Coastal NWP Data Grid Refinement Method and Device Based on Double Mapping

Abstract

The present invention discloses a refined method and device for coastal NWP data grid based on double mapping, which relates to the technical field of wind power. A specific implementation manner of the method includes: determining the corresponding relationship between the measured coarse grid NWP data and the measured fine grid meteorological monitoring data in the historical period as the first mapping; performing interpolation on the measured coarse grid NWP data according to a preset kernel function to obtain fine grid NWP data; when the fine grid NWP data meets the high-precision condition constrained by the measured fine grid meteorological monitoring data, inputting the fine grid NWP data into the second mapping for prediction to obtain the fine grid NWP prediction data in the future period; using the first mapping to convert the fine grid NWP prediction data into the first fine grid meteorological prediction data in the future period, and inputting the first fine grid meteorological prediction data into a wind power prediction model to predict wind power. This implementation manner can achieve accurate prediction of offshore wind power based on the measured coarse grid NWP data.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power, and in particular to a method and device for refining the coastal NWP data grid based on double mapping. Background Art

[0002] In recent years, the installed capacity of offshore wind power in China has developed rapidly, but the supporting technologies are relatively immature. Among them, high-precision wind power prediction is the basis for wind power grid connection and safe and reliable control, and the fine-grid NWP (Numerical Weather Prediction) is the basis for high-precision and high-resolution wind power prediction, which is currently a difficult and challenging problem recognized internationally. Currently, the NWP data that can be obtained from meteorological observatories and meteorological stations are all coarse-grid. If high-precision wind power prediction is performed based on the coarse-grid NWP data, it is an urgent problem to be solved in the field of wind power technology. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and device for refining the coastal NWP data grid based on double mapping, which can accurately predict the offshore wind power based on the coarse-grid NWP data.

[0004] To achieve the above object, according to one aspect of the present invention, a method for refining the coastal NWP data grid based on double mapping is provided.

[0005] The method for refining the coastal NWP data grid based on double mapping in the embodiments of the present invention includes: determining the corresponding relationship between the measured coarse-grid numerical weather prediction NWP data and the measured fine-grid meteorological monitoring data in the historical period as the first mapping; interpolating the measured coarse-grid NWP data according to a preset kernel function to obtain fine-grid NWP data; when the fine-grid NWP data meets the preset high-precision conditions constrained by the measured fine-grid meteorological monitoring data, inputting the fine-grid NWP data into a preset second mapping for prediction to obtain fine-grid NWP prediction data in the future period; using the first mapping to convert the fine-grid NWP prediction data into the first fine-grid meteorological prediction data in the future period, and inputting the first fine-grid meteorological prediction data into a pre-trained wind power prediction model to predict the wind power.

[0006] Optionally, the step of interpolating the measured coarse-grid NWP data according to a preset kernel function to obtain fine-grid NWP data includes: for any position to be inserted, obtaining a preset number of reference data in the neighborhood of the position to be inserted; where the reference data belongs to the measured coarse-grid NWP data; determining the weight value of each reference data for the position to be inserted according to the kernel function, and calculating the weighted sum of the reference data based on the weight value as the fine-grid NWP data at the position to be inserted.

[0007] Optionally, determining the weight value of each reference data for the to-be-inserted position according to the kernel function includes: for any reference data, dividing the calculation result of the kernel function of this reference data and the to-be-inserted position by the sum of the calculation results of the kernel functions of each reference data and the to-be-inserted position, to obtain the weight value of this reference data for the to-be-inserted position.

[0008] Optionally, satisfying the high-precision condition includes: converting the fine-grid NWP data into fine-grid meteorological data by using a first mapping, calculating the deviation between the fine-grid meteorological data and the measured fine-grid meteorological monitoring data, and determining that the deviation is less than a preset precision threshold.

[0009] Optionally, the method further includes: inputting the measured fine-grid meteorological monitoring data into a second mapping to obtain second fine-grid meteorological prediction data for a future period, inputting the second fine-grid meteorological prediction data into the wind power prediction model to obtain the wind power prediction result of the second fine-grid meteorological prediction data in the current test period; comparing the wind power prediction results of the first fine-grid meteorological prediction data and the second fine-grid meteorological prediction data in the current test period, and using the fine-grid meteorological prediction data corresponding to the better wind power prediction result as the input data of the wind power prediction model in the current application period.

[0010] To achieve the above object, according to another aspect of the present invention, there is provided a coastal NWP data grid refinement device based on a dual mapping.

[0011] The coastal NWP data grid refinement device based on a dual mapping according to an embodiment of the present invention includes: a first mapping establishment unit, configured to: determine the corresponding relationship between the measured coarse-grid numerical weather prediction (NWP) data and the measured fine-grid meteorological monitoring data in a historical period as a first mapping; a refinement unit, configured to: perform interpolation on the measured coarse-grid NWP data according to a preset kernel function to obtain fine-grid NWP data; a second mapping prediction unit, configured to: when the fine-grid NWP data satisfies a preset high-precision condition constrained by the measured fine-grid meteorological monitoring data, input the fine-grid NWP data into a preset second mapping for prediction to obtain fine-grid NWP prediction data for a future period; a wind power prediction unit, configured to: convert the fine-grid NWP prediction data into first fine-grid meteorological prediction data for a future period by using the first mapping, and input the first fine-grid meteorological prediction data into a pre-trained wind power prediction model to predict wind power.

[0012] Optionally, the refinement unit is further configured to: for any position to be inserted, obtain a preset number of reference data in the neighborhood of the position to be inserted; wherein the reference data belongs to the measured coarse grid NWP data; for any reference data, divide the calculation result of the kernel function of the reference data and the position to be inserted by the sum of the calculation results of the kernel functions of each reference data and the position to be inserted, to obtain the weight value of the reference data for the position to be inserted; calculate the weighted sum of the reference data based on the weight value as the fine grid NWP data of the position to be inserted.

[0013] Optionally, meeting the high-precision condition includes: converting the fine grid NWP data into fine grid meteorological data by using a first mapping, calculating the deviation between the fine grid meteorological data and the measured fine grid meteorological monitoring data, and determining that the deviation is less than a preset precision threshold; the wind power prediction unit is further configured to: input the measured fine grid meteorological monitoring data into a second mapping to obtain second fine grid meteorological prediction data for a future period, input the second fine grid meteorological prediction data into the wind power prediction model to obtain the wind power prediction result of the second fine grid meteorological prediction data in the current test cycle; compare the wind power prediction results of the first fine grid meteorological prediction data and the second fine grid meteorological prediction data in the current test cycle, and use the fine grid meteorological prediction data corresponding to the better wind power prediction result as the input data of the wind power prediction model in the current application cycle.

[0014] To achieve the above object, according to another aspect of the present invention, there is provided an electronic device.

[0015] An electronic device according to the present invention includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enabling the one or more processors to implement the coastal NWP data grid refinement method based on double mapping provided by the present invention.

[0016] To achieve the above object, according to still another aspect of the present invention, there is provided a computer-readable storage medium.

[0017] A computer-readable storage medium according to the present invention stores a computer program thereon, and when the program is executed by a processor, it implements the coastal NWP data grid refinement method based on double mapping provided by the present invention.

[0018] According to the technical solution of the present invention, the embodiments in the above invention have the following advantages or beneficial effects:

[0019] First, determine the corresponding relationship between the measured coarse-grid NWP data and the measured fine-grid meteorological monitoring data in the historical period as the first mapping, and interpolate the measured coarse-grid NWP data according to a preset kernel function to obtain fine-grid NWP data. Then, determine whether the fine-grid NWP data meets the high-precision conditions constrained by the measured fine-grid meteorological monitoring data. If not, adjust the kernel function or the bandwidth therein and re-interpolate. If it meets the conditions, input the fine-grid NWP data into the second mapping for prediction to obtain the fine-grid NWP prediction data for the future period. After that, use the first mapping to convert the fine-grid NWP prediction data into the first fine-grid meteorological prediction data for the future period, and input the first fine-grid meteorological prediction data into a pre-trained wind power prediction model to predict the wind power. Through the above processing, high-precision wind power prediction based on NWP data and constrained by the measured fine-grid meteorological monitoring data is achieved. By the NWP grid refinement processing under the constraint of the measured fine-grid meteorological monitoring data and the NWP prediction under the fine grid, the problem that only coarse-grid NWP data can be obtained currently and thus high-precision prediction cannot be achieved is solved. Further, as a better solution, compare the above prediction path with the prediction path that does not rely on NWP data but only uses the measured fine-grid meteorological monitoring data, and select the path with better effect for actual wind power prediction, further ensuring the reliability of the wind power prediction scheme.

[0020] The further effects of the above non-conventional optional methods will be described below in combination with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings are used to better understand the present invention and do not constitute an improper limitation to the present invention. Among them:

[0022] Figure 1 is a schematic diagram of the main steps of the coastal NWP data grid refinement method based on double mapping in an embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of the principle of the coastal NWP data grid refinement method based on double mapping in an embodiment of the present invention;

[0024] Figure 3 is a schematic diagram of the components of the coastal NWP data grid refinement device based on double mapping in an embodiment of the present invention;

[0025] Figure 4 is an exemplary system architecture diagram to which the embodiment of the present invention can be applied;

[0026] Figure 5 is a schematic diagram of the structure of an electronic device for implementing the coastal NWP data grid refinement method based on double mapping in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] The following describes exemplary embodiments of the present invention with reference to the accompanying drawings. Various details of the embodiments of the present invention are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness.

[0028] It should be noted that, without conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0029] Figure 1 It is a schematic diagram of the main steps of the refined coastal NWP data grid method based on double mapping in the embodiments of the present invention.

[0030] As Figure 1 shown, the refined coastal NWP data grid method based on double mapping in the embodiments of the present invention can be specifically executed according to the following steps:

[0031] Step S101: Determine the corresponding relationship between the measured coarse-grid NWP data and the measured fine-grid meteorological monitoring data in the historical period as the first mapping.

[0032] In the field of wind power technology, there are generally two types of original data for predicting wind power. One is the measured coarse-grid NWP data, that is, the meteorological data released by authoritative institutions such as meteorological observatories and meteorological stations. These data can include time, three-dimensional coordinates (such as longitude, latitude, altitude), temperature, humidity, wind direction, wind speed, and air pressure, that is, the meteorological data such as temperature, humidity, wind direction, wind speed, and air pressure that can represent the temperature, humidity, wind direction, wind speed, and air pressure at a certain time and a certain three-dimensional space position. The measured coarse-grid NWP data contains historical data and can also contain predicted data for future periods. The other is the measured fine-grid meteorological monitoring data, which are usually collected and recorded by power generation wind turbine recorders or surrounding monitoring points. Similarly, these data can include time, three-dimensional coordinates, temperature, humidity, wind direction, wind speed, and air pressure, but only contain historical data and no future data. It can be understood that the measured coarse-grid NWP data and the measured fine-grid meteorological monitoring data belong to two independent systems respectively (the former belongs to the general weather forecasting system, and the latter is the internal data of the professional wind power system). They cannot be directly fused and used, and need to be converted when combined for use.

[0033] It should be noted that in the embodiments of the present invention, a coarse grid refers to a large interval of data in terms of time and space scales. Relatively speaking, a fine grid refers to a small interval of data in terms of time and space scales. For example, a grid with a time interval greater than or equal to 1 hour and a space interval greater than or equal to 1 kilometer can be determined as a coarse grid, and a grid with a time interval less than half an hour and a space interval less than 500 meters can be determined as a fine grid. It can be understood that the specific definitions of the coarse grid and the fine grid can be flexibly formulated according to the actual scenario. In the following description, a coarse grid with a time interval equal to 1 hour and a space interval equal to 1 kilometer, and a fine grid with a time interval equal to 15 minutes and a space interval equal to 300 meters will be used as examples for illustration.

[0034] In step S101, the correspondence between the measured coarse grid NWP data and the measured fine grid meteorological monitoring data in the historical period is determined as the first mapping. In practical applications, the measured coarse grid NWP data D1 corresponding to a certain spatial point can be expressed as , where i is a positive integer, is the discretized time, , are the corresponding meteorological data such as temperature, humidity, wind speed, wind direction, and air pressure. Similarly, the measured fine grid meteorological monitoring data D2 corresponding to a certain spatial point can be expressed as , , are the corresponding meteorological data such as temperature, humidity, wind speed, wind direction, and air pressure. Then the first mapping f1 can be expressed as the following polynomial regression model:

[0035]

[0036] where z represents some of the measured coarse grid NWP data, represents some of the measured fine grid meteorological monitoring data, k is the power, n is the maximum value of k, are the coefficients of each term. When determining the parameters in the first mapping, multiple sets of measured coarse grid NWP data and measured fine grid meteorological monitoring data corresponding to the same historical time point can be selected, and these data can be used to solve the above polynomial regression model to obtain the parameters of the first mapping and thus determine the first mapping.

[0037] Step S102: Interpolate the measured coarse grid NWP data according to a preset kernel function to obtain fine grid NWP data.

[0038] In this step, kernel function interpolation is performed on the measured coarse-grid NWP data to obtain the fine-grid NWP data. Specifically, for any position to be inserted, first, a preset number of reference data in the neighborhood of the position to be inserted are obtained, and the above reference data belong to the measured coarse-grid NWP data. Then, according to the kernel function, the weight value of each reference data for the position to be inserted is determined, and the weighted sum of the reference data based on the weight value is calculated as the fine-grid NWP data of the position to be inserted. As a preferred solution, the above weight value can be calculated in the following way: for any reference data, divide the calculation result of the kernel function of the reference data and the position to be inserted by the sum of the calculation results of the kernel functions of each reference data and the position to be inserted to obtain the weight value of the reference data for the position to be inserted.

[0039] Taking the interpolation distance on the time axis, the time interval of the measured coarse-grid NWP data is 1 hour, and interpolation needs to be performed at 15-minute intervals. Then, for the time period between 1 o'clock and 2 o'clock, three points of interpolation are required, namely 1:15, 1:30, and 1:45. Taking the NWP data z at 1:15 as an example, first, select reference data such as the measured coarse-grid NWP data z1 at 1 o'clock and the measured coarse-grid NWP data z2 at 2 o'clock according to the preset rules. Then, calculate the weight value w1 of z1 for z and the weight value w2 of z2 for z respectively, that is:

[0040]

[0041]

[0042] where K represents a preset kernel function, and its form can be a Gaussian function or the like.

[0043] After that, the weighted sum of the reference data based on the above weight values can be used as the fine-grid NWP data of the position to be inserted, so as to realize the refinement of the coarse-grid NWP data, that is:

[0044]

[0045] Step S103: When the fine-grid NWP data meet the preset high-precision conditions constrained by the measured fine-grid meteorological monitoring data, input the fine-grid NWP data into a preset second mapping for prediction to obtain the fine-grid NWP prediction data for the future period.

[0046] In this step, first, the fine-grid NWP data formed in step S102 is verified using the measured fine-grid meteorological monitoring data to prevent inaccuracies in the interpolation process. Specifically, first, the fine-grid NWP data is converted into fine-grid meteorological data using the first mapping (i.e., the fine-grid NWP data of the weather forecasting system is converted into the fine-grid meteorological data of the wind power system), and the deviation between the fine-grid meteorological data and the measured fine-grid meteorological monitoring data at the corresponding time points is calculated. Since both the fine-grid meteorological data and the measured fine-grid meteorological monitoring data are fine-grid data with the same intervals in time and space scales, the meteorological data deviation at the corresponding time points can be comprehensively calculated, and this deviation can be the sum, weighted sum, average, or weighted average of the deviations at each time point. Finally, it is determined whether the above deviation is less than a preset accuracy threshold. If it is less than, the verification is passed, and the next step is executed; if it is not less than, the kernel function needs to be adjusted or replaced (the bandwidth parameter in the kernel function can be adjusted first, and if the effect is not good, try to replace the kernel function).

[0047] When the above verification is passed, the fine-grid NWP data can be input into the second mapping for prediction to obtain the fine-grid NWP prediction data for the future period. Exemplarily, [Wang 1] can be the Prophet model, which is composed of a trend term, a seasonal term, a sudden change term, and a random fluctuation term of the time series. The parameters of this model can be determined by training the future period data in the coarse-grid NWP data as labels.

[0048] Step S104: Use the first mapping to convert the fine-grid NWP prediction data into the first fine-grid meteorological prediction data for the future period, and input the first fine-grid meteorological prediction data into the pre-trained wind power prediction model to predict the wind power.

[0049] The above fine-grid NWP prediction data is the prediction data for future time and belongs to the weather forecasting system. It needs to be transformed into the wind power system to perform wind power prediction. Therefore, in this step, the first mapping is used to transform the fine-grid NWP prediction data into the first fine-grid meteorological prediction data of the wind power system. Finally, the first fine-grid meteorological prediction data can be input into the pre-trained wind power prediction model to predict the wind power.

[0050] As a better technical solution, based on the above prediction path, a completely different prediction path can be designed for comparison, and finally the better path is used to perform wind power prediction in practical applications. This prediction path is as follows: Input the measured fine-grid meteorological monitoring data into the second mapping to obtain the second fine-grid meteorological prediction data for the future period, and input the second fine-grid meteorological prediction data into the wind power prediction model to obtain the wind power prediction result of the second fine-grid meteorological prediction data in the current test cycle. Finally, compare the wind power prediction results of the first fine-grid meteorological prediction data and the second fine-grid meteorological prediction data in the current test cycle, and use the fine-grid meteorological prediction data corresponding to the better wind power prediction result as the input data of the wind power prediction model in the current application cycle. In this way, higher system reliability can be achieved.

[0051] Figure 2 It is a schematic diagram of the principle of the method for refining the coastal NWP data grid based on double mapping in the embodiments of the present invention. Refer to Figure 2 . After establishing the first mapping f1 and the second mapping f2, first perform kernel function interpolation on the measured coarse-grid NWP data to obtain fine-grid NWP data. Then use the first mapping to convert it into fine-grid meteorological data and verify it with the measured fine-grid meteorological monitoring data. After passing the verification, input the fine-grid NWP data into the second mapping to obtain fine-grid NWP prediction data. In this process, the second mapping needs to be constrained by the measured coarse-grid NWP data. Thereafter, the fine-grid NWP prediction data forms the first fine-grid meteorological prediction data through the first mapping and enters the wind power prediction model. This is the first prediction path. The second prediction path is that the measured fine-grid meteorological monitoring data directly enters the second mapping, forms the second fine-grid meteorological prediction data and enters the wind power prediction model. Finally, compare the prediction results of the two prediction paths and preferentially select one of them for actual wind power prediction.

[0052] In the technical solution of the embodiments of the present invention, based on the current data accuracy level in the meteorological-related industry, a data processing method based on machine learning is adopted to realize the optimization research and application of fine-grid offshore NWP data, which has positive exploration significance for further improving the accuracy of offshore wind power prediction and developing the new energy industry, especially the offshore wind power industry, and achieving the "dual carbon" goal.

[0053] It should be noted that for the foregoing method embodiments, for the convenience of description, they are expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence. In fact, some steps can be performed in other sequences or simultaneously. In addition, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential for implementing the present invention.

[0054] To facilitate better implementation of the above solutions of the embodiments of the present invention, relevant devices for implementing the above solutions are also provided below.

[0055] Please refer to Figure 3 As shown, the refined device 300 for coastal NWP data grid based on double mapping provided by the embodiments of the present invention may include: a first mapping establishment unit 301, a refinement unit 302, a second mapping prediction unit 303, and a wind power prediction unit 304.

[0056] Among them, the first mapping establishment unit 301 is used to: determine the corresponding relationship between the measured coarse-grid numerical weather prediction (NWP) data and the measured fine-grid meteorological monitoring data in the historical period as the first mapping; the refinement unit 302 is used to: interpolate the measured coarse-grid NWP data according to a preset kernel function to obtain fine-grid NWP data; the second mapping prediction unit 303 is used to: when the fine-grid NWP data meets the preset high-precision conditions constrained by the measured fine-grid meteorological monitoring data, input the fine-grid NWP data into a preset second mapping for prediction to obtain fine-grid NWP prediction data for the future period; the wind power prediction unit 304 is used to: use the first mapping to convert the fine-grid NWP prediction data into the first fine-grid meteorological prediction data for the future period, and input the first fine-grid meteorological prediction data into a pre-trained wind power prediction model to predict the wind power.

[0057] In the embodiments of the present invention, the refinement unit 302 is further used to: for any position to be inserted, obtain a preset number of reference data in the neighborhood of the position to be inserted; where the reference data belongs to the measured coarse-grid NWP data; for any reference data, divide the calculation result of the kernel function of the reference data and the position to be inserted by the sum of the calculation results of the kernel functions of each reference data and the position to be inserted to obtain the weight value of the reference data for the position to be inserted; calculate the weighted sum of the reference data based on the weight value as the fine-grid NWP data of the position to be inserted.

[0058] Preferably, satisfying the high-precision condition includes: converting the fine-grid NWP data into fine-grid meteorological data by using a first mapping, calculating the deviation between the fine-grid meteorological data and the measured fine-grid meteorological monitoring data, and determining that the deviation is less than a preset precision threshold; the wind power prediction unit 304 is further configured to: input the measured fine-grid meteorological monitoring data into a second mapping to obtain second fine-grid meteorological prediction data for a future period, and input the second fine-grid meteorological prediction data into the wind power prediction model to obtain a wind power prediction result of the second fine-grid meteorological prediction data in the current test period; compare the wind power prediction results of the first fine-grid meteorological prediction data and the second fine-grid meteorological prediction data in the current test period, and use the fine-grid meteorological prediction data corresponding to the better wind power prediction result as the input data of the wind power prediction model in the current application period.

[0059] According to the technical solution of the embodiment of the present invention, first, the corresponding relationship between the measured coarse-grid NWP data and the measured fine-grid meteorological monitoring data in the historical period is determined as the first mapping, and the measured coarse-grid NWP data is interpolated according to a preset kernel function to obtain fine-grid NWP data. Then, it is judged whether the fine-grid NWP data meets the high-precision condition constrained by the measured fine-grid meteorological monitoring data. If not, the kernel function or the bandwidth therein is adjusted and re-interpolated. If it meets the condition, the fine-grid NWP data is input into the second mapping for prediction to obtain fine-grid NWP prediction data for a future period. Thereafter, the fine-grid NWP prediction data is converted into first fine-grid meteorological prediction data for a future period by using the first mapping, and the first fine-grid meteorological prediction data is input into a pre-trained wind power prediction model to predict the wind power. Through the above processing, high-precision wind power prediction based on NWP data and constrained by the measured fine-grid meteorological monitoring data is realized. The problem that only coarse-grid NWP data can be obtained currently and thus high-precision prediction cannot be achieved is solved through the NWP grid refinement processing under the constraint of the measured fine-grid meteorological monitoring data and the NWP prediction under the fine-grid. Further, as a more optimal solution, the above prediction path is compared with a prediction path that does not rely on NWP data but only relies on the measured fine-grid meteorological monitoring data, and the path with better effect is preferably selected for actual wind power prediction, further ensuring the reliability of the wind power prediction scheme.

[0060] Figure 4 An exemplary system architecture 400 is shown that can apply the dual-mapping-based coastal NWP data grid refinement method or the dual-mapping-based coastal NWP data grid refinement device of the embodiment of the present invention.

[0061] Such as Figure 4As shown, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405 (this architecture is merely an example, and the components included in the specific architecture can be adjusted according to the specific situation of the application). The network 404 is used to provide a medium for communication links between the terminal devices 401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0062] Users can use the terminal devices 401, 402, 403 to interact with the server 405 through the network 404 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 401, 402, 403, such as a wind power prediction application (merely an example).

[0063] The terminal devices 401, 402, 403 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0064] The server 405 can be a server providing various services, such as a background server that provides support for the wind power prediction application operated by users using the terminal devices 401, 402, 403 (merely an example). The background server can process the received wind power prediction requests, etc., and feedback the processing results (such as the predicted wind power - merely an example) to the terminal devices 401, 402, 403.

[0065] It should be noted that the method for refining the coastal NWP data grid based on double mapping provided by the embodiments of the present invention is generally executed by the server 405. Correspondingly, the device for refining the coastal NWP data grid based on double mapping is generally set in the server 405.

[0066] It should be understood that Figure 4 the numbers of terminal devices, networks, and servers in

[0067] The present invention also provides an electronic device. The electronic device according to the embodiments of the present invention includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method for refining the coastal NWP data grid based on double mapping provided by the present invention.

[0068] Next, refer to Figure 5 , which shows a schematic structural diagram of a computer system 500 suitable for implementing the electronic device of the embodiments of the present invention. Figure 5The electronic device shown is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.

[0069] As Figure 5 shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the programs stored in the read-only memory (ROM) 502 or the programs loaded from the storage section 508 into the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0070] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as required. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as required so that the computer program read from it is installed into the storage section 508 as required.

[0071] Specifically, according to the embodiments disclosed in the present invention, the process described in the above main step diagram can be implemented as a computer software program. For example, the embodiments of the present invention include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the method shown in the main step diagram. In the above embodiments, the computer program can be downloaded and installed from the network through the communication section 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit 501, the above functions defined in the system of the present invention are executed.

[0072] It should be noted that the computer-readable medium shown in the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, 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 above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0073] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks can occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0074] The units involved in the embodiments of the present invention can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: a processor includes a first mapping establishment unit, a refinement unit, a second mapping prediction unit, and a wind power prediction unit. Among them, the names of these units do not constitute a limitation to the unit itself in some cases. For example, the refinement unit can also be described as "a unit that provides fine-grid NWP data to the second mapping prediction unit".

[0075] As another aspect, the present invention also provides a computer-readable medium, which can be included in the device described in the above embodiments; or it can exist alone without being assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the device, the steps executed by the device include: determining the corresponding relationship between the measured coarse-grid numerical weather prediction (NWP) data and the measured fine-grid meteorological monitoring data in the historical period as the first mapping; interpolating the measured coarse-grid NWP data according to a preset kernel function to obtain fine-grid NWP data; when the fine-grid NWP data meets the preset high-precision conditions constrained by the measured fine-grid meteorological monitoring data, inputting the fine-grid NWP data into a preset second mapping for prediction to obtain fine-grid NWP prediction data for the future period; using the first mapping to convert the fine-grid NWP prediction data into the first fine-grid meteorological prediction data for the future period, and inputting the first fine-grid meteorological prediction data into a pre-trained wind power prediction model to predict the wind power.

[0076] In the technical solution of the embodiments of the present invention, high-precision wind power prediction based on NWP data and constrained by measured fine-grid meteorological monitoring data is achieved. By the NWP grid refinement processing under the constraint of the measured fine-grid meteorological monitoring data and the NWP prediction under the fine grid, the problem that only coarse-grid NWP data can be obtained currently and thus high-precision prediction cannot be achieved is solved. Further, as a better solution, the above prediction path is compared with the prediction path that does not rely on NWP data but only uses the measured fine-grid meteorological monitoring data, and the path with better effect is preferably selected for actual wind power prediction, further ensuring the reliability of the wind power prediction scheme.

[0077] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0078] The specific content about prophet in the disclosure of invention is known technology and does not need to be written into the patent.

Claims

1. A refined method for coastal NWP data grid based on double mapping, characterized in that, Including: Determine the corresponding relationship between the measured coarse-grid numerical weather prediction (NWP) data and the measured fine-grid meteorological monitoring data in the historical period as the first mapping; Interpolate the measured coarse-grid NWP data according to a preset kernel function to obtain fine-grid NWP data; When the fine-grid NWP data meets the preset high-precision conditions constrained by the measured fine-grid meteorological monitoring data, input the fine-grid NWP data into a preset second mapping for prediction to obtain fine-grid NWP prediction data for the future period; Use the first mapping to convert the fine-grid NWP prediction data into first fine-grid meteorological prediction data for the future period, and input the first fine-grid meteorological prediction data into a pre-trained wind power prediction model to predict wind power.

2. The method according to claim 1, wherein The interpolating the measured coarse-grid NWP data according to a preset kernel function to obtain fine-grid NWP data includes: For any position to be inserted, obtain a preset number of reference data in the neighborhood of the position to be inserted; wherein, the reference data belongs to the measured coarse-grid NWP data; Determine the weight value of each reference data for the position to be inserted according to the kernel function, and calculate the weighted sum of the reference data based on the weight value as the fine-grid NWP data for the position to be inserted.

3. The method according to claim 2, wherein The determining the weight value of each reference data for the position to be inserted according to the kernel function includes: For any reference data, divide the calculation result of the kernel function of the reference data and the position to be inserted by the sum of the calculation results of the kernel functions of each reference data and the position to be inserted to obtain the weight value of the reference data for the position to be inserted.

4. The method according to claim 1, wherein Meeting the high-precision conditions includes: Convert the fine-grid NWP data into fine-grid meteorological data using the first mapping, calculate the deviation between the fine-grid meteorological data and the measured fine-grid meteorological monitoring data, and determine that the deviation is less than a preset precision threshold.

5. The method according to claim 1, wherein The method further includes: Input the measured fine-grid meteorological monitoring data into the second mapping to obtain second fine-grid meteorological prediction data for the future period, and input the second fine-grid meteorological prediction data into the wind power prediction model to obtain the wind power prediction result of the second fine-grid meteorological prediction data in the current test cycle; Compare the wind power prediction results of the first fine-grid meteorological prediction data and the second fine-grid meteorological prediction data in the current test cycle, and use the fine-grid meteorological prediction data corresponding to the better wind power prediction result as the input data of the wind power prediction model in the current application cycle.

6. A coastal NWP data grid refinement device based on double mapping, characterized in that, Including: A first mapping establishment unit, configured to: determine the corresponding relationship between the measured coarse-grid numerical weather prediction (NWP) data and the measured fine-grid meteorological monitoring data in the historical period as the first mapping; A refinement unit, configured to: interpolate the measured coarse-grid NWP data according to a preset kernel function to obtain fine-grid NWP data; A second mapping prediction unit, configured to: when the fine-grid NWP data meets a preset high-precision condition constrained by the measured fine-grid meteorological monitoring data, input the fine-grid NWP data into a preset second mapping for prediction to obtain fine-grid NWP prediction data for a future period; A wind power prediction unit, configured to: convert the fine-grid NWP prediction data into first fine-grid meteorological prediction data for a future period by using a first mapping, and input the first fine-grid meteorological prediction data into a pre-trained wind power prediction model to predict wind power.

7. The device according to claim 6, wherein The refinement unit is further configured to: For any position to be inserted, obtain a preset number of reference data in the neighborhood of the position to be inserted; wherein the reference data belongs to the measured coarse-grid NWP data; for any reference data, divide the calculation result of the kernel function of the reference data and the position to be inserted by the sum of the calculation results of the kernel functions of each reference data and the position to be inserted to obtain the weight value of the reference data for the position to be inserted; calculate the weighted sum of the reference data based on the weight value as the fine-grid NWP data of the position to be inserted.

8. The device according to claim 6, characterized in that, Meeting the high-precision condition includes: converting the fine-grid NWP data into fine-grid meteorological data by using a first mapping, calculating the deviation between the fine-grid meteorological data and the measured fine-grid meteorological monitoring data, and determining that the deviation is less than a preset precision threshold; The wind power prediction unit is further configured to: input the measured fine-grid meteorological monitoring data into a second mapping to obtain second fine-grid meteorological prediction data for a future period, input the second fine-grid meteorological prediction data into the wind power prediction model to obtain the wind power prediction result of the second fine-grid meteorological prediction data in the current test cycle; compare the wind power prediction results of the first fine-grid meteorological prediction data and the second fine-grid meteorological prediction data in the current test cycle, and use the fine-grid meteorological prediction data corresponding to the better wind power prediction result as the input data of the wind power prediction model in the current application cycle.

9. An electronic device, characterized in that, Comprising: One or more processors; A storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, the method according to any one of claims 1-5 is implemented.

Images