Weather forecast wind element data correction method and device based on spatial correlation

Abstract

The invention provides a weather forecast wind element data correction method and device based on spatial correlation. The wind element sub-data related to the wind speed, the real wind speed of the adjacent point position of the to-be-corrected point position in the first time period, the real wind speed of the upwind direction point position of the to-be-corrected point position in the first time period and the real wind speed of the to-be-corrected point position in the second time period are acquired; inputting the data into a weather forecast wind element data correction model based on spatial correlation; the weather forecast wind element data correction model based on the spatial correlation is used for correcting the real wind speed of the wind element sub-data related to the wind speed and the point position adjacent to the point position to be corrected in the first time period; processing the real wind speed of the upwind point of the to-be-corrected point in the first time period and the real wind speed of the to-be-corrected point in the second time period to obtain the corrected wind speed of the to-be-corrected point in the first time period; the accuracy of wind speed correction of weather forecast can be improved.

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 spatial correlation. 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 meteorological forecast wind element data based on spatial correlation.

[0005] In a first aspect, the present application shows a method for training a meteorological forecast wind element data correction model based on spatial correlation, the method comprising: Get the training dataset; The training data set includes multiple training data; The training data includes: sample data and labeled data; The sample data includes: wind element sub-data related to wind speed determined in the wind element data of the meteorological forecast at the sample point in the first historical time period based on the random forest algorithm, the real wind speed of the adjacent point of the sample point in the first historical time period, the real wind speed of the upwind point of the sample point in the first historical time period, and the real wind speed of the sample point in the second historical time period; The second historical time period is earlier than the first historical time period, and the second historical time period and the first historical time period are adjacent time periods; The 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; The annotated data include: the actual wind speed of the sample point in the first historical time period; Construct the network structure of the model to be trained; The model to be trained is trained according to the training data until the network parameters in the model to be trained converge, thereby obtaining a meteorological forecast wind element data correction model based on spatial correlation.

[0006] In a second aspect, the present application shows a method for correcting meteorological forecast wind element data based on spatial correlation, the method comprising: Obtaining the wind element data of the meteorological forecast for the point to be corrected in the first time period, the corrected wind speed of the adjacent point to be corrected in the first time period, the corrected wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period; The second time period is earlier than the first time period, and the second time period and the first time period are adjacent time periods; the 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; Based on the random forest algorithm, determine the wind element sub-data related to the wind speed in the wind element data of the meteorological forecast for the point to be corrected in the first time period; Input the wind element sub-data related to wind speed, the real wind speed of the adjacent point to be corrected in the first time period, the real wind speed of the upwind point of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period into the meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to wind speed, the real wind speed of the adjacent point to be corrected in the first time period, the real wind speed of the upwind point of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period to obtain the corrected wind speed of the point to be corrected in the first time period; Among them, the meteorological forecast wind element data correction model based on spatial correlation 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 meteorological forecast wind element data correction model based on spatial correlation, the device comprising: A first acquisition module is used to acquire a training data set; The training data set includes multiple training data; The training data includes: sample data and labeled data; The sample data includes: wind element sub-data related to wind speed determined in the wind element data of the meteorological forecast at the sample point in the first historical time period based on the random forest algorithm, the real wind speed of the adjacent point of the sample point in the first historical time period, the real wind speed of the upwind point of the sample point in the first historical time period, and the real wind speed of the sample point in the second historical time period; The second historical time period is earlier than the first historical time period, and the second historical time period and the first historical time period are adjacent time periods; The 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; The annotated data include: the actual wind speed of the sample point in the first historical time period; Construction module, used to build the network structure of the model to be trained; The training module is used to train the model to be trained according to the training data until the network parameters in the model to be trained converge, so as to obtain a meteorological forecast wind element data correction model based on spatial correlation.

[0008] In a fourth aspect, the present application shows a weather forecast wind element data correction device based on spatial correlation, the device comprising: The second acquisition module is used to obtain the wind element data of the meteorological forecast of the point to be corrected in the first time period, the corrected wind speed of the adjacent point to be corrected in the first time period, the corrected wind speed of the upwind point of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period; The second time period is earlier than the first time period, and the second time period and the first time period are adjacent time periods; the 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; A determination module, for determining wind element sub-data related to wind speed in the wind element data of the meteorological forecast for the point to be corrected in the first time period based on a random forest algorithm; a processing module, for inputting wind element sub-data related to wind speed, the real wind speed of a point adjacent to the point to be corrected in the first time period, the real wind speed of a point upwind of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period into a meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to wind speed, the real wind speed of a point adjacent to the point to be corrected in the first time period, the real wind speed of a point upwind of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period to obtain a corrected wind speed of the point to be corrected in the first time period; Among them, the meteorological forecast wind element data correction model based on spatial correlation is trained by any one of the methods described in the first aspect.

[0009] Alternatively, the meteorological forecast wind element data correction model based on spatial correlation is obtained by training with 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 the meteorological forecast wind factor data correction model based on spatial correlation, the present application additionally uses the real wind speed of the adjacent points of a point in the first historical time period, the real wind speed of the upwind point of the point in the first historical time period, and the real wind speed of the point in the second historical time period. The second historical time period is earlier than the first historical time period, and the second historical time period is adjacent to the first historical time period.

[0014] The correction model can learn the influence of the real wind speed of the adjacent points of the point in the first historical time period on the real wind speed of the point in the first historical time period. Since the wind speeds of adjacent points in an area often have a certain relationship, for example, are relatively close, the difference between the wind speeds of adjacent points in an area is often not large. Therefore, by considering the influence of the real wind speed of the adjacent points of the point in the first historical time period on the real wind speed of the point in the first historical time period, the accuracy of the meteorological forecast wind element data correction model based on spatial correlation on the wind speed correction of the meteorological forecast can be improved.

[0015] Also, the correction model can learn the influence of the real wind speed of the upwind point of the point in the first historical time period on the real wind speed of the point in the first historical time period. Since the wind first passes through the upwind point of the point and then passes through the point, the upwind point of the point will absorb part of the wind energy, for example, it may reduce the wind speed, etc. In this way, by considering the influence of the real wind speed of the upwind point of the point in the first historical time period on the real wind speed of the point in the first historical time period, the accuracy of the wind speed correction of the meteorological forecast based on spatial correlation wind element data correction model can be improved.

[0016] Secondly, the correction model can learn the influence of the real wind speed of the point in the second historical time period on the real wind speed of the point in the first historical time period. Since the wind speed of a point in multiple consecutive time periods is often stable, especially the wind speed in two adjacent time periods is often stable and generally does not change significantly, therefore, by considering the influence of the real wind speed of the point in the second historical time period on the real wind speed of the point in the first historical time period, the accuracy of the wind speed correction of the meteorological forecast based on spatial correlation The wind element data correction model of the meteorological forecast can be improved.

[0017] In this way, when it is necessary to correct the wind speed of the point to be corrected in the first time period, the wind element sub-data related to the wind speed in the wind element data of the meteorological forecast for the point to be corrected in the first time period, the actual wind speed of the adjacent points of the point to be corrected in the first time period, the actual wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period can be input into the meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to the wind speed, the actual wind speed of the adjacent points of the point to be corrected in the first time period, the actual wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period to obtain the corrected wind speed of the point to be corrected in the first time period; the accuracy of wind speed correction in the meteorological forecast can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of the steps of a method for training a meteorological forecast wind element data correction model based on spatial correlation in the present application.

[0019] Figure 2 It is a flowchart of the processing process of a random forest algorithm of the present application.

[0020] Figure 3 It is a schematic diagram of the network structure of a model of the present application.

[0021] Figure 4 It is a schematic diagram of the network structure of a model of the present application.

[0022] Figure 5 It is a flowchart of the steps of a method for testing a meteorological forecast wind element data correction model based on spatial correlation in the present application.

[0023] Figure 6 This is a flowchart of the steps of a method for correcting meteorological forecast wind element data based on spatial correlation in the present application.

[0024] Figure 7It is a structural block diagram of a device for training a meteorological forecast wind element data correction model based on spatial correlation in the present application.

[0025] Figure 8 This is a structural block diagram of a weather forecast wind element data correction device based on spatial correlation in the present application.

[0026] Fig. 9 It is a block diagram of an electronic device of the present application.

[0027] Fig.10 It is a block diagram of an electronic device of the present application. DETAILED DESCRIPTION

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Therefore, in order to improve the accuracy of wind speed correction, this application is proposed.

[0033] Reference Figure 1 , shows a flowchart of the steps of a method for training a meteorological forecast wind element data correction model based on spatial correlation in 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, a training data set is obtained. The training data set includes a plurality of training data. The training data includes: sample data and annotated data. The sample data includes: wind element sub-data related to wind speed determined in the wind element data of the meteorological forecast at the sample point in the first historical time period based on the random forest algorithm, the real wind speed of the adjacent point of the sample point in the first historical time period, the real wind speed of the upwind point of the sample point in the first historical time period, and the real wind speed of the sample point in the second historical time period. The second historical time period is earlier than the first historical time period, and the second historical time period is an adjacent time period to the first historical time period.

[0034] If the wind passes through a certain point first and then passes through the sample point, the certain point can be the upwind point of the sample point, and the sample point is the downwind point of the certain point. The wind passes through the upwind point of the sample point first and then passes through the sample point.

[0035] If there are other points between a certain point and the sample point, then the certain point is not an adjacent point of the sample point.

[0036] Alternatively, if there is no other point between a certain point and the sample point, then the certain point is an adjacent point of the sample point.

[0037] Alternatively, if a certain point and the sample point share a portion of the boundary, then the certain point is a neighboring point of the sample point.

[0038] The wind element data includes a plurality of wind element sub-data, and 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.

[0039] The annotated data includes: the actual wind speed of the sample point in the first historical time period.

[0040] The wind element sub-data may be the 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 and the like.

[0041] 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.

[0042] 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.

[0043] The wind element data of the meteorological forecast for the first historical time period can be understood as: the wind element data for the first historical time period given by the weather forecast model (WRF model) in the historical process.

[0044] The true wind speed of the sample point in the first historical time period can include the measured wind speeds at each altitude layer of the sample point in the first historical time period. The altitude layers of the wind speed can be 100 meters, 90 meters, 80 meters, 70 meters, 60 meters, and other altitude layers, etc. The value range of the wind speed is usually 0 - 50 m / s, etc.

[0045] The true wind speed of the sample point in the first historical time period can be obtained through a wind measurement tower or a lidar wind measurement device, and it is the real data in the historical process. For example, The duration of the first historical time period and the duration of the second historical time period can be the same. For example, it can be 15 minutes, etc.

[0046] The wind element sub - data related to the wind speed includes at least the wind speed, etc.

[0047] Among them, the wind element sub - data related to the wind speed is obtained through the following method: The wind element data of the meteorological forecast for the sample point in the first historical time period can be obtained, and then based on the random forest algorithm, the correlation degree between each wind element sub - data in the wind element data of the meteorological forecast for the sample point in the first historical time period and the wind speed is determined. Then, the TOP - N wind element sub - data with the highest correlation degree with the wind speed are selected, where N is a positive integer.

[0048] In this step, using the random forest algorithm can extract the wind element sub - data with a high correlation degree with the wind speed from each wind element sub - data in the wind element data of the meteorological forecast for the sample point in the first historical time period.

[0049] The random forest algorithm is an algorithm that integrates multiple trees through the idea of ensemble learning.

[0050] 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).

[0051] (1) Assume that the sample feature dimension is M, and the constant m << M. Randomly select m feature subsets from the M features as the attribute set for the current decision tree split.

[0052] (2) Each time the i-th tree splits, the best variable and split point are selected from the m features, and each tree grows to the maximum extent (excluding pruning), thereby generating a decision tree T i .

[0053] (3) The generated n tree The trees form a random forest, and its output is determined by the voting mechanism of the tree classifiers.

[0054] Secondly, calculate the OOB data error, assuming that the training set size is N total .

[0055] for i =1 to i =n tree .

[0056] (1) For decision tree T i , bootstrapping sampling is used to obtain N from the training set i The samples are used as the training set of the tree, and the unextracted data form the OOB data set N b_i . N i <N total .

[0057] 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).

[0058] (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 .

[0059] 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 dataset N b_i_k The calculation result is recorded as E i_k .

[0060] Then, calculate the importance D of feature k k , as shown in the following relationship:

[0061] 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.

[0062] Further, according to the processing process of the random forest algorithm, the correlation between each wind element sub-data in the wind element data of the meteorological forecast of the sample point in the first historical time period and the wind speed can be calculated, that is, the importance of each wind element sub-data in the wind element data of the meteorological forecast of the sample point in the first historical time period 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 wind element data of the meteorological forecast of the sample point in the first historical time period. N is a positive integer.

[0063] 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 historical meteorological forecast.

[0064] In this embodiment, the wind element data of the meteorological forecast for the sample point in the first historical time period are processed by the random forest algorithm, and the wind element sub-data that are not suitable for training the meteorological forecast wind element data correction model based on spatial correlation are eliminated, and the wind element sub-data that are suitable for training the meteorological forecast wind element data correction model based on spatial correlation are retained, which can improve the efficiency of training the meteorological forecast wind element data correction model based on spatial correlation and the correction accuracy.

[0065] In step S102, a network structure of a model to be trained is constructed.

[0066] In one embodiment of the present application, see Figure 3 ,The network structures of the models to be trained include: unsupervised learning networks and integrated learning networks.

[0067] The input of the model to be trained includes the input of the unsupervised learning network.

[0068] The output of the unsupervised learning network is connected to the input of the ensemble learning network.

[0069] The output end of the model to be trained includes the output end of the integrated learning network.

[0070] Among them, the output end of the integrated learning network is used to output the corrected wind speed.

[0071] The unsupervised learning network is used to extract the first feature of wind speed in the wind element sub-data related to wind speed, the second feature of other wind element sub-data except wind speed in the wind element sub-data related to wind speed, the third feature of the true wind speed of the adjacent points of the sample point in the first historical time period, the fourth feature of the true wind speed of the upwind point of the sample point in the first historical time period, and the fifth feature of the true wind speed of the sample point in the second historical time period.

[0072] The first feature, the second feature, the third feature, the fourth feature, and the fifth feature can be represented by vectors, respectively.

[0073] The first feature of the wind speed in the wind element sub-data related to the wind speed can reflect the characteristics of the wind speed in the wind element sub-data related to the wind speed.

[0074] The second feature of the other wind element sub-data except the wind speed in the wind element sub-data related to wind speed can reflect the characteristics of the other wind element sub-data except the wind speed in the wind element sub-data related to wind speed.

[0075] The third feature of the real wind speed of the adjacent points of the sample point in the first historical time period can reflect the characteristics of the real wind speed of the adjacent points of the sample point in the first historical time period.

[0076] The fourth feature of the actual wind speed of the upwind point of the sample point in the first historical time period can reflect the characteristics of the actual wind speed of the upwind point of the sample point in the first historical time period.

[0077] The fifth feature of the actual wind speed of the sample point in the second historical time period can reflect the characteristics of the actual wind speed of the sample point in the second historical time period.

[0078] The integrated learning network is used to process the first feature according to the second feature, the third feature, the fourth feature and the fifth feature to obtain the corrected wind speed of the sample point in the first historical time period.

[0079] In one embodiment, the integrated learning network is specifically used to learn the first correlation between the second feature and the first feature, to learn the second correlation between the third feature and the first feature, to learn the third correlation between the fourth feature and the first feature, and to learn the fourth correlation between the fifth feature and the first feature. Then, the first feature is processed according to the first correlation, the second correlation, the third correlation, and the fourth correlation to obtain the corrected wind speed of the sample point in the first historical time period.

[0080] The association relationship between features may include a dependency relationship and / or a mutual influence relationship between features.

[0081] Among them, the integrated learning network can include: GBDT (Gradient Boosting Decision Tree), ADABOOST (Adaptive Boosting, an iterative algorithm), XGBOOST (eXtreme GradientBoosting, extreme gradient boosting tree), LIGHTGBM (Light Gradient Boosting Machine, a machine learning algorithm), etc.

[0082] 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.

[0083] Integrated learning networks can also include: long short-term memory networks or deep belief networks, etc.

[0084] The restricted Boltzmann machine in the deep belief network can extract the correlation between different features.

[0085] The Long Short-Term Memory Network is a special type of recurrent neural network (RNN) that effectively processes long-term dependencies in sequence data by introducing "gate" structures and "cell states", thereby being able to extract the correlation between features.

[0086] 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 k 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 k, which can be determined according to actual conditions, for example, 2, 3, 4 or 5.

[0087] Among them, the k 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 k 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.

[0088] Unsupervised learning sub-models may include: RBM (Restricted Boltzmann Machines) or AE (Auto Encoders), etc.

[0089] RBM is an energy-based unsupervised learning model that extracts features of input data by building connections between visible layers (input layers) and hidden layers.

[0090] The visible layer contains the features or observations of the input data. Each neuron in the visible layer corresponds to a dimension of the input data and directly receives and represents the input data.

[0091] The hidden layer is the core of RBM, which contains a set of feature detectors or hidden features to capture high-order features and associations in the input data. The neurons in the hidden layer are not directly connected to the input data, but are connected to the visible layer through weights.

[0092] RBM captures features in data by learning the joint distribution of data. During the training process, RBM adjusts weights and bias terms so that the model can generate samples with similar distribution to the training data. Through the energy function, RBM can calculate the state distribution of the hidden layer given the visible layer state (that is, the probability distribution of the hidden layer features), and the state distribution of the visible layer given the hidden layer state. This conditional probability distribution is the basis for RBM to extract features. The state of the hidden layer neurons can be regarded as a feature representation of the input data. During the training process, the hidden layer neurons will gradually learn the important features of the input data.

[0093] AE has an encoder and a decoder.

[0094] The encoder is responsible for compressing the input data into a low-dimensional feature vector. The final output of the encoder is the feature vector, which contains the important features of the input data. This feature vector is an efficient representation of the input data and contains important information about the input data.

[0095] The decoder is responsible for reconstructing the output of the encoder (i.e., the low-dimensional feature vector) into an approximate representation of the original data.

[0096] The encoder structure can be a multilayer perceptron (MLP) or a convolutional neural network.

[0097] MLP is a feed-forward artificial neural network consisting of an input layer, one or more hidden layers, and an output layer. Each layer of neurons receives the output from the neurons in the previous layer, calculates its own output, and then passes it to the next layer.

[0098] Input layer: receives input data. For example, if the input data is a vector x = [x1, x2, …, xn], then the input layer has n nodes, each corresponding to a feature. Hidden layer: contains one or more layers of neurons. Each neuron receives the output from the previous layer, weighted sums it, and then applies a nonlinear activation function. The existence of hidden layers enables MLP to learn complex nonlinear mapping relationships, thereby extracting high-level features from the input data.

[0099] In step S103, the model to be trained is trained according to the training data until the network parameters in the model to be trained converge, thereby obtaining a meteorological forecast wind element data correction model based on spatial correlation.

[0100] In one embodiment of the present application, this step can be implemented through the following process, including: 1031. Based on the model to be trained, the wind element data related to wind speed, the actual wind speed of the adjacent points of the sample point in the first historical time period, the actual wind speed of the upwind point of the sample point in the first historical time period, and the actual wind speed of the sample point in the second historical time period are processed to obtain the corrected wind speed of the sample point in the first historical time period.

[0101] 1032. Obtain a wind speed loss value according to the corrected wind speed of the sample point in the first historical time period and the actual wind speed of the sample point in the first historical time period.

[0102] In one embodiment, the wind speed loss value may be calculated according to the corrected wind speed of the sample point in the first historical time period and the actual wind speed of the sample point in the first historical time period according to the following formula:

[0103] The above formula is the wind speed loss function. In the above formula, error is the wind speed loss value, V 1 is the corrected wind speed of the sample point in the first historical period, V 2 It is the actual wind speed of the sample point in the first historical time period.

[0104] 1034. According to the wind speed loss value, the network parameters in the training model are adjusted.

[0105] When training the meteorological forecast wind factor data correction model based on spatial correlation, the present application additionally uses the real wind speed of the adjacent points of a point in the first historical time period, the real wind speed of the upwind point of the point in the first historical time period, and the real wind speed of the point in the second historical time period. The second historical time period is earlier than the first historical time period, and the second historical time period is adjacent to the first historical time period.

[0106] The correction model can learn the influence of the real wind speed of the adjacent points of the point in the first historical time period on the real wind speed of the point in the first historical time period. Since the wind speeds of adjacent points in an area often have a certain relationship, for example, are relatively close, the difference between the wind speeds of adjacent points in an area is often not large. Therefore, by considering the influence of the real wind speed of the adjacent points of the point in the first historical time period on the real wind speed of the point in the first historical time period, the accuracy of the meteorological forecast wind element data correction model based on spatial correlation on the wind speed correction of the meteorological forecast can be improved.

[0107] Also, the correction model can learn the influence of the real wind speed of the upwind point of the point in the first historical time period on the real wind speed of the point in the first historical time period. Since the wind first passes through the upwind point of the point and then passes through the point, the upwind point of the point will absorb part of the wind energy, for example, it may reduce the wind speed, etc. In this way, by considering the influence of the real wind speed of the upwind point of the point in the first historical time period on the real wind speed of the point in the first historical time period, the accuracy of the wind speed correction of the meteorological forecast based on spatial correlation wind element data correction model can be improved.

[0108] Secondly, the correction model can learn the influence of the real wind speed of the point in the second historical time period on the real wind speed of the point in the first historical time period. Since the wind speed of a point in multiple consecutive time periods is often stable, especially the wind speed in two adjacent time periods is often stable and generally does not change significantly, therefore, by considering the influence of the real wind speed of the point in the second historical time period on the real wind speed of the point in the first historical time period, the accuracy of the wind speed correction of the meteorological forecast based on spatial correlation The wind element data correction model of the meteorological forecast can be improved.

[0109] Furthermore, after the meteorological forecast wind element data correction model based on spatial correlation is obtained through training, the meteorological forecast wind element data correction model based on spatial correlation can be tested.

[0110] For example, see Figure 5 , the specific steps include: In step S201, the wind element data of the weather forecast for the test point in the first historical time period, the corrected wind speed of the adjacent points of the test point in the first historical time period, the corrected wind speed of the upwind point of the test point in the first historical time period and the actual wind speed of the test point in the second historical time period are obtained.

[0111] The second historical time period is earlier than the first historical time period, and the second historical time period and the first historical time period are adjacent historical time periods. The wind element data includes a plurality of wind element sub-data, the wind element sub-data at least includes 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.

[0112] 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.

[0113] For details of this step, please refer to the description of step S101.

[0114] In step S202, based on the random forest algorithm, wind element sub-data related to wind speed are determined in the wind element data of the meteorological forecast at the test point in the first historical time period.

[0115] For details of this step, please refer to the description of step S101.

[0116] In step S203, the wind element sub-data related to wind speed, the actual wind speed of the adjacent points of the test point in the first historical time period, the actual wind speed of the upwind point of the test point in the first historical time period, and the actual wind speed of the test point in the second historical time period are input into the meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to wind speed, the actual wind speed of the adjacent points of the test point in the first historical time period, the actual wind speed of the upwind point of the test point in the first historical time period, and the actual wind speed of the test point in the second historical time period to obtain the corrected wind speed of the test point in the first historical time period.

[0117] In step S204, the actual wind speed of the test point in the first historical time period is obtained.

[0118] For details of this step, please refer to the description of step S101.

[0119] In step S205, a wind speed error index is calculated based on the corrected wind speed of the test point in the first historical time period and the actual wind speed of the test point in the first historical time period.

[0120] 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.

[0121] 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).

[0122] For example, the wind speed error index can be calculated based on the corrected wind speed of the test point in the first historical time period and the actual wind speed of the test point in the first historical time period, for example, the wind speed error index is calculated by the mean absolute error MAE, the root mean square error RMSE or the determination coefficient R2.

[0123] 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 spatial correlation, and the accuracy of the wind speed correction of the meteorological forecast wind element data correction model based on spatial correlation can be evaluated. After the accuracy of the wind speed correction meets the requirements, the meteorological forecast wind element data correction model based on spatial correlation can be put into online application.

[0124] For example, the wind speed in the weather forecast is corrected using a weather forecast wind element data correction model based on spatial correlation.

[0125] For example, refer to Figure 6 , shows a flow chart of the steps of a method for correcting meteorological forecast wind element data based on spatial correlation 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 wind element data of the meteorological forecast for the point to be corrected in the first time period, the corrected wind speed of the adjacent point to be corrected in the first time period, the corrected wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period are obtained.

[0126] The second time period is earlier than the first time period, and the second time period and the first time period are adjacent time periods. The wind element data includes a plurality of wind element sub-data, the wind element sub-data at least includes 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.

[0127] The duration of the first time period may be the same as the duration of the second time period, for example, 15 minutes.

[0128] The first time period may be the time period of the current moment, and the second time period may be the time period after the time period of the current moment, for example, the second time period may be the time period after the time period of the current moment and adjacent to the time period of the current moment.

[0129] For details of this step, please refer to the description of step S101.

[0130] In step S302, based on the random forest algorithm, wind element sub-data related to wind speed are determined from the wind element data of the weather forecast for the point to be corrected in the first time period.

[0131] For details of this step, please refer to the description of step S101.

[0132] In step S303, the wind element sub-data related to wind speed, the actual wind speed of the adjacent points to be corrected in the first time period, the actual wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period are input into the meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to wind speed, the actual wind speed of the adjacent points to be corrected in the first time period, the actual wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period to obtain the corrected wind speed of the point to be corrected in the first time period.

[0133] When it is necessary to correct the wind speed of the point to be corrected in the first time period, the wind element sub-data related to the wind speed in the wind element data of the meteorological forecast for the point to be corrected in the first time period, the actual wind speed of the adjacent points of the point to be corrected in the first time period, the actual wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period can be input into a meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to the wind speed, the actual wind speed of the adjacent points of the point to be corrected in the first time period, the actual wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period to obtain the corrected wind speed of the point to be corrected in the first time period; the accuracy of wind speed correction in the meteorological forecast can be improved.

[0134] Another embodiment of the present application provides a method for training a meteorological forecast wind element data correction model based on spatial correlation, including: obtaining a training data set; the training data set includes multiple training data; the training data includes: sample data and labeled data; the sample data includes: wind element sub-data related to wind direction determined in the wind element data of the meteorological forecast at the sample point in the first historical time period based on the random forest algorithm, the true wind direction of the adjacent points of the sample point in the first historical time period, the true wind direction of the upwind point of the sample point in the first historical time period, and the true wind direction of the sample point in the second historical time period wind direction; the second historical time period is earlier than the first historical time period, and the second historical time period and the first historical time period are adjacent time periods; the wind element data includes multiple wind element sub-data, 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; the annotated data includes: the actual wind direction of the sample point in the first historical time period; construct the network structure of the model to be trained; according to the training data, train the model to be trained until the network parameters in the model to be trained converge, so as to obtain a meteorological forecast wind element data correction model based on spatial correlation.

[0135] The specific explanation of this embodiment can be found in the description of the aforementioned embodiment and will not be elaborated here.

[0136] 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 spatial correlation is also provided, which obtains the meteorological forecast wind element data of the point to be corrected in the first time period, the corrected wind direction of the adjacent point to be corrected in the first time period, the corrected wind direction of the upwind point of the point to be corrected in the first time period, and the real wind direction of the point to be corrected in the second time period; the second time period is earlier than the first time period, and the second time period is adjacent to the first time period; the wind element data includes a plurality of wind element sub-data, the wind element sub-data at least includes 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; based on the random forest algorithm, the wind element data is corrected at the point to be corrected in the first time period. In the wind element data of the meteorological forecast for the first time period, wind element sub-data related to wind direction are determined; the wind element sub-data related to wind direction, the true wind direction of the adjacent points of the point to be corrected in the first time period, the true wind direction of the upwind point of the point to be corrected in the first time period, and the true wind direction of the point to be corrected in the second time period are input into a meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to wind direction, the true wind direction of the adjacent points of the point to be corrected in the first time period, the true wind direction of the upwind point of the point to be corrected in the first time period, and the true wind direction of the point to be corrected in the second time period to obtain the corrected wind direction of the point to be corrected in the first time period.

[0137] The specific explanation of this embodiment can be found in the description of the aforementioned embodiment and will not be elaborated here.

[0138] When training a meteorological forecast wind element data correction model based on spatial correlation, the present application additionally uses the actual wind direction of an adjacent point of a point in the first historical time period, the actual wind direction of the upwind point of the point in the first historical time period, and the actual wind direction of the point in the second historical time period.

[0139] The correction model can learn the influence of the real wind direction of the adjacent points of the point in the first historical time period on the real wind direction of the point in the first historical time period. Since the wind directions of adjacent points in an area often have a certain relationship, for example, are relatively close, the difference between the wind directions of adjacent points in an area is often not large. Therefore, by considering the influence of the real wind direction of the adjacent points of the point in the first historical time period on the real wind direction of the point in the first historical time period, the accuracy of the meteorological forecast wind direction correction model based on spatial correlation can be improved.

[0140] Also, the correction model can learn the influence of the real wind direction of the upwind point of the point in the first historical time period on the real wind direction of the point in the first historical time period. Since the wind first passes through the upwind point of the point and then passes through the point, the upwind point of the point will absorb part of the wind energy, for example, it may reduce the wind direction, etc. In this way, by considering the influence of the real wind direction of the upwind point of the point in the first historical time period on the real wind direction of the point in the first historical time period, the accuracy of the meteorological forecast wind direction correction model based on spatial correlation can be improved.

[0141] Secondly, the correction model can learn the influence of the real wind direction of the point in the second historical time period on the real wind direction of the point in the first historical time period. Since the wind direction of a point in multiple consecutive time periods is often stable, especially the wind direction of two adjacent time periods is often stable and generally does not change significantly, therefore, by considering the influence of the real wind direction of the point in the second historical time period on the real wind direction of the point in the first historical time period, the accuracy of the meteorological forecast wind direction correction model based on spatial correlation can be improved.

[0142] In this way, when it is necessary to correct the wind direction of the point to be corrected in the first time period, the wind element sub-data related to the wind direction, the true wind direction of the adjacent points of the point to be corrected in the first time period, the true wind direction of the upwind point of the point to be corrected in the first time period, and the true wind direction of the point to be corrected in the second time period can be input into the meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to the wind direction, the true wind direction of the adjacent points of the point to be corrected in the first time period, the true wind direction of the upwind point of the point to be corrected in the first time period, and the true wind direction of the point to be corrected in the second time period to obtain the corrected wind direction of the point to be corrected in the first time period; the accuracy of the correction of the meteorological forecast wind direction can be improved.

[0143] 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.

[0144] Reference Figure 7, shows a structural block diagram of a device for training a meteorological forecast wind element data correction model based on spatial correlation in the present application, the device comprising: A first acquisition module 11 is used to acquire a training data set; The training data set includes multiple training data; The training data includes: sample data and labeled data; The sample data includes: wind element sub-data related to wind speed determined in the wind element data of the meteorological forecast at the sample point in the first historical time period based on the random forest algorithm, the real wind speed of the adjacent point of the sample point in the first historical time period, the real wind speed of the upwind point of the sample point in the first historical time period, and the real wind speed of the sample point in the second historical time period; The second historical time period is earlier than the first historical time period, and the second historical time period and the first historical time period are adjacent time periods; The 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; The annotated data include: the actual wind speed of the sample point in the first historical time period; A construction module 12 is used to construct a network structure of a model to be trained; The training module 13 is used to train the model to be trained according to the training data until the network parameters in the model to be trained converge, thereby obtaining a meteorological forecast wind element data correction model based on spatial correlation.

[0145] In an optional implementation, the training module includes: A processing unit is used to process the wind element sub-data related to the wind speed, the real wind speed of the adjacent points of the sample point in the first historical time period, the real wind speed of the upwind point of the sample point in the first historical time period, and the real wind speed of the sample point in the second historical time period based on the to-be-trained model, so as to obtain the corrected wind speed of the sample point in the first historical time period; A first acquisition unit is used to acquire a wind speed loss value according to a corrected wind speed of the sample point in the first historical time period and a real wind speed of the sample point in the first historical time period; The adjustment unit is used to adjust the network parameters in the training model according to the wind speed loss value.

[0146] In an optional implementation, the first acquisition module includes: A second acquisition unit is used to acquire wind element data of the meteorological forecast of the sample point in the first historical time period; A determination unit, configured to determine, based on a random forest algorithm, the degree of correlation between each wind element sub-data in the wind element data of the meteorological forecast for the sample point in the first historical time period and the wind speed; The selection unit is used to select the TOP-N wind element sub-data with the greatest correlation with the wind speed, where N is a positive integer.

[0147] In an optional implementation, the network structure of the model to be trained includes: an unsupervised learning network and an integrated learning network; The unsupervised learning network is used to extract a first feature of wind speed in wind element sub-data related to wind speed, a second feature of other wind element sub-data other than wind speed in the wind element sub-data related to wind speed, a third feature of the real wind speed of a point adjacent to the sample point in the first historical time period, a fourth feature of the real wind speed of an upwind point of the sample point in the first historical time period, and a fifth feature of the real wind speed of the sample point in the second historical time period; The integrated learning network is used to process the first feature according to the second feature, the third feature, the fourth feature and the fifth feature to obtain the corrected wind speed of the sample point in the first historical time period.

[0148] In an optional implementation, the unsupervised learning network includes a plurality of unsupervised learning sub-models connected in series.

[0149] In an optional implementation, the integrated learning network is specifically used to learn the first correlation between the second feature and the first feature, to learn the second correlation between the third feature and the first feature, to learn the third correlation between the fourth feature and the first feature, and to learn the fourth correlation between the fifth feature and the first feature; then, it is used to process the first feature according to the first correlation, the second correlation, the third correlation and the fourth correlation to obtain the corrected wind speed of the sample point in the first historical time period.

[0150] When training the meteorological forecast wind factor data correction model based on spatial correlation, the present application additionally uses the real wind speed of the adjacent points of a point in the first historical time period, the real wind speed of the upwind point of the point in the first historical time period, and the real wind speed of the point in the second historical time period. The second historical time period is earlier than the first historical time period, and the second historical time period is adjacent to the first historical time period.

[0151] The correction model can learn the influence of the real wind speed of the adjacent points of the point in the first historical time period on the real wind speed of the point in the first historical time period. Since the wind speeds of adjacent points in an area often have a certain relationship, for example, are relatively close, the difference between the wind speeds of adjacent points in an area is often not large. Therefore, by considering the influence of the real wind speed of the adjacent points of the point in the first historical time period on the real wind speed of the point in the first historical time period, the accuracy of the meteorological forecast wind element data correction model based on spatial correlation on the wind speed correction of the meteorological forecast can be improved.

[0152] Also, the correction model can learn the influence of the real wind speed of the upwind point of the point in the first historical time period on the real wind speed of the point in the first historical time period. Since the wind first passes through the upwind point of the point and then passes through the point, the upwind point of the point will absorb part of the wind energy, for example, it may reduce the wind speed, etc. In this way, by considering the influence of the real wind speed of the upwind point of the point in the first historical time period on the real wind speed of the point in the first historical time period, the accuracy of the wind speed correction of the meteorological forecast based on spatial correlation wind element data correction model can be improved.

[0153] Secondly, the correction model can learn the influence of the real wind speed of the point in the second historical time period on the real wind speed of the point in the first historical time period. Since the wind speed of a point in multiple consecutive time periods is often stable, especially the wind speed in two adjacent time periods is often stable and generally does not change significantly, therefore, by considering the influence of the real wind speed of the point in the second historical time period on the real wind speed of the point in the first historical time period, the accuracy of the wind speed correction of the meteorological forecast based on spatial correlation The wind element data correction model of the meteorological forecast can be improved.

[0154] Reference Figure 8 , shows a structural block diagram of a weather forecast wind element data correction device based on spatial correlation of the present application, the device comprising: The second acquisition module 21 is used to obtain the wind element data of the meteorological forecast of the point to be corrected in the first time period, the corrected wind speed of the adjacent point to be corrected in the first time period, the corrected wind speed of the upwind point of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period; The second time period is earlier than the first time period, and the second time period and the first time period are adjacent time periods; the 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; A determination module 22, configured to determine wind element sub-data related to wind speed in the wind element data of the meteorological forecast for the point to be corrected in the first time period based on a random forest algorithm; The processing module 23 is used to input the wind element sub-data related to the wind speed, the real wind speed of the adjacent point to be corrected in the first time period, the real wind speed of the upwind point of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period into the meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to the wind speed, the real wind speed of the adjacent point to be corrected in the first time period, the real wind speed of the upwind point of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period to obtain the corrected wind speed of the point to be corrected in the first time period; Among them, the meteorological forecast wind factor data correction model based on spatial correlation is as follows Figure 1 obtained by training using any of the methods described above.

[0155] Alternatively, the meteorological forecast wind factor data correction model based on spatial correlation is Figure 7 Obtained by training with any of the above-described devices.

[0156] When it is necessary to correct the wind speed of the point to be corrected in the first time period, the wind element sub-data related to the wind speed in the wind element data of the meteorological forecast for the point to be corrected in the first time period, the actual wind speed of the adjacent points of the point to be corrected in the first time period, the actual wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period can be input into a meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to the wind speed, the actual wind speed of the adjacent points of the point to be corrected in the first time period, the actual wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period to obtain the corrected wind speed of the point to be corrected in the first time period; the accuracy of wind speed correction in the meteorological forecast can be improved.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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 .

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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 meteorological forecast wind factor data correction model based on spatial correlation, characterized in that: The method comprises: Get the training dataset; The training data set includes multiple training data; The training data includes: sample data and labeled data; The sample data includes: wind element sub-data related to wind speed determined in the wind element data of the meteorological forecast at the sample point in the first historical time period based on the random forest algorithm, the real wind speed of the adjacent point of the sample point in the first historical time period, the real wind speed of the upwind point of the sample point in the first historical time period, and the real wind speed of the sample point in the second historical time period; The second historical time period is earlier than the first historical time period, and the second historical time period and the first historical time period are adjacent time periods; The 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; The annotated data include: the actual wind speed of the sample point in the first historical time period; Construct the network structure of the model to be trained; The model to be trained is trained according to the training data until the network parameters in the model to be trained converge, thereby obtaining a meteorological forecast wind element data correction model based on spatial correlation.

2. The method according to claim 1, characterized in that The method of training the model to be trained according to the training data until the network parameters in the model to be trained converge, thereby obtaining a meteorological forecast wind element data correction model based on spatial correlation, includes: Based on the model to be trained, the wind element sub-data related to wind speed, the real wind speed of the adjacent points of the sample point in the first historical time period, the real wind speed of the upwind point of the sample point in the first historical time period, and the real wind speed of the sample point in the second historical time period are processed to obtain the corrected wind speed of the sample point in the first historical time period; Obtaining a wind speed loss value according to the corrected wind speed of the sample point in the first historical time period and the actual wind speed of the sample point in the first historical time period; According to the wind speed loss value, the network parameters in the training model are adjusted.

3. The method according to claim 1, characterized in that The wind element data related to wind speed is obtained in the following way: Obtain wind element data of the meteorological forecast for the sample point in the first historical time period; Based on the random forest algorithm, determine the correlation between each wind element sub-data in the wind element data of the meteorological forecast of the sample point in the first historical time period and the wind speed; Select the TOP-N wind element sub-data with the greatest correlation with wind speed, where N is a positive integer.

4. The method according to claim 1, characterized in that The network structures of the models to be trained include: unsupervised learning networks and integrated learning networks; The unsupervised learning network is used to extract a first feature of wind speed in wind element sub-data related to wind speed, a second feature of other wind element sub-data other than wind speed in the wind element sub-data related to wind speed, a third feature of the real wind speed of a point adjacent to the sample point in the first historical time period, a fourth feature of the real wind speed of an upwind point of the sample point in the first historical time period, and a fifth feature of the real wind speed of the sample point in the second historical time period; The integrated learning network is used to process the first feature according to the second feature, the third feature, the fourth feature and the fifth feature to obtain the corrected wind speed of the sample point in the first historical time period.

5. The method according to claim 4, characterized in that The unsupervised learning network consists of multiple unsupervised learning sub-models connected in series.

6. The method according to claim 4, characterized in that The integrated learning network is specifically used to learn the first correlation between the second feature and the first feature, to learn the second correlation between the third feature and the first feature, to learn the third correlation between the fourth feature and the first feature, and to learn the fourth correlation between the fifth feature and the first feature; then, it is used to process the first feature according to the first correlation, the second correlation, the third correlation and the fourth correlation to obtain the corrected wind speed of the sample point in the first historical time period.

7. A method for correcting meteorological forecast wind element data based on spatial correlation, characterized in that: The method comprises: Obtaining the wind element data of the meteorological forecast for the point to be corrected in the first time period, the corrected wind speed of the adjacent point to be corrected in the first time period, the corrected wind speed of the upwind point of the point to be corrected in the first time period, and the actual wind speed of the point to be corrected in the second time period; The second time period is earlier than the first time period, and the second time period and the first time period are adjacent time periods; the 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; Based on the random forest algorithm, determine the wind element sub-data related to the wind speed in the wind element data of the meteorological forecast for the point to be corrected in the first time period; Input the wind element sub-data related to wind speed, the real wind speed of the adjacent point to be corrected in the first time period, the real wind speed of the upwind point of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period into the meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to wind speed, the real wind speed of the adjacent point to be corrected in the first time period, the real wind speed of the upwind point of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period to obtain the corrected wind speed of the point to be corrected in the first time period; Wherein, the meteorological forecast wind element data correction model based on spatial correlation is obtained by training according to any one of claims 1 to 6.

8. A device for training a meteorological forecast wind factor data correction model based on spatial correlation, characterized in that: The device comprises: A first acquisition module is used to acquire a training data set; The training data set includes multiple training data; The training data includes: sample data and labeled data; The sample data includes: wind element sub-data related to wind speed determined in the wind element data of the meteorological forecast at the sample point in the first historical time period based on the random forest algorithm, the real wind speed of the adjacent point of the sample point in the first historical time period, the real wind speed of the upwind point of the sample point in the first historical time period, and the real wind speed of the sample point in the second historical time period; The second historical time period is earlier than the first historical time period, and the second historical time period and the first historical time period are adjacent time periods; The 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; The annotated data include: the actual wind speed of the sample point in the first historical time period; Construction module, used to build the network structure of the model to be trained; The training module is used to train the model to be trained according to the training data until the network parameters in the model to be trained converge, so as to obtain a meteorological forecast wind element data correction model based on spatial correlation.

9. A weather forecast wind factor data correction device based on spatial correlation, characterized in that: The device comprises: The second acquisition module is used to obtain the wind element data of the meteorological forecast of the point to be corrected in the first time period, the corrected wind speed of the adjacent point to be corrected in the first time period, the corrected wind speed of the upwind point of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period; The second time period is earlier than the first time period, and the second time period and the first time period are adjacent time periods; the 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; A determination module, for determining wind element sub-data related to wind speed in the wind element data of the meteorological forecast for the point to be corrected in the first time period based on a random forest algorithm; a processing module, for inputting wind element sub-data related to wind speed, the real wind speed of a point adjacent to the point to be corrected in the first time period, the real wind speed of a point upwind of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period into a meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to wind speed, the real wind speed of a point adjacent to the point to be corrected in the first time period, the real wind speed of a point upwind of the point to be corrected in the first time period, and the real wind speed of the point to be corrected in the second time period to obtain a corrected wind speed of the point to be corrected in the first time period; Wherein, the meteorological forecast wind element data correction model based on spatial correlation is obtained by training according to any one of claims 1 to 6.

10. A method for training a meteorological forecast wind factor data correction model based on spatial correlation, characterized in that: The method comprises: Get the training dataset; The training data set includes multiple training data; The training data includes: sample data and labeled data; The sample data includes: wind element sub-data related to wind direction determined in the wind element data of the meteorological forecast at the sample point in the first historical time period based on the random forest algorithm, the real wind direction of the adjacent point of the sample point in the first historical time period, the real wind direction of the upwind point of the sample point in the first historical time period, and the real wind direction of the sample point in the second historical time period; The second historical time period is earlier than the first historical time period, and the second historical time period and the first historical time period are adjacent time periods; The wind element data includes a plurality of wind element sub-data, 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; The annotated data include: the actual wind direction of the sample point in the first historical time period; Construct the network structure of the model to be trained; The model to be trained is trained according to the training data until the network parameters in the model to be trained converge, thereby obtaining a meteorological forecast wind element data correction model based on spatial correlation.

11. A method for correcting meteorological forecast wind element data based on spatial correlation, characterized in that: The method comprises: Obtaining the wind element data of the meteorological forecast for the point to be corrected in the first time period, the corrected wind direction of the adjacent point to be corrected in the first time period, the corrected wind direction of the upwind point of the point to be corrected in the first time period, and the real wind direction of the point to be corrected in the second time period; The second time period is earlier than the first time period, and the second time period and the first time period are adjacent time periods; the wind element data includes a plurality of wind element sub-data, 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; Determine wind element sub-data related to wind direction in the wind element data of the meteorological forecast for the point to be corrected in the first time period based on the random forest algorithm; Input the wind element sub-data related to wind direction, the real wind direction of the adjacent point to be corrected in the first time period, the real wind direction of the upwind point of the point to be corrected in the first time period, and the real wind direction of the point to be corrected in the second time period into the meteorological forecast wind element data correction model based on spatial correlation, so that the meteorological forecast wind element data correction model based on spatial correlation processes the wind element sub-data related to wind direction, the real wind direction of the adjacent point to be corrected in the first time period, the real wind direction of the upwind point of the point to be corrected in the first time period, and the real wind direction of the point to be corrected in the second time period to obtain the corrected wind direction of the point to be corrected in the first time period; Wherein, the meteorological forecast wind element data correction model based on spatial correlation is obtained by training through the method as claimed in claim 10.

12. 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 7 and 10 to 11 when executed by the processor.

13. 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 7 and 10 to 11 is implemented.

Images