New energy power generation power prediction model construction method and device
By conducting data correlation analysis and clustering of new energy power generation stations, determining category information and modeling, the modeling problem caused by insufficient data in electric field stations is solved, and the accuracy of new energy power generation power prediction is improved.
Patent Information
- Application Number
- CN202411675251.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2025-04-25
AI Technical Summary
In the prior art, the stations of some electric fields have long lacked data and cannot be modeled, resulting in the inability to effectively predict new energy power generation power.
By obtaining the data of each station, determine the initial station; obtaining the target data of the initial station, performing correlation calculations, and determining the correlation coefficient matrix; based on the correlation coefficient matrix, clustering the initial station to determine the target station; performing quadratic clustering to determine the category information of the target station; selecting the corresponding station based on the category information for modeling, and obtaining the prediction model.
By dividing the similarity of the stations based on data-driven and modeling similar stations based on regional similarity, the modeling problems caused by insufficient data are effectively improved and the accuracy of new energy power generation power prediction is improved.
Smart Images
Figure CN119891145A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a method for constructing a new energy power generation prediction model. Background Art
[0002] At present, the power grid dispatching department requires power plants (including wind power and photovoltaic power) to report power forecasts, including short-term and ultra-short-term power forecasts, for system power generation planning or real-time dispatch of power systems. However, some power plant stations currently lack data for a long time and cannot be modeled. Therefore, a better solution is urgently needed. Summary of the invention
[0003] In view of this, the present invention provides a method for constructing a new energy power generation power prediction model to solve the technical defects existing in the prior art.
[0004] In a first aspect, the present invention provides a method for constructing a new energy power generation prediction model, comprising:
[0005] Obtain data conditions of each station, and determine an initial station from each station based on the data conditions;
[0006] Obtain the target data of the initial station, perform correlation calculation based on the target data, and determine the correlation coefficient matrix;
[0007] Based on the correlation coefficient matrix, the initial stations are clustered and the target stations are determined;
[0008] Perform secondary clustering based on the target station to determine the category information of the target station;
[0009] Based on the category information, the corresponding station is selected for modeling to obtain a prediction model.
[0010] In a possible implementation, obtaining data conditions of each station and determining an initial station from each station based on the data conditions includes:
[0011] Determine the data threshold, and if the data situation of each station does not meet the data threshold, mark the station as a missing station;
[0012] The initial stations are obtained by removing the missing stations from the stations.
[0013] In a possible implementation, target data of an initial station is obtained, correlation calculation is performed based on the target data, and a correlation coefficient matrix is determined, including:
[0014] Obtain the wind speed data of the initial station, calculate the Pearson correlation coefficient based on the wind speed data, and obtain the initial coefficient matrix;
[0015] The mean is calculated based on the initial coefficient matrix to determine the correlation coefficient matrix; the specific formula is as follows:
[0016]
[0017] Where X and Y represent the measured wind speeds at the two stations respectively; Cor(X, Y i ) represents variables X and Y i The covariance of the wind speed X measured at the calculation station and the wind speed Y measured at another station i The covariance between i is the measured wind speed at two points before or after the station; var(X) represents the standard deviation of variable X, that is, the standard deviation of the measured wind speed at the station, reflecting the degree of discreteness of the variable value; var(Y i ) represents the variable Y i r(X, Y) represents the correlation coefficient between variables X and Y, that is, the correlation coefficient between the wind speed X measured at a station and the wind speed Y measured at two points shifted forward and backward at another station takes the maximum value.
[0018] In a possible implementation, clustering the initial stations based on the correlation coefficient matrix to determine the target stations includes:
[0019] According to the profile coefficient, select the number of categories;
[0020] Based on the correlation coefficient matrix, the target station is determined through DBSCAN density clustering and the number of categories.
[0021] In a possible implementation, secondary clustering is performed based on the target station to determine the category information of the target station, including:
[0022] Based on the target station, secondary clustering is performed through the Gaussian mixture model to obtain the category probability of the target station; the specific formula is as follows:
[0023]
[0024] Where x represents the observed data set; K represents the number of Gaussian components (or clusters) in the mixture model, k∈(1,2,…,K); π k Represents the mixing coefficient of the kth Gaussian component, satisfying 0≤π k ≤1 and μ k represents the mean vector of the kth Gaussian component; Σ k represents the covariance matrix of the kth Gaussian component; p(x) represents the probability density function value of the observed data point; represents the probability density function value of the kth Gaussian component at;
[0025] The category information of the target station is determined based on the category probability.
[0026] In a possible implementation, a corresponding station is selected based on the category information for modeling to obtain a prediction model, including:
[0027] When the category information is a conventional station or an isolated station, obtaining modeling data of the conventional station or the isolated station;
[0028] Modeling is performed based on the modeling data to obtain a prediction model.
[0029] In a possible implementation, a corresponding station is selected based on the category information for modeling to obtain a prediction model, including:
[0030] When the category information is a missing station, obtain the geographical coordinates of the missing station;
[0031] Determining modeling data based on geographic coordinates;
[0032] Modeling is performed based on the modeling data to obtain a prediction model.
[0033] In a second aspect, the present invention provides a device for constructing a new energy power generation prediction model, comprising:
[0034] A station determination module is configured to obtain data conditions of each station and determine an initial station from each station based on the data conditions;
[0035] A matrix calculation module is configured to obtain target data of an initial station, perform correlation calculation based on the target data, and determine a correlation coefficient matrix;
[0036] The station classification module is configured to cluster the initial stations based on the correlation coefficient matrix and determine the target stations;
[0037] An information determination module is configured to perform secondary clustering based on the target station to determine category information of the target station;
[0038] The model building module is configured to select corresponding sites for modeling based on category information to obtain a prediction model.
[0039] According to a third aspect of the present invention, there is provided a computing device, comprising:
[0040] Memory and processor;
[0041] The memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above-mentioned new energy power generation power prediction model construction method are implemented.
[0042] In a fourth aspect of the present invention, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned method for constructing a new energy power generation prediction model are implemented.
[0043] According to a fifth aspect of the present invention, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for constructing a new energy power generation prediction model.
[0044] The present invention provides a method and device for constructing a new energy power generation prediction model, wherein the method includes: obtaining data conditions of each station, determining the initial station from each station based on the data conditions; obtaining target data of the initial station, performing correlation calculation based on the target data, and determining the correlation coefficient matrix; clustering the initial station based on the correlation coefficient matrix to determine the target station; performing secondary clustering based on the target station to determine the category information of the target station; selecting the corresponding station based on the category information for modeling to obtain a prediction model. By dividing the station similarity based on data drive and modeling similar stations based on regional similarity, the modeling problem caused by insufficient data is effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 It is a flowchart of a method for constructing a new energy power generation prediction model provided by an embodiment of this specification;
[0046] Figure 2 It is a schematic diagram of a method for constructing a new energy power generation prediction model provided by an embodiment of this specification;
[0047] Figure 3 It is a structural schematic diagram of a new energy power generation prediction model building device provided by an embodiment of this specification;
[0048] Figure 4 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION
[0049] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.
[0050] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.
[0051] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0052] In this specification, a method for constructing a new energy power generation prediction model is provided. This specification also involves a new energy power generation prediction model construction device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.
[0053] See also Figure 1 , Figure 1 A flowchart of a method for constructing a new energy power generation prediction model provided according to an embodiment of this specification is shown, which specifically includes the following steps.
[0054] Step 101: Obtain data status of each station, and determine an initial station from each station based on the data status.
[0055] In a possible implementation, data conditions of each station are obtained, and an initial station is determined from each station based on the data conditions, including: determining a data threshold, and marking the station as a missing station when the data conditions of each station do not meet the data threshold; and removing the missing stations from the stations to obtain the initial station.
[0056] In practical applications, see Figure 2 For each station, determine whether the station has no measured data or the measured data is less than 1 month. If so, mark the station as a station without measurement. Otherwise, take the measured wind speed data of the station in the past 6 months. If it is less than 6 months, take the full measured wind speed data.
[0057] Step 102: Obtain target data of the initial site, perform correlation calculation based on the target data, and determine a correlation coefficient matrix.
[0058] In one possible implementation, target data of the initial site is obtained, correlation calculation is performed based on the target data, and a correlation coefficient matrix is determined, including: obtaining wind speed data of the initial site, performing Pearson correlation coefficient calculation based on the wind speed data to obtain an initial coefficient matrix; performing mean calculation based on the initial coefficient matrix to determine the correlation coefficient matrix.
[0059] In practical applications, the correlation between the measured wind speeds of all stations is calculated monthly. Considering the time lag, the maximum absolute value correlation coefficient of the two points translated forward and backward - Pearson correlation coefficient is used to obtain the correlation coefficient matrix. The corresponding data of the correlation coefficient matrix are averaged to obtain the final correlation coefficient matrix:
[0060]
[0061] Where X and Y represent the measured wind speeds at the two stations respectively; Cor(X, Y i ) represents variables X and Y i The covariance of the wind speed X measured at the calculation station and the wind speed Y measured at another station i The covariance between i is the measured wind speed at two points before or after the station; var(X) represents the standard deviation of variable X, that is, the standard deviation of the measured wind speed at the station, reflecting the degree of discreteness of the variable value; var(Y i ) represents the variable Y i r(X, Y) represents the correlation coefficient between variables X and Y, that is, the correlation coefficient between the wind speed X measured at a station and the wind speed Y measured at two points shifted forward and backward at another station takes the maximum value.
[0062] Step 103: Based on the correlation coefficient matrix, cluster the initial stations and determine the target stations.
[0063] In a possible implementation, the initial stations are clustered based on the correlation coefficient matrix to determine the target station, including: selecting the number of categories according to the profile coefficient; and determining the target station through DBSCAN density clustering and the number of categories based on the correlation coefficient matrix.
[0064] In practical applications, DBSCAN density clustering is used based on the correlation coefficient matrix. The appropriate number of categories is selected according to the profile coefficient, and points that are not successfully clustered are marked as isolated stations.
[0065] Step 104: Perform secondary clustering based on the target station to determine the category information of the target station.
[0066] In a possible implementation, secondary clustering is performed based on the target station to determine the category information of the target station, including: based on the target station, secondary clustering is performed through a Gaussian mixture model to obtain the category probability of the target station; and the category information of the target station is determined based on the category probability.
[0067] In practical applications, the electric field after removing isolated stations is clustered based on the Gaussian mixture model GMM to obtain the probability that the electric field belongs to each category; as follows:
[0068]
[0069] Where x represents the observed data set; K represents the number of Gaussian components (or clusters) in the mixture model, k∈(1,2,…,K); π k Represents the mixing coefficient of the kth Gaussian component, satisfying 0≤π k ≤1 and μ k represents the mean vector of the kth Gaussian component; Σ k represents the covariance matrix of the kth Gaussian component; p(x) represents the probability density function value of the observed data point; Represents the probability density function value of the kth Gaussian component at .
[0070] Step 105: Select corresponding stations for modeling based on the category information to obtain a prediction model.
[0071] In one possible implementation, a corresponding station is selected based on the category information for modeling to obtain a prediction model, including: when the category information is a conventional station or an isolated station, obtaining modeling data of the conventional station or the isolated station; and modeling based on the modeling data to obtain a prediction model.
[0072] In practical applications, given a station, the results are combined to determine whether the station is a conventional station, a station without measurement, or an isolated station. For conventional stations and isolated stations, the measured data are relatively complete, so the medium- and long-term prediction modeling is carried out normally.
[0073] In one possible implementation, a corresponding station is selected based on the category information for modeling to obtain a prediction model, including: when the category information is a missing station, obtaining the geographic coordinates of the missing station; determining modeling data based on the geographic coordinates; and modeling based on the modeling data to obtain a prediction model.
[0074] In practical applications, for missing stations, the geographical coordinates of the stations are used to determine whether the stations are located within a certain category of station area. If so, the measured data of the stations within the category are approximated to the measured data of the missing stations by inverse distance weighted average. If not, the reanalysis data are directly selected and inverse distance weighted average is used to approximate the measured data of the station.
[0075] Furthermore, based on similarity analysis, after obtaining sufficient modeling data, medium- and long-term forecast modeling can be carried out in combination with CFS meteorology.
[0076] The embodiments of this specification provide a method and device for constructing a new energy power generation prediction model, wherein the method includes: obtaining data conditions of each station, determining an initial station from each station based on the data conditions; obtaining target data of the initial station, performing correlation calculation based on the target data, and determining a correlation coefficient matrix; clustering the initial station based on the correlation coefficient matrix to determine the target station; performing secondary clustering based on the target station to determine the category information of the target station; selecting the corresponding station based on the category information for modeling to obtain a prediction model. By dividing the station similarity based on data drive and modeling similar stations based on regional similarity, the modeling problem caused by insufficient data is effectively improved.
[0077] Corresponding to the above method embodiment, this specification also provides an embodiment of a device for constructing a new energy power generation prediction model. Figure 3 FIG. 1 is a schematic diagram showing a structure of a device for constructing a new energy power generation prediction model provided by an embodiment of this specification. Figure 3 As shown, the device comprises:
[0078] The station determination module 301 is configured to obtain data conditions of each station and determine an initial station from each station based on the data conditions;
[0079] The matrix calculation module 302 is configured to obtain target data of the initial station, perform correlation calculation based on the target data, and determine a correlation coefficient matrix;
[0080] The station classification module 303 is configured to cluster the initial stations based on the correlation coefficient matrix to determine the target stations;
[0081] The information determination module 304 is configured to perform secondary clustering based on the target station to determine the category information of the target station;
[0082] The model building module 305 is configured to select corresponding stations for modeling based on the category information to obtain a prediction model.
[0083] In a possible implementation, the station determination module 301 is further configured to:
[0084] Determine the data threshold, and if the data situation of each station does not meet the data threshold, mark the station as a missing station;
[0085] The initial stations are obtained by removing the missing stations from the stations.
[0086] In a possible implementation, the matrix calculation module 302 is further configured to:
[0087] Obtain the wind speed data of the initial station, calculate the Pearson correlation coefficient based on the wind speed data, and obtain the initial coefficient matrix;
[0088] The mean is calculated based on the initial coefficient matrix to determine the correlation coefficient matrix.
[0089] In a possible implementation, the station classification module 303 is further configured to:
[0090] According to the profile coefficient, select the number of categories;
[0091] Based on the correlation coefficient matrix, the target station is determined through DBSCAN density clustering and the number of categories.
[0092] In a possible implementation, the information determination module 304 is further configured to:
[0093] Based on the target station, secondary clustering is performed through the Gaussian mixture model to obtain the category probability of the target station;
[0094] The category information of the target station is determined based on the category probability.
[0095] In a possible implementation, the model building module 305 is further configured to:
[0096] When the category information is a conventional station or an isolated station, obtaining modeling data of the conventional station or the isolated station;
[0097] Modeling is performed based on the modeling data to obtain a prediction model.
[0098] In a possible implementation, the model building module 305 is further configured to:
[0099] When the category information is a missing station, obtain the geographical coordinates of the missing station;
[0100] Determining modeling data based on geographic coordinates;
[0101] Modeling is performed based on the modeling data to obtain a prediction model.
[0102] The embodiments of this specification provide a method and device for constructing a new energy power generation prediction model, wherein the device includes: obtaining data conditions of each station, determining an initial station from each station based on the data conditions; obtaining target data of the initial station, performing correlation calculation based on the target data, and determining a correlation coefficient matrix; clustering the initial station based on the correlation coefficient matrix to determine the target station; performing secondary clustering based on the target station to determine the category information of the target station; selecting the corresponding station based on the category information for modeling to obtain a prediction model. By dividing the station similarity based on data drive and modeling similar stations based on regional similarity, the modeling problem caused by insufficient data is effectively improved.
[0103] The above is a schematic scheme of a new energy power generation prediction model construction device of this embodiment. It should be noted that the technical scheme of the new energy power generation prediction model construction device and the technical scheme of the above-mentioned new energy power generation prediction model construction method belong to the same concept, and the details not described in detail in the technical scheme of the new energy power generation prediction model construction device can be referred to the description of the technical scheme of the above-mentioned new energy power generation prediction model construction method.
[0104] Figure 4 The block diagram of a computing device 400 according to one embodiment of the present specification is shown. The components of the computing device 400 include but are not limited to a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and the database 450 is used to store data.
[0105] The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).
[0106] In one embodiment of the present specification, the above components of the computing device 400 and Figure 4 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 4 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.
[0107] The computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 400 may also be a mobile or stationary server.
[0108] Among them, the processor 420 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned method for constructing a new energy power generation prediction model. The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned method for constructing a new energy power generation prediction model belong to the same concept. For details not described in detail in the technical scheme of the computing device, please refer to the description of the technical scheme of the above-mentioned method for constructing a new energy power generation prediction model.
[0109] An embodiment of the present specification also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned method for constructing a new energy power generation prediction model.
[0110] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned method for constructing a new energy power generation prediction model belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned method for constructing a new energy power generation prediction model.
[0111] An embodiment of the present specification also provides a computer program, wherein when the computer program is executed in a computer, the computer is instructed to execute the steps of the above-mentioned method for constructing a new energy power generation prediction model.
[0112] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned method for constructing a new energy power generation prediction model belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be found in the description of the technical scheme of the above-mentioned method for constructing a new energy power generation prediction model.
[0113] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0114] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0115] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.
[0116] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0117] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.
Claims
1. A method for constructing a new energy power generation prediction model, characterized in that: include: Acquiring data conditions of each station, and determining an initial station from the stations based on the data conditions; Acquire target data of the initial station, perform correlation calculation based on the target data, and determine a correlation coefficient matrix; Based on the correlation coefficient matrix, clustering the initial stations to determine the target stations; Performing secondary clustering based on the target station to determine category information of the target station; The corresponding station is selected based on the category information for modeling to obtain a prediction model.
2. The method according to claim 1, characterized in that: The obtaining of data conditions of each station and determining an initial station from each station based on the data conditions comprises: Determine a data threshold, and if the data situation of each station does not meet the data threshold, mark the station as a missing station; The unmeasured stations are removed from the stations to obtain initial stations.
3. The method according to claim 1, characterized in that The step of acquiring target data of the initial station, performing correlation calculation based on the target data, and determining a correlation coefficient matrix includes: Obtaining wind speed data of the initial station, and calculating the Pearson correlation coefficient based on the wind speed data to obtain an initial coefficient matrix; The mean value is calculated based on the initial coefficient matrix to determine the correlation coefficient matrix; specifically, the following formula: Where X and Y represent the measured wind speeds at the two stations respectively; Cor(X, Y i ) represents variables X and Y i The covariance of the wind speed X measured at the calculation station and the wind speed Y measured at another station i The covariance between i is the measured wind speed at two points before or after the station; var(X) represents the standard deviation of variable X, that is, the standard deviation of the measured wind speed at the station, reflecting the discreteness of the variable value; var(Y i ) represents the variable Y i r(X, Y) represents the correlation coefficient between variables X and Y, that is, the correlation coefficient between the wind speed X measured at a station and the wind speed Y measured at two points shifted forward and backward at another station takes the maximum value.
4. The method according to claim 1, characterized in that: The clustering of the initial stations based on the correlation coefficient matrix to determine the target stations includes: According to the profile coefficient, select the number of categories; Based on the correlation coefficient matrix, the target site is determined through DBSCAN density clustering and the number of categories.
5. The method according to claim 1, characterized in that The performing secondary clustering based on the target station to determine the category information of the target station includes: Based on the target station, secondary clustering is performed through the Gaussian mixture model to obtain the category probability of the target station; specifically, it is as follows: Where x represents the observed data set; K represents the number of Gaussian components (or clusters) in the mixture model, k∈(1,2,…,K); π k Represents the mixing coefficient of the kth Gaussian component, satisfying 0≤π k ≤1 and μ k represents the mean vector of the kth Gaussian component; Σ k represents the covariance matrix of the kth Gaussian component; p(x) represents the probability density function value of the observed data point; represents the probability density function value of the kth Gaussian component at; The category information of the target station is determined based on the category probability.
6. The method according to claim 1, characterized in that The selecting the corresponding station based on the category information to perform modeling to obtain a prediction model includes: In a case where the category information is a conventional station or an isolated station, acquiring modeling data of the conventional station or the isolated station; Modeling is performed based on the modeling data to obtain a prediction model.
7. The method according to claim 1, characterized in that The selecting the corresponding station based on the category information to perform modeling to obtain a prediction model includes: When the category information is a missing station, obtaining the geographical coordinates of the missing station; determining modeling data based on the geographic coordinates; Modeling is performed based on the modeling data to obtain a prediction model.
8. A device for constructing a new energy power generation prediction model, characterized in that: include: A station determination module is configured to obtain data conditions of each station and determine an initial station from the stations based on the data conditions; A matrix calculation module is configured to obtain target data of an initial station, perform correlation calculation based on the target data, and determine a correlation coefficient matrix; A station classification module is configured to cluster the initial stations based on the correlation coefficient matrix to determine the target stations; an information determination module, configured to perform secondary clustering based on the target station to determine category information of the target station; The model building module is configured to select the corresponding site for modeling based on the category information to obtain a prediction model.
9. A computing device, characterized in that include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for constructing a new energy power generation prediction model as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for constructing a new energy power generation prediction model as described in any one of claims 1 to 7.