Standard test field generation method and device for wind farm power controller

Abstract

The present invention provides a method and device for generating a standard test field of a power controller for a wind farm site, which relates to the technical field of simulation testing. The method includes: establishing a Markov state transition model of the wind speed of the wind farm based on historical wind speed data; generating wind farm operation condition samples according to the Markov state transition model; running the K-means++ clustering algorithm based on the wind farm operation condition samples to obtain k typical operation conditions; obtaining the extreme operation conditions corresponding to each of the typical operation conditions; and using the set of the typical operation conditions and the extreme operation conditions as the standard test field of the power controller for the wind farm site. In the present invention, the Markov state transition model established using historical wind speed data describes the state transition process of the wind speed at different times, and a large number of condition samples are generated from this model, thereby solving the problem of insufficient historical data required by the clustering algorithm.

Description

Technical Field

[0001] The present invention relates to the field of simulation test technology, and in particular to a method and device for generating a standard test field for a wind farm station power controller. Background Art

[0002] At present, the cumulative grid-connected capacity of wind power has been increasing. Limited by the uncertainty and volatility of wind resources, the operating characteristics of wind farms are significantly different from conventional energy. With the continuous increase in the scale of wind power grid connection, higher requirements are placed on the power control performance of wind farms to ensure the normal operation of the power grid. However, the wind farm power control system developed from the power control system of conventional energy power stations is often only theoretically verified, and the control effect in the actual power grid still needs to be tested, especially to verify whether its control strategy can adapt to wind power conditions with significantly increased uncertainty and volatility.

[0003] At the same time, limited by the safe operation of the power grid and the constraints of actual wind resources, on-site measurements cannot cover all operating conditions of the wind farm, especially extreme scenarios that pose a great threat to the operation of the power grid. Therefore, it is necessary to use the operating conditions that may be encountered in the actual operation of the wind farm as input to carry out hardware-in-the-loop simulation performance testing for the power control system of the wind farm. Due to the complex and changeable characteristics of wind resources, simple large, medium and small output test conditions are difficult to fully cover the possible states in the actual operation of the wind farm, resulting in incomplete test results and difficulty in judging the adaptability of the power control strategy. Therefore, it is necessary to reduce the massive actual operating conditions to representative conditions required for testing. Conventional wind farm operation scenario reduction methods are mostly aimed at power grid planning and scheduling optimization problems, and standard test field generation methods for wind farm power controllers are still rare. Summary of the invention

[0004] In view of this, the present invention provides a method and device for generating a standard test field for a wind farm station power controller to solve at least one of the above-mentioned problems.

[0005] In order to achieve the above object, the present invention adopts the following scheme:

[0006] According to a first aspect of the present invention, an embodiment of the present invention provides a method for generating a standard test field for a wind farm power controller, the method comprising: establishing a Markov state transition model of wind farm wind speed based on historical wind speed data; generating wind farm operating condition samples according to the Markov state transition model; running a K-means++ clustering algorithm based on the wind farm operating condition samples to obtain k typical operating conditions; obtaining the extreme operating conditions corresponding to each of the typical operating conditions; and using the set of the typical operating conditions and the extreme operating conditions as a standard test field for a wind farm power controller.

[0007] Preferably, the Markov state transition model of the wind farm wind speed established based on the historical wind speed data in the above steps of this embodiment includes: determining the time interval and time length of the operating conditions in the standard test site according to the test requirements; using the historical wind speed data as a sample, and statistically analyzing the probability of wind speed transfer to the next time interval at different wind speeds through the wind speed state transition probability matrix.

[0008] Preferably, generating a wind farm operating condition sample according to the Markov state transition model in the above steps of this embodiment includes: performing parameter fitting on the historical wind speed data at the starting moment of the operating condition within the time length to obtain a Weibull probability distribution model; generating a number of starting moment wind speed state samples according to the Weibull probability distribution model; and generating the wind speed moment by moment according to the time interval from the wind speed state transition probability matrix, and finally forming a wind speed sequence to obtain a wind farm operating condition sample.

[0009] Preferably, obtaining k typical operating conditions by running the K-means++ clustering algorithm based on the wind farm operating condition sample in the above steps of this embodiment includes: running the K-means++ clustering algorithm based on the wind farm operating condition sample to obtain k typical operating conditions, where the value of k is determined by the elbow method.

[0010] Preferably, the extreme operating conditions in the above steps of this embodiment include: the operating condition with the largest deviation from the typical operating condition and the operating condition with the largest wind speed fluctuation.

[0011] According to the first aspect of the present invention, an apparatus for generating a standard test site of a wind farm station power controller is provided in an embodiment of the present invention. The apparatus includes: a model establishment unit for establishing a Markov state transition model of the wind farm wind speed based on historical wind speed data; an operating condition sample generation unit for generating a wind farm operating condition sample according to the Markov state transition model; a typical operating condition acquisition unit for obtaining k typical operating conditions by running the K-means++ clustering algorithm based on the wind farm operating condition sample; an extreme operating condition acquisition unit for obtaining the extreme operating conditions corresponding to each of the typical operating conditions; and a standard test site generation unit for using the set of the typical operating conditions and the extreme operating conditions as the standard test site of the wind farm station power controller.

[0012] Preferably, the model establishment unit in the above apparatus of this embodiment includes: a time period determination module for determining the time interval and time length of the operating conditions in the standard test site according to the test requirements; and a probability statistics module for using the historical wind speed data as a sample and statistically analyzing the probability of wind speed transfer to the next time interval at different wind speeds through the wind speed state transition probability matrix.

[0013] Preferably, in the above device of this embodiment, the operating condition sample generation unit includes: a probability distribution acquisition module, configured to perform parameter fitting on historical wind speed data at the starting moment of the operating condition within the time length to obtain a Weibull probability distribution model; a starting wind speed sample acquisition module, configured to generate a plurality of wind speed state samples at the starting moment according to the Weibull probability distribution model; and an operating condition generation module, configured to generate wind speeds moment by moment according to the time interval from the wind speed state transition probability matrix, and finally form a wind speed sequence to obtain a wind farm operating condition sample.

[0014] Preferably, the typical operating condition acquisition unit in the above device of this embodiment is specifically configured to: perform the K-means++ clustering algorithm based on the wind farm operating condition samples to obtain k typical operating conditions, where the value of k is determined by the elbow method.

[0015] Preferably, the extreme operating conditions in the above device of this embodiment include: the operating condition with the largest deviation from the typical operating condition and the operating condition with the largest sub-speed fluctuation.

[0016] According to the third aspect of the present invention, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0017] According to the fourth aspect of the present invention, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0018] According to the fifth aspect of the present invention, an embodiment of the present invention further provides a computer program product, including a computer program / instructions. When the computer program / instructions are executed by a processor, the steps of the above method are implemented.

[0019] The method and device for generating a standard test field of a wind farm power controller proposed by the present invention use a Markov state transition model established based on historical wind speed data to describe the state transition process of wind speed between different moments, and generate a large number of operating condition samples from this model, thus solving the problem of insufficient historical data required for the clustering algorithm. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0021] Figure 1 It is a schematic flow chart of a method for generating a standard test field of a wind farm power controller provided by an embodiment of the present application;

[0022] Figure 2 It is a schematic flow chart of a process for establishing a Markov state transition model of wind speed in a wind farm provided by another embodiment of the present application;

[0023] Figure 3 It is a schematic flow chart of a process for generating a wind farm operation condition sample provided by an embodiment of the present application;

[0024] Figure 4 It is a schematic structural diagram of a device for generating a standard test field of a wind farm power controller provided by an embodiment of the present application;

[0025] Figure 5 It is a schematic structural diagram of a model establishment unit provided by an embodiment of the present application;

[0026] Figure 6 It is a schematic structural diagram of a working condition sample generation unit provided by an embodiment of the present application;

[0027] Figure 7 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer and more understandable, the following further describes the embodiments of the present invention in detail with reference to the accompanying drawings. Herein, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but not to limit the present invention.

[0029] As Figure 1 shown is a schematic flow chart of a method for generating a standard test field of a wind farm power controller provided by an embodiment of the present application. The present application uses a clustering algorithm to generate operation conditions. However, since the amount of historical data required for the clustering algorithm is huge and the existing data is very likely to not meet the requirements, the present application also uses a Markov state transition model. Specifically, the method of the present application includes the following steps:

[0030] Step S101: Establish a Markov state transition model of wind speed in a wind farm based on historical wind speed data.

[0031] Here, the Markov state transition model is briefly described first. According to the Markov state transition theory, if the system state at the current moment is known, the state at the next moment can be predicted from the current state. The transitions between different states can be described by a state probability matrix. Therefore, the process of the wind speed state at a certain moment in the wind farm transferring to the wind speed state at the next moment can be regarded as a Markov state transition process. The entire transfer process from the wind speed state at the start time to the wind speed state at the end time within the entire time period is the Markov state transition model established in the embodiment of this method from the wind speed at the start time to the wind speed at the end time.

[0032] Preferably, as Figure 2 shown, this step may specifically include the following sub-steps:

[0033] Step S1011: Determine the time interval and time length of the operating conditions in the standard test field according to the test requirements. Here, the time interval refers to how much time it takes for the wind speed state to transfer to the wind speed state at the next moment, and the time length refers to how long the operating conditions of the standard test field need to be obtained in this application. In this embodiment, the time interval can be, for example, 5 minutes, 15 minutes, etc., and the time length can be, for example, 4 hours, 24 hours, etc., which can be freely set according to needs.

[0034] In addition, since the characteristics of wind resources are significantly different in different seasons, the historical data can be grouped as follows, such as: the four seasons of spring, summer, autumn, and winter, or dry and rainy seasons, etc. Then, the standard test fields corresponding to different seasons are obtained respectively through the method of this application.

[0035] Step S1012: Using the historical wind speed data as a sample, statistically calculate the probability of different wind speeds transferring to the wind speed after the next time interval through the wind speed state transition probability matrix.

[0036] If the historical data is grouped by season in the above steps, then using the historical wind speed data of the current calculation season as a sample, statistically calculate the probability of different wind speeds transferring to the wind speed after the next time interval, and denote the probability that the wind speed state i transfers to the wind speed state j after the next time interval as p ij ij, then the wind speed state transition probability matrix P v2v , as shown in formula (1):

[0037]

[0038] Step S102: Generate a sample of the wind farm operating conditions according to the Markov state transition model.

[0039] Preferably, as Figure 3 shown, this step may include the following sub-steps:

[0040] Step S1021: Perform parameter fitting on the historical wind speed data at the starting moment of the working condition within the time length to obtain a Weibull probability distribution model.

[0041] The wind speed distribution in a certain time period can be described by a two-parameter Weibull distribution, and its probability density function and cumulative distribution function are shown in formulas (2) and (3) respectively:

[0042]

[0043]

[0044] Where k is the shape parameter, which determines the curve shape and is dimensionless; c is the scale parameter, which determines the curve size ratio and has the same dimension as the wind speed; v represents the wind speed.

[0045] Step S1022: Generate several wind speed state samples at the starting moment according to the Weibull probability distribution model.

[0046] Step S1023: From the wind speed state transition probability matrix, generate the wind speed moment by moment according to the time interval, and finally form a wind speed sequence to obtain a wind farm operation condition sample. In this way, a large number of wind speed condition samples that retain the wind speed characteristics of the wind farm can be conveniently generated, solving the problem of insufficient historical data samples and facilitating the subsequent clustering algorithm.

[0047] Under normal circumstances, the performance detection of the wind farm power controller only requires a wind speed condition curve. The method proposed in the present invention can directly generate wind speed or wind power according to needs. If it is necessary to generate a wind power curve, the state transition process from the wind speed at this moment to the wind power is added to form a wind speed-wind power state transition matrix P as shown in formula (4) v2p :

[0048]

[0049] Step S103: Run the K-means++ clustering algorithm based on the wind farm operation condition samples to obtain k typical operation conditions.

[0050] The K-means clustering method is an effective classification method for unsupervised learning. Its basic principle is to find a partitioning scheme of k types through iteration, so that the loss function corresponding to the clustering result is minimized. Among them, the loss function can be defined as the sum of the squared errors of each sample from the center of the type it belongs to, as shown in formula (5):

[0051]

[0052] Where: x i is the i-th sample, μ i is x iThe center of the corresponding type, which is the typical operating condition of the i-th type in this embodiment, and M is the total number of samples. The selection of the clustering center for the K-means clustering algorithm greatly affects the computational complexity of each iteration. The K-means++ algorithm optimizes the selection of the initial clustering center. A sample is randomly selected as the first center point, and the distance between each sample in the dataset and the initialized clustering centers is calculated, and the shortest distance is selected; a sample with the largest distance is selected as the new clustering center with a certain probability, and the above process is repeated until k clustering centers are determined.

[0053] To achieve the best clustering effect, it is necessary to reasonably determine the value of k. In this embodiment, the elbow method can be used to determine the value of k. SSE represents the clustering effect and gradually decreases as the value of k increases. When the value of k reaches the optimal number, the SSE decreases slowly. The elbow method is to select that inflection point, and the SSE calculation method is as shown in formula (6):

[0054]

[0055] where: C j is the set composed of samples of the j-th class. By clustering the wind farm operating condition samples generated by the Markov model through the above method, k typical operating conditions are obtained, that is, k typical wind speed condition curves.

[0056] Step S104: Obtain the extreme operating conditions corresponding to each of the typical operating conditions.

[0057] The extreme operating condition refers to a condition with a relatively small occurrence probability but a relatively large impact on the operation of the wind farm. For the wind farm power control system, when the wind speed is extremely large, extremely small, or changes rapidly, the operation of the wind turbines is restricted more, which greatly tests the adaptability of its control strategy. Therefore, in the method proposed by the present invention, the conditions with the largest deviation from the typical conditions and the largest wind speed fluctuations in the set of k typical operating conditions obtained by clustering are selected as the extreme conditions in each set of typical operating conditions. The expressions of the conditions with the largest deviation from the typical conditions in the j-th set of typical operating conditions are shown in formulas (7) and (8):

[0058]

[0059]

[0060] where: represents the positive extreme condition, and each element x i,m is greater than the corresponding element μ of the typical condition j,m ; Ext j - represents the negative extreme condition, and each x i,m is less than the corresponding element μ of the typical conditionj,m 。

[0061] The extreme operating condition with the largest fluctuation The expression is as shown in Equation (9):

[0062]

[0063] Through the above formulas (7), (8) and (9), 3 extreme operating conditions can be obtained corresponding to each typical operating condition. Therefore, finally, k typical operating conditions and 3k corresponding extreme operating conditions can be generated, which cover all the operating conditions in the current season. Repeating the above process for other seasons to be considered can generate the corresponding typical operating conditions and extreme operating condition sets.

[0064] Step S105: Use the set of the typical operating conditions and the extreme operating conditions as the standard test field for the wind farm power controller.

[0065] The method for generating the standard test field of the wind farm power controller proposed by the present invention uses the Markov state transition model established based on historical wind speed data to describe the state transition process of the wind speed at different times, and generates a large number of operating condition samples from this model, thus solving the problem of insufficient historical data required by the clustering algorithm. In addition, this application adds an extreme scenario model on the basis of K-means++ clustering analysis, and generates positive and negative extreme operating conditions and extreme fluctuation operating conditions with the largest deviation from the typical operating conditions for each type of operating condition respectively. These extreme scenarios can effectively describe the extreme operating states that may be encountered in the actual operation of the wind farm, thus making the performance test of the wind farm power controller more efficient and comprehensive.

[0066] As Figure 4 shown is the structural schematic diagram of a device for generating a standard test field of a wind farm power controller provided by an embodiment of the present application. The device includes: a model establishment unit 410, an operating condition sample generation unit 420, a typical operating condition acquisition unit 430, an extreme operating condition acquisition unit 440, and a standard test field generation unit 450, which are connected in sequence.

[0067] The model establishment unit 410 is used to establish a Markov state transition model of the wind farm wind speed based on historical wind speed data.

[0068] The operating condition sample generation unit 420 is used to generate wind farm operating condition samples according to the Markov state transition model.

[0069] The typical operating condition acquisition unit 430 is used to obtain k typical operating conditions by running the K-means++ clustering algorithm based on the wind farm operating condition samples.

[0070] The extreme operating condition acquisition unit 440 is used to acquire the extreme operating conditions corresponding to each of the typical operating conditions;

[0071] The standard test field generation unit 450 is used to use the set of the typical operating conditions and the extreme operating conditions as the standard test field for the wind farm power controller.

[0072] Preferably, as Figure 5 shown, the model establishment unit 410 may specifically include a time period determination module 411 and a probability statistics module 412.

[0073] The time period determination module 411 is used to determine the time interval and time length of the operating conditions in the standard test field according to the test requirements.

[0074] The probability statistics module 412 is used to use the historical wind speed data as a sample and statistically calculate the probability of wind speed transfer in the next time interval at different wind speeds through the wind speed state transition probability matrix.

[0075] Preferably, as Figure 6 shown, the above-mentioned operating condition sample generation unit 420 may specifically include: a probability distribution acquisition module 421, a starting wind speed sample acquisition module 422, and an operating condition generation module 423, where:

[0076] The probability distribution acquisition module 421 is used to perform parameter fitting on the historical wind speed data at the starting moment of the operating condition within the time length to obtain a Weibull probability distribution model.

[0077] The starting wind speed sample acquisition module 422 is used to generate a number of starting moment wind speed state samples according to the Weibull probability distribution model.

[0078] The operating condition generation module 423 is used to generate wind speeds moment by moment according to the time interval from the wind speed state transition probability matrix, and finally form a wind speed sequence to obtain a wind farm operating condition sample.

[0079] Preferably, the above-mentioned typical condition acquisition unit 430 may specifically be used to: obtain k typical operating conditions by running the K-means++ clustering algorithm based on the wind farm operating condition samples, where the k value is determined by the elbow method.

[0080] Preferably, the above-mentioned extreme operating conditions include: the condition with the largest deviation from the typical operating condition and the condition with the largest wind speed fluctuation.

[0081] For the detailed descriptions of the above units, reference may be made to the descriptions of the corresponding method embodiments above, and details will not be repeated here.

[0082] As described above, the standard test field generation device for the wind farm power controller proposed by the present invention uses the Markov state transition model established based on historical wind speed data to describe the state transition process of wind speed at different times, and generates a large number of working condition samples from this model, thus solving the problem of insufficient historical data required by the clustering algorithm. In addition, this application adds an extreme scenario model on the basis of K-means++ clustering analysis, and respectively generates positive and negative extreme operating conditions and extreme fluctuation operating conditions with the largest deviation from the typical operating conditions for each type of working condition. These extreme scenarios can effectively describe the extreme operating states that may be encountered in the actual operation of the wind farm, thereby making the performance test of the wind farm power controller more efficient and comprehensive.

[0083] Figure 7 It is a schematic diagram of the electronic device provided by the embodiment of the present invention. Figure 7 The shown electronic device is a general data processing device, which includes a general computer hardware structure, and at least includes a processor 801 and a memory 802. The processor 801 and the memory 802 are connected through a bus 803. The memory 802 is suitable for storing one or more instructions or programs executable by the processor 801. These one or more instructions or programs are executed by the processor 801 to implement the steps in the above-mentioned standard test field generation method for the wind farm power controller.

[0084] The above-mentioned processor 801 can be an independent microprocessor, or a set of one or more microprocessors. Thus, the processor 801 executes the commands stored in the memory 802, thereby implementing the method flow of the embodiment of the present invention as described above to process data and control other devices. The bus 803 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 804, the display device, and the input / output (I / O) device 805. The input / output (I / O) device 805 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices well known in the art. Typically, the input / output (I / O) device 805 is connected to the system through an input / output (I / O) controller 806.

[0085] Among them, the memory 802 can store software components, such as an operating system, a communication module, an interaction module, and an application program. Each of the above-mentioned modules and application programs corresponds to a set of executable program instructions for completing one or more functions and the methods described in the embodiments of the invention.

[0086] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the above-mentioned standard test field generation method for the wind farm power controller.

[0087] An embodiment of the present invention also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method for generating a standard test field of the wind farm power controller as described above.

[0088] In summary, for the method and device for generating a standard test field of the wind farm power controller proposed by the present invention, a Markov state transition model established using historical wind speed data is used to describe the state transition process of the wind speed at different times, and a large number of working condition samples are generated from this model, thus solving the problem of insufficient historical data required by the clustering algorithm. In addition, in this application, an extreme scenario model is added on the basis of K-means++ clustering analysis, and positive and negative extreme operating conditions and extreme fluctuation operating conditions with the largest deviation from the typical operating conditions are respectively generated for each type of working condition. These extreme scenarios can effectively describe the extreme operating states that may be encountered in the actual operation of the wind farm, thereby making the performance test of the wind farm power controller more efficient and comprehensive.

[0089] The preferred embodiments of the present invention have been described above with reference to the accompanying drawings. Many features and advantages of these embodiments are clear from this detailed description, so the claims are intended to cover all these features and advantages that fall within the true spirit and scope of these embodiments. In addition, since those skilled in the art can easily think of many modifications and changes, the embodiments of the present invention are not limited to the exact structures and operations illustrated and described, but may cover all suitable modifications and equivalents that fall within its scope.

[0090] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.) that contain computer-usable program code.

[0091] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, 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 for implementing in the process Figure 1 one process or multiple processes and / or blocks Figure 1a device for the functions specified in one or more boxes

[0092] 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 produce a manufactured article including an instruction device, and the instruction device implements the process Figure 1 one process or more processes and / or boxes Figure 1 the functions specified in one box or more boxes.

[0093] 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 more processes and / or boxes Figure 1 the functions specified in one box or more boxes.

[0094] In the specific embodiments described above, the purpose, technical solution, and beneficial effects of the present invention have been further described in detail. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating a standard test field for a power controller of a wind farm site, characterized in that The method includes: Establishing a Markov state transition model of the wind farm wind speed based on historical wind speed data; Generating wind farm operation condition samples according to the Markov state transition model; Running the K-means++ clustering algorithm based on the wind farm operation condition samples to obtain k typical operation conditions; Obtaining the extreme operation conditions corresponding to each of the typical operation conditions; Taking the set of the typical operation conditions and the extreme operation conditions as the standard test field of the wind farm power controller; The establishing the Markov state transition model of the wind farm wind speed based on historical wind speed data includes: Determining the time interval and time length of the operation conditions in the standard test field according to the test requirements; Using the historical wind speed data as a sample, and statistically calculating the probability of wind speed transfer to the next time interval under different wind speeds through the wind speed state transition probability matrix; The generating wind farm operation condition samples according to the Markov state transition model includes: Performing parameter fitting on the historical wind speed data at the starting moment of the working condition within the time length to obtain a Weibull probability distribution model; Generating a number of starting moment wind speed state samples according to the Weibull probability distribution model; From the wind speed state transition probability matrix, generating the wind speed moment by moment according to the time interval, and finally forming a wind speed sequence to obtain the wind farm operation condition samples.

2. The method for generating a standard test field of a wind farm power controller according to claim 1, wherein, The running the K-means++ clustering algorithm based on the wind farm operation condition samples to obtain k typical operation conditions includes: Running the K-means++ clustering algorithm based on the wind farm operation condition samples to obtain k typical operation conditions, where the value of k is determined by the elbow method.

3. The standard test field generation method for the wind farm power controller according to claim 1, characterized in that The extreme operation conditions include: the condition with the largest deviation from the typical operation condition and the condition with the largest wind speed fluctuation.

4. A standard test field generating device for a power controller of a wind farm site, characterized in that The device includes: A model establishment unit for establishing a Markov state transition model of the wind farm wind speed based on historical wind speed data; An operation condition sample generation unit for generating wind farm operation condition samples according to the Markov state transition model; A typical condition acquisition unit for running the K-means++ clustering algorithm based on the wind farm operation condition samples to obtain k typical operation conditions; An extreme condition acquisition unit for obtaining the extreme operation conditions corresponding to each of the typical operation conditions; A standard test field generation unit for taking the set of the typical operation conditions and the extreme operation conditions as the standard test field of the wind farm power controller; The model establishment unit includes: A time period determination module for determining the time interval and time length of the operation conditions in the standard test field according to the test requirements; A probability statistics module for using the historical wind speed data as a sample and statistically calculating the probability of wind speed transfer to the next time interval under different wind speeds through the wind speed state transition probability matrix; The operation condition sample generation unit includes: A probability distribution acquisition module for performing parameter fitting on the historical wind speed data at the starting moment of the working condition within the time length to obtain a Weibull probability distribution model; A starting wind speed sample acquisition module for generating a number of starting moment wind speed state samples according to the Weibull probability distribution model; An operating condition generation module, configured to generate wind speeds moment by moment according to the time interval based on the wind speed state transition probability matrix, and finally form a wind speed sequence to obtain a wind farm operating condition sample.

5. The standard test field generating device of the wind farm power controller according to claim 4, characterized in that, The specific method for the typical condition acquisition unit is as follows: based on the wind farm operating condition sample, the K-means++ clustering algorithm is run to obtain k typical operating conditions, where the value of k is determined by the elbow method.

6. The standard test field generating device of the wind farm power controller according to claim 4, characterized in that The extreme operating conditions include: the condition with the largest deviation from the typical operating condition and the condition with the largest speed fluctuation.

7. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

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

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images