Wind farm group cooperative yaw optimization control method and system

Abstract

The application discloses a wind farm group coordinated yaw optimization control method and system, relates to the wind turbine control technical field, and comprises the following steps: acquiring the wind speed, wind direction, turbulence intensity and wind turbine power of a wind farm group; inputting the wind speed, wind direction, turbulence intensity and wind turbine power of each wind turbine into a target wake model; outputting a simulated wake propagation influence relationship in the wind farm; determining a target yaw offset angle of each wind turbine based on the wake propagation influence relationship and the positions of the wind turbines in the wind farm group at a preset period; and adjusting the yaw angle of each wind turbine in the wind farm group according to the target yaw offset angle. In the foregoing manner, the adverse effects of the wake of an upstream wind turbine on a downstream wind turbine can be effectively weakened, and the overall power generation efficiency of the entire wind farm group is improved.

Description

Technical Field

[0001] This application relates to the field of wind turbine control technology, and in particular to a method and system for coordinated yaw optimization control of wind farm groups. Background Technology

[0002] In large wind farms, the wake generated by upstream turbines significantly reduces the inflow velocity of downstream turbines and increases turbulence intensity, resulting in a loss of total power generation across the entire farm. Traditional independent turbine control modes cannot resolve the impact of upstream turbines on the power generation efficiency of downstream turbines.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a collaborative yaw optimization control method and system for wind farm groups, which aims to solve the technical problem in the prior art where the wake of upstream wind turbines affects the power generation efficiency of downstream wind turbines.

[0005] To achieve the above objectives, this application provides a collaborative yaw optimization control method for wind farm groups, the method comprising:

[0006] Obtain wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine in the wind farm cluster;

[0007] The wind speed, wind direction, turbulence intensity, and wind turbine power of each wind turbine are input into the target wake model, and the simulated wake propagation influence relationship within the wind farm is output. The wake model is obtained by calibrating the initial wake model, which is used to determine the wake propagation influence relationship between wind turbines.

[0008] Based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group, the target yaw offset angle of each wind turbine is determined at a preset period.

[0009] The yaw angle of each wind turbine in the wind farm group is adjusted according to the target yaw offset angle.

[0010] In one embodiment, before the step of inputting the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine into the target wake model and outputting the simulated wake propagation influence relationship within the wind farm, the method further includes:

[0011] The geographical layout of the wind farm group and the physical parameters of each wind turbine are obtained, including the turbine height, rotor diameter and hub height.

[0012] An initial wake model is established based on the geographical layout and the wind turbine height, rotor diameter, and hub height.

[0013] The initial wake model is calibrated based on historical wind speed, historical wind direction, and historical turbulence intensity to obtain the calibrated wake model.

[0014] A consistency check is performed on the calibrated wake model. If the consistency check passes, the calibrated wake model is determined as the wake model.

[0015] In one embodiment, the step of calibrating the initial wake model based on historical wind speed, historical wind direction, and historical turbulence intensity to obtain a calibrated wake model includes:

[0016] Using the historical wind speed, historical wind direction, and historical turbulence intensity as input data, the wake velocity deficit model and the wake deflection model are driven according to the input data to obtain the simulated wake velocity distribution and simulated wake deflection angle of each wind turbine.

[0017] The simulated wake velocity distribution and the simulated wake deflection angle are compared with the corresponding historical measured wake data, and the key parameters of the wake velocity deficit model and the key parameters of the wake deflection model are iteratively corrected to obtain the corrected wake velocity deficit model and the corrected wake deflection model.

[0018] The modified wake velocity deficit model and the wake deflection model are coupled to construct a preliminarily calibrated fused wake model;

[0019] Verification simulations are performed on the preliminarily calibrated fused wake model based on the historical power output data of the wind farm cluster. If the overall power simulation error is lower than a preset threshold, the calibration is considered successful, and the preliminarily calibrated fused wake model is output as the calibrated wake model.

[0020] In one embodiment, the step of inputting the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine into the target wake model and outputting the simulated wake propagation influence relationship within the wind farm includes:

[0021] The wind speed, wind direction, turbulence intensity, and power of each wind turbine are preprocessed and converted into a standard format input vector.

[0022] The input vector is input into the wake model so that the wake model determines and outputs the wake velocity deficit and wake center deflection generated by the upstream wind turbine on the downstream wind turbine based on the wind turbine layout and the input vector.

[0023] The effective wind speed and effective inflow direction at the hub height of each wind turbine in the wind farm group are determined by superimposing the wake velocity deficit and the wake center deflection.

[0024] The simulation of wake propagation effects within a wind farm is generated based on the effective wind speed and effective inflow direction.

[0025] In one embodiment, the step of determining the target yaw offset angle of each wind turbine at a preset period based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group includes:

[0026] Based on the aforementioned wake propagation influence relationship and the location of each wind turbine in the wind farm group, the upstream and downstream wind turbines are determined;

[0027] Based on the wake propagation influence relationship and the location of each wind turbine in the wind farm group, the degree of influence of the wake of each downstream wind turbine in the wind farm group on the upstream wind turbine is determined;

[0028] Calculate the initial yaw adjustment angle based on the current position and wind direction of each wind turbine;

[0029] Using the physical limitations and fatigue loads of each wind turbine as constraints, the initial yaw adjustment angle is adjusted within a preset period based on the degree of influence and the constraints to obtain the target yaw offset angle of each wind turbine.

[0030] In one embodiment, the step of determining the degree of influence of the wake of each downstream wind turbine in the wind farm group on the wake of the upstream wind turbine based on the wake propagation influence relationship and the location of each wind turbine in the wind farm group includes:

[0031] For each of the downstream wind turbines, identify all upstream wind turbines that have a wake effect on the downstream wind turbines, and extract the velocity loss ratio and additional turbulence intensity caused by the wake at the downstream wind turbines based on the wake propagation effect relationship.

[0032] Based on the speed loss ratio, the theoretical power loss rate of the downstream wind turbine due to wake effect is calculated;

[0033] The relative distance and relative orientation of the downstream wind turbine and the upstream wind turbine are determined based on the location of each wind turbine in the wind farm group;

[0034] The degree of influence is obtained by weighting and fusing the theoretical power loss rate, the additional turbulence intensity, and the relative distance and orientation between the downstream and upstream wind turbines.

[0035] In one embodiment, the step of obtaining the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine in the wind farm group includes:

[0036] Real-time acquisition of raw wind speed, raw wind direction, raw turbulence intensity, and raw real-time power of each fan;

[0037] The original wind speed, the original wind direction, the original turbulence intensity, and the original real-time power of each wind turbine are preprocessed to obtain a time-aligned standardized dataset.

[0038] The standardized dataset is subjected to correlation testing to remove outlier data segments, and the wind speed, wind direction, turbulence intensity, and wind turbine power of each wind turbine in the wind farm group are obtained.

[0039] In one embodiment, the step of adjusting the yaw angle of each wind turbine in the wind farm group based on the target yaw offset angle includes:

[0040] Determine the current yaw angle of each wind turbine, and determine the adjustment angle based on the current yaw angle and the target yaw offset angle;

[0041] An adjustment command is generated based on the preset safe yaw rate and the adjustment angle, and the adjustment command is sent to the corresponding wind turbine according to the wind turbine number. The yaw angle of each wind turbine is adjusted according to the adjustment command.

[0042] In one embodiment, after the step of adjusting the yaw angle of each of the wind turbines according to the adjustment command, the method further includes:

[0043] The operating status of each wind turbine in the wind farm group is continuously monitored. When the deviation between the actual power output and the expected power output of the wind turbine is found to be greater than the deviation threshold, or when a fault alarm signal of the wind turbine is received, the wind turbine is determined to be an abnormal wind turbine.

[0044] When an abnormal wind turbine is identified, the abnormal wind turbine is isolated and the operating status of the wind farm group is updated.

[0045] Based on the updated wind farm cluster operating status, the target yaw offset angle of the remaining normal wind turbines is calculated, and a new cooperative yaw control strategy is generated.

[0046] The new target yaw offset angle is sent to the corresponding normal wind turbine for execution, and the system status is monitored until the abnormal wind turbine returns to normal or the maintenance process is initiated.

[0047] Furthermore, to achieve the above objectives, this application also proposes a wind farm cluster collaborative yaw optimization control system, which includes:

[0048] The data acquisition module is used to acquire wind speed, wind direction, turbulence intensity, and wind turbine power of each wind turbine in the wind farm group;

[0049] The wake simulation module is used to input the wind speed, wind direction, turbulence intensity and the power of each wind turbine into the target wake model, and output the wake propagation influence relationship within the wind farm. The wake model is obtained by calibrating the initial wake model, which is used to determine the wake propagation influence relationship between wind turbines.

[0050] The control decision module is used to determine the target yaw offset angle of each wind turbine at a preset period based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group.

[0051] The control optimization module is used to adjust the yaw angle of each wind turbine in the wind farm group based on the target yaw offset angle.

[0052] In addition, to achieve the above objectives, this application also proposes a wind farm group collaborative yaw optimization control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the wind farm group collaborative yaw optimization control method described above.

[0053] In addition, to achieve the above objectives, the present invention also proposes a storage medium, which is a computer-readable storage medium, and stores a computer program on the storage medium. When the computer program is executed by a processor, it implements the steps of the wind farm group collaborative yaw optimization control method described above.

[0054] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the wind farm group collaborative yaw optimization control method described above.

[0055] This application provides a collaborative yaw optimization control method for wind farm clusters. It acquires wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine within the wind farm cluster. These parameters are input into a target wake model, which outputs a simulated wake propagation effect within the wind farm. Based on the wake propagation effect and the position of each turbine within the wind farm cluster, a target yaw offset angle for each turbine is determined at a preset period. The yaw angle of each turbine in the wind farm cluster is then adjusted using this target yaw offset angle. Through collaborative yaw control, the rotor plane of the turbines is no longer completely aligned with the wind direction, actively causing some upstream turbines to sacrifice a small amount of their own power, resulting in a lateral shift in their wakes, cleverly "bypassing" downstream turbines. This allows downstream turbines to capture more undisturbed, high-quality wind energy, with the increase in power generation far exceeding the small losses of upstream turbines, achieving a net increase in the overall power generation efficiency of the wind farm cluster. By employing the above methods, the adverse effects of upstream wind turbine wakes on downstream wind turbines can be effectively reduced, thereby improving the overall power generation efficiency of the entire wind farm cluster. Attached Figure Description

[0056] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0057] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a flowchart illustrating an embodiment of the wind farm group collaborative yaw optimization control method of this application;

[0059] Figure 2 This is a schematic diagram of a wind farm group, representing an embodiment of the wind farm group collaborative yaw optimization control method of this application.

[0060] Figure 3 This is a schematic diagram of the module structure of the wind farm group collaborative yaw optimization control system according to an embodiment of this application;

[0061] Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the wind farm group collaborative yaw optimization control method in the embodiments of this application.

[0062] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0063] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0064] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0065] The main solution of this application embodiment is as follows: obtain the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine in the wind farm group; input the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine into the target wake model, and output the simulated wake propagation influence relationship in the wind farm; based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group, determine the target yaw offset angle of each wind turbine at a preset period; and adjust the yaw angle of each wind turbine in the wind farm group according to the target yaw offset angle.

[0066] Currently, in large-scale wind farms, the wake generated by upstream wind turbines significantly reduces the inflow velocity of downstream turbines and increases turbulence intensity, resulting in a loss of total power generation across the entire farm. Traditional independent turbine control modes cannot resolve the impact of upstream turbines on the power generation efficiency of downstream turbines.

[0067] This application provides a solution that acquires wind speed, wind direction, turbulence intensity, and turbine power of a wind farm cluster. It inputs these data into a target wake model, outputting a simulated wake propagation effect within the wind farm. Based on the wake propagation effect and the location of each turbine within the wind farm cluster, it determines the target yaw angle of each turbine at a preset period. The yaw angle of each turbine in the wind farm cluster is then adjusted using this target yaw angle. Through coordinated yaw control, the rotor plane of the upstream turbines is no longer directly aligned with the wind direction, actively causing some upstream turbines to sacrifice a small amount of their own power, resulting in a lateral shift in their wakes, cleverly "bypassing" the downstream turbines. This allows the downstream turbines to capture more undisturbed, high-quality wind energy, with the increase in power generation far exceeding the small losses of the upstream turbines, achieving a net increase in the overall power generation efficiency of the wind farm cluster. This method effectively reduces the adverse effects of upstream turbine wakes on downstream turbines, improving the overall power generation efficiency of the entire wind farm cluster.

[0068] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as a wind farm group coordinated yaw optimization control device. This embodiment does not specifically limit it in this way. The following uses a wind farm group coordinated yaw optimization control device as an example to describe this embodiment and the following embodiments.

[0069] All actions involving the acquisition of signals, information, or data in this application are carried out in accordance with the relevant data protection laws and policies of the country where the application is located, and with the authorization of the owner of the relevant device.

[0070] This application provides a method for coordinated yaw optimization control of wind farm groups, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the wind farm group collaborative yaw optimization control method of this application.

[0071] In this embodiment, the wind farm group coordinated yaw optimization control method includes steps S10~S40:

[0072] Step S10: Obtain the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine in the wind farm group;

[0073] It should be noted that a wind farm cluster refers to a collection of geographically adjacent wind turbines connected to the power grid. (Refer to...) Figure 2 , Figure 2 This is a schematic diagram of a wind farm complex. Wind speed is the speed of airflow and a key factor affecting the power output of wind turbines; wind direction refers to the direction from which the wind is coming and directly affects the yaw adjustment of the wind turbines; turbulence intensity is a parameter characterizing the severity of wind speed fluctuations, defined as the ratio of the standard deviation of wind speed to the average wind speed, reflecting the stability of the wind farm and affecting the mechanical load on the wind turbines; the power of each wind turbine refers to the real-time output electrical power of a single wind turbine unit and is a core indicator for evaluating the operating status and performance of the wind turbines.

[0074] Understandably, the raw wind speed and direction data are collected in real time through a sensor network deployed in the wind farm cluster, including anemometers and wind vanes installed on weather towers and wind turbines. The power sensors of each wind turbine collect real-time power data through a SCADA (Supervisory Control and Data Acquisition) system. Turbulence intensity is not measured directly, but is obtained by performing sliding window statistical analysis on high-frequency wind speed data and calculating the ratio of its standard deviation to the average wind speed. All data is transmitted to a central monitoring platform via wired or wireless communication networks to obtain the wind speed, wind direction, turbulence intensity, and wind turbine power of the wind farm cluster.

[0075] In one feasible implementation, the steps of obtaining the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine in the wind farm group include:

[0076] Real-time acquisition of raw wind speed, raw wind direction, raw turbulence intensity, and raw real-time power of each fan;

[0077] The original wind speed, the original wind direction, the original turbulence intensity, and the original real-time power of each wind turbine are preprocessed to obtain a time-aligned standardized dataset.

[0078] The standardized dataset is subjected to correlation testing to remove outlier data segments, and the wind speed, wind direction, turbulence intensity, and wind turbine power of each wind turbine in the wind farm group are obtained.

[0079] It should be noted that a standardized dataset refers to a structured dataset formed after systematic preprocessing of raw monitoring data from different sources and formats within a wind farm cluster. This data includes wind speed, wind direction, turbulence intensity, and the power of each wind turbine. The data undergoes cleaning, format standardization, time alignment, and normalization. This dataset ensures that all variables have the same timestamp, data length, and storage format, eliminating data inconsistencies caused by differences in sampling frequency, sensor range, or communication delays.

[0080] In practical implementation, during real-time data acquisition, ultrasonic anemometers are installed on the top of the weather tower and wind turbine nacelle to collect raw data at a high frequency of 10Hz to obtain wind speed and direction. Then, the instantaneous wind speed data is continuously collected, and the ratio of the standard deviation to the average wind speed is calculated using a sliding window; this ratio represents the turbulence intensity. The sliding window typically uses a 10-minute window. The power transmitters of each wind turbine's SCADA system collect real-time power generation data at 1-second intervals to achieve power acquisition for the wind turbines.

[0081] Then, all data is unified to the same time base using NTP time synchronization, and missing time points are filled in using linear interpolation. Following this, the time-aligned data undergoes data cleaning to remove obvious outliers, constant value segments caused by sensor malfunctions, and data gaps due to communication interruptions. Correlation testing is conducted from two perspectives: physical correlation testing and spatial consistency testing. In physical correlation testing, the rationality of the wind speed-power relationship is verified based on the wind turbine power characteristic curve, and data segments that significantly deviate from the characteristic curve are removed. In spatial consistency testing, monitoring data from adjacent wind turbines are compared to identify abnormal readings caused by local sensor malfunctions. After consistency testing, statistically significant outlier data segments can be identified. After a series of tests, the data is classified into valid and invalid data. Valid data is the data that passes the tests, while invalid data is outlier data, and invalid data is stored in the anomaly log. The retained valid data includes the wind speed, wind direction, turbulence intensity, and wind turbine power of the wind farm cluster.

[0082] Step S20: Input the wind speed, wind direction, turbulence intensity and the power of each wind turbine into the target wake model, and output the simulated wake propagation influence relationship in the wind farm. The wake model is obtained by calibrating the initial wake model, which is used to determine the wake propagation influence relationship between wind turbines.

[0083] It should be noted that the wake model is a mathematical model used to quantitatively describe the mutual influence of airflow between wind turbine generators. Its core simulation simulates the wind speed deceleration zone and turbulence enhancement zone formed by the high-speed airflow generated by the rotation of the upstream wind turbine blades as it propagates downstream. The simulation of the wake propagation influence relationship within the wind farm refers to the specific quantitative relationship calculated by this model, including the degree of wind speed attenuation at the location of the downstream wind turbine, the change in turbulence intensity, and the resulting power loss and mechanical load distribution, thereby revealing the mutual constraints of energy capture among the wind turbine groups.

[0084] Understandably, by calling a pre-built wake calculation engine, the model takes a pre-processed standardized dataset, including wind speed, wind direction, turbulence intensity, and turbine power, as input parameters. The model first determines the relative positional relationship between turbines based on the wind direction, and then calculates the wake expansion radius and velocity loss field by combining the inflow wind speed and turbulence intensity. After iteratively calculating the mutual influence between all turbines, the model finally outputs a relationship matrix containing the equivalent wind speed, wake superposition factor, and power loss coefficient at each turbine location. This matrix accurately characterizes the wake influence intensity and spatial propagation path between any two turbines.

[0085] In one feasible implementation, the step of inputting the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine into the target wake model and outputting the simulated wake propagation influence relationship within the wind farm includes:

[0086] The wind speed, wind direction, turbulence intensity, and power of each wind turbine are preprocessed and converted into a standard format input vector.

[0087] The input vector is input into the wake model so that the wake model determines and outputs the wake velocity deficit and wake center deflection generated by the upstream wind turbine on the downstream wind turbine based on the wind turbine layout and the input vector.

[0088] The effective wind speed and effective inflow direction at the hub height of each wind turbine in the wind farm group are determined by superimposing the wake velocity deficit and the wake center deflection.

[0089] The simulation of wake propagation effects within a wind farm is generated based on the effective wind speed and effective inflow direction.

[0090] Understandably, the input vector refers to a structured data array formed by reorganizing preprocessed field observation data such as wind speed, wind direction, turbulence intensity, and turbine power according to the format and dimensions required by the wake model. It includes the coordinate position of each turbine, environmental wind condition parameters, and initial power readings, and serves as the unified input interface for wake calculation. The wake velocity deficit represents a quantitative indicator of the reduction in wind speed at a specific downstream location due to the extraction of wind energy by upstream turbines. It is the relative difference between the actual wind speed at that location and the free-flowing wind speed, and is a core parameter for assessing the intensity of the wake's impact.

[0091] Understandably, wake center deflection describes the horizontal or vertical offset of the wind turbine's wake centerline relative to its theoretical axis, influenced by atmospheric boundary layer shear effects and wind direction changes. This phenomenon alters the actual position of the wake's effect on downstream wind turbines. Effective wind speed and effective inflow direction refer to the magnitude of the combined wind speed actually experienced at the hub height of a wind turbine after wake superposition correction, and their corresponding inflow angle, respectively.

[0092] In the specific implementation, the standardized dataset consisting of wind speed, wind direction, turbulence intensity, and power of each wind turbine is preprocessed into an input vector. , can be represented as: .in, For each wind turbine, a Cartesian coordinate array is provided. For free-flowing wind speed, For environmental wind direction, For environmental turbulence intensity, The initial power of each wind turbine is given. Then, the input vector is fed into the wake model, which is a modified Jensen wake model used to calculate the wake velocity deficit and wake center deflection. When calculating the wake velocity deficit, the formula is used:

[0093]

[0094] in, For wind turbine For the fan The resulting speed loss, Let i be the thrust coefficient of the upstream wind turbine. The diameter of the fan rotor. The wake attenuation coefficient is... For wind turbine To the fan The distance of the tailwind, For wind turbine lateral offset relative to the wake centerline The radius is the wake radius.

[0095] The formula for calculating the wake center deflection is:

[0096]

[0097] in, For wind turbine right The deflection angle of the wake center, The wind shear coefficient, For surface roughness, The angular velocity of Earth's rotation. It refers to geographical latitude.

[0098] Then for each downstream wind turbine The effective wind speed emitted from its hub The formula, calculated using multiple wake superposition, is as follows: .

[0099] The effective inflow direction takes into account the combined effects of wake deflection and ambient wind direction, and the calculation formula is as follows:

[0100]

[0101] The final output is an N×N wake propagation influence matrix R, where the element R[i,j] represents the wind turbine. For the fan The intensity of the wake effect is calculated as follows:

[0102] This matrix fully describes the wake propagation influence relationship between any two wind turbines in a wind farm, providing a quantitative basis for subsequent layout optimization and coordinated control.

[0103] In one feasible implementation, before the step of inputting the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine into the target wake model and outputting the simulated wake propagation influence relationship within the wind farm, the method further includes:

[0104] The geographical layout of the wind farm group and the physical parameters of each wind turbine are obtained, including the turbine height, rotor diameter and hub height.

[0105] An initial wake model is established based on the geographical layout and the wind turbine height, rotor diameter, and hub height.

[0106] The initial wake model is calibrated based on historical wind speed, historical wind direction, and historical turbulence intensity to obtain the calibrated wake model.

[0107] A consistency check is performed on the calibrated wake model. If the consistency check passes, the calibrated wake model is determined as the wake model.

[0108] In the specific implementation, the precise geographic coordinates of the wind turbines are obtained through the wind farm GIS system, and a topological relationship matrix is ​​established. Simultaneously, physical parameters such as hub height, rotor diameter, and thrust coefficient curves are extracted from the wind turbine technical specification library. Based on this, an initial wake model framework is constructed. The wake velocity deficit model adopts a modified Jensen formula with a preset attenuation coefficient k=0.05, while the wake deflection model integrates the Coriolis force correction term and the wind shear factor. Subsequently, based on 6-12 months of historical SCADA data, the Nelder-Mead optimization algorithm is used to automatically calibrate the model parameters, aiming to minimize the root mean square error between simulated and actual power. The focus is on calibrating the dynamic relationship between turbulence intensity and wake attenuation coefficient k=α×TI+β, as well as the deflection coefficient. After calibration, a dual consistency test is required: the statistical test requires that the prediction error of the wind direction sector (30° interval) and the wind speed range (3-25m / s sub-box) deviate from the overall RMSE by no more than 20%; the physical test verifies whether the wake attenuation gradient and deflection direction conform to the laws of fluid mechanics. Finally, the model parameters obtained through the test will be solidified and deployed to the wind farm monitoring system to form an adaptive wake model that can be updated online.

[0109] In one feasible implementation, the step of calibrating the initial wake model based on historical wind speed, historical wind direction, and historical turbulence intensity to obtain the calibrated wake model includes:

[0110] Using the historical wind speed, historical wind direction, and historical turbulence intensity as input data, the wake velocity deficit model and the wake deflection model are driven according to the input data to obtain the simulated wake velocity distribution and simulated wake deflection angle of each wind turbine.

[0111] The simulated wake velocity distribution and the simulated wake deflection angle are compared with the corresponding historical measured wake data, and the key parameters of the wake velocity deficit model and the key parameters of the wake deflection model are iteratively corrected to obtain the corrected wake velocity deficit model and the corrected wake deflection model.

[0112] The modified wake velocity deficit model and the wake deflection model are coupled to construct a preliminarily calibrated fused wake model;

[0113] Verification simulations are performed on the preliminarily calibrated fused wake model based on the historical power output data of the wind farm cluster. If the overall power simulation error is lower than a preset threshold, the calibration is considered successful, and the preliminarily calibrated fused wake model is output as the calibrated wake model.

[0114] Understandably, historical wind speed, direction, and turbulence intensity data are first used as input vectors to drive the wake velocity deficit model and the wake deflection model, respectively. Numerical calculations are then used to obtain the simulated wake velocity distribution and simulated wake deflection angle at each wind turbine location. The simulation results are then compared with historical measured wake data. Using the root mean square error (RMSE) as the objective function, an optimization algorithm iteratively corrects the turbulence dependence factors α and β of the attenuation coefficient k in the wake velocity deficit model, as well as the deflection gain coefficient and shear exponent in the wake deflection model, until the error converges. The two corrected sub-models are then integrated through a physical coupling module, where the velocity distribution and deflection angle dynamically interact, constructing a preliminarily calibrated fused wake model. Finally, a verification simulation is performed on the fused model based on historical power output data of the wind farm cluster. The RMSE between the simulated total power and the actual total power is calculated. If the error is below a threshold (typically 5-8%), the calibration is considered successful. The calibrated wake model is then output for real-time wind farm optimization.

[0115] Step S30: Based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group, determine the target yaw offset angle of each wind turbine with a preset period;

[0116] It should be noted that the preset period refers to the fixed time interval at which the system automatically calculates and updates the yaw strategy, typically set to 10-120 minutes based on wind condition characteristics and the mechanical response capability of the wind turbine. The target yaw offset angle refers to the specific angle actively set to deviate the wind turbine axis from the current prevailing wind direction in order to maximize the total power generation of the wind farm cluster; it is typically -30° to +30°.

[0117] Understandably, the process begins by reading the influence matrix output by the wake model and real-time wind direction data, identifying key areas severely affected by the wake based on the wind turbine topology. Then, using the maximization of the total power of the wind farm cluster as the objective function, gradient descent or particle swarm optimization algorithms are employed to iteratively calculate the optimal yaw offset angle for each turbine, taking into account yaw mechanism response delays and mechanical load constraints. During the calculation, a wake deflection model is used to predict the wake path after the offset, and power generation benefits are verified through power curve mapping. Finally, the target yaw offset angle for all wind turbines is output at a preset period.

[0118] In one feasible implementation, the step of determining the target yaw offset angle of each wind turbine at a preset period based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group includes:

[0119] Based on the aforementioned wake propagation influence relationship and the location of each wind turbine in the wind farm group, the upstream and downstream wind turbines are determined;

[0120] Based on the wake propagation influence relationship and the location of each wind turbine in the wind farm group, the degree of influence of the wake of each downstream wind turbine in the wind farm group on the upstream wind turbine is determined;

[0121] Calculate the initial yaw adjustment angle based on the current position and wind direction of each wind turbine;

[0122] Using the physical limitations and fatigue loads of each wind turbine as constraints, the initial yaw adjustment angle is adjusted within a preset period based on the degree of influence and the constraints to obtain the target yaw offset angle of each wind turbine.

[0123] It should be noted that the upstream and downstream wind turbines are dynamically related based on wind direction and their relative positions. An upstream turbine is the one facing the wind in the current wind direction; its wake propagates downwind. A downstream turbine, on the other hand, is located within the influence area of ​​the upstream turbine's wake; its inflow is affected by the wake, resulting in reduced wind speed and increased turbulence. This relationship changes dynamically with wind direction and needs to be calculated using real-time wind direction data and the turbine coordinate topology.

[0124] In the specific implementation, it is first based on real-time wind direction data. Wind turbine coordinates The upstream and downstream relationships between wind turbines are determined by azimuth calculation. The criteria for judgment are that the downstream wind turbine is located within a ±45° fan-shaped area centered on the wind direction and the distance is within 20 times the rotor diameter. Then, the influence relationship matrix is ​​output based on the wake model. Extracting the degree of influence parameter This parameter quantifies the fan To the fan The percentage of relative power loss caused. Next, the initial yaw adjustment angle is calculated using a formula based on the wake deflection model:

[0125]

[0126] The optimal yaw angle that minimizes the total power loss of the downstream wind turbines is determined using the gradient descent method. Finally, with the physical limitations and fatigue loads of each wind turbine as constraints, the initial yaw adjustment angle is adjusted based on the degree of influence and constraints within a preset period to obtain the target yaw offset angle for each wind turbine.

[0127] In one feasible implementation, the step of determining the degree of influence of the wake of the upstream wind turbine on each downstream wind turbine in the wind farm group based on the wake propagation influence relationship and the location of each wind turbine in the wind farm group includes:

[0128] For each of the downstream wind turbines, identify all upstream wind turbines that have a wake effect on the downstream wind turbines, and extract the velocity loss ratio and additional turbulence intensity caused by the wake at the downstream wind turbines based on the wake propagation effect relationship.

[0129] Based on the speed loss ratio, the theoretical power loss rate of the downstream wind turbine due to wake effect is calculated;

[0130] The relative distance and relative orientation of the downstream wind turbine and the upstream wind turbine are determined based on the location of each wind turbine in the wind farm group;

[0131] The degree of influence is obtained by weighting and fusing the theoretical power loss rate, the additional turbulence intensity, and the relative distance and orientation between the downstream and upstream wind turbines.

[0132] It should be noted that the velocity deficit ratio refers to the ratio of the reduction in wind speed at the downstream turbine location due to the wake effect to the free-flow wind speed, characterizing the intensity of the wake's attenuation of wind speed. The theoretical power loss rate is the expected percentage of power loss calculated from the velocity deficit ratio based on the wind energy formula and the turbine power characteristic curve, reflecting the direct impact of the wake on power generation capacity. Additional turbulence intensity is the extra turbulence intensity component exceeding the environmental background value caused by the wake effect at the downstream turbine location, reflecting the additional impact of the wake on flow field stability and turbine mechanical load.

[0133] In practical implementation, for each downstream wind turbine Based on the current wind direction and wind turbine layout coordinates, identify all upstream wind turbines that may have a wake effect. From the pre-calculated wake influence matrix Extracting downstream wind turbines Key parameters at the location.

[0134] Speed ​​loss ratio:

[0135] Additional turbulence intensity: , Turbulence intensity caused by wake

[0136] The theoretical power loss rate is calculated based on the wind turbine power characteristic curve P(U) and the speed loss ratio. :

[0137]

[0138] Then, based on the location of each wind turbine within the wind farm cluster, the relative distance and orientation between downstream and upstream wind turbines can be determined. A multi-factor weighted evaluation model is then constructed to determine the degree of influence.

[0139]

[0140] in, Let j be the relative distance between downstream wind turbine j and upstream wind turbine i. The relative azimuth angle is α, β, and γ, which are weighting coefficients. Optionally, α = 0.6, β = 0.25, and γ = 0.15.

[0141] Step S40: Adjust the yaw angle of each wind turbine in the wind farm group according to the target yaw offset angle.

[0142] Understandably, the calculated target yaw offset angle command set is sent to the PLC controller of each wind turbine via OPC UA or Modbus TCP protocol. The controller compares the target offset angle with the current actual yaw angle and generates a yaw motor control signal. The yaw system performs angle adjustment at a typical speed of 0.3-0.5° / second, while simultaneously monitoring the yaw bearing torque and gearbox load in real time to ensure that the mechanical system design limits are not exceeded. During the adjustment process, the SCADA system continuously monitors the power output and vibration data of each wind turbine, and fine-tunes the yaw speed through feedback control algorithms to prevent overshoot. For large wind farm clusters, a phased, gradual adjustment strategy is adopted, prioritizing the adjustment of turbines in areas severely affected by wake effects to avoid sudden changes in grid power.

[0143] In one feasible implementation, the step of adjusting the yaw angle of each wind turbine in the wind farm group with the target yaw offset angle includes:

[0144] Determine the current yaw angle of each wind turbine, and determine the adjustment angle based on the current yaw angle and the target yaw offset angle;

[0145] An adjustment command is generated based on the preset safe yaw rate and the adjustment angle, and the adjustment command is sent to the corresponding wind turbine according to the wind turbine number. The yaw angle of each wind turbine is adjusted according to the adjustment command.

[0146] In the specific implementation, the current yaw angle is collected in real time by the PLC controller of each wind turbine, and the absolute angle to be adjusted is calculated by comparing it with the target yaw offset angle. At the same time, considering the mechanical characteristics of the yaw system, the shortest path principle is adopted, and the adjustment is reversed when |Δθ|>180°. Then, according to the wind turbine safety operation specifications, a preset safe yaw rate is set, and an adjustment command containing the target angle, angular velocity and acceleration curve is generated by combining the adjustment angle Δθ. This command is encapsulated in OPC UA protocol through the wind farm ring network and sent to the corresponding wind turbine controller according to the pre-assigned wind turbine number. Finally, after receiving the command, each wind turbine actuator starts the yaw motor, and the position is fed back in real time through the incremental encoder to form a closed loop control. At the same time, the yaw bearing torque and gearbox load are monitored. When abnormal vibration or over-limit load is detected, the adjustment is immediately interrupted and the safety protection mechanism is triggered.

[0147] In one feasible implementation, after the step of adjusting the yaw angle of each of the wind turbines according to the adjustment command, the method further includes:

[0148] The operating status of each wind turbine in the wind farm group is continuously monitored. When the deviation between the actual power output and the expected power output of the wind turbine is found to be greater than the deviation threshold, or when a fault alarm signal of the wind turbine is received, the wind turbine is determined to be an abnormal wind turbine.

[0149] When an abnormal wind turbine is identified, the abnormal wind turbine is isolated and the operating status of the wind farm group is updated.

[0150] Based on the updated wind farm cluster operating status, the target yaw offset angle of the remaining normal wind turbines is calculated, and a new cooperative yaw control strategy is generated.

[0151] The new target yaw offset angle is sent to the corresponding normal wind turbine for execution, and the system status is monitored until the abnormal wind turbine returns to normal or the maintenance process is initiated.

[0152] In its implementation, the system first continuously collects real-time power, vibration temperature, and alarm signals from each wind turbine every 10 seconds. If the deviation between the actual power and the expected power of the wake model exceeds the deviation threshold for three consecutive cycles, or if a fault code is received from the SCADA system, the turbine is marked as abnormal. Subsequently, the control system isolates the abnormal turbine from the current coordinated control group, updates the wind farm cluster topology matrix, removes the abnormal turbine's coordinates and status information, and recalculates the wake influence relationship. Based on the updated system state, an adaptive particle swarm optimization algorithm is used to recalculate the optimal yaw angle for the remaining normal turbines. The new strategy prioritizes the wake path changes caused by the abnormal turbine's exit, compensating for the power shortfall by adjusting the yaw angles of adjacent turbines. Finally, the recalculated target yaw angle is sent to the normal turbines via the real-time data bus for execution. Simultaneously, the system continuously monitors the status of the abnormal turbine. If it does not automatically recover within 30 minutes, a maintenance work order is automatically generated and the operation and maintenance team is notified, ensuring that the wind farm cluster maintains optimal operation even when some turbines are abnormal.

[0153] This embodiment provides a collaborative yaw optimization control method for wind farm clusters. It acquires wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine within the wind farm cluster. These parameters are input into a target wake model, which outputs a simulated wake propagation effect within the wind farm. Based on the wake propagation effect and the position of each turbine within the wind farm cluster, a target yaw offset angle for each turbine is determined at a preset period. The yaw angle of each turbine in the wind farm cluster is then adjusted using this target yaw offset angle. Through collaborative yaw control, the rotor plane of the turbines is no longer completely aligned with the wind direction, actively causing some upstream turbines to sacrifice a small amount of their own power, resulting in a lateral shift in their wakes, cleverly "bypassing" downstream turbines. This allows downstream turbines to capture more undisturbed, high-quality wind energy, with the increase in power generation far exceeding the small losses of upstream turbines, achieving a net increase in the overall power generation efficiency of the wind farm cluster. By employing the above methods, the adverse effects of upstream wind turbine wakes on downstream wind turbines can be effectively reduced, thereby improving the overall power generation efficiency of the entire wind farm cluster.

[0154] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the wind farm group collaborative yaw optimization control method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0155] This application also provides a wind farm cluster collaborative yaw optimization control system; please refer to... Figure 3 The wind farm cluster collaborative yaw optimization control system includes:

[0156] The data acquisition module 10 is used to acquire the wind speed, wind direction, turbulence intensity and wind turbine power of each wind turbine in the wind farm group;

[0157] The wake simulation module 20 is used to input the wind speed, wind direction, turbulence intensity and wind turbine power of each wind turbine into the target wake model, and output the wake propagation influence relationship in the simulated wind farm. The wake model is obtained by calibrating the initial wake model, which is used to determine the wake propagation influence relationship between wind turbines.

[0158] Control decision module 30 is used to determine the target yaw offset angle of each wind turbine at a preset period based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group.

[0159] The control optimization module 40 is used to adjust the yaw angle of each wind turbine in the wind farm group according to the target yaw offset angle.

[0160] In one feasible implementation, the wake simulation module 20 is also used to obtain the geographical layout of the wind farm group and the physical parameters of each wind turbine, including the wind turbine height, rotor diameter and hub height.

[0161] An initial wake model is established based on the geographical layout and the wind turbine height, rotor diameter, and hub height.

[0162] The initial wake model is calibrated based on historical wind speed, historical wind direction, and historical turbulence intensity to obtain the calibrated wake model.

[0163] A consistency check is performed on the calibrated wake model. If the consistency check passes, the calibrated wake model is determined as the wake model.

[0164] In one feasible implementation, the wake simulation module 20 is further configured to take the historical wind speed, historical wind direction and historical turbulence intensity as input data, and drive the wake velocity deficit model and the wake deflection model respectively according to the input data to obtain the simulated wake velocity distribution and simulated wake deflection angle of each wind turbine.

[0165] The simulated wake velocity distribution and the simulated wake deflection angle are compared with the corresponding historical measured wake data, and the key parameters of the wake velocity deficit model and the key parameters of the wake deflection model are iteratively corrected to obtain the corrected wake velocity deficit model and the corrected wake deflection model.

[0166] The modified wake velocity deficit model and the wake deflection model are coupled to construct a preliminarily calibrated fused wake model;

[0167] Verification simulations are performed on the preliminarily calibrated fused wake model based on the historical power output data of the wind farm cluster. If the overall power simulation error is lower than a preset threshold, the calibration is considered successful, and the preliminarily calibrated fused wake model is output as the calibrated wake model.

[0168] In one feasible implementation, the wake simulation module 20 is further configured to preprocess the wind speed, wind direction, turbulence intensity and the power of each wind turbine, and convert them into input vectors in a standard format.

[0169] The input vector is input into the wake model so that the wake model determines and outputs the wake velocity deficit and wake center deflection generated by the upstream wind turbine on the downstream wind turbine based on the wind turbine layout and the input vector.

[0170] The effective wind speed and effective inflow direction at the hub height of each wind turbine in the wind farm group are determined by superimposing the wake velocity deficit and the wake center deflection.

[0171] The simulation of wake propagation effects within a wind farm is generated based on the effective wind speed and effective inflow direction.

[0172] In one feasible implementation, the control decision module 30 is further configured to determine the upstream and downstream wind turbines based on the wake propagation influence relationship and the location of each wind turbine in the wind farm group.

[0173] Based on the wake propagation influence relationship and the location of each wind turbine in the wind farm group, the degree of influence of the wake of each downstream wind turbine in the wind farm group on the upstream wind turbine is determined;

[0174] Calculate the initial yaw adjustment angle based on the current position and wind direction of each wind turbine;

[0175] Using the physical limitations and fatigue loads of each wind turbine as constraints, the initial yaw adjustment angle is adjusted within a preset period based on the degree of influence and the constraints to obtain the target yaw offset angle of each wind turbine.

[0176] In one feasible implementation, the control decision module 30 is further configured to identify all upstream wind turbines that have a wake effect on each of the downstream wind turbines, and extract the velocity loss ratio and additional turbulence intensity caused by the wake at the downstream wind turbines based on the wake propagation influence relationship.

[0177] Based on the speed loss ratio, the theoretical power loss rate of the downstream wind turbine due to wake effect is calculated;

[0178] The relative distance and relative orientation of the downstream wind turbine and the upstream wind turbine are determined based on the location of each wind turbine in the wind farm group;

[0179] The degree of influence is obtained by weighting and fusing the theoretical power loss rate, the additional turbulence intensity, and the relative distance and orientation between the downstream and upstream wind turbines.

[0180] In one feasible implementation, the data acquisition module 10 is also used to collect the original wind speed, original wind direction, original turbulence intensity, and original real-time wind turbine power of each wind turbine in real time.

[0181] The original wind speed, the original wind direction, the original turbulence intensity, and the original real-time power of each wind turbine are preprocessed to obtain a time-aligned standardized dataset.

[0182] The standardized dataset is subjected to correlation testing to remove outlier data segments, and the wind speed, wind direction, turbulence intensity, and wind turbine power of each wind turbine in the wind farm group are obtained.

[0183] In one feasible implementation, the control optimization module 40 is further configured to determine the current yaw angle of each of the wind turbines, and determine the adjustment angle based on the current yaw angle and the target yaw offset angle;

[0184] An adjustment command is generated based on the preset safe yaw rate and the adjustment angle, and the adjustment command is sent to the corresponding wind turbine according to the wind turbine number. The yaw angle of each wind turbine is adjusted according to the adjustment command.

[0185] In one feasible implementation, the control optimization module 40 is also used to continuously monitor the operating status of each wind turbine in the wind farm group, and when it is detected that the deviation between the actual power output and the expected power output of the wind turbine is greater than the deviation threshold, or when a fault alarm signal of the wind turbine is received, the wind turbine is determined to be an abnormal wind turbine.

[0186] When an abnormal wind turbine is identified, the abnormal wind turbine is isolated and the operating status of the wind farm group is updated.

[0187] Based on the updated wind farm cluster operating status, the target yaw offset angle of the remaining normal wind turbines is calculated, and a new cooperative yaw control strategy is generated.

[0188] The new target yaw offset angle is sent to the corresponding normal wind turbine for execution, and the system status is monitored until the abnormal wind turbine returns to normal or the maintenance process is initiated.

[0189] The wind farm group coordinated yaw optimization control system provided in this application, employing the wind farm group coordinated yaw optimization control method in the above embodiments, can solve the technical problem of the impact of upstream wind turbine wake on the power generation efficiency of downstream wind turbines. Compared with the prior art, the beneficial effects of the wind farm group coordinated yaw optimization control system provided in this application are the same as those of the wind farm group coordinated yaw optimization control method provided in the above embodiments, and other technical features in the wind farm group coordinated yaw optimization control system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0190] This application provides a wind farm group collaborative yaw optimization control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the wind farm group collaborative yaw optimization control method in the above embodiment 1.

[0191] The following is for reference. Figure 4 The diagram illustrates a structural schematic of a wind farm cluster coordinated yaw optimization control device suitable for implementing embodiments of this application. The wind farm cluster coordinated yaw optimization control device in this application embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The wind farm cluster coordinated yaw optimization control device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0192] like Figure 4As shown, the wind farm cluster coordinated yaw optimization control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the wind farm cluster coordinated yaw optimization control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the wind farm cluster coordinated yaw optimization control equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a wind farm cluster coordinated yaw optimization control equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0193] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0194] The wind farm group coordinated yaw optimization control device provided in this application adopts the wind farm group coordinated yaw optimization control method in the above embodiments, which can solve the technical problem of wind farm group coordinated yaw optimization control. Compared with the prior art, the beneficial effects of the wind farm group coordinated yaw optimization control device provided in this application are the same as the beneficial effects of the wind farm group coordinated yaw optimization control method provided in the above embodiments, and other technical features in the wind farm group coordinated yaw optimization control device are the same as the features disclosed in the previous embodiment method, and will not be repeated here.

[0195] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0196] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0197] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the wind farm group cooperative yaw optimization control method in the above embodiments.

[0198] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0199] The aforementioned computer-readable storage medium may be included in the wind farm cluster collaborative yaw optimization control equipment; or it may exist independently and not be assembled into the wind farm cluster collaborative yaw optimization control equipment.

[0200] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the wind farm group collaborative yaw optimization control device, the wind farm group collaborative yaw optimization control device: acquires the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine in the wind farm group; inputs the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine into a target wake model, and outputs a simulated wake propagation influence relationship within the wind farm; based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group, determines the target yaw offset angle of each wind turbine at a preset period; and adjusts the yaw angle of each wind turbine in the wind farm group using the target yaw offset angle.

[0201] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0202] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0203] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0204] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described wind farm group coordinated yaw optimization control method, thereby solving the technical problem of wind farm group coordinated yaw optimization control. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the wind farm group coordinated yaw optimization control method provided in the above embodiments, and will not be repeated here.

[0205] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the wind farm group collaborative yaw optimization control method described above.

[0206] The computer program product provided in this application can solve the technical problem of coordinated yaw optimization control of wind farm groups. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the coordinated yaw optimization control method for wind farm groups provided in the above embodiments, and will not be repeated here.

[0207] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for coordinated yaw optimization control of a wind farm cluster, characterized in that, The wind farm group collaborative yaw optimization control method includes: Obtain wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine in the wind farm cluster; The wind speed, wind direction, turbulence intensity, and wind turbine power of each wind turbine are input into the target wake model, and the simulated wake propagation influence relationship within the wind farm is output. The wake model is obtained by calibrating the initial wake model, which is used to determine the wake propagation influence relationship between wind turbines. Based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group, the target yaw offset angle of each wind turbine is determined at a preset period. The yaw angle of each wind turbine in the wind farm group is adjusted according to the target yaw offset angle; The step of determining the target yaw offset angle of each wind turbine at a preset period based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group includes: Based on the aforementioned wake propagation influence relationship and the location of each wind turbine in the wind farm group, the upstream and downstream wind turbines are determined; Based on the wake propagation influence relationship and the location of each wind turbine in the wind farm group, the degree of influence of the wake of each downstream wind turbine in the wind farm group on the upstream wind turbine is determined; Calculate the initial yaw adjustment angle based on the current position and wind direction of each wind turbine; Using the physical limitations and fatigue loads of each wind turbine as constraints, the initial yaw adjustment angle is adjusted within a preset period based on the degree of influence and the constraints to obtain the target yaw offset angle of each wind turbine.

2. The method as described in claim 1, characterized in that, Before the step of inputting the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine into the target wake model and outputting the simulated wake propagation influence relationship within the wind farm, the method further includes: The geographical layout of the wind farm group and the physical parameters of each wind turbine are obtained, including the turbine height, rotor diameter and hub height. An initial wake model is established based on the geographical layout, the wind turbine height, the rotor diameter, and the hub height; The initial wake model is calibrated based on historical wind speed, historical wind direction, and historical turbulence intensity to obtain the calibrated wake model. A consistency check is performed on the calibrated wake model. If the consistency check passes, the calibrated wake model is determined as the target wake model.

3. The method as described in claim 2, characterized in that, The initial wake model includes a wake velocity deficit model and a wake deflection model. The step of calibrating the parameters of the initial wake model based on historical wind speed, historical wind direction, and historical turbulence intensity to obtain the calibrated wake model includes: Using the historical wind speed, historical wind direction, and historical turbulence intensity as input data, the wake velocity deficit model and the wake deflection model are driven according to the input data to obtain the simulated wake velocity distribution and simulated wake deflection angle of each wind turbine. The simulated wake velocity distribution and the simulated wake deflection angle are compared with the corresponding historical measured wake data, and the key parameters of the wake velocity deficit model and the key parameters of the wake deflection model are iteratively corrected to obtain the corrected wake velocity deficit model and the corrected wake deflection model. The modified wake velocity deficit model and the wake deflection model are coupled to construct a preliminarily calibrated fused wake model; The preliminary calibrated fused wake model is verified by historical power output data of the wind farm cluster. When the overall power simulation error is lower than a preset threshold, the calibration is deemed successful, and the preliminary calibrated fused wake model is output as the calibrated wake model.

4. The method as described in claim 1, characterized in that, The step of inputting the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine into the target wake model and outputting the simulated wake propagation influence relationship within the wind farm includes: The wind speed, wind direction, turbulence intensity, and power of each wind turbine are preprocessed and converted into a standard format input vector. The input vector is input into the wake model so that the wake model determines and outputs the wake velocity deficit and wake center deflection generated by the upstream wind turbine on the downstream wind turbine based on the wind turbine layout and the input vector. The effective wind speed and effective inflow direction at the hub height of each wind turbine in the wind farm group are determined by superimposing the wake velocity deficit and the wake center deflection. The simulation of wake propagation effects within a wind farm is generated based on the effective wind speed and the effective inflow direction.

5. The method as described in claim 1, characterized in that, The step of determining the degree of influence of the wake of the upstream wind turbine on each downstream wind turbine in the wind farm group based on the wake propagation influence relationship and the location of each wind turbine in the wind farm group includes: Identify all upstream wind turbines that have wake effects on the downstream wind turbines, and based on the wake propagation effect relationship, extract the velocity loss ratio and additional turbulence intensity caused by the wake at the downstream wind turbines; Based on the speed loss ratio, calculate the theoretical power loss rate of the downstream wind turbine due to wake effect; The relative distance and relative orientation of the downstream wind turbine and the upstream wind turbine are determined based on the location of each wind turbine in the wind farm group; The degree of influence is obtained by weighting and fusing the theoretical power loss rate, the additional turbulence intensity, and the relative distance and orientation between the downstream and upstream wind turbines.

6. The method as described in claim 1, characterized in that, The steps for obtaining the wind speed, wind direction, turbulence intensity, and turbine power of each wind turbine in the wind farm group include: Real-time acquisition of raw wind speed, raw wind direction, raw turbulence intensity, and raw real-time power of each fan; The original wind speed, the original wind direction, the original turbulence intensity, and the original real-time power of each wind turbine are preprocessed to obtain a time-aligned standardized dataset. The standardized dataset is subjected to correlation testing to remove outlier data segments, and the wind speed, wind direction, turbulence intensity, and wind turbine power of each wind turbine in the wind farm group are obtained.

7. The method as described in claim 1, characterized in that, The step of adjusting the yaw angle of each wind turbine in the wind farm group based on the target yaw offset angle includes: Determine the current yaw angle of each wind turbine, and determine the adjustment angle based on the current yaw angle and the target yaw offset angle; An adjustment command is generated based on the preset safe yaw rate and the adjustment angle, and the adjustment command is sent to the corresponding wind turbine according to the wind turbine number. The yaw angle of each wind turbine is adjusted according to the adjustment command.

8. The method as described in claim 7, characterized in that, After the step of adjusting the yaw angle of each wind turbine according to the adjustment command, the method further includes: The operating status of each wind turbine in the wind farm group is continuously monitored. When the deviation between the actual power output and the expected power output of the wind turbine is found to be greater than the deviation threshold, or when a fault alarm signal of the wind turbine is received, the wind turbine is determined to be an abnormal wind turbine. When an abnormal wind turbine is identified, the abnormal wind turbine is isolated and the operating status of the wind farm group is updated. Based on the updated wind farm cluster operating status, the target yaw offset angle of the remaining normal wind turbines is calculated, and a new cooperative yaw control strategy is generated. The new target yaw offset angle is sent to the corresponding normal wind turbine for execution, and the system status is monitored until the abnormal wind turbine returns to normal or the maintenance process is initiated.

9. A wind farm cluster collaborative yaw optimization control system, characterized in that, The wind farm cluster collaborative yaw optimization control system includes: The data acquisition module is used to acquire wind speed, wind direction, turbulence intensity, and wind turbine power of each wind turbine in the wind farm group; The wake simulation module is used to input the wind speed, wind direction, turbulence intensity and the power of each wind turbine into the target wake model, and output the wake propagation influence relationship within the wind farm. The wake model is obtained by calibrating the initial wake model, which is used to determine the wake propagation influence relationship between wind turbines. The control decision module is used to determine the target yaw offset angle of each wind turbine at a preset period based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group. The control optimization module is used to adjust the yaw angle of each wind turbine in the wind farm group based on the target yaw offset angle. The step of determining the target yaw offset angle of each wind turbine at a preset period based on the wake propagation influence relationship and the position of each wind turbine in the wind farm group includes: Based on the aforementioned wake propagation influence relationship and the location of each wind turbine in the wind farm group, the upstream and downstream wind turbines are determined; Based on the wake propagation influence relationship and the location of each wind turbine in the wind farm group, the degree of influence of the wake of each downstream wind turbine in the wind farm group on the upstream wind turbine is determined; Calculate the initial yaw adjustment angle based on the current position and wind direction of each wind turbine; Using the physical limitations and fatigue loads of each wind turbine as constraints, the initial yaw adjustment angle is adjusted within a preset period based on the degree of influence and the constraints to obtain the target yaw offset angle of each wind turbine.

Images