attribute set for splitting the current decision tree.

[0048] (2) During each split of the i-th tree, select the best variable and split point from the m features, and each tree grows to the maximum extent (without the pruning process) to generate the decision tree T i .

[0049] (3) Combine the generated n tree trees into a random forest, and its output is determined according to the voting mechanism of the tree classifier.

[0050] Secondly, calculate the OOB data error. Assume that the training set size is N total .

[0051] for i = 1 to i = n tree .

[0052] (1) For the decision tree T i , use bootstrapping sampling to obtain N i samples from the training set as the training set of this tree, and the data not drawn forms the OOB data set N b_i . N i < Ntotal .

[0053] Bootstrapping sampling is a statistical method used to deal with small sample data sets. It reconstructs the original distribution by sampling with replacement (there may be repeated observations in the sample).

[0054] (2) Obtain decision tree T i For the OOB dataset N b_i The calculation results are compared with the actual results to obtain the calculation error E i .

[0055] For feature k (k = 1, 2, ..., M), for the OOB dataset N b_i Add noise interference to feature k in and obtain decision tree T i For the disturbed data set N b_i_k The calculation result is recorded as E i_k .

[0056] Then, calculate the importance D of feature k k , as shown in the following relationship:

[0057] Finally, the importance of each feature is ranked, the feature variables with lower importance are eliminated, and the feature variables with higher importance are retained to form a feature variable data set.

[0058] Further, according to the processing process of the random forest algorithm, the correlation between each wind element sub-data in the second wind element data and the wind speed can be calculated, that is, the importance of each wind element sub-data in the second wind element data to the wind speed, that is, the importance score, can be obtained, and then the TOP-N wind element sub-data with the largest correlation with the wind speed can be selected from each wind element sub-data in the second wind element data. N is a positive integer.

[0059] N is greater than or equal to 1, and N is less than or equal to the number of wind element sub-data in the wind element data of the weather forecast.

[0060] In this embodiment, the second wind element data is processed by the random forest algorithm, the wind element sub-data that is not suitable for training the meteorological forecast wind element data correction model based on data decomposition is eliminated, and the wind element sub-data that is suitable for training the meteorological forecast wind element data correction model based on data decomposition is retained, which can improve the efficiency of training the meteorological forecast wind element data correction model based on data decomposition and the correction accuracy.

[0061] In step S105, the historical measured wind speed of the sample point in the first historical time period is obtained.

[0062] The historical measured wind speed of the first historical time period of the sample point may include the historical measured wind speed of each height layer of the first historical time period of the sample point.

[0063] The height layer of wind speed can be 100 meters, 90 meters, 80 meters, 70 meters, 60 meters and other height layers, etc. The value range of wind speed is usually 0-50m / s, etc.

[0064] The first historical time period of the sample point can be obtained through a wind tower or a lidar wind measuring device, which is real data in the historical process. For example, the historical measured wind speed of the sample point is the real wind speed of the sample point in the historical process.

[0065] The duration of the first historical time period may be the same as the duration of the second historical time period, for example, 15 minutes.

[0066] In step S106, the CEEMDAN algorithm is used to decompose the historical measured wind speed of the sample point in the first historical time period to obtain multiple IMF wind speed components and a residual component.

[0067] In an example, for example, assuming that the historical measured wind speed of the first historical time period of the sample point is V, the CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive NoiseAnalysis) algorithm is used to decompose the historical measured wind speed V of the first historical time period of the sample point into: several IMF (Intrinsic Mode Function) subsequences and residuals R, as shown below:

[0068] That is, V = IMF1 + ... + IMF k +R.

[0069] In the aforementioned steps, step S101 and step S105 may be executed in parallel, or may be executed sequentially. If they are executed sequentially, the present application does not limit the execution order of step S101 and step S105.

[0070] Secondly, after step S101 is executed, step S102 may be executed, after step S102 is executed, step S103 may be executed, and after step S103 is executed, step S104 may be executed.

[0071] In addition, step S106 may be executed after step S105 is completed.

[0072] After step S104 and step S106 are executed, step S107 may be executed.

[0073] Among them, the decomposition process of the CEEMDAN algorithm is illustrated by example.

[0074] Assume E i (·) is the i-th eigenmode component obtained after EMD decomposition, and the i-th eigenmode component obtained by CEEMDAN decomposition is , v j is a Gaussian white noise signal that satisfies the standard normal distribution, j=1,2…,N is the number of times white noise is added, ε is the standard table of white noise, and y(t) is the signal to be decomposed.

[0075] The CEEMDAN decomposition steps are as follows: Add Gaussian white noise to the signal to be decomposed V to obtain a new signal , q=1,2.

[0076] Perform EMD decomposition on the new signal to obtain the first-order eigenmode component C1:

[0077] r j It represents the deviation obtained by subtracting each IMF decomposed from the signal to be decomposed after each IMF is decomposed.

[0078] The first eigenmode component of the decomposition is obtained by averaging the N generated modal components:

[0079] Compute the residual after removing the first modal component:

[0080] Add positive and negative paired Gaussian white noise to r1(t) to get a new signal, perform EMD decomposition on the new signal to get the first-order modal component D1, from which the second eigenmode component can be obtained:

[0081] Compute the residual after removing the second modal component:

[0082] Repeat the above steps until the residual signal is a monotonic function and cannot be further decomposed, and the algorithm ends. At this time, the number of intrinsic mode components obtained is K, and the original signal y(t) is decomposed into:

[0083] C k (t) is expressed as IMF k , r k (t) is denoted as R.

[0084] In step S107, for any one of the multiple IMF wind speed components and a residual component, the wind element sub-data related to the wind speed is used as sample data and the component is used as labeled data to train a wind element data correction sub-model corresponding to the component.

[0085] The same is true for multiple IMF wind speed components and each other component in a residual component, thereby obtaining a wind element data correction sub-model corresponding to each component.

[0086] It should be noted that, in one embodiment, there may be multiple first historical time periods. Any two first historical time periods do not overlap, and multiple first historical time periods may be sequentially adjacent time periods. Each first historical time period is later than any second historical time period.

[0087] In this way, the first wind element data of the weather forecast for the first historical time period of the sample point may include: the first wind element data of the weather forecast for each first historical time period in multiple first historical time periods of the sample point.

[0088] Accordingly, the second wind element data of the weather forecast for the first historical time period of the sample point may include: the second wind element data of the weather forecast for each first historical time period in multiple first historical time periods of the sample point.

[0089] Accordingly, the wind element sub-data related to wind speed in the first historical time period of the sample point may include: the wind element sub-data related to wind speed in each first historical time period of multiple first historical time periods of the sample point.

[0090] The historical measured wind speed of the first historical time period of the sample point may include: the historical measured wind speed of each first historical time period in multiple first historical time periods of the sample point.

[0091] In this way, for any first historical time period, there may be wind element sub-data related to wind speed at the sample point in the first historical time period and the historical measured wind speed at the sample point in the first historical time period.

[0092] Thus, the first historical time period corresponds to training data.

[0093] The sample data in the training data corresponding to the first historical time period is: wind element sub-data related to wind speed in the first historical time period of the sample point.

[0094] The annotated data in the training data corresponding to the first historical time period is: the historical measured wind speed of the sample point in the first historical time period.

[0095] The same is true for every other first historical time period.

[0096] In this way, there may be training data corresponding to a plurality of first historical time periods. A portion of the training data corresponding to the first historical time periods is used to train the meteorological forecast wind factor data correction model based on data decomposition, and another portion of the training data corresponding to the first historical time periods is used to test the trained meteorological forecast wind factor data correction model based on data decomposition.

[0097] Among the training data corresponding to the multiple first historical time periods, the number of training data used for testing and training the meteorological forecast wind element data correction model based on data decomposition accounts for at least 10% of the number of training data corresponding to the multiple first historical time periods.

[0098] In one example, following the example of step S106, the wind element sub-data related to wind speed is used as sample data and IMF1 is used as labeled data to train the wind element data correction sub-model 1 corresponding to IMF1, the wind element sub-data related to wind speed is used as sample data and IMF2 is used as labeled data to train the wind element data correction sub-model 2 corresponding to IMF2, and so on. k To label data, train IMF k The corresponding wind element data correction sub-model k is trained, and the wind element data correction sub-model R corresponding to R is trained using the wind element sub-data related to wind speed as sample data and R as labeled data.

[0099] In step S108, a meteorological forecast wind element data correction model based on data decomposition is obtained at least according to the wind element data correction sub-models corresponding to the various components.

[0100] In one embodiment, a fully connected layer may be obtained, and the fully connected layer is used to overlay and reconstruct the data output by the wind element data correction sub-model corresponding to each component. Overlay and reconstruction include addition, etc., or include calculation of average value, etc.

[0101] The output ends of the wind element data correction sub-model corresponding to each component are connected to the input ends of the fully connected layer respectively.

[0102] The output end of the meteorological forecast wind element data correction model based on data decomposition includes the output end of the fully connected layer.

[0103] For example, the network structure of the weather forecast wind factor data correction model based on data decomposition can be as follows: Figure 3shown.

[0104] Furthermore, the weather forecast wind element data correction model based on data decomposition also includes: an unsupervised learning network.

[0105] The input end of the meteorological forecast wind element data correction model based on data decomposition includes an input end of an unsupervised learning network.

[0106] The output end of the unsupervised learning network is connected to the input end of the wind element data correction sub-model corresponding to each component.

[0107] The unsupervised learning network is used to extract the features of wind element sub-data related to wind speed.

[0108] Each wind element data correction sub-model is used to process the wind element sub-data related to the wind speed, and obtain the corrected wind speed of the sample point in the first historical time period.

[0109] Among them, the wind factor data correction sub-models can include: GBDT (Gradient Boosting DecisionTree), ADABOOST (Adaptive Boosting, an iterative algorithm), XGBOOST (eXtremeGradientBoosting, extreme gradient boosting tree), LIGHTGBM (Light Gradient Boosting Machine, a machine learning algorithm), etc.

[0110] Among them, GBDT is an integrated algorithm based on decision trees. Its core idea is to fit the residual of the previous round of weak learners through the negative gradient of the loss function. Through the accumulation of multiple rounds of learning, the output gradually approaches the true value and accelerates convergence to the global or local optimal solution.

[0111] exist Figure 3 Based on the above, see Figure 4 , the unsupervised learning network includes multiple unsupervised learning sub-models connected in series. Figure 4 The figure shows j unsupervised learning sub-models connected in series, and the present application does not limit the number of unsupervised learning sub-models connected in series. The present application does not limit the number of j, which can be determined according to actual conditions, for example, 2, 3, 4 or 5.

[0112] Unsupervised learning sub-models may include: RBM (Restricted Boltzmann Machines) or AE (Auto Encoders), etc.

[0113] Among them, the j unsupervised learning sub-models connected in series can be understood as: the output end of the adjacent previous unsupervised learning sub-model is connected to the input end of the adjacent next unsupervised learning sub-model, and the j unsupervised learning sub-models connected in series are used to perform unsupervised learning on the input data, so as to perform feature transformation on the input data, so as to extract more abstract and more beneficial features in the input data.

[0114] The inventors have found through statistics that if the wind speed in an area of ​​sea or land changes, the change of wind speed in the time series is sometimes irregular, and sometimes changes suddenly. In this way, if the real wind speed is directly used as the annotation data to train the model for correcting the wind speed, the sudden change of wind speed will make it impossible to extract the real wind speed law, resulting in large gradient changes, and then the model for correcting the wind speed will fail to converge, or fail to converge to the optimal solution, which will result in low accuracy of the wind speed correction model for wind speed correction.

[0115] In view of this, the inventors have come up with a way to search for the law of change of wind speed in time series, and then reduce the gradient change so that the model for correcting wind speed can converge, or converge to the optimal solution, so as to improve the accuracy of wind speed correction by the model for correcting wind speed.

[0116] For example, the inventors thought of using the CEEMDAN algorithm to decompose the historical measured wind speed of the first historical time period of the sample point to obtain multiple IMF wind speed components and a residual component. Different components respectively have the characteristics of different frequency domains of the historical measured wind speed of the first historical time period of the sample point, and different components can reflect some regularities of the historical measured wind speed of the first historical time period of the sample point in different frequency domains. In this way, for each component, the corresponding wind element data correction sub-models can be trained respectively. Since different components can reflect some regularities of the historical measured wind speed of the first historical time period of the sample point in different frequency domains, different components can be divided into different IMF components and the residual component. The wind element data correction sub-models corresponding to the different components can learn some rules of the historical measured wind speed in the first historical time period of the sample point in different frequency domains, so that when training the wind element data correction sub-models corresponding to different components, the characteristics of different frequency domains of the historical measured wind speed in the first historical time period of the sample point can be better, more comprehensive and more accurate, so that the gradient change is small when training the wind element data correction sub-models corresponding to different components, so that the wind element data correction sub-models corresponding to different components of the training can converge, or converge to the optimal solution, which can improve the accuracy of wind speed correction of the trained meteorological forecast wind element data correction model based on data decomposition.

[0117] Furthermore, since the CEEMDAN algorithm has the ability to eliminate mode mixing and residual noise, it can adaptively decompose the nonlinear data in the historical measured wind speed of the first historical time period of the sample point to eliminate the noise inside the data and improve the data availability.

[0118] Secondly, the CEEMDAN algorithm can diversify the data, meet the prerequisite of more complete and diverse data required for the use of interpolation algorithms, and improve the accuracy of wind speed correction by the trained meteorological forecast wind factor data correction model based on data decomposition.

[0119] In addition, the CEEMDAN algorithm can eliminate modal aliasing and achieve zero reconstruction error of decomposed data, which greatly reduces the consumption of computing resources and improves data decomposition efficiency.

[0120] In addition, when training the meteorological forecast wind element data correction model based on data decomposition, the wind element sub-data related to the wind speed determined in the second wind element data is used. The second wind element data is obtained by replacing the "wind speed in the first wind element data" with the "wind speed difference between the wind speed in the first wind element data and the preset benchmark wind speed error". In the second wind element data, the wind speed difference can be regarded as the wind speed, which is close to the historical measured wind speed, narrowing the gap between the wind speed in the sample data and the historical measured wind speed, which is conducive to improving the accuracy of wind speed correction of the trained meteorological forecast wind element data correction model based on data decomposition.

[0121] It should be noted that in the scenario of training the correction model, when the labeled data does not change suddenly, the labeled data can be used directly to train the correction model. In this way, the regularity of the labeled data that has not changed suddenly can be extracted. The correction accuracy of the correction model trained in this way is often higher. In this case, it is not necessary to use the CEEMDAN algorithm to decompose the labeled data. This will consume a lot of computing resources, increase the length of the process of training the correction model, and will not improve the correction accuracy. In the process of development, technology will not develop in a direction that has no benefits and will increase costs.

[0122] The scenario of the present application is to train a wind speed correction model, and the labeled data used are the real historical wind speeds. The real historical wind speeds may change suddenly. It can be seen that the present application is a situation where the labeled data may change suddenly. In this case, if the labeled data is used directly to train the wind speed correction model, the correction accuracy of the trained wind speed correction model will often be very low due to the inability to extract the regularity of the suddenly changing labeled data. Therefore, the inventors thought of using the CEEMDAN algorithm to decompose the labeled data to extract the regularity of the labeled data in different frequency domains, which will significantly improve the correction accuracy of the wind speed correction model.

[0123] It can be seen that in the scenario of training the correction model, if the labeled data does not change suddenly, there is no need or necessity to use the CEEMDAN algorithm.

[0124] Further, after obtaining the meteorological forecast wind element data correction model based on data decomposition, a second average value of the wind speed difference between the wind speed in the meteorological forecast wind element data of the third historical time period of the sample point and the historical measured wind speed of the third historical time period of the sample point can be obtained. The third historical time period is later than the second historical time period.

[0125] When the error between the second average value and the first average value is greater than the preset benchmark wind speed error, it may be due to changes in the organization or technology that provides the meteorological forecast wind element data, resulting in the meteorological forecast wind element data being closer to the actual situation or further away from the actual situation than before, and the old preset benchmark wind speed error is no longer applicable. Therefore, in order to make the correction of the meteorological forecast wind element data more accurate, a meteorological forecast wind element data correction model based on data decomposition and applicable to the new preset benchmark wind speed error can be retrained. For example, the preset benchmark wind speed error is updated to the second average value, and the step of obtaining the first wind element data of the meteorological forecast for the first historical time period of the sample point is returned. That is, the second average value is used as the preset benchmark wind speed error and the correction model is retrained. Figure 1 The illustrated embodiment trains a weather forecast wind element data correction model based on data decomposition.

[0126] Furthermore, after the multi-channel-based meteorological forecast wind element data correction model is obtained through training, the multi-channel-based meteorological forecast wind element data correction model can be tested.

[0127] For example, see Figure 5 , the specific steps include: In step S201, the first wind element data of the weather forecast for the first historical time period of the test point is obtained, the first wind element data includes multiple wind element sub-data, the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure and light intensity.

[0128] For details of this step, please refer to the description of step S101.

[0129] In step S202, the wind speed difference between the wind speed in the first wind element data and the preset reference wind speed error is calculated. The preset reference wind speed error includes: the average of the wind speed differences between the wind speed in the wind element data of the meteorological forecast for multiple second historical time periods of the test point and the historical measured wind speed of each second historical time period of the test point. The second historical time period is earlier than the first historical time period.

[0130] The first historical time period of this embodiment is Figure 1 The first historical time period shown may be a different historical time period. The second historical time period in this embodiment is different from Figure 1 The second historical time period shown may be a different historical time period.

[0131] For details of this step, please refer to the description of step S102.

[0132] In step S203, the calculated wind speed difference is used to replace the wind speed in the first wind element data, so as to obtain the second wind element data of the weather forecast for the first historical time period of the test point.

[0133] For details of this step, please refer to the description of step S103.

[0134] The first wind element data in this embodiment is Figure 1 The first wind element data shown can be different data. The second wind element data in this embodiment is different from Figure 1 The second wind element data shown may be different data.

[0135] In step S204, based on the random forest algorithm, wind element sub-data related to wind speed is determined in the second wind element data.

[0136] For details of this step, please refer to the description of step S104.

[0137] In step S205, the wind element sub-data related to wind speed is input into the meteorological forecast wind element data correction model based on data decomposition, wherein the meteorological forecast wind element data correction model based on data decomposition includes multiple wind element data correction sub-models, each wind element data correction sub-model processes the wind element sub-data related to wind speed respectively, obtains each output wind speed correction component, and then obtains the corrected wind speed of the test point in the first historical time period according to each output wind speed correction component.

[0138] In step S206, the historical measured wind speed of the test point in the first historical time period is obtained.

[0139] For details of this step, please refer to the description of step S105.

[0140] In step S207, a wind speed error index is calculated based on the corrected wind speed of the first historical time period at the test point and the historical measured wind speed of the first historical time period at the test point.

[0141] For example, the error metric can be calculated by the mean absolute error (MAE), the root mean square error (RMSE), or the coefficient of determination (R2).

[0142] Among them, the wind speed error index can be used to evaluate the correction effect of the meteorological forecast wind element data correction model based on data decomposition, that is, the accuracy of the wind speed correction of the meteorological forecast wind element data correction model based on data decomposition can be evaluated. After the accuracy of the wind speed correction meets the requirements, the meteorological forecast wind element data correction model based on data decomposition can be put into online application.

[0143] For example, the wind speed in the weather forecast is corrected using a weather forecast wind element data correction model based on data decomposition.

[0144] For example, refer to Figure 6 , shows a flow chart of the steps of a method for correcting wind element data of a meteorological forecast based on data decomposition of the present application, the method can be applied to an electronic device, the electronic device can include a terminal or a server, etc., wherein the method can specifically include the following steps: In step S301, the first wind element data of the weather forecast for the first time period of the point to be corrected is obtained, the first wind element data includes multiple wind element sub-data, the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure and light intensity.

[0145] For details of this step, please refer to the description of step S101.

[0146] In step S302, the wind speed difference between the wind speed in the first wind element data and the preset reference wind speed error is calculated. The preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast for multiple second time periods of the point to be corrected and the historical measured wind speed of each second time period of the point to be corrected. The second time period is earlier than the first time period.

[0147] The first time period may be a future time period after the current moment, and the second time period may be a historical time period before the current moment.

[0148] For details of this step, please refer to the description of step S102.

[0149] In step S303, the calculated wind speed difference is used to replace the wind speed in the first wind element data, so as to obtain the second wind element data of the weather forecast for the first time period of the point to be corrected.

[0150] For details of this step, please refer to the description of step S103.

[0151] In step S304, based on the random forest algorithm, wind element sub-data related to wind speed is determined in the second wind element data.

[0152] For details of this step, please refer to the description of step S104.

[0153] In step S305, the wind element sub-data related to wind speed is input into the meteorological forecast wind element data correction model based on data decomposition, wherein the meteorological forecast wind element data correction model based on data decomposition includes multiple wind element data correction sub-models, each wind element data correction sub-model processes the wind element sub-data related to wind speed respectively, obtains each output wind speed correction component, and then obtains the corrected wind speed of the first time period of the point to be corrected according to each output wind speed correction component.

[0154] When correcting the wind speed for a future time period at a point to be corrected, the meteorological forecast wind element data correction model based on data decomposition trained in the present application can be used to process the wind element sub-data related to the wind speed in the wind element data of the meteorological forecast for the future time period at the point to be corrected to obtain the corrected wind speed. For example, the meteorological forecast wind element data correction model based on data decomposition includes multiple wind element data correction sub-models, each of which processes the wind element sub-data related to the wind speed in the wind element data of the meteorological forecast for the future time period at the point to be corrected to obtain its own output wind speed correction component, and then the corrected wind speed for the future time period of the point to be corrected is obtained based on the respective output wind speed correction components. In this way, the accuracy of wind speed correction can be improved through the present application.

[0155] Further, after obtaining the measured wind speed of the third time period of the point to be corrected, a second average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast of the third time period of the point to be corrected and the measured wind speed of the third time period of the point to be corrected can be obtained. The third time period is later than the second time period.

[0156] When the error between the second average value and the first average value is greater than the preset benchmark wind speed error, a prompt message is output, which is used to prompt the meteorological forecast wind element data correction model based on data decomposition to be retrained using the second average value as the preset benchmark wind speed error.

[0157] Among them, when the error between the second average value and the first average value is greater than the preset benchmark wind speed error, it may be due to changes in the organization or technology that provides the meteorological forecast wind element data, resulting in the provided meteorological forecast wind element data being closer to the actual situation or further away from the actual situation than before, and the old preset benchmark wind speed error is no longer applicable. Therefore, in order to make the correction of the meteorological forecast wind element data more accurate, it can be prompted to retrain the meteorological forecast wind element data correction model based on data decomposition that is suitable for the new preset benchmark wind speed error. For example, a prompt message is output, and the prompt message is used to prompt the retraining of the meteorological forecast wind element data correction model based on data decomposition using the second average value as the preset benchmark wind speed error.

[0158] Alternatively, if there is already a meteorological forecast wind element data correction model based on data decomposition that has been retrained using the second average value as the preset benchmark wind speed error, then a prompt may be provided to subsequently replace the meteorological forecast wind element data correction model based on data decomposition that has been trained using the second average value as the preset benchmark wind speed error.

[0159] Another embodiment of the present application provides a method for training a meteorological forecast wind element data correction model based on data decomposition, including: obtaining first wind element data of a meteorological forecast for a first historical time period of a sample point, the first wind element data including a plurality of wind element sub-data, the wind element sub-data including at least wind direction, and the wind element sub-data also including at least one of the following: wind speed, precipitation, temperature, humidity, air pressure, and light intensity; calculating the wind direction difference between the wind direction in the first wind element data and a preset reference wind direction error; the preset reference wind direction error includes: a first average value of the wind direction difference between the wind direction in the meteorological forecast wind element data for a plurality of second historical time periods of the sample point and the historical measured wind direction of each second historical time period of the sample point; the second historical time period is earlier than the first historical time period; using the calculated wind direction difference to replace the wind direction in the first wind element data direction, obtain the second wind element data of the meteorological forecast for the first historical time period of the sample point; based on the random forest algorithm, determine the wind element sub-data related to the wind direction in the second wind element data; obtain the historical measured wind direction of the first historical time period of the sample point; use the fully adaptive noise ensemble empirical mode decomposition CEEMDAN algorithm to decompose the historical measured wind direction of the first historical time period of the sample point to obtain multiple inherent mode function IMF wind direction components and a residual component; for any one of the multiple IMF wind direction components and the one residual component, use the wind element sub-data related to the wind direction as sample data and the component as labeled data to train the wind element data correction sub-model corresponding to the component; at least according to the wind element data correction sub-models corresponding to each component, obtain the meteorological forecast wind element data correction model based on data decomposition.

[0160] The specific explanation of this embodiment can be found in the description of the aforementioned embodiment and will not be elaborated here.

[0161] The correction model of this embodiment is used to correct the wind direction. For example, in another embodiment, a method for correcting meteorological forecast wind element data based on data decomposition is also provided, including: obtaining first wind element data of the meteorological forecast for the first time period of the point to be corrected, the first wind element data including multiple wind element sub-data, the wind element sub-data including at least wind direction, and the wind element sub-data also including at least one of the following: wind speed, precipitation, temperature, humidity, air pressure and light intensity; calculating the wind direction difference between the wind direction in the first wind element data and a preset reference wind direction error; the preset reference wind direction error includes: a first average value of the wind direction difference between the wind direction in the meteorological forecast wind element data of multiple second time periods of the point to be corrected and the historical measured wind direction of each second time period of the point to be corrected; the second time period is earlier than the first time period; using The calculated wind direction difference replaces the wind direction in the first wind element data to obtain the second wind element data of the meteorological forecast for the first time period of the point to be corrected; based on the random forest algorithm, the wind element sub-data related to the wind direction is determined in the second wind element data; the wind element sub-data related to the wind direction is input into the meteorological forecast wind element data correction model based on data decomposition, wherein the meteorological forecast wind element data correction model based on data decomposition includes multiple wind element data correction sub-models, each wind element data correction sub-model processes the wind element sub-data related to the wind direction respectively to obtain the wind direction correction component output by each, and then obtains the corrected wind direction of the first time period of the point to be corrected according to the wind direction correction component output by each; wherein the meteorological forecast wind element data correction model based on data decomposition is trained by the method mentioned above.

[0162] The specific explanation of this embodiment can be found in the description of the aforementioned embodiment and will not be elaborated here.

[0163] The inventors have found through statistics that if the wind direction of an area in the sea or land changes, the change of wind direction in the time series is sometimes irregular, and sometimes changes suddenly. In this way, if the real wind direction is directly used as the annotation data to train the model for correcting the wind direction, the sudden change of the wind direction will make it impossible to extract the real wind direction pattern, resulting in large gradient changes, and then the model for correcting the wind direction will fail to converge, or fail to converge to the optimal solution, which results in low accuracy of the wind direction correction model.

[0164] In view of this, the inventors have come up with a way to search for the law of change of wind direction in time series, and then reduce the gradient change so that the model for correcting wind direction can converge, or converge to the optimal solution, so as to improve the accuracy of the model for correcting wind direction in correcting wind direction.

[0165] For example, the inventors thought of using the CEEMDAN algorithm to decompose the historical measured wind direction of the first historical time period of the sample point to obtain multiple IMF wind direction components and a residual component. Different components respectively have the characteristics of different frequency domains of the historical measured wind direction of the first historical time period of the sample point, and different components can reflect some regularities of the historical measured wind direction of the first historical time period of the sample point in different frequency domains. In this way, for each component, the corresponding wind element data correction sub-models can be trained respectively. Since different components can reflect some regularities of the historical measured wind direction of the first historical time period of the sample point in different frequency domains, different components can be respectively trained. The corresponding wind element data correction sub-model can learn some rules of the historical measured wind direction in the first historical time period of the sample point in different frequency domains, so that when training the wind element data correction sub-models corresponding to different components, the characteristics of different frequency domains of the historical measured wind direction in the first historical time period of the sample point can be better, more comprehensive and more accurately extracted, so that when training the wind element data correction sub-models corresponding to different components, the gradient change is small, so that the wind element data correction sub-models corresponding to different components of the training can converge, or converge to the optimal solution, which can improve the accuracy of wind direction correction of the trained meteorological forecast wind element data correction model based on data decomposition.

[0166] Furthermore, since the CEEMDAN algorithm has the ability to eliminate mode mixing and residual noise, it can adaptively decompose the nonlinear data in the historical measured wind direction decomposition of the first historical time period of the sample point, thereby eliminating the noise inside the data and improving data availability.

[0167] Secondly, the CEEMDAN algorithm can diversify the data, meet the prerequisite of more complete and diverse data required for the use of interpolation algorithms, and improve the accuracy of wind direction correction of the trained meteorological forecast wind element data correction model based on data decomposition.

[0168] In addition, the CEEMDAN algorithm can eliminate modal aliasing and achieve zero reconstruction error of decomposed data, which greatly reduces the consumption of computing resources and improves data decomposition efficiency.

[0169] In addition, when training the meteorological forecast wind element data correction model based on data decomposition, the wind element sub-data related to the wind direction determined in the second wind element data is used. The second wind element data is obtained by replacing the "wind direction in the first wind element data" with the "wind direction difference between the wind direction in the first wind element data and the preset benchmark wind direction error". In the second wind element data, the wind direction error can be regarded as the wind direction, which is close to the historical measured wind direction, narrowing the gap between the wind direction in the sample data and the historical measured wind direction, which is conducive to improving the accuracy of wind direction correction of the trained meteorological forecast wind element data correction model based on data decomposition.

[0170] In this way, when correcting the wind direction of the future time period of the point to be corrected, the meteorological forecast wind element data correction model based on data decomposition trained in the present application can be used to process the wind element sub-data related to the wind direction in the meteorological forecast wind element data for the future time period of the point to be corrected, and obtain the corrected wind direction. For example, the meteorological forecast wind element data correction model based on data decomposition includes multiple wind element data correction sub-models, and each wind element data correction sub-model processes the wind element sub-data related to the wind direction in the meteorological forecast wind element data for the future time period of the point to be corrected, respectively, to obtain the wind direction correction component output by each, and then according to the wind direction correction component output by each, the corrected wind direction of the future time period of the point to be corrected is obtained; in this way, through the present application, the accuracy of wind direction correction can be improved.

[0171] It should be noted that in the scenario of training the correction model, when the labeled data does not change suddenly, the labeled data can be used directly to train the correction model. In this way, the regularity of the labeled data that has not changed suddenly can be extracted. The correction accuracy of the correction model trained in this way is often higher. In this case, it is not necessary to use the CEEMDAN algorithm to decompose the labeled data. This will not only consume a lot of computing resources and increase the length of the process of training the correction model, but will not improve the correction accuracy. In the process of development, technology will not develop in a direction that has no benefits and will increase costs.

[0172] The scenario of the present application is to train a wind direction correction model, and the labeled data used are the real historical wind directions. The real historical wind directions may change suddenly. It can be seen that the present application is a situation where the labeled data may change suddenly. In this case, if the labeled data is used directly to train the wind direction correction model, the correction accuracy of the trained wind direction correction model will often be very low due to the inability to extract the regularity of the suddenly changing labeled data. Therefore, the inventors thought of using the CEEMDAN algorithm to decompose the labeled data to extract the regularity of the labeled data in different frequency domains, which will significantly improve the correction accuracy of the wind direction correction model.

[0173] It can be seen that in the scenario of training the correction model, if the labeled data does not change suddenly, there is no need or necessity to use the CEEMDAN algorithm.

[0174] It should be noted that, for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions involved are not necessarily required by the present application.

[0175] Reference Figure 7 , shows a structural block diagram of a device for training a weather forecast wind element data correction model based on data decomposition of the present application, the device comprising: A first acquisition module 11 is used to acquire first wind element data of a meteorological forecast for a first historical time period at a sample point, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; The first calculation module 12 is used to calculate the wind speed difference between the wind speed in the first wind element data and a preset reference wind speed error; the preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast of multiple second historical time periods of the sample point and the historical measured wind speed of each second historical time period of the sample point; the second historical time period is earlier than the first historical time period; A first replacement module 13 is used to replace the wind speed in the first wind element data with the calculated wind speed difference to obtain the second wind element data of the meteorological forecast for the first historical time period of the sample point; A first determination module 14 is used to determine wind element sub-data related to wind speed in the second wind element data based on a random forest algorithm; The second acquisition module 15 is used to obtain the historical measured wind speed of the sample point in the first historical time period; The decomposition module 16 is used to decompose the historical measured wind speed of the first historical time period of the sample point by using a fully adaptive noise ensemble empirical mode decomposition (CEEMDAN) algorithm to obtain multiple intrinsic mode function (IMF) wind speed components and a residual component; A training module 17 is used for training a wind element data correction sub-model corresponding to any one of the multiple IMF wind speed components and a residual component, using wind element sub-data related to the wind speed as sample data and the component as labeled data; The third acquisition module 18 is used to obtain a meteorological forecast wind element data correction model based on data decomposition at least according to the wind element data correction sub-model corresponding to each component.

[0176] In an optional implementation, the wind factor data correction sub-models corresponding to the respective components are used to obtain a weather forecast wind factor data correction model based on data decomposition, including: Obtain a fully connected layer, which is used to superimpose and reconstruct the data output by the wind element data correction sub-model corresponding to each component; The output ends of the wind element data correction sub-models corresponding to the respective components are respectively connected to the input ends of the fully connected layer, and the output end of the meteorological forecast wind element data correction model based on data decomposition includes the output end of the fully connected layer.

[0177] In an optional implementation, the device further includes: A fourth acquisition module is used to obtain, after obtaining the meteorological forecast wind element data correction model based on data decomposition, a second average value of the wind speed difference between the wind speed in the meteorological forecast wind element data of the sample point in the third historical time period and the historical measured wind speed of the sample point in the third historical time period; the third historical time period is later than the second historical time period; The updating module is used to update the preset reference wind speed error to the second average value when the error between the second average value and the first average value is greater than the preset reference wind speed error, and return to execute the step of obtaining the first wind element data of the meteorological forecast for the first historical time period of the sample point.

[0178] The inventors have found through statistics that if the wind speed in an area of ​​sea or land changes, the change of wind speed in the time series is sometimes irregular, and sometimes changes suddenly. In this way, if the real wind speed is directly used as the annotation data to train the model for correcting the wind speed, the sudden change of wind speed will make it impossible to extract the real wind speed law, resulting in large gradient changes, and then the model for correcting the wind speed will fail to converge, or fail to converge to the optimal solution, which will result in low accuracy of the wind speed correction model for wind speed correction.

[0179] In view of this, the inventors have come up with a way to search for the law of change of wind speed in time series, and then reduce the gradient change so that the model for correcting wind speed can converge, or converge to the optimal solution, so as to improve the accuracy of wind speed correction by the model for correcting wind speed.

[0180] For example, the inventors thought of using the CEEMDAN algorithm to decompose the historical measured wind speed of the first historical time period of the sample point to obtain multiple IMF wind speed components and a residual component. Different components respectively have the characteristics of different frequency domains of the historical measured wind speed of the first historical time period of the sample point, and different components can reflect some regularities of the historical measured wind speed of the first historical time period of the sample point in different frequency domains. In this way, for each component, the corresponding wind element data correction sub-models can be trained respectively. Since different components can reflect some regularities of the historical measured wind speed of the first historical time period of the sample point in different frequency domains, different components can be divided into different IMF components and the residual component. The wind element data correction sub-models corresponding to the different components can learn some rules of the historical measured wind speed in the first historical time period of the sample point in different frequency domains, so that when training the wind element data correction sub-models corresponding to different components, the characteristics of different frequency domains of the historical measured wind speed in the first historical time period of the sample point can be better, more comprehensive and more accurate, so that the gradient change is small when training the wind element data correction sub-models corresponding to different components, so that the wind element data correction sub-models corresponding to different components of the training can converge, or converge to the optimal solution, which can improve the accuracy of wind speed correction of the trained meteorological forecast wind element data correction model based on data decomposition.

[0181] Furthermore, since the CEEMDAN algorithm has the ability to eliminate mode mixing and residual noise, it can adaptively decompose the nonlinear data in the historical measured wind speed of the first historical time period of the sample point to eliminate the noise inside the data and improve the data availability.

[0182] Secondly, the CEEMDAN algorithm can diversify the data, meet the prerequisite of more complete and diverse data required for the use of interpolation algorithms, and improve the accuracy of wind speed correction by the trained meteorological forecast wind factor data correction model based on data decomposition.

[0183] In addition, the CEEMDAN algorithm can eliminate modal aliasing and achieve zero reconstruction error of decomposed data, which greatly reduces the consumption of computing resources and improves data decomposition efficiency.

[0184] In addition, when training the meteorological forecast wind element data correction model based on data decomposition, the wind element sub-data related to the wind speed determined in the second wind element data is used. The second wind element data is obtained by replacing the "wind speed in the first wind element data" with the "wind speed difference between the wind speed in the first wind element data and the preset benchmark wind speed error". In the second wind element data, the wind speed difference can be regarded as the wind speed, which is close to the historical measured wind speed, narrowing the gap between the wind speed in the sample data and the historical measured wind speed, which is conducive to improving the accuracy of wind speed correction of the trained meteorological forecast wind element data correction model based on data decomposition.

[0185] Reference Figure 8 , shows a structural block diagram of a weather forecast wind element data correction device based on data decomposition of the present application, the device comprising: A fifth acquisition module 21 is used to acquire first wind element data of a weather forecast for a first time period of a point to be corrected, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; The second calculation module 22 is used to calculate the wind speed difference between the wind speed in the first wind element data and a preset reference wind speed error; the preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast for multiple second time periods of the point to be corrected and the historical measured wind speed of each second time period of the point to be corrected; the second time period is earlier than the first time period; The second replacement module 23 is used to replace the wind speed in the first wind element data with the calculated wind speed difference to obtain the second wind element data of the weather forecast for the first time period of the point to be corrected; A second determination module 24 is used to determine wind element sub-data related to wind speed in the second wind element data based on a random forest algorithm; The processing module 25 is used to input the wind element sub-data related to the wind speed into the meteorological forecast wind element data correction model based on data decomposition, wherein the meteorological forecast wind element data correction model based on data decomposition includes a plurality of wind element data correction sub-models, each wind element data correction sub-model processes the wind element sub-data related to the wind speed respectively to obtain a respective output wind speed correction component, and then obtains the corrected wind speed of the first time period of the point to be corrected according to the respective output wind speed correction components; In an optional implementation, the device further includes: A sixth acquisition module is used to obtain a second average value of the difference between the wind speed in the wind element data of the meteorological forecast in the third time period of the point to be corrected and the measured wind speed in the third time period of the point to be corrected; the third time period is later than the second time period; The output module is used to output a prompt message when the error between the second average value and the first average value is greater than the preset benchmark wind speed error. The prompt message is used to prompt the meteorological forecast wind element data correction model based on data decomposition to be retrained using the second average value as the preset benchmark wind speed error.

[0186] Among them, the meteorological forecast wind factor data correction model based on data decomposition is as follows Figure 1 obtained by training using any of the methods described above.

[0187] Alternatively, the weather forecast wind factor data correction model based on data decomposition is obtained by Figure 7 Obtained by training with any of the above-described devices.

[0188] When correcting the wind speed for a future time period at a point to be corrected, the meteorological forecast wind element data correction model based on data decomposition trained in the present application can be used to process the wind element sub-data related to the wind speed in the wind element data of the meteorological forecast for the future time period at the point to be corrected to obtain the corrected wind speed. For example, the meteorological forecast wind element data correction model based on data decomposition includes multiple wind element data correction sub-models, each of which processes the wind element sub-data related to the wind speed in the wind element data of the meteorological forecast for the future time period at the point to be corrected to obtain its own output wind speed correction component, and then the corrected wind speed for the future time period of the point to be corrected is obtained based on the respective output wind speed correction components. In this way, the accuracy of wind speed correction can be improved through the present application.

[0189] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0190] Optionally, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0191] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each process of the above method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0192] FIG9 is a block diagram of an electronic device 800 shown in the present application. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0193] Reference Fig. 9 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0194] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0195] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, images, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0196] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0197] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0198] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0199] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0200] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0201] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast operation information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0202] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0203] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by a processor 820 of an electronic device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0204] Fig.101 is a block diagram of an electronic device 1900 shown in the present application. For example, the electronic device 1900 may be provided as a server.

[0205] Reference Fig.10 , the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0206] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0207] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0208] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0209] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0210] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0211] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0212] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0213] 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.

[0214] 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.

[0215] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. 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, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0216] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present 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 method for training a weather forecast wind factor data correction model based on data decomposition, characterized in that: The method comprises: Acquire first wind element data of a weather forecast for a first historical time period at a sample point, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; Calculate the wind speed difference between the wind speed in the first wind element data and a preset reference wind speed error; the preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast of multiple second historical time periods of the sample point and the historical measured wind speed of each second historical time period of the sample point; the second historical time period is earlier than the first historical time period; The wind speed in the first wind element data is replaced by the calculated wind speed difference to obtain the second wind element data of the meteorological forecast for the first historical time period of the sample point; Based on the random forest algorithm, in the second wind element data, wind element sub-data related to the wind speed is determined; Obtain the historical measured wind speed of the first historical time period of the sample point; The fully adaptive noise ensemble empirical mode decomposition (CEEMDAN) algorithm is used to decompose the historical measured wind speed of the first historical time period of the sample point to obtain multiple intrinsic mode function (IMF) wind speed components and a residual component. For any one of the multiple IMF wind speed components and a residual component, using wind element sub-data related to the wind speed as sample data and the component as labeled data, training a wind element data correction sub-model corresponding to the component; At least according to the wind element data correction sub-models respectively corresponding to the various components, a meteorological forecast wind element data correction model based on data decomposition is obtained.

2. The method according to claim 1, characterized in that The method of correcting the sub-models of wind element data corresponding to each component to obtain a meteorological forecast wind element data correction model based on data decomposition includes: Obtain a fully connected layer, which is used to overlay and reconstruct the data output by the wind element data correction sub-model corresponding to each component; Connect the output ends of the wind factor data correction sub-models corresponding to each component to the input ends of the fully connected layer respectively; The output end of the meteorological forecast wind element data correction model based on data decomposition includes the output end of the fully connected layer.

3. The method according to claim 1, characterized in that The method further comprises: After obtaining the meteorological forecast wind element data correction model based on data decomposition, obtaining a second average value of the wind speed difference between the wind speed in the meteorological forecast wind element data of the third historical time period of the sample point and the historical measured wind speed of the third historical time period of the sample point; the third historical time period is later than the second historical time period; When the error between the second average value and the first average value is greater than the preset reference wind speed error, the preset reference wind speed error is updated to the second average value, and the step of obtaining the first wind element data of the meteorological forecast for the first historical time period of the sample point is returned.

4. A method for correcting wind factor data in meteorological forecast based on data decomposition, characterized in that: The method comprises: Acquire first wind element data of a weather forecast for a first time period of a point to be corrected, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; Calculate the wind speed difference between the wind speed in the first wind element data and a preset reference wind speed error; the preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast for multiple second time periods of the point to be corrected and the historical measured wind speed of each second time period of the point to be corrected; the second time period is earlier than the first time period; The wind speed in the first wind element data is replaced by the calculated wind speed difference to obtain the second wind element data of the weather forecast for the first time period of the point to be corrected; Based on the random forest algorithm, in the second wind element data, wind element sub-data related to the wind speed is determined; Inputting the wind element sub-data related to the wind speed into the meteorological forecast wind element data correction model based on data decomposition, wherein the meteorological forecast wind element data correction model based on data decomposition includes a plurality of wind element data correction sub-models, each wind element data correction sub-model processes the wind element sub-data related to the wind speed respectively to obtain a respective output wind speed correction component, and then obtaining the corrected wind speed of the first time period of the point to be corrected according to the respective output wind speed correction components; Wherein, the meteorological forecast wind element data correction model based on data decomposition is obtained by training according to any one of the methods described in claims 1 to 3.

5. The method according to claim 4, characterized in that The method further comprises: Obtaining a second average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast for the third time period of the point to be corrected and the actually measured wind speed for the third time period of the point to be corrected; the third time period is later than the second time period; When the error between the second average value and the first average value is greater than the preset benchmark wind speed error, a prompt message is output, which is used to prompt the meteorological forecast wind element data correction model based on data decomposition to be retrained using the second average value as the preset benchmark wind speed error.

6. A device for training a weather forecast wind factor data correction model based on data decomposition, characterized in that: The device comprises: A first acquisition module is used to acquire first wind element data of a meteorological forecast for a first historical time period at a sample point, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; The first calculation module is used to calculate the wind speed difference between the wind speed in the first wind element data and the preset reference wind speed error; the preset reference wind speed error includes: the first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast of multiple second historical time periods of the sample point and the historical measured wind speed of each second historical time period of the sample point; the second historical time period is earlier than the first historical time period; A first replacement module is used to replace the wind speed in the first wind element data with the calculated wind speed difference to obtain the second wind element data of the meteorological forecast for the first historical time period of the sample point; A first determination module is used to determine wind element sub-data related to wind speed in the second wind element data based on a random forest algorithm; The second acquisition module is used to obtain the historical measured wind speed of the sample point in the first historical time period; A decomposition module is used to decompose the historical measured wind speed of the first historical time period of the sample point by using a fully adaptive noise ensemble empirical mode decomposition (CEEMDAN) algorithm to obtain multiple intrinsic mode function (IMF) wind speed components and a residual component; A training module, for training a wind element data correction sub-model corresponding to any one of a plurality of IMF wind speed components and a residual component, using wind element sub-data related to the wind speed as sample data and the component as labeled data; The third acquisition module is used to obtain a meteorological forecast wind element data correction model based on data decomposition at least according to the wind element data correction sub-model corresponding to each component.

7. A weather forecast wind factor data correction device based on data decomposition, characterized in that: The device comprises: a fifth acquisition module, configured to acquire first wind element data of a weather forecast for a first time period of a point to be corrected, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind speed, and the wind element sub-data also includes at least one of the following: wind direction, precipitation, temperature, humidity, air pressure, and light intensity; The second calculation module is used to calculate the wind speed difference between the wind speed in the first wind element data and a preset reference wind speed error; the preset reference wind speed error includes: a first average value of the wind speed difference between the wind speed in the wind element data of the meteorological forecast for multiple second time periods of the point to be corrected and the historical measured wind speed of each second time period of the point to be corrected; the second time period is earlier than the first time period; A second replacement module is used to replace the wind speed in the first wind element data with the calculated wind speed difference to obtain the second wind element data of the weather forecast for the first time period of the point to be corrected; A second determination module is used to determine wind element sub-data related to wind speed in the second wind element data based on a random forest algorithm; A processing module, used for inputting wind element sub-data related to wind speed into a meteorological forecast wind element data correction model based on data decomposition, wherein the meteorological forecast wind element data correction model based on data decomposition includes a plurality of wind element data correction sub-models, each wind element data correction sub-model processes the wind element sub-data related to wind speed respectively to obtain a respective output wind speed correction component, and then obtains a corrected wind speed of a first time period of a point to be corrected according to the respective output wind speed correction components; Wherein, the meteorological forecast wind element data correction model based on data decomposition is obtained by training according to any one of the methods described in claims 1 to 3.

8. A method for training a weather forecast wind factor data correction model based on data decomposition, characterized in that: The method comprises: Acquire first wind element data of a weather forecast for a first historical time period at a sample point, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind direction, and the wind element sub-data also includes at least one of the following: wind speed, precipitation, temperature, humidity, air pressure, and light intensity; Calculate the wind direction difference between the wind direction in the first wind element data and a preset reference wind direction error; the preset reference wind direction error includes: a first average value of the wind direction difference between the wind direction in the wind element data of the meteorological forecast of multiple second historical time periods of the sample point and the historical measured wind direction of each second historical time period of the sample point; the second historical time period is earlier than the first historical time period; The wind direction in the first wind element data is replaced by the calculated wind direction difference to obtain the second wind element data of the meteorological forecast for the first historical time period of the sample point; Based on the random forest algorithm, in the second wind element data, wind element sub-data related to the wind direction is determined; Obtain the historical measured wind direction of the first historical time period of the sample point; The fully adaptive noise ensemble empirical mode decomposition (CEEMDAN) algorithm is used to decompose the historical measured wind direction of the first historical time period of the sample point to obtain multiple intrinsic mode function (IMF) wind direction components and a residual component. For any one of the multiple IMF wind direction components and a residual component, using wind element sub-data related to the wind direction as sample data and the component as labeled data, training a wind element data correction sub-model corresponding to the component; At least according to the wind element data correction sub-models respectively corresponding to the various components, a meteorological forecast wind element data correction model based on data decomposition is obtained.

9. A method for correcting wind factor data in meteorological forecast based on data decomposition, characterized in that: The method comprises: Acquire first wind element data of a weather forecast for a first time period of a point to be corrected, wherein the first wind element data includes a plurality of wind element sub-data, wherein the wind element sub-data includes at least wind direction, and the wind element sub-data also includes at least one of the following: wind speed, precipitation, temperature, humidity, air pressure, and light intensity; Calculate the wind direction difference between the wind direction in the first wind element data and a preset reference wind direction error; the preset reference wind direction error includes: a first average value of the wind direction difference between the wind direction in the wind element data of the meteorological forecast for multiple second time periods of the point to be corrected and the historical measured wind direction of each second time period of the point to be corrected; the second time period is earlier than the first time period; The wind direction in the first wind element data is replaced by the calculated wind direction difference to obtain the second wind element data of the weather forecast for the first time period of the point to be corrected; Based on the random forest algorithm, in the second wind element data, wind element sub-data related to the wind direction is determined; Inputting the wind element sub-data related to the wind direction into a meteorological forecast wind element data correction model based on data decomposition, wherein the meteorological forecast wind element data correction model based on data decomposition includes a plurality of wind element data correction sub-models, each of which processes the wind element sub-data related to the wind direction respectively to obtain a respective output wind direction correction component, and then obtaining a corrected wind direction of the first time period of the point to be corrected according to the respective output wind direction correction components; Wherein, the meteorological forecast wind element data correction model based on data decomposition is obtained by training through the method as claimed in claim 8.

10. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method according to any one of claims 1 to 5 and 8 to 9 when executed by the processor.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 and 8 to 9 is implemented.

Images