A wind power cluster control method, system and storage medium

Abstract

The present invention relates to the technical field of power regulation, and proposes a wind power cluster control method, system and storage medium, wherein the method comprises: obtaining power generation data and numerical weather forecast data of each wind farm in the wind power cluster; constructing a power generation probability distribution model of each wind turbine according to the power generation data and numerical weather forecast data; grouping the wind turbines deployed in each wind farm in the wind power cluster based on the similarity of the power generation characteristics of the wind turbines; allocating power to each wind turbine group according to the power generation probability distribution model, and monitoring the real-time power generation change of each wind turbine group, and when there is a wind turbine group whose real-time power generation change is greater than a preset first threshold, updating the power generation probability distribution model of all wind turbines in the corresponding wind turbine group and re-allocating power to each wind turbine group. The present invention can avoid frequent adjustment of wind turbines due to slight fluctuations in wind force, and enhance the adaptability and responsiveness of the wind power cluster to wind force changes.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power regulation and control, and more specifically, to a wind power cluster control method, system and storage medium. Background Art

[0002] For wind power generation clusters with densely deployed equipment, the utilization efficiency of wind energy is higher than that of traditional wind farms. In particular, for a collection of wind farms with the same wind characteristics and centralized access to the same grid connection point, the output changes of wind farms within the cluster are highly correlated and have a high simultaneity rate, which has unique temporal and spatial complementarity. Unified scheduling and coordinated control of such wind power clusters that are geographically adjacent, related in characteristics, and have a common access point can effectively smooth out the volatility of the output of a single wind farm, forming a power source that is similar to conventional power plants in terms of installed capacity and external regulation characteristics, and enabling it to have the ability to quickly respond to grid scheduling and control. However, due to the instability of wind power, wind farms have the problem of large power fluctuations.

[0003] Among the wind power cluster control methods currently proposed, the model predictive control technology is generally used to combine the spatial correlation of wind power and numerical weather prediction (NWP) data to achieve ultra-short-term power prediction of wind power clusters. However, this control method relies on the historical data of wind speed, wind direction and wind power as well as the accuracy of numerical weather forecast data, which is difficult to meet the real-time regulation needs of electricity. In addition, this method aims to perform ultra-short-term prediction and control. However, due to the change of wind force, the wind force may have changed when the wind turbine actually responds to the control. In the frequent control of the wind turbine, the wind turbine repeatedly changes its working state, which will affect the power stability of the wind farm and easily increase the wear of the wind turbine. Summary of the invention

[0004] In order to overcome the defect of the above-mentioned prior art that wind turbines are frequently controlled due to unstable numerical weather forecast data, thus affecting the power stability of the wind farm, the present invention provides a wind power cluster control method, system and storage medium.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] A wind power cluster control method comprises the following steps:

[0007] S1. Obtain power generation data and numerical weather forecast data of each wind farm in the wind power cluster;

[0008] S2. construct a power generation probability distribution model of each wind turbine based on power generation data and numerical weather forecast data;

[0009] S3, grouping the wind turbines deployed in each wind farm in the wind power cluster based on the similarity of the wind turbine power generation characteristics;

[0010] S4. Allocate power to each wind turbine group according to the power generation probability distribution model, and monitor the real-time power generation change of each wind turbine group. When the real-time power generation change of a wind turbine group is greater than a preset first threshold, update the power generation probability distribution model of all wind turbines in the corresponding wind turbine group and re-execute step S4.

[0011] Furthermore, the present invention also proposes a wind power cluster control system, which applies the wind power cluster control method of the present invention. The system comprises:

[0012] Data acquisition module, used to collect power generation data and numerical weather forecast data of each wind farm in the wind power cluster;

[0013] A prediction module is used to construct a probability distribution model of the power generation of each wind turbine based on power generation data and numerical weather forecast data;

[0014] A grouping module, used for grouping wind turbines deployed in each wind farm in the wind power cluster based on similarity of power generation characteristics of the wind turbines;

[0015] The control module is used to allocate power to each wind turbine group according to the power generation probability distribution model, and monitor the real-time power generation change of each wind turbine group. When the real-time power generation change of a wind turbine group is greater than a preset first threshold, the power generation probability distribution model of all wind turbines in the corresponding wind turbine group is updated and power is re-allocated to each wind turbine group.

[0016] Furthermore, the present invention also proposes a storage medium on which computer-readable instructions are stored, wherein the computer-readable instructions, when executed by a processor, implement the steps of the wind power cluster control method as described in the present invention.

[0017] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0018] The present invention constructs a power generation probability distribution model of the wind turbine to perform short-term power prediction, which can more accurately reflect the actual operation of the wind farm, thereby improving the prediction accuracy of wind power changes; the present invention also groups wind turbines based on the similarity of their power generation characteristics. When there is a situation where the wind turbines are frequently adjusted due to wind fluctuations, the power generation probability distribution model of the corresponding wind turbine group is updated and power is reallocated, thereby avoiding frequent adjustment of wind turbines due to slight wind fluctuations, thereby enhancing the adaptability and responsiveness of the wind power cluster to wind changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of the wind power cluster control method of Example 1.

[0020] Figure 2 This is an architectural diagram of a wind power cluster control system according to Example 2. DETAILED DESCRIPTION

[0021] The accompanying drawings are only used for illustrative purposes and are not to be construed as limiting the present invention;

[0022] It is understandable to those skilled in the art that some well-known descriptions may be omitted in the drawings.

[0023] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0024] Example 1

[0025] This embodiment proposes a wind power cluster control method, such as Figure 1 FIG. 1 is a flow chart of the wind power cluster control method of this embodiment.

[0026] The wind power cluster control method proposed in this embodiment includes the following steps:

[0027] S1. Obtain power generation data and numerical weather forecast data of each wind farm in the wind power cluster;

[0028] S2. construct a power generation probability distribution model of each wind turbine based on power generation data and numerical weather forecast data;

[0029] S3, grouping the wind turbines deployed in each wind farm in the wind power cluster based on the similarity of the wind turbine power generation characteristics;

[0030] S4. Allocate power to each wind turbine group according to the power generation probability distribution model, and monitor the real-time power generation change of each wind turbine group. When the real-time power generation change of a wind turbine group is greater than a preset first threshold, update the power generation probability distribution model of all wind turbines in the corresponding wind turbine group and re-execute step S4.

[0031] In this embodiment, by constructing a probability distribution model of wind turbine power generation to perform short-term power prediction, the actual operation of the wind farm can be more accurately reflected, thereby improving the prediction accuracy of wind power changes.

[0032] Furthermore, wind turbines are grouped based on the similarity of their power generation characteristics, and the real-time power generation changes of the wind farm are monitored. When the real-time power generation change of a wind turbine group is greater than a preset first threshold, it indicates that there is a fluctuation in actual power generation due to unstable actual wind speed and wind direction data. At this time, the power generation probability distribution model update strategy is triggered, and the probability distribution model of the power generation of the corresponding wind turbine group is recalculated. The corresponding wind turbine group reallocates power according to the new distribution model to avoid frequent adjustment of wind turbines due to small fluctuations in wind force, thereby enhancing the adaptability and responsiveness of the wind power cluster to wind force changes.

[0033] In an optional embodiment, in step S1, the collected power generation data includes the real-time power generation of each wind turbine, and the historical power generation; the collected numerical weather forecast data includes wind speed data and wind direction.

[0034] The collected historical power generation is the historical power generation within a certain period of time in the past.

[0035] Taking into account the dynamic characteristics of wind power changes and the real-time requirements of data collection and processing, the time period for historical power generation collection should be selected to reflect the wind power change trend but not too long to cause data obsolete.

[0036] Exemplarily, the set historical power generation collection time period is the past 30 minutes to 1 hour.

[0037] The collected numerical weather forecast data includes wind speed data and wind direction, and optionally, meteorological parameters such as temperature and air pressure. The wind speed data includes wind speed prediction value and wind speed measurement value, and the wind direction includes predicted wind direction and actual measured wind direction.

[0038] In an optional embodiment, in step S2, a power generation probability distribution model of each wind turbine is constructed based on power generation data and numerical weather forecast data, including:

[0039] For any wind turbine, the kernel density estimation method is used to perform kernel density estimation on the wind speed data to obtain the probability density function of the wind speed; its expression is:

[0040]

[0041] Where h is the bandwidth of the kernel function K(·); n is the total number of wind speed data samples; x i represents the i-th wind speed data sample;

[0042] The historical power generation is fitted with the wind speed data at the corresponding moment to obtain a power curve about the relationship between wind speed and output;

[0043] The probability density function of the wind speed and the power curve are used to estimate the probability distribution of the output under different wind speeds, and the probability distribution model of the power generation of the wind turbine is obtained by integration.

[0044] In this embodiment, the power generation probability distribution model obtained by the kernel density estimation method can more accurately reflect the actual operation of the wind farm, thereby improving the prediction accuracy of wind power changes.

[0045] Further, in an optional embodiment, the kernel function in the power generation probability distribution model is selected according to the terrain, distance and average difference in altitude of the wind farm; the steps include analyzing the terrain, distance and average difference in altitude of the current wind farm:

[0046] When the wind farm is located on flat terrain, set l = 0, otherwise set l = 1;

[0047] When the wind farm spacing is less than the preset spacing threshold, set d = 0, otherwise set d = 1;

[0048] set up Where H is the average altitude difference between wind farms, Indicates rounding down;

[0049] Then, when D+l+d>2 is satisfied, the kernel function selects the Gaussian kernel function; otherwise, the kernel function selects the Epanechnikov kernel function.

[0050] In this embodiment, the kernel function in the probability distribution model is adaptively adjusted according to the geographical location of the wind farm, so that the power generation probability distribution model can more accurately reflect the actual operation of the wind farm, thereby improving the prediction accuracy of wind power changes.

[0051] Among them, for wind farms located on non-flat land, with large distances between wind farms and / or large average interpolation of altitudes between wind farms, that is, for wind farms with relatively rugged terrain, a Gaussian kernel function with smoothness and central expansion is selected to construct a power generation probability distribution model, which can adaptively adjust the degree of attention to different samples and better fit the data; and for wind farms with flat terrain, the Epanechnikov kernel function is selected, which has a simpler calculation formula and high computational efficiency and accuracy.

[0052] Furthermore, in an optional embodiment, the bandwidth h of the kernel function K(·) in the power generation probability distribution model is set according to the change gradient of the wind speed.

[0053] Exemplarily, for each time the wind direction change rate is greater than 10° / hour, the bandwidth h is increased by 50%.

[0054] In an optional embodiment, in step S3, the power generation characteristics include historical power generation, power generation prediction value, and location, altitude and main wind direction angle of the wind turbine; the wind turbines deployed in each wind farm in the wind power cluster are grouped based on the similarity of the power generation characteristics of the wind turbines, including the following steps:

[0055] S3.1, randomly select K wind turbines from the wind farm as the initial cluster centers;

[0056] S3.2, calculate the distance between each wind turbine and K cluster centers, and assign the wind turbine to the cluster with the closest cluster center according to the distance;

[0057] S3.3. Calculate the average value of the power generation characteristics of all wind turbines in each current cluster as the new cluster center, jump to execute step S3.2 until the cluster center no longer changes or reaches the preset number of iterations, and obtain K wind turbine groups.

[0058] This embodiment uses the K-Means clustering algorithm to divide the wind turbines in the wind farm into K wind turbine groups based on the similarity of the power generation characteristics of any wind turbine. During the clustering process, the algorithm will classify similar wind turbines into the same group based on the similarity of the power generation characteristics of the wind turbines, so that the wind turbines in each group have similar power output characteristics, thereby achieving the purpose of grouping according to power output characteristics, achieving more effective use of wind power resources, and improving the control efficiency of wind power clusters.

[0059] Further optionally, when there is a wind turbine group whose real-time power generation change is greater than a preset first threshold, the wind turbines in the wind farm are regrouped.

[0060] In an optional embodiment, in step S4, the first threshold is set according to the acquired numerical weather forecast data; wherein, the step includes any of the following steps:

[0061] (1) Obtain the maximum predicted wind speed value S within a predetermined time period from the numerical weather forecast data max and the minimum predicted wind speed S min ; Based on the maximum predicted wind speed value S within the predetermined time period max and the minimum predicted wind speed S min The first threshold ΔP is set; its expression is:

[0062] ΔP=0.5ρA(S max -S min ) 3

[0063] Among them, ρ is the air density, A is the contact area between the fan blade and the wind;

[0064] (2) Obtain the maximum predicted wind speed value S within a predetermined time period from the numerical weather forecast data max and the minimum predicted wind speed S min ; According to the maximum predicted wind speed S max and the minimum predicted wind speed S min , calculate the maximum possible value P of wind turbine power generation under the upper and lower wind speed limits max and the minimum possible value P min , take the maximum possible value of wind turbine power generation P max and the minimum possible value P min The first threshold ΔP is half of the value; its expression is:

[0065] ΔP=0.5(P max -P min )

[0066]

[0067] Where k is the proportionality constant.

[0068] In this embodiment, the influence of wind speed change on the threshold value and the potential change range of wind turbine power generation are taken into consideration, and two threshold setting steps are set.

[0069] In step (1), according to the numerical weather forecast data of the wind farm area obtained from the NWP system, including meteorological parameters such as wind speed, wind direction, temperature, and air pressure, the extracted wind speed data is statistically analyzed to calculate the maximum predicted value S of the wind speed within a predetermined time period. max and the minimum predicted value S min As the upper and lower limits of the wind speed, a first threshold is further set based on a relationship between wind speed and power.

[0070] In step (2), the maximum possible value of the generated power P is selected max and the minimum possible value P min as the first threshold, wherein the maximum possible value and the minimum possible value of the generated power are the generated power at extreme wind speeds under the most ideal wind direction and the most unideal wind direction.

[0071] Further, in an optional embodiment, in step S4, the power allocation to each wind turbine group according to the power generation probability distribution model includes the following steps:

[0072] The maximum wind speed S within a predetermined time period is obtained from the numerical weather forecast data. max and the minimum predicted wind speed S min , and according to the power generation probability distribution model, the power output range of each wind turbine group under different wind speed prediction values ​​[P min , P max]; Among them, the relationship between the wind turbine's power generation power P and wind speed S and wind direction θ is expressed as:

[0073] P(S,θ)=k·S 3 ·cos(θ);

[0074] Obtaining a current wind speed prediction value and an actual wind speed measurement value according to the numerical weather forecast data for comparison, when the difference between the wind speed prediction value and the actual wind speed measurement value is less than a preset second threshold, selecting the power generation corresponding to the wind speed prediction value as the optimal power generation in combination with the power generation probability distribution model; otherwise, selecting the power generation corresponding to the actual wind speed measurement value as the optimal power generation in combination with the power generation probability distribution model;

[0075] Determine whether the currently selected optimal power generation is within the power output range [P min ,P max ], if so, the currently selected optimal power generation power is allocated to the target wind turbine, otherwise, the power generation probability distribution model of the corresponding wind turbine is updated and step S4 is re-executed.

[0076] Further optionally, the influence of wind direction change on wind turbine power is analyzed by constructing a wind direction change function f(θ), wherein θ represents the wind direction, specifically, the angle between the wind direction and the main shaft of the wind turbine.

[0077] By way of example, experiments have shown that the power generation efficiency of a wind power cluster using the wind power cluster control method proposed in this embodiment is increased by 15%, the maintenance cost of wind turbine equipment is reduced by 20%, the stability of the power grid is significantly improved, and the scheduling of wind farms is more flexible and efficient.

[0078] In this embodiment, by setting the first threshold, the system can automatically adjust the power allocation strategy according to the real-time data and short-term forecast of wind turbine power, thereby enhancing the adaptability and responsiveness of the wind power cluster to wind power changes, while reducing the frequent adjustment of wind turbines due to small fluctuations in wind power, thereby reducing operating costs and equipment wear.

[0079] Example 2

[0080] This embodiment proposes a wind power cluster control system, and applies the wind power cluster control method proposed in Embodiment 1. Figure 2 , which is an architecture diagram of the wind power cluster control system of this embodiment.

[0081] The wind power cluster control system proposed in this embodiment includes:

[0082] Data acquisition module, used to collect power generation data and numerical weather forecast data of each wind farm in the wind power cluster;

[0083] A prediction module is used to construct a probability distribution model of the power generation of each wind turbine based on the power generation data;

[0084] A grouping module, used for grouping wind turbines deployed in each wind farm in the wind power cluster based on similarity of power generation characteristics of the wind turbines;

[0085] The control module is used to allocate power to each wind turbine group according to the power generation probability distribution model, and monitor the real-time power generation change of each wind turbine group. When the real-time power generation change of a wind turbine group is greater than a preset first threshold, the power generation probability distribution model of all wind turbines in the corresponding wind turbine group is updated and power is re-allocated to each wind turbine group.

[0086] It can be understood that the system of this embodiment corresponds to the method of the above-mentioned embodiment 1, and the options in the above-mentioned embodiment 1 are also applicable to this embodiment, so they will not be described repeatedly here.

[0087] Example 3

[0088] This embodiment proposes a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the wind power cluster control method proposed in Embodiment 1.

[0089] Example 4

[0090] This embodiment provides a storage medium on which computer-readable instructions are stored, wherein the computer-readable instructions, when executed by a processor, implement the steps of the wind power cluster control method provided in Embodiment 1.

[0091] Exemplarily, the storage medium includes, but is not limited to, a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0092] Exemplarily, the instructions, programs, code sets or instruction sets may be implemented using conventional programming languages.

[0093] Exemplarily, the processor includes but is not limited to a smart phone, a personal computer, a server, a network device, etc., and is used to execute all or part of the steps of the wind power cluster control method described in Example 1.

[0094] The terms in the drawings are only used for illustrative purposes and are not to be construed as limiting the present invention;

[0095] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A wind power cluster control method, characterized in that: The following steps are involved: S1. Obtain power generation data and numerical weather forecast data of each wind farm in the wind power cluster; S2. construct a power generation probability distribution model of each wind turbine based on power generation data and numerical weather forecast data; S3, grouping the wind turbines deployed in each wind farm in the wind power cluster based on the similarity of the wind turbine power generation characteristics; S4, allocating power to each wind turbine group according to the power generation probability distribution model, and monitoring the real-time power generation change of each wind turbine group. When the real-time power generation change of a wind turbine group is greater than a preset first threshold, the power generation probability distribution model of all wind turbines in the corresponding wind turbine group is updated and step S4 is re-executed; The first threshold is set according to the acquired numerical weather forecast data; wherein, the method comprises any of the following steps: (1) Obtain the maximum predicted wind speed value S within a predetermined time period from the numerical weather forecast data max and the minimum predicted wind speed S min ; Based on the maximum predicted wind speed value S within the predetermined time period max and the minimum predicted wind speed S min The first threshold ΔP is set; its expression is: ΔP=0.5ρA(S max -S min ) 3 Among them, ρ is the air density, A is the contact area between the fan blade and the wind; (2) Obtain the maximum predicted wind speed value S within a predetermined time period from the numerical weather forecast data max and the minimum predicted wind speed S min ; According to the maximum predicted wind speed S max and the minimum predicted wind speed S min , calculate the maximum possible value P of wind turbine power generation under the upper and lower wind speed limits max and the minimum possible value P min , take the maximum possible value of wind turbine power generation P max and the minimum possible value P min The first threshold ΔP is half of the value; its expression is: ΔP=0.5(P max -P min ) Where k is the proportionality constant.

2. The wind power cluster control method according to claim 1, characterized in that: The power generation data includes the real-time power generation of each wind turbine and the historical power generation; the numerical weather forecast data includes wind speed data and wind direction.

3. The wind power cluster control method according to claim 2, characterized in that: The method of constructing a power generation probability distribution model of each wind turbine according to power generation data and numerical weather forecast data includes: For any wind turbine, the kernel density estimation method is used to perform kernel density estimation on the wind speed data to obtain the probability density function of the wind speed; its expression is: Where h is the bandwidth of the kernel function K(·); n is the total number of wind speed data samples; x i represents the i-th wind speed data sample; K(·) is the kernel function; The historical power generation is fitted with the wind speed data at the corresponding moment to obtain a power curve about the relationship between wind speed and output; The probability density function of the wind speed and the power curve are used to estimate the probability distribution of the output under different wind speeds, and the probability distribution model of the power generation of the wind turbine is obtained by integration.

4. The wind power cluster control method according to claim 3, characterized in that: The kernel function in the power generation probability distribution model is selected according to the terrain, distance and average difference in altitude of the wind farm; the steps include analyzing the terrain, distance and average difference in altitude of the current wind farm: When the wind farm is located on flat terrain, set l = 0, otherwise set l = 1; When the wind farm spacing is less than the preset spacing threshold, set d = 0, otherwise set d = 1; set up Where H is the average altitude difference between wind farms, Indicates rounding down; Then, when D+l+d>2 is satisfied, the kernel function selects the Gaussian kernel function; otherwise, the kernel function selects the Epanechnikov kernel function.

5. The wind power cluster control method according to claim 3, characterized in that: The bandwidth h of the kernel function in the power generation probability distribution model is set according to the change gradient of the wind speed.

6. The wind power cluster control method according to claim 1, characterized in that: The method of allocating power to each wind turbine group according to the power generation probability distribution model comprises the following steps: The maximum wind speed S within a predetermined time period is obtained from the numerical weather forecast data. max and the minimum predicted wind speed S min , and according to the power generation probability distribution model, the power output range of each wind turbine group under different wind speed prediction values ​​[P min ,P max ]; Among them, the relationship between the wind turbine's power generation power P and wind speed S and wind direction θ is expressed as: P(S,θ)=k·S 3 ·cos(θ); Obtaining a current wind speed prediction value and an actual wind speed measurement value according to the numerical weather forecast data for comparison, when the difference between the wind speed prediction value and the actual wind speed measurement value is less than a preset second threshold, selecting the power generation corresponding to the wind speed prediction value as the optimal power generation in combination with the power generation probability distribution model; otherwise, selecting the power generation corresponding to the actual wind speed measurement value as the optimal power generation in combination with the power generation probability distribution model; Determine whether the currently selected optimal power generation is within the power output range [P min ,P max ], if yes, the currently selected optimal power generation power is allocated to the target wind turbine, otherwise, the power generation probability distribution model of the corresponding wind turbine is updated and the power allocation is re-executed.

7. The wind power cluster control method according to any one of claims 1 to 6, characterized in that: The power generation characteristics include historical power generation, power generation prediction value, and location, altitude and main wind direction angle of the wind turbine; the wind turbines deployed in each wind farm in the wind power cluster are grouped based on the similarity of the power generation characteristics of the wind turbines, including the following steps: (1) Randomly select K wind turbines from the wind farm as the initial cluster centers; (2) Calculate the distance between each wind turbine and the K cluster centers, and assign the wind turbine to the cluster with the closest cluster center based on the distance; (3) Calculate the average value of the power generation characteristics of all wind turbines in each cluster as the new cluster center, and jump to step (2) until the cluster center no longer changes or reaches the preset number of iterations, and obtain K wind turbine groups.

8. A wind power cluster control system, applying the wind power cluster control method according to any one of claims 1 to 7, characterized in that: The system comprises: Data acquisition module, used to collect power generation data and numerical weather forecast data of each wind farm in the wind power cluster; A prediction module is used to construct a probability distribution model of the power generation of each wind turbine based on power generation data and numerical weather forecast data; A grouping module, used for grouping wind turbines deployed in each wind farm in the wind power cluster based on similarity of power generation characteristics of the wind turbines; The control module is used to allocate power to each wind turbine group according to the power generation probability distribution model, and monitor the real-time power generation change of each wind turbine group. When the real-time power generation change of a wind turbine group is greater than a preset first threshold, the power generation probability distribution model of all wind turbines in the corresponding wind turbine group is updated and power is re-allocated to each wind turbine group.

9. A storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the steps of the wind power cluster control method according to any one of claims 1 to 7 are implemented.

Images