A wind speed prediction method, device, equipment and medium

Abstract

The present application discloses a wind speed prediction method, device, equipment and medium. Among them, the method obtains at least two sets of initial wind speed prediction data of the target area in a preset time period; wherein the initial wind speed prediction data comes from different data sources, and the initial wind speed prediction data includes wind speed prediction values ​​corresponding to at least two test moments in the preset time period; the initial wind speed prediction data is compared with each standard wind speed meteorological data, and the wind speed meteorological type corresponding to the target area in the preset time period is determined according to the comparison result, and the wind speed prediction model corresponding to the wind speed meteorological type is used as the target wind speed prediction model; based on the target wind speed prediction model, the initial wind speed prediction data is predicted to determine the target wind speed prediction data. This technical solution divides the wind speed meteorological types to achieve accurate optimization of wind speed prediction data from multiple data sources, thereby improving the accuracy and reliability of wind speed prediction.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a wind speed prediction method, device, equipment and medium. Background Art

[0002] Wind speed prediction is of great significance for wind farm management, railway transportation, and disaster warning. However, due to its strong randomness and volatility, wind speed is one of the most complex and difficult to predict elements in weather forecasting.

[0003] At present, for numerical forecasting of wind speed, the classical Fourier signal decomposition algorithm and deep learning time series algorithm are often used to learn the changing patterns of historically observed wind speeds. It has high accuracy and applicability for areas with gentle wind speed changes and simple terrain, but for areas with strong wind speed fluctuations and complex terrain, the model error based on historical wind speed data is large, and the overall forecast trend will show that the longer the forecast period, the greater the forecast wind speed error.

[0004] Therefore, how to provide a technical solution that can optimize wind speed prediction data is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0005] The present application provides a wind speed prediction method, device, equipment and medium, which classifies wind speed meteorological types to achieve accurate optimization of wind speed prediction data from multiple data sources, thereby improving the accuracy and reliability of wind speed prediction.

[0006] According to one aspect of the present application, a wind speed prediction method is provided, the method comprising: obtaining at least two sets of initial wind speed prediction data for a target area in a preset time period; wherein the initial wind speed prediction data come from different data sources, and the initial wind speed prediction data include wind speed prediction values ​​corresponding to at least two test moments in the preset time period; comparing the initial wind speed prediction data with each standard wind speed meteorological data, respectively, determining the wind speed meteorological type corresponding to the target area in the preset time period according to the comparison result, and using the wind speed prediction model corresponding to the wind speed meteorological type as a target wind speed prediction model; wherein the standard wind speed meteorological data, the wind speed meteorological type and the wind speed prediction model have a one-to-one correspondence; based on the target wind speed prediction model, predicting the initial wind speed prediction data, and determining the target wind speed prediction data.

[0007] According to another aspect of the present application, a wind speed prediction device is provided, which includes: a data acquisition module, used to obtain at least two groups of initial wind speed prediction data of a target area in a preset time period; wherein the initial wind speed prediction data comes from different data sources, and the initial wind speed prediction data includes wind speed prediction values ​​corresponding to at least two test moments in the preset time period; a model determination module, used to compare the initial wind speed prediction data with each standard wind speed meteorological data, respectively, determine the wind speed meteorological type corresponding to the target area in the preset time period according to the comparison result, and use the wind speed prediction model corresponding to the wind speed meteorological type as the target wind speed prediction model; wherein the standard wind speed meteorological data, the wind speed meteorological type and the wind speed prediction model have a one-to-one correspondence; a wind speed prediction module, used to predict the initial wind speed prediction data based on the target wind speed prediction model, and determine the target wind speed prediction data.

[0008] According to another aspect of the present application, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the wind speed prediction method described in any embodiment of the present application.

[0009] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the wind speed prediction method described in any embodiment of the present application when executed.

[0010] The technical solution provided by the present application is to obtain at least two sets of initial wind speed prediction data of the target area in a preset time period; wherein the initial wind speed prediction data comes from different data sources, and the initial wind speed prediction data includes wind speed prediction values ​​corresponding to at least two test moments in the preset time period; the initial wind speed prediction data is compared with each standard wind speed meteorological data, and the wind speed meteorological type corresponding to the target area in the preset time period is determined according to the comparison result, and the wind speed prediction model corresponding to the wind speed meteorological type is used as the target wind speed prediction model; based on the target wind speed prediction model, the initial wind speed prediction data is predicted to determine the target wind speed prediction data. The present technical solution divides the wind speed meteorological types to achieve accurate optimization of wind speed prediction data from multiple data sources, thereby improving the accuracy and reliability of wind speed prediction.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A flow chart of a wind speed prediction method provided in Example 1 of the present application.

[0014] Figure 2 A flow chart of a wind speed prediction method provided in Example 2 of the present application.

[0015] Figure 3 This is a flow chart of a wind speed prediction method provided in Example 3 of the present application.

[0016] Figure 4 A schematic diagram of the structure of a wind speed prediction device provided in Example 4 of the present application.

[0017] Figure 5 It is a structural schematic diagram of a device for implementing a wind speed prediction method in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present application.

[0019] It should be noted that the terms "initial", "preset", "target", "to be tested", "candidate", "secondary", "standard", "reference", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] Embodiment 1

[0021] Figure 1 This is a flow chart of a wind speed prediction method provided in the first embodiment of the present application. This embodiment is applicable to the case of optimizing multi-source wind speed forecast data. The method can be executed by a wind speed prediction device. The wind speed prediction device can be implemented in the form of hardware and / or software. The wind speed prediction device can be configured in a device with data processing capabilities. Figure 1 As shown, the method includes the following steps.

[0022] S110, obtaining at least two sets of initial wind speed prediction data of the target area in a preset time period, wherein the initial wind speed prediction data comes from different data sources, and the initial wind speed prediction data includes wind speed prediction values ​​corresponding to at least two test moments in the preset time period.

[0023] The target area may be a geographical range where wind speed forecast optimization is required. The preset time period may be determined according to actual needs.

[0024] The initial wind speed forecast data may be wind speed forecast information of the target area in a preset time period obtained from a data source, wherein the data source may be a website or tool that can publicly obtain wind speed forecast information, such as the European Center for Medium-Range Weather Forecasts, the National Center for Environmental Prediction of the United States, and the Earth System Numerical Prediction Center of the China Meteorological Administration.

[0025] Specifically, a set of initial wind speed prediction data may be wind speed prediction values ​​corresponding to at least two test times within a preset time period. For example, the preset time period is from 19:00 to 23:00, the test times are 19:00, 20:00, 21:00, 22:00 and 23:00, and the wind speed prediction value is meters per second. Then the obtained set of initial wind speed prediction data may be expressed as (2, 3, 3, 4, 3).

[0026] In the present application, by acquiring at least two groups of initial wind speed prediction data from different data sources, the problem of one-sidedness of data from a single data source is avoided.

[0027] S120, comparing the initial wind speed forecast data with each standard wind speed meteorological data, determining the wind speed meteorological type corresponding to the target area in the preset time period according to the comparison result, and using the wind speed forecast model corresponding to the wind speed meteorological type as the target wind speed forecast model. The standard wind speed meteorological data, the wind speed meteorological type and the wind speed forecast model correspond one to one.

[0028] Wind speed meteorological types may be different categories divided according to wind speed, such as light wind, moderate wind, strong wind, etc. Standard wind speed meteorological data may be wind speed data representative of a specific wind speed meteorological type, which may be used to divide wind speed meteorological types. A wind speed prediction model may be a model trained based on wind speed data of the same wind speed meteorological type, such as a wind speed prediction model for a light wind type, a wind speed prediction model for a strong wind type, etc.

[0029] For example, the present application divides wind speed meteorological types into the following eight types: low wind speed meteorological type, medium-low wind speed meteorological type, medium-high wind speed meteorological type, high wind speed meteorological type, uniform wind speed meteorological type, medium wind meteorological type, medium-high wind speed meteorological type and medium-low wind speed meteorological type. The basis for the division is shown in Table 1.

[0030] Table 1

[0031]

[0032] According to the above classification criteria, meteorological forecast data that meet the standards are manually selected from the historical wind speed prediction data and used as standard wind speed meteorological data.

[0033] In the present application, each set of initial wind speed forecast data can be compared with each standard wind speed meteorological data. For example, there are two sets of initial wind speed forecast data A and B, and there are three types of wind speed meteorological data, and their corresponding standard wind speed meteorological data are a, b and c, respectively. Therefore, A can be compared with a, b and c, respectively, and B can be compared with a, b and c, respectively, and the wind speed meteorological type corresponding to the target area in the preset time period can be determined according to each comparison result.

[0034] Among them, the comparison method can be to directly compare the initial wind speed forecast data with the standard wind speed meteorological data; or to perform interval matching; or to compare the deviation between the initial wind speed forecast data and the standard wind speed meteorological data with a preset threshold; or to pre-set that the appearance of each wind speed in the standard wind speed meteorological data follows a certain probability distribution, and by calculating the possibility that the initial wind speed forecast data conforms to each probability distribution, determine the wind speed meteorological type to which it belongs. The embodiment of the present application does not limit this, and the comparison method can be determined according to actual needs.

[0035] Optionally, the process of constructing the wind speed prediction model includes: obtaining historical wind speed prediction data, and dividing the historical wind speed prediction data into at least one training data set based on the standard wind speed meteorological data; for each of the training data sets, using the training data set to train the initial model to obtain a wind speed prediction model corresponding to the wind speed meteorological type.

[0036] The historical wind speed prediction data may be wind speed data predicted by multiple data sources in multiple historical time periods.

[0037] After obtaining the historical wind speed forecast data, it can be screened and standardized. The data screening conditions can be: 1) delete the data with a value of 0 or empty, and remove duplicate data; 2) data with negative values ​​is equivalent to missing value processing; 3) data with a value greater than the maximum limit or less than the minimum limit is equivalent to missing value processing. Standardization can use the Z-Score method, that is, use the following formula for standardization: , where represents the standardized value, Represents historical wind speed forecast data, represents the mean of the overall data, Represents the standard deviation of the population data.

[0038] In the present application, when dividing the training data set, for each historical wind speed prediction data, it can be compared with each standard wind speed meteorological data respectively, and the wind speed meteorological type corresponding to each historical wind speed prediction data is determined according to the comparison result. Finally, the historical wind speed prediction data belonging to the same wind speed meteorological type are divided into the same training data set.

[0039] In addition, each standard wind speed meteorological data may be used as a clustering center to perform clustering processing on the historical wind speed prediction data, so as to divide the historical wind speed prediction data into at least one training data set.

[0040] Furthermore, the model is trained using the training data set and the measured wind speed at the observation station, so that the model can learn the error relationship between the predicted value and the measured value in different wind speed meteorological types, and obtain the wind speed prediction model corresponding to the wind speed meteorological type.

[0041] It should be noted that, for different wind speed meteorological types, the structure of the initial model used may also be different to adapt to the wind speed prediction model of different wind speed meteorological types.

[0042] S130: Based on the target wind speed prediction model, predict the initial wind speed prediction data to determine target wind speed prediction data.

[0043] Specifically, at least two groups of initial wind speed prediction data from multiple data sources can be input into the target wind speed prediction model. The target wind speed prediction model processes and calculates the input initial wind speed prediction data based on internal algorithms, parameters and learning of historical wind speed prediction data to output target wind speed prediction data.

[0044] In the present application, the initial wind speed prediction data is optimized by using a target wind speed prediction model, thereby reducing the error of wind speed prediction.

[0045] The embodiment of the present invention provides a wind speed prediction method, which obtains at least two groups of initial wind speed prediction data of a target area in a preset time period; wherein the initial wind speed prediction data comes from different data sources, and the initial wind speed prediction data includes wind speed prediction values ​​corresponding to at least two test moments in the preset time period; the initial wind speed prediction data is compared with each standard wind speed meteorological data, and the wind speed meteorological type corresponding to the target area in the preset time period is determined according to the comparison result, and the wind speed prediction model corresponding to the wind speed meteorological type is used as the target wind speed prediction model; based on the target wind speed prediction model, the initial wind speed prediction data is predicted to determine the target wind speed prediction data. This technical solution divides the wind speed meteorological types to achieve accurate optimization of wind speed prediction data from multiple data sources, thereby improving the accuracy and reliability of wind speed prediction.

[0046] Embodiment 2

[0047] Figure 2 This is a flow chart of a wind speed prediction method provided in Example 2 of the present application. This embodiment is optimized based on the above embodiment. Figure 2 As shown, the method of this embodiment specifically includes the following steps.

[0048] S210. Obtain at least two sets of initial wind speed prediction data for the target area in a preset time period; wherein the initial wind speed prediction data come from different data sources, and the initial wind speed prediction data include wind speed prediction values ​​corresponding to at least two test moments in the preset time period.

[0049] S220. Compare the initial wind speed prediction data with each standard wind speed meteorological data respectively, determine the wind speed meteorological type corresponding to the target area in the preset time period according to the comparison result, and use the wind speed prediction model corresponding to the wind speed meteorological type as the target wind speed prediction model; wherein the standard wind speed meteorological data, the wind speed meteorological type and the wind speed prediction model correspond one-to-one.

[0050] S230. Based on at least two base learner models in the target wind speed prediction model, respectively predict the initial wind speed prediction data to obtain at least two candidate wind speed prediction data.

[0051] In order to avoid the problem of overfitting of a single model, this application uses multi-model fusion to improve the generalization ability of the wind speed prediction model.

[0052] Specifically, multiple different base learner models, also called first-level learners, are pre-trained in the wind speed prediction model, and each base learner model is independently trained by using different algorithms or parameters. When the model is running, each base learner model will output the corresponding prediction result based on the model input data, that is, the candidate wind speed prediction data.

[0053] In the present application, at least two groups of initial wind speed prediction data can be respectively input into each base learner model for prediction, and candidate wind speed prediction data of each base learner model can be obtained respectively. For example, there are two groups of initial wind speed prediction data A and B, and three base learner models a, b and c. On this basis, data A and B are input into base learner model a to obtain candidate wind speed prediction data m, data A and B are input into base learner model b to obtain candidate wind speed prediction data n, and data A and B are input into base learner model c to obtain candidate wind speed prediction data s.

[0054] Optionally, the base learner model is at least one of a linear regression model, a decision tree model, a KNN model, a neural network model, a random forest model, and a support vector machine model.

[0055] It should be noted that the appropriate model combination can be selected according to the wind speed meteorological type and actual conditions.

[0056] S240: Based on the secondary learner model in the target wind speed prediction model, predict the at least two candidate wind speed prediction data to obtain target wind speed prediction data.

[0057] The secondary learner model is also called a meta-learner model or a secondary learner model. Its purpose is to obtain the final target wind speed prediction data by combining the candidate wind speed prediction data predicted by each base learner model.

[0058] Specifically, each candidate wind speed prediction data obtained in step S230 may be input into the secondary learner model, so that the secondary learner model performs secondary prediction on the prediction results of each base learner model, thereby obtaining the final target wind speed prediction data.

[0059] Optionally, the secondary learner model can be a linear regression model.

[0060] The embodiment of the present invention provides a wind speed prediction method, which obtains at least two groups of initial wind speed prediction data of a target area in a preset time period; wherein the initial wind speed prediction data comes from different data sources, and the initial wind speed prediction data includes wind speed prediction values ​​corresponding to at least two test moments in the preset time period; the initial wind speed prediction data are compared with each standard wind speed meteorological data, and the wind speed meteorological type corresponding to the target area in the preset time period is determined according to the comparison result, and the wind speed prediction model corresponding to the wind speed meteorological type is used as the target wind speed prediction model; based on at least two base learner models in the target wind speed prediction model, the initial wind speed prediction data are predicted respectively to obtain at least two candidate wind speed prediction data; based on the secondary learner model in the target wind speed prediction model, at least two candidate wind speed prediction data are predicted to obtain the target wind speed prediction data. This technical solution avoids the problem of easy overfitting of a single model through multi-model fusion modeling, improves the generalization ability of the wind speed prediction model, and thus improves the accuracy and reliability of wind speed prediction.

[0061] Embodiment 3

[0062] Figure 3 This is a flow chart of a wind speed prediction method provided in Example 3 of the present application. This embodiment is optimized based on the above embodiment. Figure 3 As shown, the method of this embodiment specifically includes the following steps.

[0063] S310. Obtain at least two sets of initial wind speed prediction data for the target area in a preset time period; wherein the initial wind speed prediction data come from different data sources, and the initial wind speed prediction data include wind speed prediction values ​​corresponding to at least two test moments in the preset time period.

[0064] S320: Select one group from the at least two groups of initial wind speed prediction data as wind speed prediction data to be compared.

[0065] In order to facilitate subsequent comparison with standard wind speed meteorological data, this application selects initial wind speed prediction data from a certain data source as the wind speed prediction data to be compared.

[0066] Optionally, initial wind speed forecast data obtained from the European Centre for Medium-Range Weather Forecasts is used as the wind speed forecast data to be compared.

[0067] S330. For each standard wind speed meteorological data, determine the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data.

[0068] Among them, similarity is a quantitative indicator used to measure the degree of proximity or similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data.

[0069] In the present application, the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data can be determined by calculating the numerical distance, such as calculating the Euclidean distance, Manhattan distance, etc. between the two. The smaller the distance, the higher the similarity; it can also be determined by comparing similarity ratios. For example, the standard wind speed meteorological data is a fixed wind speed value or range, and the proportion of the wind speed forecast data to be compared within the value or range can be calculated; it can also be matched by features between the wind speed forecast data to be compared and the standard wind speed meteorological data, for example, comparing the consistency of the two in features such as wind speed change trend and periodicity. The present application embodiment does not limit the method for determining the similarity, and it can be determined according to actual needs.

[0070] Optionally, determining the similarity between the wind speed prediction data to be compared and the standard wind speed meteorological data includes: determining the wind speed reference value corresponding to each of the time points to be measured based on the standard wind speed meteorological data; respectively determining the sub-similarity between the wind speed reference value and the wind speed prediction value at each of the time points to be measured; and determining the similarity between the wind speed prediction data to be compared and the standard wind speed meteorological data based on each of the sub-similarity.

[0071] Since both the wind speed forecast data to be compared and the standard wind speed meteorological data contain wind speed forecast values ​​at multiple times, in order to take into account the time series of wind speed, the wind speed reference value at each time to be measured in the standard wind speed meteorological data can be extracted.

[0072] For example, the test times in the wind speed forecast data to be compared include 10 o'clock, 11 o'clock, 12 o'clock, 13 o'clock, 14 o'clock and 15 o'clock, while the standard wind speed meteorological data include wind speed reference values ​​every hour from 1 o'clock to 24 o'clock. Therefore, it is only necessary to extract the wind speed reference values ​​of 10 o'clock, 11 o'clock, 12 o'clock, 13 o'clock, 14 o'clock and 15 o'clock from the standard wind speed meteorological data.

[0073] In the present application, the wind speed reference value at each measured moment can be compared with the wind speed prediction value to determine their sub-similarity, and on this basis, the similarity between the wind speed prediction data to be compared and the standard wind speed meteorological data can be determined, thereby improving the accuracy and reliability of the wind speed prediction.

[0074] Specifically, the sub-similarity can be determined using the following formula: ; In the formula, Indicates The sub-similarity between the wind speed reference value and the wind speed prediction value at the time to be measured, Indicates The wind speed reference value at the time to be measured, Indicates The wind speed forecast value at the time to be tested.

[0075] Optionally, determining the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data according to each of the sub-similarity comprises: determining the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data using the following formula: ; In the formula, Indicates the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data. Indicates the number of moments to be measured in the preset time period. Indicates The sub-similarity between the wind speed reference value and the wind speed prediction value at the time to be tested.

[0076] S340. Determine the wind speed meteorological type corresponding to the target area in the preset time period according to each of the similarities, and use the wind speed prediction model corresponding to the wind speed meteorological type as the target wind speed prediction model; wherein the standard wind speed meteorological data, the wind speed meteorological type and the wind speed prediction model correspond one to one.

[0077] Specifically, the wind speed meteorological types corresponding to each standard wind speed meteorological data can be sorted in descending order according to similarity, and the wind speed meteorological type ranked first can be used as the wind speed meteorological type corresponding to the target area in the preset time period, and the wind speed prediction model corresponding to the wind speed meteorological type can be used as the target wind speed prediction model.

[0078] S350: Based on the target wind speed prediction model, predict the initial wind speed prediction data to determine target wind speed prediction data.

[0079] The embodiment of the present application provides a wind speed prediction method, which obtains at least two groups of initial wind speed prediction data of the target area in a preset time period; selects one group from the at least two groups of initial wind speed prediction data as the wind speed prediction data to be compared; determines the similarity between the wind speed prediction data to be compared and the standard wind speed meteorological data for each standard wind speed meteorological data; determines the wind speed meteorological type corresponding to the target area in the preset time period according to each similarity, and uses the wind speed prediction model corresponding to the wind speed meteorological type as the target wind speed prediction model; predicts the initial wind speed prediction data based on the target wind speed prediction model to determine the target wind speed prediction data. This technical solution divides different wind speed meteorological types by a similarity calculation method, and predicts based on the wind speed prediction model corresponding to the wind speed meteorological type, thereby improving the accuracy of wind speed prediction.

[0080] Embodiment 4

[0081] Figure 4 This is a schematic diagram of the structure of a wind speed prediction device provided in Example 4 of the present application. Figure 4 As shown, the device includes the following modules.

[0082] The data acquisition module 410 is used to obtain at least two sets of initial wind speed prediction data for the target area in a preset time period; wherein the initial wind speed prediction data comes from different data sources, and the initial wind speed prediction data includes wind speed prediction values ​​corresponding to at least two test moments in the preset time period.

[0083] The model determination module 420 is used to compare the initial wind speed prediction data with each standard wind speed meteorological data, determine the wind speed meteorological type corresponding to the target area in the preset time period according to the comparison result, and use the wind speed prediction model corresponding to the wind speed meteorological type as the target wind speed prediction model; wherein the standard wind speed meteorological data, the wind speed meteorological type and the wind speed prediction model correspond one-to-one.

[0084] The wind speed prediction module 430 is used to predict the initial wind speed prediction data based on the target wind speed prediction model to determine the target wind speed prediction data.

[0085] The embodiment of the present invention provides a wind speed prediction device, which obtains at least two groups of initial wind speed prediction data of a target area in a preset time period; wherein the initial wind speed prediction data comes from different data sources, and the initial wind speed prediction data includes wind speed prediction values ​​corresponding to at least two test moments in the preset time period; the initial wind speed prediction data is compared with each standard wind speed meteorological data, and the wind speed meteorological type corresponding to the target area in the preset time period is determined according to the comparison result, and the wind speed prediction model corresponding to the wind speed meteorological type is used as the target wind speed prediction model; based on the target wind speed prediction model, the initial wind speed prediction data is predicted to determine the target wind speed prediction data. This technical solution divides the wind speed meteorological types to achieve accurate optimization of wind speed prediction data from multiple data sources, thereby improving the accuracy and reliability of wind speed prediction.

[0086] Furthermore, the wind speed prediction module 430 includes: a first prediction unit, used to predict the initial wind speed prediction data based on at least two base learner models in the target wind speed prediction model, respectively, to obtain at least two candidate wind speed prediction data; a second prediction unit, used to predict the at least two candidate wind speed prediction data based on the secondary learner model in the target wind speed prediction model, to obtain the target wind speed prediction data.

[0087] Furthermore, the base learner model is at least one of a linear regression model, a decision tree model, a KNN model, a neural network model, a random forest model, and a support vector machine model.

[0088] Furthermore, the construction process of the wind speed prediction model includes: obtaining historical wind speed prediction data, and dividing the historical wind speed prediction data into at least one training data set based on the standard wind speed meteorological data; for each of the training data sets, using the training data set to train the initial model to obtain a wind speed prediction model corresponding to the wind speed meteorological type.

[0089] Furthermore, the model determination module 420 includes: a data determination unit, used to select one group from the at least two groups of initial wind speed prediction data as the wind speed prediction data to be compared; a data comparison unit, used to determine the similarity between the wind speed prediction data to be compared and the standard wind speed meteorological data for each standard wind speed meteorological data; a type determination unit, used to determine the wind speed meteorological type corresponding to the target area in the preset time period according to each similarity.

[0090] Furthermore, the data comparison unit includes: a wind speed reference value determination subunit, used to determine the wind speed reference value corresponding to each of the test moments based on the standard wind speed meteorological data; a sub-similarity determination subunit, used to respectively determine the sub-similarity between the wind speed reference value and the wind speed prediction value at each of the test moments; and a similarity determination subunit, used to determine the similarity between the wind speed prediction data to be compared and the standard wind speed meteorological data based on each of the sub-similarity.

[0091] Furthermore, the similarity determination subunit is specifically used to determine the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data using the following formula: ; In the formula, Indicates the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data. Indicates the number of moments to be measured in the preset time period. Indicates The sub-similarity between the wind speed reference value and the wind speed prediction value at the time to be tested.

[0092] A wind speed prediction device provided in an embodiment of the present application can execute a wind speed prediction method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

[0093] Embodiment 5

[0094] Figure 5A schematic diagram of a device 10 that can be used to implement an embodiment of the present application is shown. The device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0095] like Figure 5 As shown, the device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0096] A number of components in the device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0097] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a wind speed prediction method.

[0098] In some embodiments, the wind speed prediction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the wind speed prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the wind speed prediction method in any other appropriate manner (e.g., by means of firmware).

[0099] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0100] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow charts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0101] In the context of the present application, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0102] To provide interaction with a user, the systems and techniques described herein may be implemented on a device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0103] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0104] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0105] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0106] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A wind speed prediction method, characterized in that: The method comprises: Obtain at least two sets of initial wind speed prediction data for the target area in a preset time period; wherein the initial wind speed prediction data come from different data sources, and the initial wind speed prediction data include wind speed prediction values ​​corresponding to at least two test moments in the preset time period; The initial wind speed forecast data is compared with each standard wind speed meteorological data respectively, and the wind speed meteorological type corresponding to the target area in the preset time period is determined according to the comparison result, and the wind speed forecast model corresponding to the wind speed meteorological type is used as the target wind speed forecast model; wherein the standard wind speed meteorological data, the wind speed meteorological type and the wind speed forecast model correspond one to one; Based on the target wind speed prediction model, the initial wind speed prediction data is predicted to determine the target wind speed prediction data; The method of predicting the initial wind speed prediction data based on the target wind speed prediction model to determine the target wind speed prediction data includes: Based on at least two base learner models in the target wind speed prediction model, respectively predict the initial wind speed prediction data to obtain at least two candidate wind speed prediction data; Based on the secondary learner model in the target wind speed prediction model, the at least two candidate wind speed prediction data are predicted to obtain target wind speed prediction data.

2. The method according to claim 1, characterized in that The base learner model is at least one of a linear regression model, a decision tree model, a KNN model, a neural network model, a random forest model, and a support vector machine model.

3. The method according to claim 1, characterized in that The construction process of the wind speed prediction model includes: Acquire historical wind speed forecast data, and divide the historical wind speed forecast data into at least one training data set based on the standard wind speed meteorological data; For each of the training data sets, the initial model is trained using the training data set to obtain a wind speed prediction model corresponding to the wind speed meteorological type.

4. The method according to claim 1, characterized in that: The initial wind speed forecast data is compared with each standard wind speed meteorological data, and the wind speed meteorological type corresponding to the target area in the preset time period is determined according to the comparison result, including: Selecting one set of the at least two sets of initial wind speed prediction data as the wind speed prediction data to be compared; For each standard wind speed meteorological data, determining the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data; According to each of the similarities, the wind speed meteorological type corresponding to the target area in the preset time period is determined.

5. The method according to claim 4, characterized in that Determining the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data includes: Determine the wind speed reference value corresponding to each of the time points to be measured according to the standard wind speed meteorological data; respectively determining the sub-similarity between the wind speed reference value and the wind speed prediction value at each of the test moments; According to each of the sub-similarity, the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data is determined.

6. The method according to claim 5, characterized in that Determining the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data according to each of the sub-similarity comprises: The following formula is used to determine the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data: ； In the formula, Indicates the similarity between the wind speed forecast data to be compared and the standard wind speed meteorological data. Indicates the number of moments to be measured in the preset time period. Indicates The sub-similarity between the wind speed reference value and the wind speed prediction value at the time to be tested.

7. A wind speed prediction device, characterized in that: The device comprises: A data acquisition module, used to acquire at least two sets of initial wind speed prediction data of a target area in a preset time period; wherein the initial wind speed prediction data comes from different data sources, and the initial wind speed prediction data includes wind speed prediction values ​​corresponding to at least two test moments in the preset time period; A model determination module is used to compare the initial wind speed forecast data with each standard wind speed meteorological data, determine the wind speed meteorological type corresponding to the target area in the preset time period according to the comparison result, and use the wind speed forecast model corresponding to the wind speed meteorological type as the target wind speed forecast model; wherein the standard wind speed meteorological data, the wind speed meteorological type and the wind speed forecast model have a one-to-one correspondence; A wind speed prediction module, used to predict the initial wind speed prediction data based on the target wind speed prediction model to determine the target wind speed prediction data; Wherein, the wind speed prediction module includes: A first prediction unit, configured to predict the initial wind speed prediction data based on at least two base learner models in the target wind speed prediction model, respectively, to obtain at least two candidate wind speed prediction data; The second prediction unit is used to predict the at least two candidate wind speed prediction data based on the secondary learner model in the target wind speed prediction model to obtain target wind speed prediction data.

8. An electronic device, characterized in that: The device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the wind speed prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the wind speed prediction method according to any one of claims 1 to 6 when executed.

Images