Wind farm operation control method, device, equipment and storage medium

Abstract

The present disclosure relates to a wind farm operation control method, device, equipment and storage medium. The method includes: obtaining target wind condition time series data of the target wind farm; inputting the target wind condition time series data into a pre-trained wind farm wake control model to obtain target operating condition time series data corresponding to the target power generation of the target wind farm, the wind farm wake control model is trained based on sample wind condition time series data and sample operating condition time series data corresponding to the target power generation, the target power generation is determined based on the wind farm simulation model of the target wind farm, and the target power generation is the maximum power generation of the target wind farm under the target wind condition time series data; based on the target operating condition time series data, the operation of each wind turbine unit in the target wind farm is controlled. According to the embodiment of the present disclosure, the wind farm wake effect is reduced and the overall power generation of the wind farm is increased to meet the demand for improving the economic benefits of the wind farm.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind power generation, and in particular to a method, device, equipment and storage medium for controlling operation of a wind farm. Background Art

[0002] A wind turbine is a power generation device that converts wind energy in the air into electrical energy. After the wind turbine absorbs part of the energy in the incoming air and applies disturbance, a wake effect will be formed behind the wind rotor surface. In a larger wind farm, when the wind turbine is operating in the wake area of ​​the upstream wind turbine, the wake effect will cause uneven wind speed distribution in the wind farm, affecting the operating status and power output of each wind turbine in the wind farm, resulting in a reduction in the overall power generation of the wind farm.

[0003] In order to increase the overall power generation of a wind farm, the wind turbines in the wind farm are generally controlled to reduce the wake effect and further increase the overall power generation of the wind farm. However, the existing wind turbine method cannot control the wake effect of the wind farm well, resulting in the inability to effectively increase the overall power generation of the wind farm, and it is difficult to meet the demand for improving the economic benefits of the wind farm. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a wind farm operation control method, device, equipment and storage medium.

[0005] In a first aspect, the present disclosure provides a wind farm operation control method, the method comprising:

[0006] Obtaining target wind condition time series data of the target wind farm, wherein the target wind condition time series data is wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or wind speed data of the front incoming flow measured by using a laser radar measurement method;

[0007] Inputting the target wind condition time series data into a pre-trained wind farm wake control model to obtain target operating condition time series data corresponding to the target power generation of the target wind farm, the wind farm wake control model is trained based on sample wind condition time series data and sample operating condition time series data corresponding to the target power generation, the target power generation is determined based on a wind farm simulation model of the target wind farm, and the target power generation is the maximum power generation of the target wind farm under the target wind condition time series data;

[0008] Based on the target operating condition time series data, the operation of each wind turbine generator set in the target wind farm is controlled.

[0009] In a second aspect, the present disclosure provides a wind farm operation control device, the device comprising:

[0010] A target wind condition time series data acquisition module is used to acquire target wind condition time series data of a target wind farm, wherein the target wind condition time series data is wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or wind speed data of the front incoming flow measured by using a laser radar measurement method;

[0011] a target operating condition time series data determination module, used for inputting the target wind condition time series data into a pre-trained wind farm wake control model to obtain the target operating condition time series data corresponding to the target power generation of the target wind farm, the wind farm wake control model is trained based on sample wind condition time series data and sample operating condition time series data corresponding to the target power generation, the target power generation is determined based on a wind farm simulation model of the target wind farm, and the target power generation is the maximum power generation of the target wind farm under the target wind condition time series data;

[0012] The wind farm operation control module is used to control the operation of each wind turbine in the target wind farm based on the target operating condition time series data.

[0013] In a third aspect, the embodiments of the present disclosure further provide a wind farm operation control device, the device comprising:

[0014] one or more processors;

[0015] a storage device for storing one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the wind farm operation control method provided in the first aspect.

[0017] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the wind farm operation control method provided in the first aspect is implemented.

[0018] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0019] A wind farm operation control method, device and storage medium of an embodiment of the present disclosure can, after acquiring target wind condition time series data of a target wind farm, input the target wind condition time series data into a pre-trained wind farm wake control model to obtain target operating condition time series data corresponding to the target power generation of the target wind farm. The wind farm wake control model is trained based on sample wind condition time series data and sample operating condition time series data corresponding to the target power generation. The target wind condition time series data is wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or wind speed data for a period of time in the future measured by a laser radar measurement method. The target power generation is determined based on the wind farm simulation model of the target wind farm, and the target power generation is the maximum power generation of the target wind farm under the target wind condition time series data. Therefore, the target operating condition time series data may be the operating condition time series data that enables the target wind farm to output the maximum power generation. Further, based on the target operating condition time series data, the operation of each wind turbine in the target wind farm is controlled so that the target wind farm can output the maximum power generation. Therefore, the wake effect of the wind farm is reduced and the overall power generation of the wind farm is increased to meet the demand for improving the economic benefits of the wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0022] Figure 1 A schematic flow chart of a wind farm operation control method provided by an embodiment of the present disclosure;

[0023] Figure 2 A logic diagram for determining target operating condition time series data provided by an embodiment of the present disclosure;

[0024] Figure 3 A flow chart of another wind farm operation control method provided by an embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram of the structure of a wind farm operation control device provided by an embodiment of the present disclosure;

[0026] Figure 5 A module schematic diagram of a wind farm operation control system provided by an embodiment of the present disclosure;

[0027] Figure 6A schematic diagram of the structure of a wind farm operation control device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0029] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0030] According to statistics, in large wind farms, the overall power generation loss of the wind farm due to the wake effect is usually 10% to 20% of the annual power generation of the station. Therefore, it is necessary to control the wake of the wind farm to coordinate the distribution of the power generation of all wind turbines in the wind farm and alleviate the impact of the wake effect, so as to further improve the comprehensive economic benefits of the wind farm.

[0031] In order to increase the overall power generation of a wind farm, the operation of wind turbines in the wind farm is generally controlled to reduce the wake effect and further increase the overall power generation of the wind farm.

[0032] The current wind farm operation control method generally controls the operating conditions of each wind turbine in the wind farm at a specific wind speed and wind direction, and takes the maximum overall power of the wind farm as the output target. However, at different wind speeds and wind directions, the operating conditions of each wind turbine in the wind farm vary greatly. Therefore, this method cannot control the wake effect of the wind farm well, resulting in the inability to effectively increase the overall power generation of the wind farm, and it is difficult to meet the needs of improving the economic benefits of the wind farm.

[0033] In order to solve the above problems, the embodiments of the present disclosure provide a wind farm operation control method, device and storage medium capable of improving the overall power generation of the wind farm.

[0034] Next, first combine Figures 1 to 3 The wind farm operation control method provided by the embodiment of the present disclosure is described.

[0035] Figure 1 A schematic flow chart of a wind farm operation control method provided by an embodiment of the present disclosure is shown.

[0036] In the disclosed embodiment, Figure 1The wind farm operation control method shown can be executed by a wind farm operation control device. The wind farm operation control device can be an electronic device or a server. The electronic device can include but is not limited to fixed terminals such as smart phones, laptops, desktop computers, etc. The server can be a cloud server or a server cluster or other device with storage and computing functions.

[0037] like Figure 1 As shown, the wind farm operation control method may include the following steps.

[0038] S110. Obtain target wind condition time series data of a target wind farm.

[0039] In the disclosed embodiment, when the wake effect of a wind farm needs to be reduced, the electronic device may obtain target wind condition timing data of the target wind farm in the future period, so as to control the operation of each wind turbine in the target wind farm based on the target wind condition timing data.

[0040] In the disclosed embodiment, the target wind farm may be any large wind farm that needs to control the wake effect, wherein the target wind farm may include multiple wind turbines, each of which generates wind power according to the distribution of wind condition data in the wind farm.

[0041] In the embodiment of the present disclosure, the target wind condition time series data may be the inflow wind condition time series data of the target wind farm.

[0042] Optionally, the target wind condition time series data may be wind speed data for a period of time in the future obtained using a wind condition prediction algorithm, or wind speed data of the forward flow measured using a laser radar measurement method.

[0043] Optionally, the target wind condition time series data may include predicted wind direction time series data and predicted wind speed time series data within a target time period after the current time. That is, the predicted wind condition data includes predicted wind direction data and predicted wind speed data within a future period of time, so that the electronic device controls the operation of each wind turbine in the target wind farm based on the predicted wind direction data and predicted wind speed data within a future period of time to reduce the wake effect in the target wind farm.

[0044] S120. Input the target wind condition time series data into a pre-trained wind farm wake control model to obtain the target operating condition time series data corresponding to the target power generation of the target wind farm. The wind farm wake control model is trained based on the sample wind condition time series data and the sample operating condition time series data corresponding to the target power generation. The target power generation is determined based on a wind farm simulation model of the target wind farm. The target power generation is the maximum power generation of the target wind farm under the target wind condition time series data.

[0045] It should be noted that for each wind turbine in the target wind farm, when the wind speed and wind direction change slowly, the yaw angle, rotation speed and pitch angle of each wind turbine change slowly. Therefore, if each wind turbine is directly controlled by the target wind condition time series data with slow wind speed and wind direction changes, it is difficult to accurately track the optimal yaw angle, optimal rotation speed and optimal pitch angle at each moment, resulting in the inability to accurately control the operation of each wind turbine, making it impossible to control the yaw of the wind turbine well, resulting in the inability to reduce the wake effect of the wind farm. In addition, directly using the target wind condition time series data with slow wind speed and wind direction changes to control each wind turbine will cause each wind turbine to frequently yaw, change pitch and change speed, resulting in fatigue of the wind turbine, thereby affecting the service life of the wind turbine and causing economic losses.

[0046] In order to accurately track the optimal yaw angle, optimal rotation speed and optimal pitch angle without frequently controlling the yaw, pitch change and speed change of each wind turbine. In the disclosed embodiment, after the electronic device obtains the target wind condition time series data, the target wind condition time series data can be input into a pre-trained wind farm wake control model, so as to use the wind farm wake control model to output the target operating condition time series data corresponding to the target power generation of the target wind farm.

[0047] Specifically, the electronic device can input the target wind condition time series data into a pre-trained wind farm wake control model to obtain multiple power generation powers of the target wind farm, and use the power generation power as the target power generation power as the power generation target, so that the wind farm wake control model outputs the target operating condition time series data corresponding to the target power generation power, so as to further control the operation of the wind turbines in the target wind farm based on the target operating condition time series data, thereby improving the power generation power of the target wind farm.

[0048] Specifically, the target power generation power may be one of the sample power generation powers when training the wind farm wake control model, and the sample power generation power is the maximum power generation power under different sample wind condition time series data when training the wind farm wake control model.

[0049] In the embodiment of the present disclosure, the target operating condition time series data may be operating condition time series data for controlling each wind turbine generator set in the target wind farm.

[0050] Optionally, the target operating condition time series data includes at least one of a target yaw angle, a target rotation speed, and a target pitch angle of each wind turbine generator set within a target time period after the current time.

[0051] Figure 2 A logical schematic diagram for determining target operating condition timing data provided by an embodiment of the present disclosure is shown.

[0052] like Figure 2 As shown, the state S at time t can be tInput wind farm wake control model, based on the maximum reward R at time t t , output action A at time t, input action A into the wind farm simulation model, and obtain the maximum reward R at time t+1 t+1 . Further, the state S at time t t+1 Input the wind farm wake control model again, based on the maximum reward R at time t+1 t+1 , output action A at time t+1, and continue to loop according to the above steps until the action A at the target time is obtained. In this way, the action series at each time can be obtained. Among them, action A includes at least one of the yaw angle, speed and pitch angle at time t, and the maximum reward R t can be the target power generation at time t, state S t Includes wind speed data and wind direction data at time t.

[0053] Therefore, in the disclosed embodiment, the wind farm simulation model and the wind farm wake control model can be used to accurately determine the operating data for controlling the operation of the wind turbines, and the operating data can be collected without actually controlling the wind turbines to continuously operate, thereby improving the accuracy of the operating data and reducing the fatigue of the wind turbines, thereby ensuring the service life and economic benefits of the wind turbines. In addition, the wind farm wake control model can determine the target operating time series data for controlling the operation of each wind turbine based on the target power generation of the target wind farm, so as to control the operation of the wind turbines in the target wind farm based on the target operating time series data, and ensure that the power generation of the target wind farm is maximized.

[0054] S130: Based on the target operating condition time series data, control the operation of each wind turbine unit in the target wind farm.

[0055] In the embodiment of the present disclosure, after the electronic device determines the target operating condition time series data, it can control the operation of each wind turbine in the target wind farm based on the target operating condition time series data to control the operating state of each wind turbine.

[0056] Specifically, each wind turbine in the target wind farm can operate and generate electricity based on the yaw angle, rotation speed, and pitch angle at each moment in the corresponding target operating condition time series data, so that the target wind farm can output maximum power.

[0057] In the embodiment of the present disclosure, after the target wind condition time series data of the target wind farm is obtained, the target wind condition time series data can be input into a pre-trained wind farm wake control model to obtain the target operating condition time series data corresponding to the target power generation of the target wind farm. The wind farm wake control model is trained based on the sample wind condition time series data and the sample operating condition time series data corresponding to the target power generation. The target wind condition time series data is the wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or the wind speed data of the front incoming flow measured by a laser radar measurement method. Since the target power generation is determined based on the wind farm simulation model of the target wind farm, and the target power generation is the maximum power generation of the target wind farm under the target wind condition time series data, the target operating condition time series data may be the operating condition time series data that enables the target wind farm to output the maximum power generation. Further, based on the target operating condition time series data, the operation of each wind turbine of the target wind farm is controlled so that the target wind farm can output the maximum power generation. Therefore, the wind farm wake effect is reduced and the overall power generation of the wind farm is increased to meet the demand for improving the economic benefits of the wind farm.

[0058] In another embodiment of the present disclosure, in order to ensure that the wind farm wake control model can be used to determine the predicted operating condition time series data, the electronic device may further perform a model training step for the wind farm wake control model before executing S110.

[0059] Figure 3 A flow chart of another wind farm operation control method provided by an embodiment of the present disclosure is shown.

[0060] like Figure 3 As shown, the wind farm operation control method includes the following steps.

[0061] S310, obtaining sample wind condition time series data.

[0062] In an embodiment of the present disclosure, when it is necessary to train a wind farm wake control model, the electronic device can obtain sample wind condition time series data to use the sample wind condition time series data to train the wind farm wake control model for obtaining target operating condition time series data corresponding to the target power generation.

[0063] In the embodiment of the present disclosure, the sample wind condition time series data may be the inflow wind condition time series data of the target wind farm.

[0064] Optionally, the sample wind condition time series data may include sample wind direction time series data and sample wind speed time series data.

[0065] S320, obtaining sample operating condition time series data corresponding to the sample power generation power, where the sample power generation power is the maximum power generation power of the target wind farm under the sample wind condition time series data.

[0066] In the embodiment of the present disclosure, the sample operating condition time series data may be operating condition time series data that can enable the target wind farm to achieve maximum power generation.

[0067] Optionally, the sample operating condition timing data includes at least one of a sample yaw angle, a sample rotation speed, and a sample pitch angle.

[0068] In the embodiment of the present disclosure, optionally, S320 may specifically include the following steps:

[0069] S3201, obtaining random working condition time series data;

[0070] S3202, determining the wind condition data of the wind turbines at the hub of each wind turbine in the target wind farm based on the sample wind condition time series data;

[0071] S3203, inputting the random operating condition time series data and the wind condition data of the wind turbine generator set into the wind turbine generator set operation simulation model to obtain the random power generation of each wind turbine generator set;

[0072] S3204. Determine sample operating condition time series data based on the random power generation and sample power generation of each wind turbine generator set.

[0073] Specifically, when training the wake control model of a wind farm, the electronic device can obtain random operating condition time series data, use the sample wind condition time series data as the inflow wind condition data of the target wind farm, and determine the wind turbine wind condition data at the hub of each wind turbine in the target wind farm according to the coordinate data of each wind turbine in the target wind farm, the terrain data of the target wind farm, and the hub height of each wind turbine. Then, the wind turbine wind condition data at the hub of each wind turbine and the random operating condition time series data corresponding to each wind turbine are input into the wind turbine operation simulation model to obtain the random power generation of each wind turbine, and then the sample operating condition time series data is determined based on the random power generation of each wind turbine and the sample power generation.

[0074] Among them, the random operating condition time series data is randomly generated operating condition time series data.

[0075] The wind turbine operation simulation model may be a model for simulating control of each wind turbine in a target wind farm, so as to simulate the output of the generated power of each wind turbine.

[0076] It should be noted that the electronic device can also obtain actual operating condition time series data and actual wind condition time series data, and determine the wind condition data of the wind turbine at the hub of each wind turbine in the target wind farm based on the actual wind condition time series data, input the actual operating condition time series data and the wind turbine wind condition data into the wind turbine operation simulation model to obtain the random power generation of each wind turbine, and determine the sample wind condition time series data and the sample operating condition time series data based on the random power generation and sample power generation of each wind turbine.

[0077] In the embodiment of the present disclosure, optionally, S3204 may specifically include:

[0078] S32041. Calculate the sum of the random power generation of each wind turbine generator set;

[0079] S32042. The random operating condition time series data whose sum of power is the sample power generation power is used as the sample operating condition time series data.

[0080] Specifically, for the random power generation of each wind turbine, the electronic device may calculate the sum of the random power generation of each wind turbine, and select the sum of the powers as the sample operating condition time series data of the sample power generation.

[0081] Therefore, in the embodiment of the present disclosure, sample operating condition time series data can be selected from random operating condition time series data based on sample wind condition time series data and sample power generation power.

[0082] S330: Based on the sample wind condition time series data and the sample operating condition time series data, an initial wake control model is trained to obtain a wind farm wake control model for determining target operating condition time series data of the target wind farm.

[0083] In an embodiment of the present disclosure, after the electronic device obtains the sample wind condition time series data and the sample operating condition time series data, the sample wind condition time series data and the sample operating condition time series data can be input into the initial wake control model to iteratively train the initial wake control model until the model parameters of the initial wake control model under the current training times reach a stable state, thereby obtaining a wind farm wake control model for determining the target operating condition time series data of the target wind farm.

[0084] In the embodiment of the present disclosure, the initial wake control model may be any model that can reduce the wake effect.

[0085] Optionally, the initial wake control model may be an empirical wake model or another type of wake model.

[0086] The model parameters of the initial wake control model may include environmental parameters such as atmospheric stability Ats, turbulence intensity Tur, and wind shear value Wsh, which are not limited here.

[0087] In the embodiment of the present disclosure, when training the wind farm wake control model, the operating condition issuing cycle, action type and action permission range of the wind farm wake control model may be set.

[0088] The working condition delivery cycle refers to the working condition delivery cycle T of the sample working condition time series data.

[0089] The action type may include at least one of the yaw angle Yg, rotation speed and pitch angle in the sample operating condition time series data.

[0090] The action permission range may include the yaw angle range {Yg min ,Yg max}, speed range, pitch angle range, maximum load, maximum power generation of wind farm, maximum fatigue damage of wind turbine, safe operation parameters, etc.

[0091] In some embodiments, the electronic device can use a random action exploration method to target the maximum power generation of the sample wind farm, that is, to target the sample power generation of the target wind farm, based on taking the environmental state S as the sample wind condition time series data, taking the action A as the sample operating condition time series data, and taking the maximum reward R as the sample power generation, and taking the maximum reward R as the target, based on the sample wind condition time series data and the sample operating condition time series data, train the initial wake control model to obtain the wind farm wake control model.

[0092] In other embodiments, the electronic device can utilize deep reinforcement learning, game theory algorithms, genetic algorithms, particle swarm algorithms, ant colony algorithms, etc., with the goal of maximizing the power generation power of the target wind farm, that is, taking the sample power generation power of the target wind farm as the goal, based on taking the environmental state S as the sample wind condition time series data, taking the action A as the sample operating condition time series data, taking the maximum reward R as the sample power generation power, and taking the maximum reward R as the goal, based on the sample wind condition time series data and the sample operating condition time series data, the initial wake control model is trained to obtain the wind farm wake control model.

[0093] For the above two methods, optionally, the environment state can be expressed as follows: S = {ws zt ,wd zt ,ws ave ,ws std ,wd ave ,wd std ,Yg0}.

[0094] Optionally, action A is the yaw angle of n wind turbines, and reward R is the total power generation of n turbines in period t.

[0095] Among them, ws zt , wd zt are the wind speed set and wind direction set within the action command issuance period t, ws ave 、ws std are the mean and standard deviation of wind speed within the period t of the action command, wd ave 、wd std They are the mean and standard deviation of wind direction within the period t when the action command is issued, and Yg0 is the yaw angle of each unit at time 0.

[0096] Specifically, ws zt It can be expressed as follows: ws zt ={ws0,…,ws t};

[0097] Specifically, wd zt It can be expressed as follows: wd zt ={wd0,…,wd t};

[0098] Specifically, ws ave It can be expressed as follows: ws ave =(ws0+…+ws t )÷t;

[0099] Specifically, wd std It can be expressed as follows:

[0100] Specifically, wd ave It can be expressed as follows: wd ave =(wd0+…+wd t )÷t;

[0101] Specifically, wd std It can be expressed as follows:

[0102] Specifically, A can be expressed as follows: A = {Yg1, ..., Yg n};

[0103] Specifically, R can be expressed as follows: R = P 01 +…+P tn .

[0104] Among them, P 01 +…+P tn It is the sum of the power generation of each wind turbine in period t.

[0105] Therefore, in the embodiments of the present disclosure, the initial wake control model can be effectively trained based on the sample wind condition time series data and the sample operating condition time series data to accurately obtain a trained wind farm wake control model.

[0106] S340: Obtain target wind condition time series data of the target wind farm.

[0107] The target wind condition time series data is wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or wind speed data of the front flow measured by using a laser radar measurement method. S340 is similar to S110 and will not be described in detail here.

[0108] S350. Input the target wind condition time series data into a pre-trained wind farm wake control model to obtain the target operating condition time series data corresponding to the target power generation of the target wind farm. The wind farm wake control model is trained based on the sample wind condition time series data and the sample operating condition time series data corresponding to the target power generation. The target power generation is the maximum power generation of the target wind farm under the target wind condition time series data.

[0109] It should be noted that when training the wind farm wake control model, the action permission range is set, that is, the yaw angle range {Yg min ,Yg max}, speed range, pitch angle range, maximum load, maximum power generation of wind farm, maximum fatigue damage of wind turbine, safe operation parameters, etc. Therefore, the target operating condition timing data needs to meet the operating condition timing data of the above-mentioned action permission range.

[0110] S360: Based on the target operating condition time series data, control the operation of each wind turbine unit in the target wind farm.

[0111] Among them, S360 is similar to S130 and will not be elaborated here.

[0112] Therefore, in the embodiment of the present disclosure, the target power generation can be used as the power generation target, and the sample wind condition time series data and the sample operating condition time series data used to train the wind farm wake control model can be determined to fully train the wind farm wake control model, so that the operating condition time series data predicted by the wind farm wake control model is the operating condition data that maximizes the power generation of the target wind farm. Therefore, when the predicted operating condition time series data is used to control the operation of each wind turbine in the target wind farm, the wake effect of the target wind farm is reduced.

[0113] In yet another embodiment of the present disclosure, a wind farm simulation model may be used to obtain a sample power generation of a target wind farm under sample wind condition time series data.

[0114] In the embodiment of the present disclosure, optionally, after S3201, the method may further include the following steps:

[0115] The sample wind condition time series data and the sample operating condition time series data are input into the wind farm simulation model corresponding to the target wind farm to obtain the sample power generation.

[0116] In the embodiment of the present disclosure, optionally, inputting the sample wind condition time series data and the sample operating condition time series data into a wind farm simulation model corresponding to the target wind farm to obtain the sample power generation may specifically include the following steps:

[0117] S1. Determine the relative positional relationship between the wind turbines according to the terrain data of the target wind farm, the coordinate data of each wind turbine and the hub height of each wind turbine;

[0118] S2. Determine the power generation sequence between the wind turbines according to the sample wind condition time series data, the sample operating condition time series data and the mutual position relationship;

[0119] S3, starting with the first wind turbine in the target wind farm, input the sample wind condition time series data and the sample operating condition time series data into the operation simulation model of each wind turbine in the initial wind farm simulation model according to the power generation order, and obtain the power generation corresponding to each wind turbine, until the current wind turbine is the last wind turbine;

[0120] S4. The sum of the power generated by each wind turbine is taken as the sample power generated.

[0121] Specifically, for S1, the electronic device may establish a three-dimensional coordinate system according to the terrain data of the target wind farm, the coordinate data of each wind turbine, and the hub height of each wind turbine, and determine the relative positional relationship between each wind turbine in the target wind farm based on the coordinates of each wind turbine in the three-dimensional coordinate system;

[0122] Specifically, for S2, the electronic device can determine the power generation sequence among the wind turbines, that is, determine the sequence among the wind turbines, based on the sample wind condition time series data, the sample operating condition time series data and the mutual position relationship.

[0123] Specifically, for S3, the following steps are included:

[0124] S31. The electronic device may use the sample wind condition time series data as the wind condition data of the first wind turbine generator set, and input the sample wind condition time series data and the working condition time series data corresponding to the first wind turbine generator set in the random working condition time series data into the wind turbine generator set operation simulation model to obtain the output power and thrust coefficient of the first wind turbine generator set;

[0125] S32, the electronic device may input the sample wind condition time series data, the thrust coefficient of the first wind turbine group, and the yaw angle of the first wind turbine group into the wind farm wake control model to obtain the wind speed distribution in the target wind farm, and calculate the wind speed at the hub of the second wind turbine group according to the coordinates of each wind turbine group in the target wind farm in the three-dimensional coordinate system and the relative position relationship between each wind turbine group;

[0126] S33, the electronic device inputs the wind speed at the hub of the second wind turbine set, the operating condition time series data corresponding to the second wind turbine set in the random operating condition time series data, and the thrust coefficient of the first wind turbine set into the wind turbine set operation simulation model to obtain the output power and thrust coefficient of the second wind turbine set;

[0127] S34. The electronic device calculates the output power and thrust coefficient of the subsequent wind turbines according to the method of S31 to S33 until the current wind turbine is the last wind turbine, and obtains the corresponding power generation of each wind turbine.

[0128] Specifically, for S4, the electronic device may add up the generated powers corresponding to the wind turbines to obtain the sum of the powers, and use the sum of the powers as the sample generated power.

[0129] Therefore, in the embodiment of the present disclosure, the relative position relationship between the wind turbines can be determined based on the terrain data of the target wind farm, the coordinate data of each wind turbine, and the hub height of each wind turbine, so as to accurately determine the sample power generation capacity based on the relative position relationship, sample wind condition time series data and random operating condition time series data, and in combination with the wind farm simulation model.

[0130] Furthermore, after controlling the operation of each wind turbine in the target wind farm based on the target operating condition time series data, the actual operating power of each wind turbine in the target wind farm and the actual wind condition time series data can be used to update the wind farm wake control model, so that the wind farm wake control model is more in line with the actual operating conditions of the target wind farm.

[0131] In the embodiment of the present disclosure, optionally, after S130, the wind farm operation control method may further include:

[0132] Obtain the actual operating power and actual wind condition time series data of each wind turbine in the target wind farm;

[0133] Determine the actual operating time series data of each wind turbine generator set corresponding to the actual operating power of each wind turbine generator set;

[0134] Based on the actual working condition time series data and the actual wind condition time series data, the wind farm wake control model is updated to obtain an updated wind farm wake control model.

[0135] Specifically, when the electronic device controls the operation of each wind turbine in the target wind farm based on the target operating condition time series data, the actual operating power and actual wind condition time series data of each wind turbine in the target wind farm can be obtained, and the actual operating condition time series data of each wind turbine corresponding to the actual operating power of each wind turbine can be determined based on the wind farm simulation model. Then, the actual wind condition time series data is used as the input of the wind farm wake control model, and the actual operating condition time series data is used as the output of the wind farm wake control model, and the training wind farm wake control model is updated to obtain an updated wind farm wake control model.

[0136] Therefore, in the disclosed embodiment, the electronic device can use the actual operating power of each wind turbine in the target wind farm and the actual wind condition timing data to update the wind farm wake control model, so that the wind farm wake control model is more in line with the actual operating conditions of the target wind farm.

[0137] The embodiment of the present disclosure also provides a wind farm operation control device for implementing the above-mentioned wind farm operation control method. Figure 4 In the embodiment of the present disclosure, the wind farm operation control device may be an electronic device. The electronic device may include a mobile terminal, a tablet computer, or other device with a communication function.

[0138] Figure 4 A schematic structural diagram of a wind farm operation control device provided in an embodiment of the present disclosure is shown.

[0139] like Figure 4 As shown, the wind farm operation control device 400 may include: a target wind condition time series data acquisition module 410 , a target operating condition time series data determination module 420 and a wind farm operation control module 430 .

[0140] The target wind condition time series data acquisition module 410 can be used to acquire the target wind condition time series data of the target wind farm. The target wind condition time series data is the wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or the wind speed data of the front flow measured by using a laser radar measurement method;

[0141] The target operating condition time series data determination module 420 can be used to input the target wind condition time series data into a pre-trained wind farm wake control model to obtain the target operating condition time series data corresponding to the target power generation of the target wind farm. The wind farm wake control model is trained based on the sample wind condition time series data and the sample operating condition time series data corresponding to the target power generation. The target power generation is determined based on the wind farm simulation model of the target wind farm. The target power generation is the maximum power generation of the target wind farm under the target wind condition time series data.

[0142] The wind farm operation control module 430 can control the operation of each wind turbine in the target wind farm based on the target operating condition time series data.

[0143] In the embodiment of the present disclosure, after the target wind condition time series data of the target wind farm is obtained, the target wind condition time series data can be input into a pre-trained wind farm wake control model to obtain the target operating condition time series data corresponding to the target power generation of the target wind farm. The wind farm wake control model is trained based on the sample wind condition time series data and the sample operating condition time series data corresponding to the target power generation. The target wind condition time series data is the wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or the wind speed data of the front incoming flow measured by a laser radar measurement method. Since the target power generation is determined based on the wind farm simulation model of the target wind farm, and the target power generation is the maximum power generation of the target wind farm under the target wind condition time series data, the target operating condition time series data may be the operating condition time series data that enables the target wind farm to output the maximum power generation. Further, based on the target operating condition time series data, the operation of each wind turbine of the target wind farm is controlled so that the target wind farm can output the maximum power generation. Therefore, the wind farm wake effect is reduced and the overall power generation of the wind farm is increased to meet the demand for improving the economic benefits of the wind farm.

[0144] Optionally, the device may further include: a wind farm wake control model training module;

[0145] The wind farm wake control model training module may include: a sample wind condition time series data acquisition unit, a sample operating condition time series data acquisition unit and a wind farm wake control model training unit;

[0146] A sample wind condition time series data acquisition unit can be used to acquire sample wind condition time series data;

[0147] The sample operating condition time series data acquisition unit can be used to acquire the sample operating condition time series data corresponding to the sample power generation, where the sample power generation is the maximum power generation of the target wind farm under the sample wind condition time series data;

[0148] The wind farm wake control model training unit can be used to train the initial wake control model based on sample wind condition time series data and sample operating condition time series data to obtain a wind farm wake control model for determining target operating condition time series data of a target wind farm.

[0149] Optionally, the sample operating condition time series data acquisition unit is further used to acquire random operating condition time series data;

[0150] Based on the sample wind condition time series data, determine the wind turbine wind condition data at the hub of each wind turbine in the target wind farm;

[0151] The random working condition time series data and the wind condition data of the wind turbine are input into the wind turbine operation simulation model to obtain the random power generation of each wind turbine;

[0152] Based on the random power generation and sample power generation of each wind turbine, the sample operating condition time series data is determined.

[0153] Optionally, the sample operating condition time series data acquisition unit is further used to calculate the sum of the random power generation powers of each wind turbine generator set;

[0154] The random operating condition time series data whose sum of power is the sample power generation power is taken as the sample operating condition time series data.

[0155] Optionally, the device may further include: a sample power generation determination module;

[0156] The sample power generation determination module can be used to input sample wind condition time series data and sample operating condition time series data into a wind farm simulation model corresponding to a target wind farm to obtain sample power generation.

[0157] Optionally, the predicted power generation determination module may include: a mutual position relationship determination unit, a power generation sequence determination unit, a power generation determination unit, and a predicted power generation determination unit;

[0158] The mutual position relationship determination unit can be used to determine the mutual position relationship between each wind turbine according to the terrain data of the target wind farm, the coordinate data of each wind turbine, and the hub height of each wind turbine;

[0159] A power generation sequence determination unit can be used to determine the power generation sequence between wind turbines according to sample wind condition time series data, random operating condition time series data and mutual position relationship;

[0160] The power generation determination unit may be used to start with the first wind turbine in the target wind farm, and input the sample wind condition time series data and the random working condition time series data into the wind turbine operation simulation model in the wind farm simulation model according to the power generation order, so as to obtain the power generation corresponding to each wind turbine, until the current wind turbine is the last wind turbine;

[0161] The predicted power generation determination unit may be used to take the sum of the power generation corresponding to each wind turbine as the sample power generation.

[0162] Optionally, the device further comprises: an actual wind condition data acquisition module, an actual operating condition data acquisition module and a wind farm wake control model update module;

[0163] The actual wind condition data acquisition module can be used to obtain the actual operating power and actual wind condition time series data of each wind turbine in the target wind farm;

[0164] The actual working condition data acquisition module can be used to determine the actual working condition time series data of each wind turbine generator set corresponding to the actual operating power of each wind turbine generator set;

[0165] The wind farm wake control model updating module can be used to update the wind farm wake control model based on actual working condition time series data and actual wind condition time series data to obtain an updated wind farm wake control model.

[0166] It should be noted that Figure 4 The wind farm operation control device 400 shown can execute Figures 1 to 3 The various steps in the method embodiment shown in the figure are implemented Figures 1 to 3 The various processes and effects in the method or system embodiments shown are not described in detail here.

[0167] Figure 5 A module schematic diagram of a wind farm operation control system provided by an embodiment of the present disclosure is shown.

[0168] like Figure 5 As shown, the wind farm operation control system includes: a wind farm modeling data acquisition module 501, a wind farm state acquisition module 502, a wind farm wake control model setting module 503, a wind farm simulation model module 504, a wind farm wake control model training module 505, a target wind condition time series data acquisition module 506, a wind farm wake control model control module 507, a wind farm operation control module 508 and a data sorting and feedback module 509.

[0169] The wind farm modeling data acquisition module 501 may be used to acquire the three-dimensional coordinates of each wind turbine in the target wind farm and the wind turbine operation simulation model.

[0170] The wind farm state acquisition module 502 may be used to acquire sample operating condition time series data, sample wind condition time series data and sample power generation of the target wind farm.

[0171] The wind farm wake control model setting module 503 may be used to set model parameters of the wind farm wake control model.

[0172] Among them, the wind farm simulation model module 504 can be used to construct a wind farm simulation model using sample wind condition time series data, sample operating condition time series data, the three-dimensional coordinates of each wind turbine, the wind turbine operation simulation model and the initial wake control model in the wind farm wake control model training module 505.

[0173] The wind farm wake control model training module 505 can be used to train the wind farm wake control model by combining sample wind condition time series data and sample operating condition time series data corresponding to sample power generation.

[0174] Among them, the target wind condition time series data acquisition module 506 can be used to acquire the target wind condition time series data.

[0175] The wind farm wake control model control module 507 may be used to input the target wind condition time series data into a pre-trained wind farm wake control model to obtain the predicted operating condition time series data of the target wind farm.

[0176] The wind farm simulation model module 504 may also be used to obtain target operating condition time series data corresponding to the target power generation of the target wind farm using the predicted operating condition time series data of the target wind farm and the constructed wind farm simulation model module.

[0177] The wind farm operation control module 508 may be used to control the operation of wind turbines in the target wind farm using the target operating condition time series data.

[0178] The data sorting and feedback module 509 can be used to obtain the actual operating power and actual wind condition time series data of each wind turbine in the target wind farm, and send the actual operating power and actual wind condition time series data to the wind farm wake control model training module 505 .

[0179] The wind farm wake control model training module 505 is also used to update the wind farm wake control model based on the actual working condition time series data and the actual wind condition time series data to obtain an updated wind farm wake control model.

[0180] Figure 6 A schematic structural diagram of a wind farm operation control device provided by an embodiment of the present disclosure is shown.

[0181] like Figure 6 As shown, the wind farm operation control device may include a processor 601 and a memory 602 storing computer program instructions.

[0182] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0183] The memory 602 may include a large capacity memory for information or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 602 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 602 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 602 is a non-volatile solid-state memory. In a particular embodiment, the memory 602 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0184] The processor 601 reads and executes the computer program instructions stored in the memory 602 to perform the steps of the wind farm operation control method provided in the embodiment of the present disclosure.

[0185] In one example, the wind farm operation control device may further include a transceiver 603 and a bus 604. Figure 6 As shown, the processor 601, the memory 602 and the transceiver 603 are connected via a bus 604 and communicate with each other.

[0186] The bus 604 includes hardware, software, or both. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a Memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 604 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0187] The following is an embodiment of a computer-readable storage medium provided in an embodiment of the present disclosure. The computer-readable storage medium and the wind farm operation control method of the above-mentioned embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the computer-readable storage medium, reference can be made to the embodiment of the above-mentioned wind farm operation control method.

[0188] This embodiment provides a storage medium containing computer executable instructions. When the computer executable instructions are executed by a computer processor, they are used to execute a wind farm operation control method. The method includes:

[0189] Obtaining target wind condition time series data of the target wind farm, the target wind condition time series data is wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or wind speed data of the front incoming flow measured by using a laser radar measurement method;

[0190] Input the target wind condition time series data into a pre-trained wind farm wake control model to obtain the target operating condition time series data corresponding to the target power generation of the target wind farm. The wind farm wake control model is trained based on the sample wind condition time series data and the sample operating condition time series data corresponding to the target power generation. The target power generation is determined based on the wind farm simulation model of the target wind farm. The target power generation is the maximum power generation of the target wind farm under the target wind condition time series data.

[0191] Based on the target operating condition time series data, the operation of each wind turbine in the target wind farm is controlled.

[0192] Of course, the computer executable instructions of a storage medium including computer executable instructions provided in an embodiment of the present disclosure are not limited to the above method operations, and can also execute related operations in the wind farm operation control method provided in any embodiment of the present disclosure.

[0193] Through the above description of the implementation methods, the technical personnel in the relevant field can clearly understand that the present disclosure can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk or an optical disk, etc., including a number of instructions for a computer cloud platform (which can be a personal computer, a server, or a network cloud platform, etc.) to execute the wind farm operation control method provided by each embodiment of the present disclosure.

[0194] Note that the above are only preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art will understand that the present disclosure is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present disclosure. Therefore, although the present disclosure is described in more detail through the above embodiments, the present disclosure is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present disclosure, and the scope of the present disclosure is determined by the scope of the appended claims.

Claims

1. A wind farm operation control method, characterized in that: include: Obtaining target wind condition time series data of the target wind farm, wherein the target wind condition time series data is wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or wind speed data of the front incoming flow measured by using a laser radar measurement method; Inputting the target wind condition time series data into a pre-trained wind farm wake control model to obtain target operating condition time series data corresponding to the target power generation of the target wind farm, the wind farm wake control model is trained based on sample wind condition time series data and sample operating condition time series data corresponding to the target power generation, the target power generation is determined based on a wind farm simulation model of the target wind farm, and the target power generation is the maximum power generation of the target wind farm under the target wind condition time series data; Based on the target operating condition time series data, controlling the operation of each wind turbine unit in the target wind farm; The training method of the wind farm wake control model includes the following steps: Obtain sample wind condition time series data; Acquire sample operating condition time series data corresponding to sample power generation, where the sample power generation is the maximum power generation of the target wind farm under the sample wind condition time series data; Based on the sample wind condition time series data and the sample operating condition time series data, an initial wake control model is trained to obtain a wind farm wake control model for determining the target operating condition time series data of the target wind farm; The obtaining of sample operating condition time series data corresponding to the sample power generation includes: Obtain random working condition time series data; Based on the sample wind condition time series data, determining the wind turbine wind condition data at the hub of each wind turbine in the target wind farm; Inputting the random operating condition time series data and the wind condition data of the wind turbine generator set into a wind turbine generator set operation simulation model to obtain the random power generation of each wind turbine generator set; Determining the sample operating condition time series data based on the random power generation of each wind turbine generator set and the sample power generation; After acquiring the random operating condition time series data, the method further includes: Inputting the sample wind condition time series data and the sample operating condition time series data into a wind farm simulation model corresponding to the target wind farm to obtain sample power generation; The step of inputting the sample wind condition time series data and the sample operating condition time series data into a wind farm simulation model corresponding to the target wind farm to obtain sample power generation includes: Determining the relative positional relationship between the wind turbines according to the terrain data of the target wind farm, the coordinate data of each wind turbine, and the hub height of each wind turbine; Determining a power generation sequence between the wind turbines according to the sample wind condition time series data, the random operating condition time series data and the mutual position relationship; Starting with the first wind turbine in the target wind farm, according to the power generation order, the sample wind condition time series data and the random operating condition time series data are input into the operation simulation model of each wind turbine in the wind farm simulation model to obtain the power generation corresponding to each wind turbine, until the current wind turbine is the last wind turbine; The sum of the power generated by each wind turbine generator set is taken as the sample power generated.

2. The method according to claim 1, characterized in that The determining of the sample operating condition time series data based on the random power generation of each wind turbine generator set and the sample power generation comprises: Calculating the sum of the random power generation of each of the wind turbines; The sum of the powers is the random operating condition time series data of the sample power generation power, which is used as the sample operating condition time series data.

3. The method according to claim 1, characterized in that After controlling the operation of each wind turbine generator set of the target wind farm based on the target operating condition time series data, the method further includes: Acquire the actual operating power and actual wind condition time series data of each wind turbine in the target wind farm; Determine the actual operating condition time series data of each wind turbine generator set corresponding to the actual operating power of each wind turbine generator set; Based on the actual working condition time series data and the actual wind condition time series data, the wind farm wake control model is updated to obtain an updated wind farm wake control model.

4. A wind farm operation control device, characterized in that: include: A target wind condition time series data acquisition module is used to acquire target wind condition time series data of a target wind farm, wherein the target wind condition time series data is wind speed data for a period of time in the future obtained by using a wind condition prediction algorithm, or wind speed data of the front incoming flow measured by using a laser radar measurement method; a target operating condition time series data determination module, used for inputting the target wind condition time series data into a pre-trained wind farm wake control model to obtain the target operating condition time series data corresponding to the target power generation of the target wind farm, the wind farm wake control model is trained based on sample wind condition time series data and sample operating condition time series data corresponding to the target power generation, the target power generation is determined based on a wind farm simulation model of the target wind farm, and the target power generation is the maximum power generation of the target wind farm under the target wind condition time series data; A wind farm operation control module, used to control the operation of each wind turbine in the target wind farm based on the target operating condition time series data; The device also includes: a wind farm wake control model training module; The wind farm wake control model training module includes: a sample wind condition time series data acquisition unit, a sample operating condition time series data acquisition unit and a wind farm wake control model training unit; A sample wind condition time series data acquisition unit, used to acquire sample wind condition time series data; A sample operating condition time series data acquisition unit is used to acquire sample operating condition time series data corresponding to the sample power generation, where the sample power generation is the maximum power generation of the target wind farm under the sample wind condition time series data; A wind farm wake control model training unit, used for training an initial wake control model based on sample wind condition time series data and sample operating condition time series data, so as to obtain a wind farm wake control model for determining target operating condition time series data of a target wind farm; The sample working condition time series data acquisition unit is also used to acquire random working condition time series data; Based on the sample wind condition time series data, determine the wind turbine wind condition data at the hub of each wind turbine in the target wind farm; The random working condition time series data and the wind condition data of the wind turbine are input into the wind turbine operation simulation model to obtain the random power generation of each wind turbine; Based on the random power generation and sample power generation of each wind turbine, determine the sample operating condition time series data; The device further comprises: a sample power generation determination module; A sample power generation determination module is used to input the sample wind condition time series data and the sample operating condition time series data into a wind farm simulation model corresponding to the target wind farm to obtain the sample power generation; A predicted power generation determination module, comprising: a mutual position relationship determination unit, a power generation sequence determination unit, a power generation determination unit and a predicted power generation determination unit; A mutual position relationship determination unit, used to determine the mutual position relationship between each wind turbine according to the terrain data of the target wind farm, the coordinate data of each wind turbine, and the hub height of each wind turbine; A power generation sequence determination unit, used to determine the power generation sequence between wind turbines according to sample wind condition time series data, random operating condition time series data and mutual position relationship; The power generation determination unit is used to input the sample wind condition time series data and the random working condition time series data into each wind turbine in the wind farm simulation model to run the simulation model according to the power generation order, starting from the first wind turbine in the target wind farm, to obtain the power generation corresponding to each wind turbine until the current wind turbine is the last wind turbine; The predicted power generation determination unit is used to take the sum of the power generation corresponding to each wind turbine as the sample power generation.

5. A wind farm operation control device, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the wind farm operation control method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the wind farm operation control method according to any one of claims 1 to 3.

Images