Wind power plant abnormal value screening method and system

Abstract

The invention discloses a wind power plant abnormal value screening method and system, and the method comprises the steps: obtaining a wind speed-power first data set of a wind power plant, and carrying out the screening to obtain a second data set; calculating a first set inner limit of the second data set by adopting a transverse quartile method, and deleting points with wind speeds outside the first set inner limit in the second data set; calculating a second set inner limit of the second data set by adopting a longitudinal quartile method, and deleting points of which the power is outside the second set inner limit in the second data set to obtain a third data set; and performing first operation on all points in the third data set by adopting a clustering algorithm, and outputting a wind speed-power data set which is identified as normal. According to the method, the normal ranges of the wind speed and the power are accurately defined through the transverse and longitudinal quartile method, abnormal values are eliminated, and an accurate and reliable third data set is obtained; and a clustering algorithm is adopted for further screening, so that the data set only contains normal wind speed-power data points, and the data quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind farm station data processing, and in particular to a method and system for screening abnormal values ​​of a wind farm. Background Art

[0002] In the process of data collection and transmission in wind farms, some abnormal data often appear. These abnormal values ​​may be caused by sensor failure, environmental interference or data processing errors. If these abnormal data are not effectively screened and processed, it may lead to deviations in wind farm power forecasting, operation optimization and scheduling strategy execution, thus affecting the overall operation efficiency of the power system. Therefore, accurate and effective screening of abnormal data in wind farms is a key step to ensure the reliable operation of wind farms and improve system stability.

[0003] At present, the screening methods for abnormal data in wind farms mainly include the quartile method based on statistical characteristics, the isolation forest algorithm, the K-means clustering algorithm, and the robust regression method (such as RANSAC). The quartile method identifies abnormal points that are out of range by calculating the interquartile range of the data. It has the advantages of simple calculation and easy implementation, and is suitable for processing isolated discrete abnormal data. The isolation forest algorithm constructs an anomaly detection model through random sampling and tree structure, which can efficiently identify isolated abnormal points in high-dimensional data. The K-means clustering algorithm divides the data into multiple clusters, identifies outliers based on the distance between the cluster centers, and is suitable for processing abnormal samples with relatively uniform distribution. The RANSAC robust regression algorithm can identify and fit the model when most of the data contains noise, and is suitable for processing data sets with many abnormal values.

[0004] Existing technologies have certain limitations in filtering outliers in wind farm power data. The quartile method is often difficult to effectively handle horizontally stacked abnormal data. The K-means clustering algorithm is less effective when dealing with clusters of complex shapes or uneven sizes, especially deviation cluster type anomalies. The RANSAC robust regression algorithm may not be able to effectively fit data with complex distributions, and it is easy to ignore nonlinear anomalies that deviate from the mainstream model. Therefore, existing methods have deficiencies in processing various types of abnormal data and cannot comprehensively and accurately filter out all outliers. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a method for screening abnormal values ​​in a wind farm to solve the limitation of the prior art in processing abnormal data of a wind farm and the problem of low accuracy of abnormal value identification.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for screening outliers in a wind farm, comprising:

[0009] Acquire a first wind speed-power data set of a wind farm, and filter the first wind speed-power data set of the wind farm to obtain a second data set;

[0010] The inner limit of the first set of the second data set is calculated by using the horizontal quartile method, and the points in the second data set whose wind speed is outside the inner limit of the first set are deleted;

[0011] The second set inner limit of the second data set is calculated by using the longitudinal quartile method, and the points in the second data set whose power is outside the second set inner limit are deleted to obtain a third data set;

[0012] A clustering algorithm is used to perform a first operation on all points in the third data set, and an output is identified as a normal wind speed-power data set.

[0013] As a preferred solution of the method for screening outliers in a wind farm according to the present invention, the first set inner limit of the second data set calculated by using the horizontal quartile method includes:

[0014] The first set of inner limits of wind speed in the second data set is calculated using the lateral quartile method, expressed as:

[0015]

[0016] Among them, Q s1 , Q s3 The first and third quantiles of the wind speed data set, IQR s 、IQR p is the interquartile range of the wind speed dataset and the power dataset, [W s，l , W s，h ] is the set inner limit of the wind speed dataset.

[0017] As a preferred solution of the method for screening abnormal values ​​of a wind farm according to the present invention, the second set inner limit of the second data calculated by the longitudinal quartile method includes:

[0018] The second set inner limit of the power in the second data set is calculated using the longitudinal quartile method, which is expressed as:

[0019]

[0020] Among them, Q p1 , Q p3 are the first and third quartiles of the power dataset, IQR and IQRp are the interquartile ranges of the wind speed dataset and the power dataset, [W p，l , W p，h ] is the collective inner limit of the power data set.

[0021] As a preferred solution of the method for screening outliers in a wind farm according to the present invention, the clustering algorithm includes:

[0022] The DBSCAN clustering algorithm is used to perform secondary outlier screening on the third data set, and the radius eps and minimum inlier point MinPts parameters are selected.

[0023] As a preferred solution of the method for screening abnormal values ​​of a wind farm according to the present invention, the first operation includes:

[0024] All points in the third data set are scanned and marked as core points, boundary points or noise points, and noise points are removed.

[0025] As a preferred solution of the method for screening outliers in a wind farm according to the present invention, the core points, boundary points or noise points include:

[0026] Points with more than MinPts number within the radius eps are represented as core points;

[0027] Points within the radius eps where the number of points is less than MinPts but are within the domain of the core points are represented as boundary points;

[0028] The number of points within the radius eps is less than MinPts, but the points outside the range of any core points are represented as noise points.

[0029] As a preferred solution of the method for screening abnormal values ​​of a wind farm according to the present invention, a normal wind speed-power data set is expressed as:

[0030] A Q-D ={(S i ,P i )|i=1,2,...,l}

[0031] Among them, S i is the wind speed data, P i is the power data corresponding to the wind speed, l is the number of wind speed-power points selected by DBSCAN clustering, A Q-D is a normal wind speed-power data set.

[0032] In a second aspect, the present invention provides a system for screening outliers in a wind farm, comprising:

[0033] Acquire a first wind speed-power data set of a wind farm, and filter the first wind speed-power data set of the wind farm to obtain a second data set;

[0034] The inner limit of the first set of the second data set is calculated by using the horizontal quartile method, and the points in the second data set whose wind speed is outside the inner limit of the first set are deleted;

[0035] The second set inner limit of the second data set is calculated by using the longitudinal quartile method, and the points in the second data set whose power is outside the second set inner limit are deleted to obtain a third data set;

[0036] A clustering algorithm is used to perform a first operation on all points in the third data set, and an output is identified as a normal wind speed-power data set.

[0037] In a third aspect, the present invention provides a computing device, comprising:

[0038] Memory and processor;

[0039] 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 wind farm abnormal value screening method are implemented.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the wind farm abnormal value screening method.

[0041] Compared with the prior art, the present invention has the following beneficial effects: the present invention systematically processes the wind speed-power data of a wind farm through a wind farm outlier screening method; screens out a reasonable second data set from the original data set, and then accurately defines the normal range of wind speed and power through the horizontal and vertical quartile method, removes outliers, and obtains a more accurate and reliable third data set; further screening is performed using the DBSCAN clustering algorithm to ensure that the data set only contains normal wind speed-power data points, thereby improving data quality and providing a solid foundation for subsequent wind farm performance analysis, operation and maintenance management, and improvement of energy output efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0043] Figure 1 This is a schematic diagram of the overall process of a method for screening abnormal values ​​in a wind farm according to an embodiment of the present invention;

[0044] Figure 2 A schematic diagram of wind speed-power scatter points after outliers are screened by the quartile method in a method for screening outliers in a wind farm according to an embodiment of the present invention;

[0045] Figure 3 This is a schematic diagram of wind speed-power scatter points after secondary outlier screening through DBSCAN clustering in a method for screening outliers in a wind farm according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0049] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0050] At the same time, in the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0051] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0052] Example 1

[0053] Reference Figure 1 , as an embodiment of the present invention, provides a method for screening abnormal values ​​in a wind farm, comprising:

[0054] S100: Acquire a first data set of wind speed-power of a wind farm, and filter the first data set of wind speed-power of the wind farm to obtain a second data set;

[0055] Specifically, the wind speed data S of the wind farm and the corresponding power data P are input;

[0056] Assuming that the number of wind speed-power points in the wind farm is n, the first data set of wind speed-power in the wind farm is obtained, which is expressed as:

[0057] A0={(S i ,P i )|i=1,2,...,n}

[0058] When the wind speed s∈[s ci ,s co ], where s ci ,s co Respectively represent the cut-in and cut-out wind speeds of the wind turbine;

[0059] In the embodiment of the present application, the screening operation is: modify the wind power less than 0 to 0, and remove the data greater than the rated power of the wind farm, to obtain m wind speed-power points, i.e., the second data set, denoted as A1={(S i , P i )|i=1, 2, ..., m};

[0060] It should be noted that the present invention effectively cleans up unreasonable data points in the wind farm wind speed-power data set, such as correcting negative power to zero and eliminating abnormal values ​​that exceed the rated power of the wind farm. This processing step not only ensures the accuracy and reliability of the data set.

[0061] S102: Calculate the inner limit of the first set of the second data set by using the horizontal quartile method, and delete the points in the second data set whose wind speed is outside the inner limit of the first set;

[0062] Preferably, the first set inner limit of the wind speed in the second data set is calculated using the lateral quartile method, which is expressed as:

[0063]

[0064] Among them, Q s1 , Q s3 The first and third quantiles of the wind speed data set, IQR s 、IQR p is the interquartile range of the wind speed dataset and the power dataset, [W s，l , W s，h ] is the set inner limit of the wind speed data set;

[0065] In the embodiment of the present application, the power is first divided into p intervals to divide p wind speed data sample sets, which are expressed as:

[0066]

[0067] where q j represents the number of wind speed samples contained in the jth sample set;

[0068] In the embodiment of the present application, the first and third quantiles Q of the j-th wind speed data sample set are calculated. s1，j , Q s3，j , expressed as:

[0069]

[0070]

[0071] In the embodiment of the present application, according to the first and third quantiles Q s1，j , Q s3，j Calculate the interquartile range IQR of the j-th wind speed data sample set s，j , expressed as:

[0072] IQR s，j =Q s3 -Q s1

[0073] In the embodiment of the present application, according to the interquartile range IQRs，j Calculate the Whisker upper limit W of the j-th wind speed data sample set s，j，h , lower limit W s，j，l , expressed as:

[0074]

[0075] Define the i-th wind speed data set S j In W s，j，l and W s，j，h The samples between are normal samples, and the remaining points in the set are considered abnormal samples and need to be screened and eliminated;

[0076] According to the above process, the abnormal points in the p wind speed data sample set are removed;

[0077] It should be noted that, by using the horizontal quartile method to calculate the first set of inner limits of the wind speed in the second data set and removing the abnormal points outside the inner limits, the present invention further purifies the wind speed-power data set of the wind farm. This method can accurately identify and eliminate abnormal wind speed data caused by factors such as sensor failure, data transmission errors or extreme weather conditions, ensuring that the remaining data points can better reflect the actual operating conditions of the wind farm.

[0078] S104: Calculate the second set inner limit of the second data set by using the longitudinal quartile method, delete the points in the second data set whose power is outside the second set inner limit, and obtain a third data set;

[0079] Preferably, the second set inner limit of the power in the second data set is calculated using the longitudinal quartile method, which is expressed as:

[0080]

[0081] Among them, Q p1 , Q p3 is the first and third quartile of the power data set, IQR s 、IQR p is the interquartile range of the wind speed dataset and the power dataset, [W p，l , W p，h ] is the collective inner limit of the power data set;

[0082] In the embodiment of the present application, the wind speed is divided into a intervals to divide the output power data sample sets, which are expressed as:

[0083]

[0084] where b j represents the number of power samples contained in the jth sample set;

[0085] In the embodiment of the present application, the first and third quantiles Q of the jth power data sample set are calculated. p1，j , Q p3，j , expressed as:

[0086]

[0087]

[0088] In the embodiment of the present application, according to the first and third quantiles Q p1，j , Q p3，j Calculate the interquartile range IQR of the j-th power data sample set p，j , expressed as:

[0089] IQR p，j =Q p3 -Q p1

[0090] In the embodiment of the present application, according to the interquartile range IQR p，j Calculate the Whisker upper limit W of the jth power data sample set p，j，h , lower limit W p，j，l , expressed as:

[0091]

[0092] Define the i-th power data set P j In W p，j，l and W p，j，h The samples between are normal samples, and the remaining points in the set are considered abnormal samples and need to be screened and eliminated;

[0093] According to the above process, outliers in a power data sample set are removed;

[0094] The horizontal quartile method and the vertical quartile method are used to delete the points in the second data set whose wind speed and power are outside the set limit, and the wind speed-power set after the quartile method is obtained, that is, the third data set, which is recorded as A. Q ={(S i , P i )|i=1,2,...,k};

[0095] like Figure 2 The figure shows a wind speed-power scatter plot after outliers are screened by the quartile method. The green sample points indicate normal data, and the red sample points indicate abnormal data. The quartile method screens out most of the isolated discrete and deviation cluster abnormal data. The outlier residual fragments 1 and 2 in the figure are some horizontal accumulation abnormal data that have not been screened.

[0096] It should be noted that, through the above-mentioned process of double screening the second data set using the horizontal quartile method and the vertical quartile method, the present invention achieves deep purification of the wind speed-power data of the wind farm. This method not only excludes abnormal data from the wind speed dimension, but also further screens from the power dimension, ensuring the rationality and matching of the wind speed and power values ​​in the data set. After this step, the third data set obtained more accurately reflects the actual operating characteristics of the wind farm.

[0097] S106: performing a first operation on all points in the third data set using a clustering algorithm, and outputting a wind speed-power data set identified as normal;

[0098] Preferably, the DBSCAN clustering algorithm is used to perform secondary outlier screening on the third data set, and the radius eps and the minimum interior point MinPts parameters are selected.

[0099] Preferably, all points in the third data set are scanned and marked as core points, boundary points or noise points, and the noise points are removed.

[0100] Preferably, the points with more than MinPts number within the radius eps are represented as core points;

[0101] Preferably, the number of points within the radius eps is less than MinPts, but the points located within the domain of the core points are represented as boundary points;

[0102] Preferably, the number of points within the radius eps is less than MinPts, but points outside the region of any core point are represented as noise points.

[0103] Preferably, a normal wind speed-power data set is expressed as:

[0104] A Q-D ={(S i , P i )|i=l,2,...,l}

[0105] Among them, S i is the wind speed data, P i is the power data corresponding to the wind speed, l is the number of wind speed-power points selected by DBSCAN clustering, A Q-D is a normal wind speed-power data set;

[0106] like Figure 3 As shown in the figure, it is a wind speed-power scatter plot after secondary screening of outliers by DBSCAN clustering. Figure 3 It can be seen that the remaining horizontal accumulation value fragments after quartile screening have been completely screened out after DBSCAN clustering;

[0107] It should be noted that the DBSCAN clustering algorithm is used to perform secondary outlier screening on the third data set. The present invention further improves the accuracy and reliability of the wind speed-power data set. The DBSCAN algorithm effectively distinguishes core points, boundary points and noise points by scanning data points and based on preset radius and minimum interior point parameters, thereby achieving accurate elimination of abnormal data. This process not only ensures that the remaining data points can better reflect the actual operating conditions of the wind farm.

[0108] The above is a schematic scheme of a method for screening abnormal values ​​of a wind farm in this embodiment. It should be noted that the technical scheme of the system for screening abnormal values ​​of a wind farm and the technical scheme of the above-mentioned method for screening abnormal values ​​of a wind farm are of the same concept. For details not described in detail in the technical scheme of the system for screening abnormal values ​​of a wind farm in this embodiment, please refer to the description of the technical scheme of the above-mentioned method for screening abnormal values ​​of a wind farm.

[0109] The wind farm outlier screening system in this embodiment includes:

[0110] Acquire a first wind farm wind speed-power data set, and filter the first wind farm wind speed-power data set to obtain a second data set;

[0111] The inner limit of the first set of the second data set is calculated by using the horizontal quartile method, and the points in the second data set whose wind speed is outside the inner limit of the first set are deleted;

[0112] The second set inner limit of the second data set is calculated by using the longitudinal quartile method, and the points in the second data set whose power is outside the second set inner limit are deleted to obtain a third data set;

[0113] A clustering algorithm is used to perform a first operation on all points in the third data set, and an output is identified as a normal wind speed-power data set.

[0114] This embodiment further provides a computing device, which is applicable to the case of outlier screening in a wind farm, and includes:

[0115] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method for screening abnormal values ​​of wind farms as proposed in the above embodiment.

[0116] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for screening abnormal values ​​of a wind farm as proposed in the above embodiment is implemented.

[0117] The storage medium proposed in this embodiment and the method for implementing wind farm abnormal value screening proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0118] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0119] Example 2

[0120] Referring to Table 1, an embodiment of the present invention provides a method for screening abnormal values ​​in a wind farm. In order to verify its beneficial effects, comparison results of several solutions are provided.

[0121] In order to verify the superiority of the method of the present invention, four models were used to select one year of actual operation data of a wind farm in South China for research, to identify and filter outliers, and to compare their effects.

[0122] Table 1 lists the comparison results of the outlier recognition accuracy of different methods;

[0123] Table 1 Comparison of outlier recognition accuracy of different methods

[0124] Outlier Screening Methods Outlier recognition accuracy Quartile method and DBSCAN clustering 93.75％ k-means clustering 87.29％ Isolation Forest Algorithm 82.72％ RANSAC robust regression algorithm 89.83％

[0125] As shown in Table 1, the combination of the quartile method and DBSCAN clustering improves the recognition accuracy by about 6% compared with K-means clustering, by about 11% higher than the recognition accuracy of the isolation forest algorithm, and by about 4% higher than the RANSAC robust regression algorithm.

[0126] Through the above data analysis, it can be seen that the performance and accuracy of combining the quartile method with DBSCAN clustering to identify and screen outliers in wind farms are significantly better than other models.

[0127] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for screening abnormal values ​​in a wind farm, characterized in that: include: Acquire a first wind speed-power data set of a wind farm, and filter the first wind speed-power data set of the wind farm to obtain a second data set; The inner limit of the first set of the second data set is calculated by using the horizontal quartile method, and the points in the second data set whose wind speed is outside the inner limit of the first set are deleted; The second set inner limit of the second data set is calculated by using the longitudinal quartile method, and the points in the second data set whose power is outside the second set inner limit are deleted to obtain a third data set; A clustering algorithm is used to perform a first operation on all points in the third data set, and an output is identified as a normal wind speed-power data set.

2. The method for screening abnormal values ​​of a wind farm according to claim 1, characterized in that: The inner limits of the first set of the second data set calculated using the horizontal quartile method include: The first set of inner limits of wind speed in the second data set is calculated using the lateral quartile method, expressed as: Among them, Q s1 , Q s3 The first and third quantiles of the wind speed data set, IQR s 、IQR p is the interquartile range of the wind speed dataset and the power dataset, [W s,l ,W s,h ] is the set inner limit of the wind speed dataset.

3. The method for screening abnormal values ​​of a wind farm according to claim 1 or 2, characterized in that: The second set of inner limits of the second data calculated using the longitudinal quartile method include: The second set inner limit of the power in the second data set is calculated using the longitudinal quartile method, which is expressed as: Among them, Q p1 , Q p3 is the first and third quartile of the power data set, IQR s 、IQR p is the interquartile range of the wind speed dataset and the power dataset, [W p,l ,W p,h ] is the collective inner limit of the power data set.

4. The method for screening abnormal values ​​of a wind farm according to claim 3, characterized in that: Clustering algorithms include, The DBSCAN clustering algorithm is used to perform secondary outlier screening on the third data set, and the radius eps and minimum inlier point MinPts parameters are selected.

5. The method for screening abnormal values ​​of a wind farm according to claim 4, characterized in that: The first operation includes, All points in the third data set are scanned and marked as core points, boundary points or noise points, and noise points are removed.

6. The method for screening abnormal values ​​of a wind farm according to claim 5, characterized in that: Core points, boundary points or noise points include, Points with more than MinPts number within the radius eps are represented as core points; Points within the radius eps where the number of points is less than MinPts but are within the domain of the core points are represented as boundary points; The number of points within the radius eps is less than MinPts, but the points outside the range of any core points are represented as noise points.

7. The method for screening abnormal values ​​of a wind farm according to claim 6, characterized in that: A normal wind speed-power data set is expressed as: A Q-D ={(S i ,P i )|i=1,2,...,l} Among them, S i is the wind speed data, P i is the power data corresponding to the wind speed, l is the number of wind speed-power points selected by DBSCAN clustering, A Q-D is a normal wind speed-power data set.

8. A system for screening outliers in a wind farm, characterized in that: include, Acquire a first wind speed-power data set of a wind farm, and filter the first wind speed-power data set of the wind farm to obtain a second data set; The inner limit of the first set of the second data set is calculated by using the horizontal quartile method, and the points in the second data set whose wind speed is outside the inner limit of the first set are deleted; The second set inner limit of the second data set is calculated by using the longitudinal quartile method, and the points in the second data set whose power is outside the second set inner limit are deleted to obtain a third data set; A clustering algorithm is used to perform a first operation on all points in the third data set, and an output is identified as a normal wind speed-power data set.

9. An electronic device, comprising: 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 wind farm abnormal value screening method according to 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 screening abnormal values ​​of a wind farm according to any one of claims 1 to 7.

Images