1. A wind farm data processing method, comprising:

converting the initial wind field data into low-resolution gray scale data;

inputting the low-resolution gray data into a super-resolution neural network to obtain high-resolution gray data; wherein the high resolution is N times the low resolution, and N > 1;

and acquiring target wind field data according to the high-resolution gray scale data.

2. The method of claim 1, wherein the wind farm data comprises horizontal wind farm data and vertical wind farm data;

converting the initial wind field data to low resolution gray scale data, comprising:

converting the initial horizontal wind field data into low-resolution horizontal gray scale data; converting the initial vertical wind field data into low-resolution vertical gray scale data;

correspondingly, inputting the low-resolution gray data into a super-resolution neural network to obtain high-resolution gray data, and the method comprises the following steps:

inputting the low-resolution horizontal direction gray scale data into the super-resolution neural network to obtain high-resolution horizontal direction gray scale data; inputting the low-resolution vertical direction gray scale data into the super-resolution neural network to obtain high-resolution vertical direction gray scale data;

correspondingly, obtaining target wind field data according to the high-resolution gray scale data comprises:

converting the high-resolution horizontal direction gray scale data into target horizontal direction wind field data; converting the high-resolution vertical direction gray scale data into target vertical direction wind field data;

and synthesizing the target horizontal direction wind field data and the target vertical direction wind field data into target wind field data.

3. The method of claim 2, wherein the wind field data is comprised of a matrix of wind speeds and the gray scale data is comprised of a matrix of gray scale values; before converting the initial wind field data into low-resolution gray scale data, the method further comprises the following steps:

acquiring a first value range of wind speed and a second value range of gray value;

and determining the mapping relation between the wind speed and the gray value according to the first value range and the second value range.

4. The method of claim 3, wherein converting the initial wind field data to low resolution gray scale data comprises:

converting each horizontal direction wind speed in a wind speed matrix corresponding to the initial horizontal direction wind field data into a gray value according to the mapping relation, and obtaining low-resolution horizontal direction gray data;

and converting each vertical direction wind speed in the wind speed matrix corresponding to the initial vertical direction wind field data into a gray value according to the mapping relation, and obtaining low-resolution vertical direction gray data.

5. The method of claim 3, wherein the high resolution horizontal direction grayscale data is converted to target horizontal direction wind field data; converting the high resolution vertical direction grayscale data to target vertical direction wind field data, comprising:

converting each gray value in a gray value matrix corresponding to the high-resolution horizontal direction gray data into horizontal direction wind speed according to the mapping relation to obtain target horizontal direction wind field data;

and converting each gray value in the gray value matrix corresponding to the high-resolution vertical direction gray data into a vertical direction wind speed according to the mapping relation, and obtaining target vertical direction wind field data.

6. The method according to any one of claims 1 to 5, wherein the super-resolution neural network is trained in a manner that:

converting the first-resolution wind field data into first-resolution gray scale data;

converting the second-resolution wind field data into second-resolution gray scale data; wherein the second resolution is greater than the first resolution, and the second resolution is an integer multiple of the first resolution;

forming a training data pair by the first-resolution gray data and the second-resolution gray data;

training the super-resolution neural network based on the training data.

7. The method of claim 6, wherein the multiple relationship between the second resolution and the first resolution comprises at least two;

forming a training data pair by the first-resolution gray data and the second-resolution gray data, including:

forming at least two training data pairs by the second-resolution gray data and the first-resolution gray data according to the multiple relation;

correspondingly, training the super-resolution neural network based on the training data comprises:

and training the super-resolution neural network based on the training data in sequence according to the sequence of the multiple relation from small to large.

8. A wind farm data processing apparatus, comprising:

the low-resolution gray data acquisition module is used for converting the initial wind field data into low-resolution gray data;

the high-resolution gray data acquisition module is used for inputting the low-resolution gray data into a super-resolution neural network to acquire high-resolution gray data; wherein the high resolution is N times the low resolution, and N > 1;

and the target wind field data acquisition module is used for acquiring the target wind field data according to the high-resolution gray scale data.

9. Computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the wind farm data processing method according to any of claims 1 to 7 when executing the program.

10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out a wind farm data processing method according to any one of claims 1 to 7.

Background

When predicting a wind field, a general method is to divide a prediction area into grids according to a certain distance, and acquire wind speeds at the grid points to obtain wind field data. An excessively coarse grid often fails to meet the accuracy of wind field prediction, and therefore downscaling calculation needs to be performed on wind field data. And the downscaling calculation is performed on a supercomputer for weather forecast of wind field data because parameters are large in calculation amount. Many computers that do not have super-computing power simply cannot perform computations. Supercomputers are quite expensive and burdensome to most researchers.

Disclosure of Invention

Embodiments of the present invention provide a method, an apparatus, a device, and a storage medium for processing wind field data, which can implement downscaling calculation of wind field data without a supercomputer, reduce the amount of calculation for processing wind field data, and reduce cost.

In a first aspect, an embodiment of the present invention provides a method for processing wind farm data, including:

converting the initial wind field data into low-resolution gray scale data;

inputting the low-resolution gray data into a super-resolution neural network to obtain high-resolution gray data; wherein the high resolution is N times the low resolution, and N > 1;

and acquiring target wind field data according to the high-resolution gray scale data.

In a second aspect, an embodiment of the present invention further provides a wind farm data processing apparatus, including:

the low-resolution gray data acquisition module is used for converting the initial wind field data into low-resolution gray data;

the high-resolution gray data acquisition module is used for inputting the low-resolution gray data into a super-resolution neural network to acquire high-resolution gray data; wherein the high resolution is N times the low resolution, and N > 1;

and the target wind field data acquisition module is used for acquiring the target wind field data according to the high-resolution gray scale data.

In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the wind farm data processing method according to the embodiment of the present invention when executing the program.

The embodiment of the invention discloses a wind field data processing method, a wind field data processing device, wind field data processing equipment and a storage medium. Converting the initial wind field data into low-resolution gray scale data; inputting the low-resolution gray data into a super-resolution neural network to obtain high-resolution gray data; and acquiring target wind field data according to the high-resolution gray scale data. According to the wind field data processing method disclosed by the embodiment of the invention, the initial wind field data is converted into the low-resolution gray data, the low-resolution gray data is input into the super-resolution neural network, the high-resolution gray data is obtained, the target wind field data is obtained, the downscaling calculation of the wind field data can be realized without a super computer, the calculation amount of wind field data processing can be reduced, and the cost is reduced.

Drawings

Fig. 1 is a flowchart of a wind farm data processing method according to a first embodiment of the present invention;

FIG. 2 is a diagram illustrating a super-resolution neural network training process according to a second embodiment of the present invention;

FIG. 3 is an exemplary illustration of wind farm data processing in a second embodiment of the present invention;

fig. 4 is a schematic structural diagram of a wind farm data processing apparatus according to a third embodiment of the present invention;

fig. 5 is a schematic structural diagram of a computer device in the fourth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a flowchart of a wind farm data processing method according to an embodiment of the present invention, where the present embodiment is applicable to a case where wind farm data is downscaled, and the method may be executed by a wind farm data processing apparatus, and the apparatus may be composed of hardware and/or software, and may be generally integrated in a device having a wind farm data processing function. As shown in fig. 1, the method specifically includes the following steps:

step 110, converting the initial wind field data into low-resolution gray scale data.

The wind field data may be formed by a wind speed matrix, and the gray data may be formed by a gray value matrix. The wind speed matrix may be formed by acquiring wind speeds at positions of the grid points after the prediction region is subjected to grid division. For example: and carrying out grid division on the prediction region according to the length of 25 kilometers, namely the side length of a grid is 25 kilometers.

Wherein the wind speed in the wind field data comprises a magnitude and a direction. Low-resolution gray-scale data may be understood as gray-scale data with a resolution of less than 100 x 100, for example: 40*40. Wherein 100 × 100 and 40 × 40 represent the number of pixels included in the horizontal and vertical directions of the image. In this embodiment, the manner of converting the initial wind field data into the low-resolution gray scale data may be: the wind speed direction is not considered, only the wind speed is considered, and each wind speed in a wind speed matrix corresponding to the initial wind field data is converted into a gray value; or, in consideration of the wind speed direction, decomposing the initial wind field data into initial horizontal-direction wind field data and initial vertical-direction wind field data, converting the initial horizontal-direction wind field data into low-resolution horizontal-direction gray data, and converting the initial vertical-direction wind field data into low-resolution vertical-direction gray data.

In this embodiment, before converting the initial wind field data into the low-resolution gray scale data, the method further includes the following steps: acquiring a first value range of wind speed and a second value range of gray value; and determining the mapping relation between the wind speed and the gray value according to the first value range and the second value range.

Wherein, the first value range of the wind speed can be determined according to the climate of the prediction area, for example: can be set to [ -a, a [ -a]And a can take any value between 30 and 60. The second value range of the gray value is [0,255%]. Then, the mapping relationship between the wind speed and the gray value isWherein A is a wind speed value, and B is a corresponding gray value.

Specifically, the process of converting the initial wind field data into the low-resolution gray scale data may be: converting each horizontal direction wind speed in a wind speed matrix corresponding to the initial horizontal direction wind field data into a gray value according to the mapping relation, and obtaining low-resolution horizontal direction gray data; and converting each vertical direction wind speed in the wind speed matrix corresponding to the initial vertical direction wind field data into a gray value according to the mapping relation, and obtaining low-resolution vertical direction gray data.

In this embodiment, after each wind speed value in the wind speed matrix is obtained, the wind speed matrix may be converted into a gray value matrix according to the mapping relationship between the wind speed and the gray value, that is, the wind field data is converted into low-resolution gray data. Illustratively, assume that the wind speed ranges from [ -50,50 [ -50 [ ]]If one of the wind speeds in the horizontal direction in the wind speed matrix corresponding to the initial horizontal-direction wind field data is 20, the converted gray value is the gray valueI.e. wind speed 20 corresponds to a grey value of 178.5. And converting each horizontal direction wind speed in the wind speed matrix corresponding to the initial horizontal direction wind field data and each vertical direction wind speed in the wind speed matrix corresponding to the initial vertical direction wind field data according to the mode to obtain low-resolution horizontal direction gray scale data and low-resolution vertical direction gray scale data.

And 120, inputting the low-resolution gray data into a super-resolution neural network to obtain high-resolution gray data.

The high resolution gray scale data may be understood as gray scale data with a resolution greater than 100 × 100, for example: 400*400. And the high resolution is N times the low resolution, N > 1. For example: and taking N as 4. The super-resolution neural network is a trained neural network, can implement downscaling processing of data, and can be composed of a Residual Channel Attention Block (RCAB).

In this embodiment, for the case where the wind speed direction is not considered, the low-resolution gray scale data converted from the initial wind field data may be directly input to the super-resolution neural network to obtain the high-resolution gray scale data. For the condition of considering the wind speed direction, inputting the low-resolution horizontal direction gray data into a super-resolution neural network to obtain high-resolution horizontal direction gray data; and inputting the low-resolution vertical gray data into a super-resolution neural network to obtain high-resolution vertical gray data.

And step 130, acquiring target wind field data according to the high-resolution gray scale data.

In this embodiment, for the case that the wind speed direction is not considered, the high-resolution gray scale data may be directly converted into a target wind speed matrix according to the mapping relationship between the wind speed and the gray scale value, and then the wind speeds in the matrix are fused to obtain the target wind field data.

For the condition of considering the wind speed direction, converting each gray value in the gray value matrix corresponding to the high-resolution horizontal direction gray data into the wind speed in the horizontal direction according to the mapping relation, and obtaining target horizontal direction wind field data; and converting each gray value in the gray value matrix corresponding to the high-resolution vertical direction gray data into a vertical direction wind speed according to the mapping relation, and obtaining target vertical direction wind field data.

Wherein, the mapping relationship between the wind speed and the gray value is assumed to beThe gray value in the gray matrix corresponding to the gray data can be converted into the wind speed, that is, a can be calculated according to the mapping relation under the condition that B is known.

Specifically, the process of acquiring the target wind field data according to the high-resolution gray scale data may be: converting the high-resolution horizontal direction gray scale data into target horizontal direction wind field data; converting the high-resolution vertical-direction gray scale data into target vertical-direction wind field data; and synthesizing the target horizontal direction wind field data and the target vertical direction wind field data into target wind field data.

According to the technical scheme of the embodiment, initial wind field data are converted into low-resolution gray scale data; inputting the low-resolution gray data into a super-resolution neural network to obtain high-resolution gray data; and acquiring target wind field data according to the high-resolution gray scale data. According to the wind field data processing method disclosed by the embodiment of the invention, the initial wind field data is converted into the low-resolution gray data, the low-resolution gray data is input into the super-resolution neural network, the high-resolution gray data is obtained, the target wind field data is obtained, the downscaling calculation of the wind field data can be realized without a super computer, the calculation amount of wind field data processing can be reduced, and the cost is reduced.

Example two

Fig. 2 is a schematic diagram of a super-resolution neural network training process provided by the second embodiment of the present invention. Based on the above embodiment, as shown in fig. 2, the training method of the super-resolution neural network includes the following steps:

step 210, converting the first-resolution wind field data into first-resolution gray scale data.

The first-resolution wind field data comprises first-resolution horizontal wind field data and first-resolution vertical wind field data. Specifically, the manner of converting the first-resolution wind field data into the first-resolution gray scale data may be: converting each horizontal direction wind speed in a wind speed matrix corresponding to the first resolution horizontal direction wind field data into a gray value according to the mapping relation between the wind speed and the gray value to obtain first resolution horizontal direction gray data; and converting each vertical direction wind speed in the wind speed matrix corresponding to the first resolution vertical direction wind field data into a gray value according to the mapping relation between the wind speed and the gray value, and obtaining the first resolution vertical direction gray data.

Step 220, converting the second resolution wind field data into second resolution gray scale data.

Wherein the second resolution is greater than the first resolution, and the second resolution is N times the first resolution. The second-resolution wind field data includes second-resolution horizontal-direction wind field data and second-resolution vertical-direction wind field data. Specifically, the manner of converting the second-resolution wind field data into the second-resolution gray scale data may be: converting each horizontal direction wind speed in a wind speed matrix corresponding to the second resolution horizontal direction wind field data into a gray value according to the mapping relation between the wind speed and the gray value to obtain second resolution horizontal direction gray data; and converting each vertical direction wind speed in the wind speed matrix corresponding to the wind field data in the vertical direction of the second resolution ratio into a gray value according to the mapping relation between the wind speed and the gray value, and obtaining the gray data in the vertical direction of the second resolution ratio.

Step 230, the first resolution gray data and the second resolution gray data are combined into a training data pair.

Specifically, the first-resolution horizontal-direction grayscale data and the second-resolution horizontal-direction grayscale data form a training data pair, and the first-resolution vertical-direction grayscale data and the second-resolution vertical-direction grayscale data form a training data pair.

Step 240, training the super-resolution neural network based on the training data.

In this embodiment, the process of training the super-resolution neural network based on the training data may be to input the first-resolution gray data into the super-resolution neural network, output the predicted gray data, calculate a loss function according to the predicted gray data and the second-resolution gray data, and adjust parameters in the super-resolution neural network based on the loss function until the super-resolution neural network meets the accuracy requirement.

Optionally, the multiple relationship between the second resolution and the first resolution includes at least two. The manner of forming the first-resolution gray data and the second-resolution gray data into the training data pair may be: and forming at least two training data pairs by the second-resolution gray data and the first-resolution gray data according to the multiple relation.

Wherein, the multiple relation may include a 2-fold relation, a 4-fold relation, a 6-fold relation, and the like. The composed training data pairs include: the training data pair is composed of the first resolution gray data and the 2-time second resolution gray data, the training data pair is composed of the first resolution gray data and the 4-time second resolution gray data, and the training data pair is composed of the first resolution gray data and the 6-time second resolution gray data.

Optionally, the method for training the super-resolution neural network based on the training data may be: and training the super-resolution neural network based on the training data in sequence according to the sequence of the multiple relation from small to large.

Specifically, firstly, training a super-resolution neural network based on training data composed of first-resolution gray data and 2-fold relation second-resolution gray data to obtain a first super-resolution neural network; training the first super-resolution neural network based on training data consisting of the first-resolution gray data and 4 times of second-resolution gray data to obtain a second super-resolution neural network; and training the second super-resolution neural network based on the training data pair consisting of the first-resolution gray data and the 6-fold second-resolution gray data, and repeating the steps until all the training data pairs are trained, so as to obtain the final super-resolution neural network. This has the advantage that the accuracy of the super-resolution neural network can be improved.

Illustratively, fig. 3 is an exemplary diagram of the processing of the session data in the present embodiment. Table 1 shows the recognition accuracy of the super-resolution neural network in this embodiment.

TABLE 1

According to the technical scheme of the embodiment, first-resolution wind field data are converted into first-resolution gray scale data; converting the second-resolution wind field data into second-resolution gray scale data; forming a training data pair by the first resolution gray data and the second resolution gray data; the super-resolution neural network is trained based on the training data. The processing precision of the super-resolution neural network can be improved.

EXAMPLE III

Fig. 4 is a schematic structural diagram of a wind farm data processing apparatus according to a third embodiment of the present invention, and as shown in fig. 4, the apparatus includes:

a low-resolution gray data acquisition module 410, configured to convert the initial wind field data into low-resolution gray data;

the high-resolution gray data acquisition module 420 is configured to input the low-resolution gray data into the super-resolution neural network to obtain high-resolution gray data; wherein the high resolution is N times the low resolution, and N > 1;

and a target wind field data obtaining module 430, configured to obtain target wind field data according to the high-resolution grayscale data.

Optionally, the wind field data includes horizontal wind field data and vertical wind field data;

the low resolution gray scale data acquisition module 410 is further configured to:

converting the initial horizontal wind field data into low-resolution horizontal gray scale data; converting the initial vertical wind field data into low-resolution vertical gray scale data;

optionally, the high resolution gray scale data obtaining module 420 is further configured to:

inputting the low-resolution horizontal direction gray data into a super-resolution neural network to obtain high-resolution horizontal direction gray data; inputting the low-resolution vertical direction gray data into a super-resolution neural network to obtain high-resolution vertical direction gray data;

optionally, the target wind field data obtaining module 430 is further configured to:

converting the high-resolution horizontal direction gray scale data into target horizontal direction wind field data; converting the high-resolution vertical-direction gray scale data into target vertical-direction wind field data;

and synthesizing the target horizontal direction wind field data and the target vertical direction wind field data into target wind field data.

Optionally, the wind field data is composed of a wind speed matrix, and the gray data is composed of a gray value matrix; further comprising: a mapping relation obtaining module, configured to:

acquiring a first value range of wind speed and a second value range of gray value;

and determining the mapping relation between the wind speed and the gray value according to the first value range and the second value range.

Optionally, the low-resolution gray scale data obtaining module 410 is further configured to:

converting each horizontal direction wind speed in a wind speed matrix corresponding to the initial horizontal direction wind field data into a gray value according to the mapping relation, and obtaining low-resolution horizontal direction gray data;

and converting each vertical direction wind speed in the wind speed matrix corresponding to the initial vertical direction wind field data into a gray value according to the mapping relation, and obtaining low-resolution vertical direction gray data.

Optionally, the target wind field data obtaining module 430 is further configured to:

converting each gray value in a gray value matrix corresponding to the high-resolution horizontal direction gray data into horizontal direction wind speed according to the mapping relation, and obtaining target horizontal direction wind field data;

and converting each gray value in the gray value matrix corresponding to the high-resolution vertical direction gray data into a vertical direction wind speed according to the mapping relation, and obtaining target vertical direction wind field data.

Optionally, the method further includes: the super-resolution neural network training module is used for:

converting the first-resolution wind field data into first-resolution gray scale data;

converting the second-resolution wind field data into second-resolution gray scale data; wherein the second resolution is greater than the first resolution, and the second resolution is an integer multiple of the first resolution;

forming a training data pair by the first resolution gray data and the second resolution gray data;

the super-resolution neural network is trained based on the training data.

Optionally, the multiple relationship between the second resolution and the first resolution includes at least two; the super-resolution neural network training module is also used for:

forming at least two training data pairs by the second-resolution gray data and the first-resolution gray data according to the multiple relation;

and training the super-resolution neural network based on the training data in sequence according to the sequence of the multiple relation from small to large.

The device can execute the methods provided by all the embodiments of the invention, and has corresponding functional modules and beneficial effects for executing the methods. For details not described in detail in this embodiment, reference may be made to the methods provided in all the foregoing embodiments of the present invention.

Example four

Fig. 5 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 5 illustrates a block diagram of a computer device 312 suitable for use in implementing embodiments of the present invention. The computer device 312 shown in FIG. 5 is only an example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention. The device 312 is a computing device for typical wind farm data processing functions.

As shown in FIG. 5, computer device 312 is in the form of a general purpose computing device. The components of computer device 312 may include, but are not limited to: one or more processors 316, a storage device 328, and a bus 318 that couples the various system components including the storage device 328 and the processors 316.

Bus 318 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

Computer device 312 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 312 and includes both volatile and nonvolatile media, removable and non-removable media.

Storage 328 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 330 and/or cache Memory 332. The computer device 312 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 334 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk-Read Only Memory (CD-ROM), a Digital Video disk (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 318 by one or more data media interfaces. Storage 328 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

Program 336 having a set (at least one) of program modules 326 may be stored, for example, in storage 328, such program modules 326 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which may comprise an implementation of a network environment, or some combination thereof. Program modules 326 generally carry out the functions and/or methodologies of embodiments of the invention as described herein.

The computer device 312 may also communicate with one or more external devices 314 (e.g., keyboard, pointing device, camera, display 324, etc.), with one or more devices that enable a user to interact with the computer device 312, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 312 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 322. Also, computer device 312 may communicate with one or more networks (e.g., a Local Area Network (LAN), Wide Area Network (WAN), etc.) and/or a public Network, such as the internet, via Network adapter 320. As shown, network adapter 320 communicates with the other modules of computer device 312 via bus 318. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the computer device 312, including but not limited to: microcode, device drivers, Redundant processing units, external disk drive Arrays, disk array (RAID) systems, tape drives, and data backup storage systems, to name a few.

The processor 316 executes various functional applications and data processing by running programs stored in the storage device 328, for example, to implement the wind farm data processing method provided by the above-described embodiment of the present invention.

Example four

Embodiments of the present invention provide a computer-readable storage medium on which a computer program is stored, where the computer program, when executed by a processing device, implements a wind farm data processing method as in embodiments of the present invention.

The computer readable medium of the present invention described above may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: converting the initial wind field data into low-resolution gray scale data; inputting the low-resolution gray data into a super-resolution neural network to obtain high-resolution gray data; and acquiring target wind field data according to the high-resolution gray scale data.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.