Improved floating type wind generating set typical day division method and system

Abstract

The invention discloses an improved floating type wind generating set typical day division method and system, and belongs to the field of wind power generation. The method comprises the following steps: carrying out acquisition and normalization processing on the SCADA system of the wind turbine generator; constructing a wind power output characteristic value matrix; determining an optimal clustering number; performing clustering analysis by taking an improved Euclidean distance as a measurement mode; and determining typical days in different output scenes: calculating improved distances between each sample in different categories and other samples, and taking the sample sequence with the minimum sum of the distances as the clustering center of the category, namely the typical day in the output scene. The system comprises a historical data collection module, a wind power output characteristic value matrix construction module, an optimal clustering number determination module, a clustering analysis module and a typical day analysis module. According to the method, advantages and disadvantages of the Euclidean distance and the cosine similarity are considered, a distance measurement mode of a traditional clustering algorithm is improved, and effective division of wind power output typical days is realized.

Description

Technical Field

[0001] The present invention belongs to the field of wind turbine generators, and particularly relates to an improved method and system for dividing typical days of a floating wind turbine generator set. Background Art

[0002] Due to the inherent attributes of wind resources such as randomness, volatility, and uncertainty, the impact of wind power generation on the power grid has become increasingly obvious, and the adverse effects on the power grid have also been increasing. The output of wind power is affected by factors such as wind energy, solar radiation intensity, and temperature, and its random volatility is closely related to the dynamic changes of weather systems. Quantitative analysis of dividing the output of wind power into different typical daily outputs through clustering algorithms is of great significance for quantitatively analyzing the impact of wind power output on the power grid and studying wind power dispatching. Summary of the Invention

[0003] The purpose of the present invention is to propose an improved method and system for dividing typical days of a floating wind turbine generator set. The present invention considers the advantages and disadvantages of Euclidean distance and cosine similarity, improves the distance measurement method of traditional clustering algorithms, and realizes the effective division of typical days of wind power output.

[0004] To achieve the above purpose, the present invention adopts the following technical solutions: An improved method for dividing typical days of a floating wind turbine generator set, comprising: Step 1: Collect historical data of the SCADA system of the wind turbine generator; Step 2: Map the collected historical data to the interval [0, 1] by using the maximum-minimum normalization method, and construct a characteristic value matrix of wind power output; Step 3: Determine the optimal number of clusters based on the characteristic value matrix of wind power output; Step 4: According to the optimal number of clusters, use the characteristic value matrix of wind power output as the input and the improved Euclidean distance as the measurement method to perform clustering analysis; Step 5: Since the position of the cluster center cannot be determined after fusion, calculate the improved distance between each sample in different categories and the remaining samples, and use the sample sequence with the smallest sum of distances as the cluster center of this category, that is, the typical day in this output scenario.

[0005] A further improvement of the present invention is that in Step 1, the data sampling period is 1 year, and the data resolution is in seconds or minutes.

[0006] A further improvement of the present invention is that in Step 3, to determine the optimal number of clusters based on the characteristic value matrix of wind power output, the Gap statistic algorithm is adopted, including: Step 3-1: Cluster the characteristic value matrix of wind power output, and calculate the standardized within-cluster sum of squared errors ; (4) Among them, is the sum of the improved Euclidean distances between points within the k-th cluster; n k is the number of data belonging to the k cluster; is the i-th data observation point; C k is the k cluster data set; k = 1, 2, …, K ; K is the range of the number of clusters selected; Step 3-2: Randomly generate a total of B reference data sets, and calculate the for each reference data set, and then obtain the reference measure value ; (5) Among them, is the sum of squared errors within the cluster of the b-th reference data set; represents expectation; ; Step 3-3: Calculate the standard deviation of , and the smallest k value that satisfies the following condition is the optimal number of clusters; (6).

[0007] A further improvement of the present invention lies in that, in step 4, the improved Euclidean distance measurement method is as follows: Step 4-1, the Euclidean distance measurement formula for the output of the wind turbine is as follows: (1) In the formula, x , y are the wind power output matrices on the x-th day and the y-th day of the year respectively; Step 4-2, the cosine similarity measurement formula for the output of the wind turbine is as follows: (2) Step 4-3, based on the characteristics of cosine similarity and Euclidean distance, the improved Euclidean distance measurement method is as follows: (3) In the formula, is the maximum value of the Euclidean distance within the sampling time of one year; is the Euclidean distance measurement of the wind turbine output; is the cosine similarity measurement of the wind turbine output.

[0008] A typical day division system for a floating wind power generation unit based on improved Euclidean distance, comprising: A historical data collection module that collects historical data from the SCADA system of the wind turbine; A wind power output eigenvalue matrix construction module that maps the collected historical data to the interval [0, 1] using the maximum-minimum normalization method and constructs a wind power output eigenvalue matrix; An optimal clustering number determination module that determines the optimal clustering number based on the wind power output eigenvalue matrix; A clustering analysis module that performs clustering analysis according to the optimal clustering number, using the wind power output eigenvalue matrix as the input and the improved Euclidean distance as the measurement method; A typical day analysis module. Since the position of the clustering center cannot be determined after fusion, by calculating the improved distances between each sample in different categories and the remaining samples, the sample sequence with the smallest sum of distances is used as the clustering center of this category, that is, the typical day under this output scenario.

[0009] A further improvement of the present invention is that in the historical data collection module, the data sampling period is 1 year, and the data resolution is in seconds or minutes.

[0010] A further improvement of the present invention is that in the optimal clustering number determination module, based on the wind power output eigenvalue matrix, the optimal clustering number is determined using the Gap statistic algorithm, including: Step 3-1: Cluster the wind power output eigenvalue matrix and calculate the standardized within-cluster sum of squared errors ; (4) where is the sum of the improved Euclidean distances between points within the k-th cluster of data; n k is the number of data belonging to the k cluster; is the i-th data observation point; C k is the k cluster data set; k = 1, 2, …, K ; K is the range of clustering number selection; Step 3-2: Randomly generate a total of B reference data sets and calculate the for each reference data set, and then obtain the reference measure value ; (5) where is the within-cluster sum of squared errors of the b-th reference data set; represents expectation; ; Step 3-3: Calculate The standard deviation of, and the minimum k value that satisfies the following conditions is the optimal number of clusters; (6).

[0011] A further improvement of the present invention lies in that, in the clustering analysis module, the Euclidean distance metric method is improved as follows: The Euclidean distance metric formula for the output of the wind turbine in Step 4-1 is as follows: (1) In the formula, x , y are the wind power output matrices on the x-th day and the y-th day of the year respectively; Step 4-2, the cosine similarity metric formula for the output of the wind turbine is as follows: (2) Step 4-3, based on the characteristics of cosine similarity and Euclidean distance, the Euclidean distance metric method is improved as follows: (3) In the formula, is the maximum value of the Euclidean distance within the sampling time of one year; is the Euclidean distance metric for the output of the wind turbine; is the cosine similarity metric for the output of the wind turbine.

[0012] An electronic device includes: a processor and a memory coupled to the processor, where the memory stores a computer program, and when the computer program is executed by the processor, the steps of the improved method for dividing typical days of a floating wind power generation unit are implemented.

[0013] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the improved method for dividing typical days of a floating wind power generation unit are implemented.

[0014] Compared with the prior art, the present invention has at least the following beneficial technical effects: The improved method and system for dividing typical days of a floating wind power generation unit provided by the present invention perform typical day division on the wind power generation output, and by improving the distance metric method of the clustering algorithm, it can effectively divide the typical days of the wind power output. The selected typical output scenarios can reflect the characteristics of the wind power output and be used for differential modeling analysis of optimal scheduling under different output scenarios. The advantages of the present invention are: The Euclidean distance metric mainly measures the distance between sample points and does not involve the measurement of the distance between multi-dimensional time series samples, so it cannot reflect the change information in continuous time periods. The cosine similarity requires normalizing the lengths of two vectors and then measuring the directions of the two vectors. However, the cosine similarity is not sensitive to the absolute values of specific numerical values. Therefore, by improving the Euclidean distance with the cosine similarity and integrating the advantages of the two distance measurement methods, the typical days of wind power output can be better divided. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 FIG. shows a schematic flow chart of an improved method for dividing typical days of a floating wind turbine generator set according to the present invention.

[0017] Figure 2 FIG. is a schematic diagram showing the selection result of the optimal number of clusters in an embodiment of the present invention.

[0018] Figure 3 FIG. is a schematic diagram showing the clustering results of different typical days in an embodiment of the present invention.

[0019] Figure 4 FIG. shows a structural block diagram of a system for dividing typical days of a floating wind turbine generator set based on an improved Euclidean distance according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] In the following, only some exemplary embodiments are simply described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present invention. Therefore, the drawings and the description are considered to be exemplary in nature rather than restrictive.

[0021] It should be understood that when used in this specification and the appended claims, the terms "comprises" and "comprising" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0022] It should also be understood that the terms used in the specification of the present invention are merely for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0023] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0024] Schematic diagrams of various structures according to the disclosed embodiments of the present invention are shown in the drawings. These figures are not drawn to scale, where for the purpose of clear expression, some details are enlarged and some details may be omitted. The shapes of various regions and layers shown in the figures and their relative sizes and positional relationships are merely exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations. Those skilled in the art can additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0025] The embodiments of the present invention will be described in detail below with reference to the drawings.

[0026] The object of the present invention is to propose an improved method for dividing typical days of a floating wind power generation unit. The method is as Figure 1 shown, and the specific steps include: Step 1: Collect historical data of the wind turbine SCADA system.

[0027] Step 2: Use the maximum-minimum normalization method to map the collected historical data to the interval [0, 1] and construct a wind power output eigenvalue matrix.

[0028] Step 3: Based on the wind power output eigenvalue matrix, determine the optimal number of clusters. The Gap statistic algorithm is used in the embodiments of the present invention.

[0029] Step 4: According to the optimal number of clusters, use the wind power output eigenvalue matrix as the input and the improved Euclidean distance as the measurement method to perform clustering analysis. The K-means++ algorithm is used in the embodiments of the present invention.

[0030] Step 5: Determine the typical days of different output scenarios. Since the position of the clustering center cannot be determined after fusion, in this paper, the improved distance between each sample in different categories and the remaining samples is calculated, and the sample sequence with the smallest sum of distances is used as the clustering center of this category, that is, the typical day under this output scenario.

[0031] The calculation method of the improved Euclidean distance described in the present invention is as follows: The Euclidean distance metric formula for the output of a wind turbine is as follows: (1) In the formula, x , y are the wind power output matrices on the x-th day and the y-th day within a year respectively.

[0032] The cosine similarity metric formula for the output of a wind turbine is as follows: (2) Furthermore, based on the characteristics of cosine similarity and Euclidean distance, the Euclidean distance metric method is improved as follows: (3) In the formula, is the maximum value of the Euclidean distance within the sampling time of one year.

[0033] The historical data of the wind turbine SCADA system mentioned in step 1 has a data sampling period of generally 1 year and a data resolution of generally second level or minute level.

[0034] The Gap statistic algorithm process in step 3 in the embodiments of the present invention is as follows: Step 3-1: Cluster the wind power output eigenvalue matrix and calculate the normalized sum of within-cluster squared errors ; (4) Among them, is the sum of the improved Euclidean distances between points within the k-th cluster of data; n k is the number of data belonging to the k cluster; is the i-th data observation point; C k is the k cluster data set; k =1,2,…, K ; K is the range of the number of clusters selected; Step 3-2: Randomly generate a total of B reference data sets and calculate the for each reference data set, and then obtain the reference measure value ; (5) Among them, is the sum of within-cluster squared errors of the b-th reference data set; represents expectation; ; Step 3-3: Calculate The standard deviation, and the smallest k value that satisfies the following conditions is the optimal number of clusters; (6).

[0035] In the embodiment of the present invention, step 4 specifically includes the following steps: Step 4-1: Given a data set containing n samples , randomly select a sample point from the data set as the initial cluster center; Step 4-2: Calculate the shortest distance between all samples and the current cluster center:

[0036] Step 4-3: Calculate the probability that each sample is selected as the next cluster center:

[0037] Step 4-4: Generate a random number R in the interval [0, 1], and subtract R successively from , , …, , and define the sample point corresponding to the first time the difference is less than or equal to 0 as the next cluster center; Step 4-5: Repeat steps 4-2 to 4-4 until / cluster centers are selected; Step 4-6: Calculate the distance between each sample data object, that is, the non-cluster center, and each cluster center, and assign it to the class with the closest distance; Step 4-7: Calculate the average value of each class of data sample points and use it as the new cluster center for each class; Step 4-8: Repeat steps 4-6 to 4-7 until the cluster centers no longer change, and obtain the clustering result.

[0038] Embodiment 2 Adopt the implementation method introduced in the present invention, and select the typical day division of a floating offshore wind turbine in a certain place. The results are as follows: The selection result of the optimal number of clusters is as Figure 2 shown, and the optimal number of clusters is 6. The clustering result is as Figure 3As shown in the figure. Category 1 (stable low output), the power output is close to 0 for most of the day; Category 2 (fluctuating medium output), the power output fluctuates between 20 and 60, showing multiple small fluctuations and peaks; Category 3 (single-peak medium output), the power output fluctuates between 20 and 60, with an obvious single peak; Category 4 (fluctuating high output), the power output fluctuates between 20 and 80, showing multiple peaks; Category 5 (fluctuating low output), the power output rises rapidly to a peak at the beginning, then drops rapidly, and then fluctuates within a lower power value range; Category 6 (fluctuating output), the power output fluctuates between 20 and 60, showing multiple small fluctuations and peaks.

[0039] Example 3 As Figure 4 shown, a typical day division system for a floating wind power generation unit based on an improved Euclidean distance provided by the present invention includes: A historical data collection module for collecting historical data of the wind turbine SCADA system; A wind power output eigenvalue matrix construction module that maps the collected historical data to the interval [0, 1] using the maximum-minimum normalization method and constructs a wind power output eigenvalue matrix; An optimal clustering number determination module for determining the optimal clustering number based on the wind power output eigenvalue matrix; A clustering analysis module that performs clustering analysis according to the optimal clustering number, using the wind power output eigenvalue matrix as the input and the improved Euclidean distance as the metric; A typical day analysis module. Since the position of the clustering center cannot be determined after fusion, by calculating the improved distance between each sample in different categories and the remaining samples, the sample sequence with the minimum sum of distances is used as the clustering center of this category, that is, the typical day under this output scenario.

[0040] Example 4 An electronic device provided by the present invention includes: a processor and a memory coupled to the processor, where the memory stores a computer program, and when the computer program is executed by the processor, it implements the steps of an improved method for dividing typical days of a floating wind power generation unit.

[0041] The electronic device may further include one or more of a multimedia component, an input / output (I / O) interface, and a communication component.

[0042] Among them, the processor is used to control the overall operation of the electronic device to complete all or part of the steps in the storage medium sharing method. The memory is used to store various types of data to support the operation of the electronic device. These data may include, for example, instructions for any application or method operating on the electronic device, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, and so on. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc. The multimedia component can include a screen and an audio component. Among them, the screen can be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component can include a microphone, and the microphone is used to receive external audio signals. The received audio signal can be further stored in the memory or sent through the communication component. The audio component also includes at least one speaker for outputting audio signals. The I / O interface provides an interface between the processor and other interface modules, and the above other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component is used for wired or wireless communication between the electronic device and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them. Therefore, the corresponding communication component can include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0043] In an exemplary embodiment, an electronic device may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing a storage medium sharing method.

[0044] Embodiment 5 A computer-readable storage medium provided by the present invention stores a computer program, and when the computer program is executed by a processor, the steps of the improved method for dividing a typical day of a floating wind power generation set are implemented.

[0045] Those skilled in the art should understand that the embodiments of the present application may be provided as a method, a system, or a computer program product. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0046] The present application is described with reference to the flowcharts and / or block diagrams of methods, systems, and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a system for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0047] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions in the flowFigure 1 one process or multiple processes and / or boxes Figure 1 the functions specified in one box or multiple boxes.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one process or multiple processes and / or boxes Figure 1 one box or multiple boxes.

[0049] The foregoing has shown and described the basic principles, main features and advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and without departing from the spirit or basic features of the present invention, the present invention can be implemented in other specific forms. Therefore, in any regard, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claimed invention.

[0050] In addition, it should be understood that although this specification is described according to embodiments, not every embodiment only contains an independent technical solution. This narrative manner of the specification is only for clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of the present invention and cannot be used to limit the protection scope of the present invention. Any modification made on the basis of the technical solution according to the technical idea proposed by the present invention falls within the protection scope of the claims of the present invention.

Claims

1. An improved method for dividing typical days of floating wind turbines, characterized in that: include: Step 1: Collect historical data from the wind turbine SCADA system; Step 2: Use the maximum and minimum normalization method to map the collected historical data to the [0, 1] interval and construct the wind power output eigenvalue matrix; Step 3: Determine the optimal number of clusters based on the wind power output eigenvalue matrix; Step 4: Based on the optimal number of clusters, the wind power output eigenvalue matrix is ​​used as input and the improved Euclidean distance is used as the measurement method to perform cluster analysis; Step 5: Since the location of the cluster center cannot be determined after fusion, the improved distance between each sample in different categories and the remaining samples is calculated, and the sample sequence with the smallest sum of distances is taken as the cluster center of the category, that is, the typical day under the output scenario.

2. The improved method for dividing typical days of floating wind turbine generators according to claim 1, characterized in that: In step 1, the data sampling period is 1 year, and the data resolution is second or minute.

3. The improved method for dividing typical days of floating wind turbine generators according to claim 1, characterized in that: In step 3, based on the wind power output eigenvalue matrix, the optimal number of clusters is determined using the Gap statistic algorithm, including: Step 3-1: Cluster the wind power output eigenvalue matrix and calculate the standardized intra-cluster sum of squared errors ; （4） in, is the sum of the improved Euclidean distances between points in the k-th cluster data; n k For the k The number of cluster data; is the i-th data observation point; C k For the k Cluster data set; k =1,2,…, K ; K is the range of cluster number selection; Step 3-2: Randomly generate a total of B reference data sets and calculate the , and then obtain the reference measurement value ; （5） in, is the intra-cluster square error sum of the b-th reference data set; express expectations; ; Step 3-3: Calculation The standard deviation of , the minimum k value that satisfies the following conditions is the optimal number of clusters; （6）。 4. The improved method for dividing typical days of floating wind turbine generators according to claim 3, characterized in that: In step 4, the Euclidean distance metric is improved as follows: Step 4-1 The Euclidean distance measurement formula for wind turbine output is as follows: (1) In the formula, x , y They are the wind power output matrices on the xth and yth day of a year respectively; Step 4-2, the wind turbine output cosine similarity measurement formula is as follows: (2) Step 4-3, based on the characteristics of cosine similarity and Euclidean distance, the Euclidean distance measurement method is improved as follows: (3) In the formula, It is the maximum value of the Euclidean distance within the sampling time of one year; It is the Euclidean distance measure of wind turbine output; It is the cosine similarity measure of wind turbine output.

5. A typical day division system for floating wind turbines based on improved Euclidean distance, characterized in that: include: Historical data collection module, which collects historical data of wind turbine SCADA system; The wind power output eigenvalue matrix construction module uses the maximum and minimum normalization method to map the collected historical data to the [0, 1] interval to construct the wind power output eigenvalue matrix; An optimal cluster number determination module determines the optimal cluster number based on the wind power output eigenvalue matrix; The cluster analysis module performs cluster analysis based on the optimal number of clusters, taking the wind power output eigenvalue matrix as input and the improved Euclidean distance as the measurement method; In the typical day analysis module, since the location of the cluster center cannot be determined after fusion, the improved distance between each sample in different categories and the remaining samples is calculated, and the sample sequence with the smallest sum of distances is taken as the cluster center of the category, that is, the typical day under the output scenario.

6. The floating wind turbine generator typical day division system based on improved Euclidean distance according to claim 5, characterized in that: In the historical data collection module, the data sampling period is 1 year, and the data resolution is at the second or minute level.

7. The floating wind turbine generator typical day division system based on improved Euclidean distance according to claim 5, characterized in that: In the module for determining the optimal number of clusters, the optimal number of clusters is determined based on the wind power output eigenvalue matrix, using the Gap statistic algorithm, including: Step 3-1: Cluster the wind power output eigenvalue matrix and calculate the standardized intra-cluster sum of squared errors ; （4） in, is the sum of the improved Euclidean distances between points in the k-th cluster data; n k For the k The number of cluster data; is the i-th data observation point; C k For the k Cluster data set; k =1,2,…, K ; K is the range of cluster number selection; Step 3-2: Randomly generate a total of B reference data sets and calculate the , and then obtain the reference measurement value ; （5） in, is the intra-cluster square error sum of the b-th reference data set; express expectations; ; Step 3-3: Calculation The standard deviation of , the minimum k value that satisfies the following conditions is the optimal number of clusters; （6）。 8. The floating wind turbine generator typical day division system based on improved Euclidean distance according to claim 7, characterized in that: In the cluster analysis module, the Euclidean distance measurement method is improved as follows: Step 4-1 The Euclidean distance measurement formula for wind turbine output is as follows: (1) In the formula, x , y They are the wind power output matrices on the xth and yth day of a year respectively; Step 4-2, the wind turbine output cosine similarity measurement formula is as follows: (2) Step 4-3, based on the characteristics of cosine similarity and Euclidean distance, the Euclidean distance measurement method is improved as follows: (3) In the formula, It is the maximum value of the Euclidean distance within the sampling time of one year; It is the Euclidean distance measure of wind turbine output; It is the cosine similarity measure of wind turbine output.

9. An electronic device, characterized in that: include: A processor and a memory coupled to the processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of an improved method for dividing a typical day of a floating wind turbine generator set according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of an improved method for dividing a typical day of a floating wind turbine generator set according to any one of claims 1 to 4.

Images