A wind power prediction method, device, equipment and storage medium

Through the wind power prediction method combined with a generalized additive model and a k-means clustering algorithm, the problem of insufficient prediction accuracy of stroke power in the existing technology is solved, and the explanation and accurate prediction of factors affecting wind power are realized, which significantly improves the prediction accuracy .

CN114298395BActive Publication Date: 2024-11-12GUANGDONG POWER GRID CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111601297.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-24
Publication Date
2024-11-12
Estimated Expiration
2041-12-24

AI Technical Summary

Technical Problem

Existing deep learning models are difficult to explain the nonlinear relationship between wind power and multiple influencing factors, resulting in insufficient wind power prediction accuracy.

Method used

The generalized additive model is used to combine the k-means clustering algorithm to extract and cluster analysis the wind speed, wind direction and temperature data to explain the impact of each variable on wind power and improve the prediction accuracy.

Benefits of technology

The generalized additive model is used to explain the impact of each variable on wind power. Combined with clustering analysis, the accuracy of wind power prediction is significantly improved, the average absolute percentage error is reduced, and the accuracy of prediction is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114298395B_ABST
    Figure CN114298395B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention discloses a wind power prediction method, device, equipment and storage medium. The method includes: collecting sample data, and performing feature extraction on the sample data to obtain a model input feature data set; using a k-means clustering algorithm to perform cluster analysis on the model input feature data set, and adding the data category obtained by clustering as a new feature to the model input feature data set; training a pre-set generalized additive model according to the model input feature data set to obtain a wind power prediction model; inputting the data to be tested into the wind power prediction model to obtain the data category of the data to be tested and the prediction result of the wind power. The technical solution of the embodiment of the present invention realizes the explanation of the influence of each variable on wind power through a generalized additive model, and effectively improves the accuracy of wind power prediction by combining cluster analysis.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of artificial intelligence technology, and in particular to a wind power prediction method, device, equipment and storage medium. Background Art

[0002] In recent years, with the rapid development of the wind power industry, the installed capacity of wind power is growing on a large scale. However, the randomness and volatility of wind power generation will have a huge impact on the stability of the power system after it is connected to the grid. If the output of wind power can be predicted in advance, it will effectively improve the utilization rate of wind energy and help dispatchers to reasonably arrange the dispatch plan, thereby ensuring the safe operation of the power grid. Therefore, the research on short-term wind power prediction algorithm is of great significance.

[0003] In addition, there are many influencing factors in wind power prediction, and the nonlinear relationship is complex. However, the existing deep learning models cannot explain the nonlinear relationship between wind power and multiple influencing factors due to the number of parameters and the complex methods of extracting and combining features. Summary of the invention

[0004] The embodiments of the present invention provide a wind power prediction method, device, equipment and storage medium to explain the influence of various variables on wind power through a generalized additive model, and effectively improve the accuracy of wind power prediction in combination with cluster analysis.

[0005] In a first aspect, an embodiment of the present invention provides a wind power prediction method, comprising:

[0006] Collect sample data and extract features from the sample data to obtain a model input feature data set;

[0007] The k-means clustering algorithm is used to perform cluster analysis on the model input feature data set, and the data categories obtained by clustering are added as new features to the model input feature data set;

[0008] The pre-set generalized additive model is trained according to the model input feature data set to obtain a wind power prediction model;

[0009] The data to be measured are input into the wind power prediction model to obtain the data category of the data to be measured and the prediction result of the wind power.

[0010] Optionally, a model input feature data set, including: the model input x value and the model input y value;

[0011] Extract features from sample data to obtain the model input feature data set, including:

[0012] The wind speed data, wind direction data and temperature data in the sample data are used as the x-values ​​of the model input, and the power data in the sample data are used as the y-values ​​of the model input.

[0013] Optionally, a k-means clustering algorithm is used to perform cluster analysis on the model input feature data set, and the data categories obtained by clustering are added as new features to the model input feature data set, including:

[0014] Set the cluster category to k, and randomly select k model input feature data from the model input feature data set as the initial cluster center;

[0015] Calculate the distance from each model input feature data to each cluster center, and divide each model input feature data into the cluster corresponding to the cluster center closest to it;

[0016] Calculate the mean of all model input feature data within each cluster and use the mean to update the cluster center of the cluster;

[0017] Return to the step of calculating the distance from each model input feature data to each cluster center, and dividing each model input feature data into the cluster corresponding to the cluster center closest to it, until the position change of each cluster center before and after the update is less than the specified threshold;

[0018] The data category of each model input feature data is taken as a new feature and added to the x value of the model input.

[0019] Optionally, the distance from each model input feature data to each cluster center is the Euclidean distance.

[0020] Alternatively, the generalized additive model can be expressed as:

[0021] y Linear =β0+β1f1(X1)+β2f2(X2)+β3f3(X3)+β4f4(X4),

[0022] Among them, X1 represents wind speed, X2 represents wind direction, X3 represents temperature, X4 represents data category, β k (k=1,2,3,4) represents constant parameters, f i (x) is a smooth function, y Linear is the power value.

[0023] Optionally, before extracting features from the sample data, the process further includes: deleting sample data containing abnormal values ​​and null values.

[0024] Optionally, the data to be measured include: wind speed data, wind direction data and temperature data at the time when the wind power needs to be predicted.

[0025] In a second aspect, an embodiment of the present invention further provides a wind power prediction device, comprising:

[0026] The feature extraction module is used to collect sample data and extract features from the sample data to obtain a model input feature data set;

[0027] The clustering analysis module is used to perform cluster analysis on the model input feature data set using the k-means clustering algorithm, and add the data categories obtained by clustering as new features to the model input feature data set;

[0028] A model training module is used to train a pre-set generalized additive model according to a model input feature data set to obtain a wind power prediction model;

[0029] The power prediction module is used to input the data to be tested into the wind power prediction model to obtain the data category of the data to be tested and the prediction result of the wind power.

[0030] In a third aspect, an embodiment of the present invention further provides a computer device, the device comprising:

[0031] one or more processors;

[0032] a storage device for storing one or more programs,

[0033] When one or more programs are executed by one or more processors, the one or more processors implement the wind power prediction method provided by any embodiment of the present invention.

[0034] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the wind power prediction method provided by any embodiment of the present invention.

[0035] The technical solution of the embodiment of the present invention obtains a model input feature data set by collecting sample data and performing feature extraction on the sample data; clustering analysis is performed on the model input feature data set using a k-means clustering algorithm, and the data categories obtained by clustering are added as new features to the model input feature data set; a pre-set generalized additive model is trained according to the model input feature data set to obtain a wind power prediction model; the data to be tested is input into the wind power prediction model to obtain the data category of the data to be tested and the prediction result of the wind power, which solves the problem in the prior art that the wind power cannot be accurately and effectively predicted, realizes the explanation of the influence of various variables on the wind power by the generalized additive model, and effectively improves the accuracy of wind power prediction in combination with cluster analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1a is a flow chart of a wind power prediction method in Embodiment 1 of the present invention;

[0037] Figure 1b This is an effect diagram of wind speed, wind direction and temperature on wind power in Embodiment 1 of the present invention;

[0038] Figure 1c This is an actual prediction effect diagram in the first embodiment of the present invention;

[0039] Figure 2 is a structural schematic diagram of a wind power prediction device in Embodiment 2 of the present invention;

[0040] Figure 3 It is a structural diagram of a computer device in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0041] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0042] Embodiment 1

[0043] Figure 1a This is a flow chart of a wind power prediction method in Embodiment 1 of the present invention. This embodiment is applicable to the case of predicting wind power based on wind energy data to be measured. The method can be executed by a wind power prediction device, which can be implemented by hardware and / or software and can generally be integrated in a computer device that provides a wind power prediction function. Specifically, refer to Figure 1a , the method may include the following steps:

[0044] Step 110: Collect sample data and perform feature extraction on the sample data to obtain a model input feature data set.

[0045] In this embodiment, the sample data includes wind speed data, wind direction data, temperature data and wind power. For example, the sample data may be the wind speed data, wind direction data, temperature data and power data of a wind turbine in a wind farm in a certain region from 2019-01-01 00:00 to 2020-12-31 23:45, and the resolution of data collection is 15min. Among them, the sample data from 2019-01-01 00:00 to 2020-12-28 23:45 is used as the training set of the model, and the sample data from 2020-12-29 00:00 to 2020-12-31 23:45 is used as the test set of the model.

[0046] Optionally, before extracting features from the sample data, the process may further include: deleting sample data containing abnormal values ​​and null values.

[0047] In this embodiment, in order to avoid affecting the accuracy of the subsequent training model, for the sample data in the training set, abnormal sample data whose values ​​obviously deviate from the other values ​​and sample data with null values ​​are first screened out, and the screened out abnormal sample data are deleted, and then feature extraction is performed on the remaining sample data.

[0048] Optionally, the model input feature data set includes: the model input x value and the model input y value; extracting features from the sample data to obtain the model input feature data set may include: using the wind speed data, wind direction data and temperature data in the sample data as the model input x value, and using the power data in the sample data as the model input y value. That is, the model input feature data set: x = {wind speed, wind direction, temperature}, y = {power}.

[0049] Step 120: Use the k-means clustering algorithm to perform cluster analysis on the model input feature data set, and add the data categories obtained by clustering as new features to the model input feature data set.

[0050] In this embodiment, in order to further improve the prediction accuracy of wind power, wind speed, wind direction and temperature are used as clustering indicators, k-means clustering is performed on the sample data after feature processing, and the data category of each sample data obtained by clustering is added to the sample data.

[0051] Optionally, a k-means clustering algorithm is used to perform cluster analysis on the model input feature data set, and the data categories obtained by clustering are added as new features to the model input feature data set, which may include: setting the cluster category to k, and randomly selecting k model input feature data from the model input feature data set as initial cluster centers; calculating the distance from each model input feature data to each cluster center, and dividing each model input feature data into a cluster corresponding to the nearest cluster center; calculating the mean of all model input feature data in each cluster, and using the mean to update the cluster center of the cluster; returning to execute the steps of calculating the distance from each model input feature data to each cluster center, and dividing each model input feature data into a cluster corresponding to the nearest cluster center, until the position change of each cluster center before and after the update is less than a specified threshold; adding the obtained data category of each model input feature data as a new feature to the model input x value.

[0052] The threshold can be set to 0.0001, or other values ​​as required. After adding the data category, the model input feature data set is updated to: x = {wind speed, wind direction, temperature, data category}, y = {power}.

[0053] Optionally, the distance from each model input feature data to each cluster center is the Euclidean distance. In n-dimensional space, the formula for the Euclidean distance is:

[0054]

[0055] Where x=(x1,x2…x n ) represents a model input feature data, y=(y1,y2…y n ) represents a cluster center, and d(x,y) represents the Euclidean distance between the model input feature data x and the cluster center y.

[0056] Step 130: training a preset generalized additive model according to the model input feature data set to obtain a wind power prediction model.

[0057] Alternatively, the generalized additive model can be expressed as: Linear =β0+β1f1(X1)+β2f2(X2)+β3f3(X3)+β4f4(X4), where X1 represents wind speed, X2 represents wind direction, X3 represents temperature, X4 represents data category, and β k (k=1,2,3,4) represents constant parameters, f i (x) is a smooth function, y Linear is the power value.

[0058] In this embodiment, the clustered updated model input feature data set is input into the generalized additive model to train the model parameters so that the model's prediction ability reaches the best. When the model training is completed to obtain the wind power prediction model, the test set is input into the wind power prediction model to objectively evaluate the performance of the wind power prediction model.

[0059] For example, Figure 1bAs shown, the horizontal axis represents the measured value of each explanatory variable, the vertical axis represents the smooth fitting value of the influence of each explanatory variable on wind power, the solid line represents the smooth fitting curve of wind power, and the dotted line is the 95% confidence interval. The results show that wind speed, wind direction and temperature are all nonlinearly related to wind power. From the relationship between wind speed and power, it can be seen that at the beginning, when the wind speed is between 0-2m / s, the power decreases with the increase of wind speed. Between 2-5m / s, the power increases with the increase of wind speed, reaches a peak at 5m / s, then begins to decline to 10m / s and then begins to rise again, and begins to decline again at 15m / s, and finally begins to rise at 18m / s. From the relationship between wind direction and power, it can be seen that when the wind direction is between 0-200°, the power decreases with the increase of wind direction, reaches the minimum value at 200°, and then begins to increase with the increase of wind direction. From the relationship between temperature and power, we can see that when the temperature is between 0-4℃, the power decreases as the temperature rises, and when the temperature is between 4-20℃, the power increases as the temperature rises, reaches a maximum value at 20℃, then begins to decrease to 30℃ and then starts to increase again.

[0060] like Figure 1c The figure shows the prediction effect of short-term wind power forecast, the solid line is the actual value, and the dotted line is the predicted value. Figure 1c It can be seen that the wind power prediction method proposed in this embodiment can better predict the power of the wind farm. The mean absolute percentage error MAPE is used to verify the accuracy of the wind power prediction model, and its calculation method is: Where N is the number of samples, y i is the actual value, is the predicted value. According to the error analysis, the average absolute percentage error is 11.43%, and the prediction accuracy is relatively high.

[0061] Step 140: input the data to be measured into the wind power prediction model to obtain the data category of the data to be measured and the prediction result of the wind power.

[0062] Optionally, the data to be measured include: wind speed data, wind direction data and temperature data at the time when the wind power needs to be predicted.

[0063] The technical solution of the embodiment of the present invention obtains a model input feature data set by collecting sample data and performing feature extraction on the sample data; clustering analysis is performed on the model input feature data set using a k-means clustering algorithm, and the data categories obtained by clustering are added as new features to the model input feature data set; a pre-set generalized additive model is trained according to the model input feature data set to obtain a wind power prediction model; the data to be tested is input into the wind power prediction model to obtain the data category of the data to be tested and the prediction result of the wind power, which solves the problem in the prior art that the wind power cannot be accurately and effectively predicted, realizes the explanation of the influence of various variables on the wind power by the generalized additive model, and effectively improves the accuracy of wind power prediction in combination with cluster analysis.

[0064] Embodiment 2

[0065] Figure 2 : is a schematic diagram of the structure of a wind power prediction device in the second embodiment of the present invention. This embodiment is applicable to the case of predicting wind power based on wind energy data to be measured. The device can be implemented by hardware and / or software and can generally be integrated in a computer device that provides a wind power prediction function. Specifically, refer to Figure 2 , the device may include:

[0066] The feature extraction module 210 is used to collect sample data and perform feature extraction on the sample data to obtain a model input feature data set;

[0067] The cluster analysis module 220 is used to perform cluster analysis on the model input feature data set using the k-means clustering algorithm, and add the data categories obtained by clustering as new features to the model input feature data set;

[0068] A model training module 230 is used to train a preset generalized additive model according to a model input feature data set to obtain a wind power prediction model;

[0069] The power prediction module 240 is used to input the data to be measured into the wind power prediction model to obtain the data category of the data to be measured and the prediction result of the wind power.

[0070] The technical solution of the embodiment of the present invention obtains a model input feature data set by collecting sample data and performing feature extraction on the sample data; clustering analysis is performed on the model input feature data set using a k-means clustering algorithm, and the data categories obtained by clustering are added as new features to the model input feature data set; a pre-set generalized additive model is trained according to the model input feature data set to obtain a wind power prediction model; the data to be tested is input into the wind power prediction model to obtain the data category of the data to be tested and the prediction result of the wind power, which solves the problem in the prior art that the wind power cannot be accurately and effectively predicted, realizes the explanation of the influence of various variables on the wind power by the generalized additive model, and effectively improves the accuracy of wind power prediction in combination with cluster analysis.

[0071] Optionally, the model input feature data set includes: the model input x value and the model input y value; the feature extraction module 210 is used to: use the wind speed data, wind direction data and temperature data in the sample data as the model input x value, and use the power data in the sample data as the model input y value.

[0072] Optionally, the cluster analysis module 220 is used to:

[0073] Set the cluster category to k, and randomly select k model input feature data from the model input feature data set as the initial cluster center;

[0074] Calculate the distance from each model input feature data to each cluster center, and divide each model input feature data into the cluster corresponding to the cluster center closest to it;

[0075] Calculate the mean of all model input feature data within each cluster and use the mean to update the cluster center of the cluster;

[0076] Return to the step of calculating the distance from each model input feature data to each cluster center, and dividing each model input feature data into the cluster corresponding to the cluster center closest to it, until the position change of each cluster center before and after the update is less than the specified threshold;

[0077] The data category of each model input feature data is taken as a new feature and added to the x value of the model input.

[0078] Optionally, the distance from each model input feature data to each cluster center is the Euclidean distance.

[0079] Alternatively, the generalized additive model can be expressed as:

[0080] y Linear =β0+β1f1(X1)+β2f2(X2)+β3f3(X3)+β4f4(X4),

[0081] Among them, X1 represents wind speed, X2 represents wind direction, X3 represents temperature, X4 represents data category, β k (k=1,2,3,4) represents constant parameters, f i (x) is a smooth function, y Linear is the power value.

[0082] Optionally, it also includes: a preprocessing module, which is used to delete sample data with abnormal values ​​and null values ​​before extracting features from the sample data.

[0083] Optionally, the data to be measured include: wind speed data, wind direction data and temperature data at the time when the wind power needs to be predicted.

[0084] The wind power prediction device provided in the embodiment of the present invention can execute the wind power prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0085] Embodiment 3

[0086] Figure 3 It is a structural diagram of a computer device in Embodiment 3 of the present invention. Figure 3 A block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 3 The device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0087] like Figure 3 As shown, device 12 is in the form of a general purpose computing device. Components of device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and bus 18 that connects various system components (including system memory 28 and processing unit 16).

[0088] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0089] Device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by device 12, including volatile and non-volatile media, removable and non-removable media.

[0090] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 3 not shown, usually called a "hard drive"). Although Figure 3 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0091] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0092] The device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the device 12, and / or may communicate with any device that enables the device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the device 12, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0093] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing the wind power prediction method provided in the embodiment of the present invention.

[0094] That is, a wind power prediction method is implemented, including:

[0095] Collect sample data and extract features from the sample data to obtain a model input feature data set;

[0096] The k-means clustering algorithm is used to perform cluster analysis on the model input feature data set, and the data categories obtained by clustering are added as new features to the model input feature data set;

[0097] The pre-set generalized additive model is trained according to the model input feature data set to obtain a wind power prediction model;

[0098] The data to be measured are input into the wind power prediction model to obtain the data category of the data to be measured and the prediction result of the wind power.

[0099] Embodiment 4

[0100] Embodiment 4 of the present invention further discloses a computer storage medium, on which a computer program is stored. When the program is executed by a processor, a wind power prediction method is implemented, including:

[0101] Collect sample data and extract features from the sample data to obtain a model input feature data set;

[0102] The k-means clustering algorithm is used to perform cluster analysis on the model input feature data set, and the data categories obtained by clustering are added as new features to the model input feature data set;

[0103] The pre-set generalized additive model is trained according to the model input feature data set to obtain a wind power prediction model;

[0104] The data to be measured are input into the wind power prediction model to obtain the data category of the data to be measured and the prediction result of the wind power.

[0105] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: 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 this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0106] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0107] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0108] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0109] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A wind power prediction method, It is characterized in that include: Collecting sample data and performing feature extraction on the sample data to obtain a model input feature data set, wherein the sample data includes wind speed data, wind direction data, temperature data, and wind power; Performing cluster analysis on the model input feature data set using a k-means clustering algorithm, and adding the data categories obtained by clustering as new features to the model input feature data set; Training a pre-set generalized additive model according to the model input feature data set to obtain a wind power prediction model; Inputting the data to be measured into the wind power prediction model to obtain the data category of the data to be measured and the prediction result of the wind power, wherein the data to be measured includes: wind speed data, wind direction data and temperature data at the time when the wind power needs to be predicted; The model input feature data set includes: the model input x value and the model input y value; Perform feature extraction on the sample data to obtain a model input feature data set, including: Using the wind speed data, wind direction data and temperature data in the sample data as the x value of the model input, and using the power data in the sample data as the y value of the model input; The k-means clustering algorithm is used to perform cluster analysis on the model input feature data set, and the data categories obtained by clustering are added as new features to the model input feature data set, including: The cluster category is set to k, and k model input feature data are randomly selected from the model input feature data set as initial cluster centers; Calculate the distance from each model input feature data to each cluster center, and divide each model input feature data into the cluster corresponding to the cluster center closest to it; Calculate the mean of all model input feature data within each cluster, and use the mean to update the cluster center of the cluster; Return to the step of calculating the distance from each model input feature data to each cluster center, and dividing each model input feature data into the cluster corresponding to the cluster center closest to it, until the position change of each cluster center before and after the update is less than the specified threshold; The data category of each model input feature data is taken as a new feature and added to the x value of the model input; The expression of the generalized additive model is: y Linear =b 0 +b 1 f 1 (X 1 )+b 2 f 2 (X 2 )+b 3 f 3 (X 3 )+b 4 f 4 (X 4 ); Among them, X 1 Indicates wind speed, X 2 Indicates wind direction, X 3 represents the temperature, X 4 represents the data category, β k (k=1,2,3,4) represents constant parameters, f i (x is a smooth function, y Linear is the power value.

2. The method according to claim 1, It is characterized in that The distance from each model input feature data to each cluster center is the Euclidean distance.

3. The method according to claim 1, It is characterized in that Before extracting features from the sample data, the method further includes: deleting sample data with abnormal values ​​and null values.

4. A wind power prediction device, It is characterized in that include: A feature extraction module is used to collect sample data and perform feature extraction on the sample data to obtain a model input feature data set, wherein the sample data includes wind speed data, wind direction data, temperature data and wind power; A clustering analysis module, used to perform cluster analysis on the model input feature data set using a k-means clustering algorithm, and add the data categories obtained by clustering as new features to the model input feature data set; The model training module is used to train a pre-set generalized additive model according to the model input feature data set to obtain a wind power prediction model; wherein the expression of the generalized additive model is: y Linear =b 0 +b 1 f 1 (X 1 )+b 2 f 2 (X 2 )+b 3 f 3 (X 3 )+b 4 f 4 (X 4 ); Among them, X 1 Indicates wind speed, X 2 Indicates wind direction, X 3 represents the temperature, X 4 represents the data category, β k (k=1,2,3,4) represents constant parameters, f i (x is a smooth function, y Linear is the power value; A power prediction module is used to input the data to be measured into the wind power prediction model to obtain the data category of the data to be measured and the prediction result of the wind power, wherein the data to be measured includes: wind speed data, wind direction data and temperature data at the time when the wind power needs to be predicted; The model input feature data set includes: the model input x value and the model input y value; The feature extraction module is used to use the wind speed data, wind direction data and temperature data in the sample data as the x value of the model input, and use the power data in the sample data as the y value of the model input; The cluster analysis module is used to set the cluster category to k, and randomly select k model input feature data from the model input feature data set as initial cluster centers; calculate the distance from each model input feature data to each cluster center, and divide each model input feature data into a cluster corresponding to the nearest cluster center; calculate the mean of all model input feature data in each cluster, and use the mean to update the cluster center of the cluster; return to execute the steps of calculating the distance from each model input feature data to each cluster center, and dividing each model input feature data into a cluster corresponding to the nearest cluster center, until the position change of each cluster center before and after the update is less than a specified threshold; and add the data category of each model input feature data obtained as a new feature to the x value of the model input.

5. A computer device, It is characterized in that The device comprises: 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 wind power prediction method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the wind power prediction method according to any one of claims 1 to 3 is implemented.