Wind power plant data linear interpolation processing method and system

Abstract

The invention relates to the technical field of wind power plant data processing, and particularly discloses a wind power plant data linear interpolation processing method and system, and the method comprises the steps: obtaining the historical wind speed data of a wind power plant, carrying out the partitioning of a wind turbine generator in the wind power plant according to the historical wind speed data, and obtaining wind turbine generator partitions; acquiring real-time wind speed data of the wind turbine generators in the wind turbine generator partitions, predicting theoretical power data of the wind turbine generators according to the real-time wind speed data of the wind turbine generators, screening out abnormal data in the theoretical power data of the wind turbine generators, and rejecting the abnormal data; filling the theoretical power data of the wind turbine generator after the abnormal data is removed based on a linear interpolation method to obtain complete theoretical power data of the wind turbine generator; and determining a target error value according to the real-time wind speed data of the wind turbine generator, and correcting the theoretical power data of the wind turbine generator according to the target error value. The wind power plant is partitioned, theoretical power data is filled based on a linear interpolation method, and the accuracy and integrity of the data are improved.

Description

Technical Field

[0001] The present application relates to the technical field of wind farm data processing, and more specifically, to a method and system for linear interpolation processing of wind farm data. Background Art

[0002] In recent years, wind power installed capacity has been increasing year by year across the country, and the proportion of wind power installed capacity in the three northern regions of my country has exceeded 25%. The reform of the power market is also deepening year by year. In 2022, the country launched the construction of a unified national power market system, emphasizing the construction of spot markets and ancillary service markets. This puts forward higher requirements for effectively evaluating the deviation between wind farm power forecasts and actual real-time output in power generation operations.

[0003] The existing technology lacks specificity in power prediction of wind farms and cannot flexibly predict power values ​​according to the specific operating conditions of wind turbines, resulting in a large amount of abnormal data in the theoretical power data of wind farms. In addition, the traditional data completion method has large completion errors and cannot guarantee the integrity and accuracy of the theoretical power data of wind farms. Summary of the invention

[0004] The present invention provides a method and system for linear interpolation processing of wind farm data, which is used to solve the problem of low integrity and poor accuracy of theoretical power data of wind farms in the prior art, including:

[0005] Obtain historical wind speed data of the wind farm, and partition the wind turbines in the wind farm according to the historical wind speed data to obtain wind turbine partitions;

[0006] Obtain real-time wind speed data of wind turbines in the wind turbine zone, predict theoretical power data of wind turbines based on real-time wind speed data of wind turbines, screen out abnormal data in theoretical power data of wind turbines and remove the abnormal data;

[0007] Based on the linear interpolation method, the theoretical power data of the wind turbine after the abnormal data is removed is filled to obtain the complete theoretical power data of the wind turbine;

[0008] The target error value is determined according to the real-time wind speed data of the wind turbine generator set, and the theoretical power data of the wind turbine generator set is corrected according to the target error value.

[0009] Furthermore, the wind turbines in the wind farm are divided into zones according to the historical wind speed data, including:

[0010] Determine the historical wind speed curve of each wind turbine in the wind farm according to the historical wind speed data of the wind farm, obtain a preset wind speed data interval, and determine the wind speed frequency distribution of the historical wind speed curve according to the preset wind speed data interval;

[0011] Draw a wind speed frequency curve according to the wind speed frequency distribution, obtain a preset wind speed threshold, and filter out the frequencies corresponding to wind speed data greater than the preset wind speed threshold in the wind speed frequency curve;

[0012] Calculate the ratio of the corresponding frequency of the wind speed data exceeding the preset wind speed threshold to the preset allowable frequency to obtain the wind speed fluctuation coefficient;

[0013] Obtain wind speed data less than or equal to a preset wind speed threshold in the wind speed frequency curve graph, calculate the average value of wind speed data less than or equal to the preset wind speed threshold in the wind speed frequency curve graph, and multiply the average value of wind speed data less than or equal to the preset wind speed threshold in the wind speed frequency curve graph by the wind speed fluctuation coefficient to obtain a wind speed distribution coefficient;

[0014] Based on the k-means clustering algorithm, the wind turbines in the wind farm are clustered according to the wind speed distribution coefficient, and the wind turbine zones are determined according to the clustering results.

[0015] Furthermore, the wind turbines in the wind farm are clustered according to the wind speed distribution coefficient based on the k-means clustering algorithm, including:

[0016] According to the number of wind turbines in the wind farm, k initial cluster centers are randomly selected, and the Euclidean distance from the wind speed distribution coefficient of each wind turbine to the initial cluster center is calculated;

[0017] According to the Euclidean distance from the wind speed distribution coefficient to the initial cluster center, each wind turbine is divided into corresponding partitions, and the average value of all wind speed distribution coefficients in each partition is calculated;

[0018] The cluster center is updated according to the average value of all wind speed distribution coefficients in each cluster, and repeated iterations are performed according to the new cluster center until the cluster center no longer changes, and k final cluster centers are obtained;

[0019] The wind turbines in the wind farm are divided into k wind turbine partitions according to the Euclidean distance from the wind speed distribution coefficient to the final cluster center.

[0020] Furthermore, the abnormal data in the real-time power data of the wind turbines is screened out and removed, including:

[0021] Draw a theoretical power curve according to the theoretical power data, obtain a standard power curve corresponding to the wind turbine group partition of the wind turbine group, calculate the sum of the correlation coefficients of the theoretical power curve and the standard power curve in a preset rolling time window, and filter out a time period in which the sum of the correlation coefficients is less than a first preset threshold;

[0022] Calculate the absolute value of the difference between each power data point and the average value of two adjacent power data points in the time period in which the sum of the correlation coefficients in the theoretical power curve is less than the first preset threshold, and determine the power change rate of the power data point according to the absolute value of the difference between the power data point and the average value of the two adjacent power data points;

[0023] If the power change rate of the power data point is greater than the second preset threshold, the power data point is determined as abnormal data and the abnormal data is removed.

[0024] Furthermore, the theoretical power data of the wind turbine after removing the abnormal data is filled based on the linear interpolation method, including:

[0025] Obtain the average value of two non-abnormal data points adjacent to the abnormal data point in the theoretical power curve, and determine the initial linear interpolation value according to the average value of the non-abnormal data points;

[0026] An interpolation correction coefficient is determined according to the wind turbine group partition where the wind turbine group is located, and an initial linear interpolation is corrected according to the interpolation correction coefficient to obtain a linear interpolation;

[0027] The linear interpolation of each abnormal data point is added to the theoretical power data to complete the filling of the theoretical power data of the wind turbine.

[0028] Furthermore, the interpolation correction coefficient is determined according to the wind turbine group partition where the wind turbine group is located, including:

[0029] Obtain the cluster center value of the wind turbine group partition, and determine the interpolation correction coefficient based on the cluster center value combined with the correction coefficient calculation formula. The correction coefficient calculation formula is as follows:

[0030]

[0031] Among them, L is the interpolation correction coefficient, L α is the preset interpolation correction coefficient, W is the cluster center value, W α is the preset allowable wind speed, and R is the preset range coefficient.

[0032] Further, the target error value is determined according to the real-time wind speed data of the wind turbine generator set, including:

[0033] Draw a real-time wind speed curve according to the real-time wind speed data of the wind turbine generator set, calculate the wind speed fluctuation coefficient according to the real-time wind speed curve, and determine whether the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than a third preset threshold value;

[0034] If the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than a third preset threshold, setting the preset first error value as the target error value;

[0035] If the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is less than or equal to the third preset threshold, determining whether the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than a fourth preset threshold;

[0036] If the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than a fourth preset threshold, setting the preset second error value as the target error value;

[0037] If the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is less than or equal to a fourth preset threshold, the preset third error value is set as the target error value.

[0038] Furthermore, the wind speed fluctuation coefficient is calculated according to the real-time wind speed curve, including:

[0039] Obtain a preset sliding time window, and divide the real-time wind speed curve graph into a number of sub-wind speed curves according to the preset sliding time window;

[0040] Calculate the absolute value of the slope of each sub-wind speed curve, screen out the sub-wind speed curves whose absolute value of the slope is greater than the fifth preset threshold, calculate the ratio of the number of sub-wind speed curves whose absolute value of the slope is greater than the fifth preset threshold to the preset allowable number, and obtain the wind speed fluctuation coefficient.

[0041] Furthermore, the theoretical power data of the wind turbine is corrected according to the target error value, including:

[0042] Obtain the real-time power curve of the wind turbine, calculate the difference between the real-time power curve and the theoretical power curve, and obtain the theoretical power error;

[0043] Calculate the difference between the theoretical power error and the target error value, normalize the difference between the theoretical power error and the target error value, and obtain an error correction coefficient;

[0044] Multiply the error correction coefficient by the theoretical power data to obtain the corrected theoretical power data.

[0045] In order to achieve the above object, the present invention also provides a wind farm data linear interpolation processing system, comprising:

[0046] A data acquisition module is used to acquire historical wind speed data of the wind farm, and to partition the wind turbines in the wind farm according to the historical wind speed data to obtain wind turbine partitions;

[0047] The power data acquisition module is used to acquire the real-time wind speed data of the wind turbines in the wind turbine zone, predict the theoretical power data of the wind turbines according to the real-time wind speed data of the wind turbines, screen out the abnormal data in the theoretical power data of the wind turbines and remove the abnormal data;

[0048] The power data processing module is used to fill in the theoretical power data of the wind turbine after removing the abnormal data based on the linear interpolation method to obtain the complete theoretical power data of the wind turbine;

[0049] The power data correction module is used to determine the target error value according to the real-time wind speed data of the wind turbine generator set, and correct the theoretical power data of the wind turbine generator set according to the target error value.

[0050] The beneficial effects of the present invention are:

[0051] By applying the above technical scheme, the present invention divides the wind turbines into zones according to the historical wind speed data of the wind farm, sets corresponding correction coefficients for the wind turbines in different zones, and fills the theoretical power data of the wind farm based on the linear interpolation method. At the same time, the theoretical power data is corrected according to the real-time wind speed data of the turbines, which can effectively prevent the deviation of the theoretical power data and greatly improve the accuracy and completeness of the theoretical power curve. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 The overall flow chart of a method for linear interpolation processing of wind farm data proposed in an embodiment of the present invention is shown;

[0054] Figure 2 A schematic structural diagram of a wind farm data linear interpolation processing system proposed in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] The present application embodiment provides a method for linear interpolation processing of wind farm data, such as Figure 1 As shown, including:

[0057] S101, obtaining historical wind speed data of the wind farm, and partitioning the wind turbines in the wind farm according to the historical wind speed data to obtain wind turbine partitions;

[0058] In some embodiments of the present application, wind turbines in a wind farm are zoned according to historical wind speed data, including: determining a historical wind speed curve of each wind turbine in the wind farm according to the historical wind speed data of the wind farm, obtaining a preset wind speed data interval, and determining a wind speed frequency distribution of the historical wind speed curve according to the preset wind speed data interval; drawing a wind speed frequency curve diagram according to the wind speed frequency distribution, obtaining a preset wind speed threshold, and screening out the frequencies corresponding to wind speed data greater than the preset wind speed threshold in the wind speed frequency curve diagram; calculating the ratio of the corresponding frequency of wind speed data exceeding the preset wind speed threshold to the preset allowable frequency to obtain a wind speed fluctuation coefficient; obtaining wind speed data less than or equal to the preset wind speed threshold in the wind speed frequency curve diagram, calculating the average value of wind speed data less than or equal to the preset wind speed threshold in the wind speed frequency curve diagram, multiplying the average value of wind speed data less than or equal to the preset wind speed threshold in the wind speed frequency curve diagram by the wind speed fluctuation coefficient to obtain a wind speed distribution coefficient; clustering the wind turbines in the wind farm according to the wind speed distribution coefficient based on the k-means clustering algorithm, and determining the wind turbine zones according to the clustering results.

[0059] In this embodiment, a plurality of preset wind speed data intervals are set, the historical wind speed curve is segmented by the preset wind speed intervals, and the frequency of occurrence of wind speed in each preset wind speed interval is statistically analyzed by the historical wind speed data of the wind farm, thereby determining the wind speed frequency distribution.

[0060] In some embodiments of the present application, wind turbines in a wind farm are clustered according to wind speed distribution coefficients based on a k-means clustering algorithm, including: randomly selecting k initial clustering centers according to the number of wind turbines in the wind farm, and calculating the Euclidean distance from the wind speed distribution coefficient of each wind turbine to the initial clustering center; dividing each wind turbine into corresponding partitions according to the Euclidean distance from the wind speed distribution coefficient to the initial clustering center, and calculating the average value of all wind speed distribution coefficients in each partition; updating the clustering center according to the average value of all wind speed distribution coefficients in each cluster, and repeatedly iterating according to the new clustering center until the clustering center no longer changes, thereby obtaining k final clustering centers; and dividing the wind turbines in the wind farm into k wind turbine partitions according to the Euclidean distance from the wind speed distribution coefficient to the final clustering center.

[0061] In this embodiment, the number of partitions k is determined by the number of wind turbines in the wind farm. The more wind turbines there are, the larger the corresponding k value is. The wind turbines in the wind farm are partitioned based on the k-means clustering algorithm to facilitate subsequent adjustment of the power data of each wind turbine.

[0062] S102, obtaining real-time wind speed data of wind turbines in the wind turbine zone, predicting theoretical power data of the wind turbines according to the real-time wind speed data of the wind turbines, screening out abnormal data in the theoretical power data of the wind turbines and removing the abnormal data;

[0063] In some embodiments of the present application, abnormal data in the real-time power data of a wind turbine is screened out and the abnormal data is eliminated, including: drawing a theoretical power curve according to the theoretical power data, obtaining a standard power curve corresponding to the wind turbine partition of the wind turbine, calculating the sum of the correlation coefficients between the theoretical power curve and the standard power curve in a preset rolling time window, and screening out a time period in which the sum of the correlation coefficients is less than a first preset threshold; calculating the absolute value of the difference between each power data point and the average value of two adjacent power data points in the time period in which the sum of the correlation coefficients in the theoretical power curve is less than the first preset threshold, and determining the power change rate of the power data point according to the absolute value of the difference between the power data point and the average value of the two adjacent power data points; if the power change rate of the power data point is greater than the second preset threshold, the power data point is determined as abnormal data and the abnormal data is eliminated.

[0064] In this embodiment, a neural network model can be established to predict the theoretical power data of the wind turbine according to the real-time wind speed data of the wind turbine, or the theoretical power data of the wind turbine can be calculated according to the real-time wind speed data of the wind turbine. The optimal power curve of each wind turbine in the historical operation process is divided into zones as the standard power curve. By calculating the sum of the correlation coefficients between the theoretical power curve and the standard power curve in a preset rolling time window, the time periods with low correlation of the curves are screened out, and the abnormal data in the time periods with low correlation are eliminated to ensure the accuracy of the theoretical power data.

[0065] S103, filling the theoretical power data of the wind turbine generator set after removing the abnormal data based on a linear interpolation method to obtain complete theoretical power data of the wind turbine generator set;

[0066] In some embodiments of the present application, the theoretical power data of the wind turbine after eliminating abnormal data is filled based on a linear interpolation method, including: obtaining the average value of two non-abnormal data points adjacent to the abnormal data point in the theoretical power curve diagram, and determining an initial linear interpolation based on the average value of the non-abnormal data points; determining an interpolation correction coefficient based on the wind turbine partition in which the wind turbine is located, and correcting the initial linear interpolation based on the interpolation correction coefficient to obtain a linear interpolation; and adding the linear interpolation of each abnormal data point to the theoretical power data to complete the filling of the theoretical power data of the wind turbine.

[0067] In some embodiments of the present application, the interpolation correction coefficient is determined according to the wind turbine partition in which the wind turbine is located, including:

[0068] Obtain the cluster center value of the wind turbine group partition, and determine the interpolation correction coefficient based on the cluster center value combined with the correction coefficient calculation formula. The correction coefficient calculation formula is as follows:

[0069]

[0070] Among them, L is the interpolation correction coefficient, L α is the preset interpolation correction coefficient, W is the cluster center value, W α is the preset allowable wind speed, R is the preset range coefficient, and exp is the natural exponential function.

[0071] In this embodiment, the eliminated power points are filled based on the linear interpolation method, and the interpolation correction coefficient is calculated by the cluster center value. The linear interpolation is corrected by multiplying the interpolation correction coefficient with the linear interpolation to achieve targeted interpolation of the theoretical power data of the wind turbine.

[0072] S104, determining a target error value according to the real-time wind speed data of the wind turbine generator set, and correcting the theoretical power data of the wind turbine generator set according to the target error value.

[0073] In some embodiments of the present application, a target error value is determined based on real-time wind speed data of a wind turbine generator set, including: drawing a real-time wind speed curve graph based on the real-time wind speed data of the wind turbine generator set, calculating a wind speed fluctuation coefficient based on the real-time wind speed curve graph, and judging whether the difference between the wind speed fluctuation coefficient and a preset allowable wind speed fluctuation coefficient is greater than a third preset threshold value; if the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than the third preset threshold value, setting a preset first error value as the target error value; if the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is less than or equal to the third preset threshold value, judging whether the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than a fourth preset threshold value; if the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than the fourth preset threshold value, setting a preset second error value as the target error value; if the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is less than or equal to the fourth preset threshold value, setting a preset third error value as the target error value.

[0074] In some embodiments of the present application, the wind speed fluctuation coefficient is calculated based on the real-time wind speed curve graph, including: obtaining a preset sliding time window, dividing the real-time wind speed curve graph into a number of sub-wind speed curves according to the preset sliding time window; calculating the absolute value of the slope of each sub-wind speed curve, screening out the sub-wind speed curves whose absolute value of the slope is greater than the fifth preset threshold, calculating the ratio of the number of sub-wind speed curves whose absolute value of the slope is greater than the fifth preset threshold to the preset allowable number, and obtaining the wind speed fluctuation coefficient.

[0075] In this embodiment, the first error value, the second error value, and the third error value increase sequentially. The larger the wind speed fluctuation coefficient, the lower the corresponding target error value. The target error value is dynamically set by the wind speed fluctuation coefficient to increase the accuracy of the theoretical power data.

[0076] In some embodiments of the present application, the theoretical power data of the wind turbine is corrected according to the target error value, including: obtaining the real-time power curve of the wind turbine, calculating the difference between the real-time power curve and the theoretical power curve, and obtaining the theoretical power error; calculating the difference between the theoretical power error and the target error value, normalizing the difference between the theoretical power error and the target error value, and obtaining an error correction coefficient; multiplying the error correction coefficient by the theoretical power data to obtain the corrected theoretical power data.

[0077] In this embodiment, the theoretical power error is calculated based on the difference between the real-time power of the wind turbine and the power in the corresponding theoretical power curve. The error correction coefficient is obtained by the deviation between the theoretical power error and the target error value to correct the theoretical power data, thereby ensuring the accuracy of the theoretical power data.

[0078] Based on the same technical concept, such as Figure 2 As shown, the present invention also provides a linear interpolation processing system for wind farm data, including: a data acquisition module, used to acquire historical wind speed data of the wind farm, and partition the wind turbines in the wind farm according to the historical wind speed data to obtain wind turbine partitions; a power data acquisition module, used to acquire real-time wind speed data of wind turbines in the wind turbine partitions, predict theoretical power data of wind turbines according to the real-time wind speed data of wind turbines, screen out abnormal data in the theoretical power data of wind turbines and remove the abnormal data; a power data processing module, used to fill the theoretical power data of wind turbines after removing abnormal data based on a linear interpolation method to obtain complete theoretical power data of wind turbines; a power data correction module, used to determine a target error value according to the real-time wind speed data of the wind turbines, and correct the theoretical power data of the wind turbines according to the target error value.

[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0080] By applying the above technical scheme, the present invention obtains the historical wind speed data of the wind farm, partitions the wind turbines in the wind farm according to the historical wind speed data, and obtains the wind turbine partitions; obtains the real-time wind speed data of the wind turbines in the wind turbine partitions, predicts the theoretical power data of the wind turbines according to the real-time wind speed data of the wind turbines, screens out the abnormal data in the theoretical power data of the wind turbines and removes the abnormal data; fills the theoretical power data of the wind turbines after removing the abnormal data based on the linear interpolation method to obtain the complete theoretical power data of the wind turbines; determines the target error value according to the real-time wind speed data of the wind turbines, and corrects the theoretical power data of the wind turbines according to the target error value. The wind farm is partitioned, and the theoretical power data is filled based on the linear interpolation method, which improves the accuracy and integrity of the data.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for linear interpolation processing of wind farm data, characterized in that: include: Obtain historical wind speed data of the wind farm, and partition the wind turbines in the wind farm according to the historical wind speed data to obtain wind turbine partitions; Obtain real-time wind speed data of wind turbines in the wind turbine zone, predict theoretical power data of wind turbines based on real-time wind speed data of wind turbines, screen out abnormal data in theoretical power data of wind turbines and remove the abnormal data; Based on the linear interpolation method, the theoretical power data of the wind turbine after the abnormal data is removed is filled to obtain the complete theoretical power data of the wind turbine; The target error value is determined according to the real-time wind speed data of the wind turbine generator set, and the theoretical power data of the wind turbine generator set is corrected according to the target error value.

2. The method for linear interpolation of wind farm data according to claim 1, characterized in that: The wind turbines in the wind farm are divided into zones based on historical wind speed data, including: Determine the historical wind speed curve of each wind turbine in the wind farm according to the historical wind speed data of the wind farm, obtain a preset wind speed data interval, and determine the wind speed frequency distribution of the historical wind speed curve according to the preset wind speed data interval; Draw a wind speed frequency curve according to the wind speed frequency distribution, obtain a preset wind speed threshold, and filter out the frequencies corresponding to wind speed data greater than the preset wind speed threshold in the wind speed frequency curve; Calculate the ratio of the corresponding frequency of the wind speed data exceeding the preset wind speed threshold to the preset allowable frequency to obtain the wind speed fluctuation coefficient; Obtain wind speed data less than or equal to a preset wind speed threshold in the wind speed frequency curve graph, calculate the average value of wind speed data less than or equal to the preset wind speed threshold in the wind speed frequency curve graph, and multiply the average value of wind speed data less than or equal to the preset wind speed threshold in the wind speed frequency curve graph by the wind speed fluctuation coefficient to obtain a wind speed distribution coefficient; Based on the k-means clustering algorithm, the wind turbines in the wind farm are clustered according to the wind speed distribution coefficient, and the wind turbine zones are determined according to the clustering results.

3. The method for linear interpolation of wind farm data according to claim 2, characterized in that: Based on the k-means clustering algorithm, the wind turbines in the wind farm are clustered according to the wind speed distribution coefficient, including: According to the number of wind turbines in the wind farm, k initial cluster centers are randomly selected, and the Euclidean distance from the wind speed distribution coefficient of each wind turbine to the initial cluster center is calculated; According to the Euclidean distance from the wind speed distribution coefficient to the initial cluster center, each wind turbine is divided into corresponding partitions, and the average value of all wind speed distribution coefficients in each partition is calculated; The cluster center is updated according to the average value of all wind speed distribution coefficients in each cluster, and repeated iterations are performed according to the new cluster center until the cluster center no longer changes, and k final cluster centers are obtained; The wind turbines in the wind farm are divided into k wind turbine partitions according to the Euclidean distance from the wind speed distribution coefficient to the final cluster center.

4. The method for linear interpolation of wind farm data according to claim 1, characterized in that: Filter out abnormal data in the real-time power data of wind turbines and remove the abnormal data, including: Draw a theoretical power curve according to the theoretical power data, obtain a standard power curve corresponding to the wind turbine group partition of the wind turbine group, calculate the sum of the correlation coefficients of the theoretical power curve and the standard power curve in a preset rolling time window, and filter out a time period in which the sum of the correlation coefficients is less than a first preset threshold; Calculate the absolute value of the difference between each power data point and the average value of two adjacent power data points in the time period in which the sum of the correlation coefficients in the theoretical power curve is less than the first preset threshold, and determine the power change rate of the power data point according to the absolute value of the difference between the power data point and the average value of the two adjacent power data points; If the power change rate of the power data point is greater than the second preset threshold, the power data point is determined as abnormal data and the abnormal data is removed.

5. The method for linear interpolation of wind farm data according to claim 4, characterized in that: The theoretical power data of wind turbines after removing abnormal data is filled based on the linear interpolation method, including: Obtain the average value of two non-abnormal data points adjacent to the abnormal data point in the theoretical power curve, and determine the initial linear interpolation value according to the average value of the non-abnormal data points; An interpolation correction coefficient is determined according to the wind turbine group partition where the wind turbine group is located, and an initial linear interpolation is corrected according to the interpolation correction coefficient to obtain a linear interpolation; The linear interpolation of each abnormal data point is added to the theoretical power data to complete the filling of the theoretical power data of the wind turbine.

6. The method for linear interpolation of wind farm data according to claim 5, characterized in that: The interpolation correction coefficient is determined according to the wind turbine partition where the wind turbine is located, including: Obtain the cluster center value of the wind turbine group partition, and determine the interpolation correction coefficient based on the cluster center value combined with the correction coefficient calculation formula. The correction coefficient calculation formula is as follows: Among them, L is the interpolation correction coefficient, L α is the preset interpolation correction coefficient, W is the cluster center value, W α is the preset allowable wind speed, and R is the preset range coefficient.

7. The method for linear interpolation of wind farm data according to claim 1, characterized in that: Determine the target error value based on the real-time wind speed data of the wind turbine, including: Draw a real-time wind speed curve according to the real-time wind speed data of the wind turbine generator set, calculate the wind speed fluctuation coefficient according to the real-time wind speed curve, and determine whether the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than a third preset threshold value; If the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than a third preset threshold, setting the preset first error value as the target error value; If the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is less than or equal to the third preset threshold, determining whether the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than a fourth preset threshold; If the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is greater than a fourth preset threshold, setting the preset second error value as the target error value; If the difference between the wind speed fluctuation coefficient and the preset allowable wind speed fluctuation coefficient is less than or equal to a fourth preset threshold, the preset third error value is set as the target error value.

8. The method for linear interpolation of wind farm data according to claim 7, characterized in that: Calculate the wind speed fluctuation coefficient based on the real-time wind speed curve, including: Obtain a preset sliding time window, and divide the real-time wind speed curve graph into a number of sub-wind speed curves according to the preset sliding time window; Calculate the absolute value of the slope of each sub-wind speed curve, screen out the sub-wind speed curves whose absolute value of the slope is greater than the fifth preset threshold, calculate the ratio of the number of sub-wind speed curves whose absolute value of the slope is greater than the fifth preset threshold to the preset allowable number, and obtain the wind speed fluctuation coefficient.

9. The method for linear interpolation of wind farm data according to claim 8, characterized in that: Correct the theoretical power data of the wind turbine according to the target error value, including: Obtain the real-time power curve of the wind turbine, calculate the difference between the real-time power curve and the theoretical power curve, and obtain the theoretical power error; Calculate the difference between the theoretical power error and the target error value, normalize the difference between the theoretical power error and the target error value, and obtain an error correction coefficient; Multiply the error correction coefficient by the theoretical power data to obtain the corrected theoretical power data.

10. A wind farm data linear interpolation processing system, characterized in that: include: A data acquisition module is used to acquire historical wind speed data of the wind farm, and to partition the wind turbines in the wind farm according to the historical wind speed data to obtain wind turbine partitions; The power data acquisition module is used to acquire the real-time wind speed data of the wind turbines in the wind turbine zone, predict the theoretical power data of the wind turbines according to the real-time wind speed data of the wind turbines, screen out the abnormal data in the theoretical power data of the wind turbines and remove the abnormal data; The power data processing module is used to fill in the theoretical power data of the wind turbine after removing the abnormal data based on the linear interpolation method to obtain the complete theoretical power data of the wind turbine; The power data correction module is used to determine the target error value according to the real-time wind speed data of the wind turbine generator set, and correct the theoretical power data of the wind turbine generator set according to the target error value.

Images