Systems and methods of autonomous farm-level control and optimization of wind turbines are provided. Exemplary embodiments comprise a site controller running on a site server. The site controller collects and analyzes yaw control data of a plurality of wind turbines and wind direction data relating to the plurality of wind turbines. The site server determines collective wind direction across an area occupied by the plurality of wind turbines and sends yaw control signals including desired nacelle yaw position instructions to the plurality of wind turbines. The site controller performs wake modeling analysis and determines desired nacelle positions of one or more of the plurality of wind turbines. The desired nacelle yaw position instructions systematically correct static yaw misalignment for all of the plurality of wind turbines. Embodiments of the disclosure provide means to perform whole site or partial site level controls of the yaw controllers of a utility scale wind turbine farm. The overall effect of the coordinated yaw control of wind turbines across the whole or partial site is intended to keep the wake loss of the wind turbines from the upstream wind turbines to the minimum and to maximize the production of turbines that are not waking other turbines.

Disclosed are a method and apparatus for detecting a yaw-to-wind abnormality. The method includes: acquiring a wind direction deviation angle within a specified time period; calculating a power performance index, wherein the power performance index is a dimensionless number used to characterize power generation performance of a wind turbine; determining an optimal wind direction deviation angle based on the power performance index; determining a current wind direction deviation angle according to probability distribution of the wind direction deviation angle; and if a difference between the optimal wind direction deviation angle and the current wind direction deviation angle is greater than a preset threshold, determining that a yaw-to-wind abnormality is detected. Compared with the related technology in which yaw-to-wind detection is performed through a power fitting curve, in the technical solution according to the embodiments of the present disclosure, a power index is directly used, which avoids the problem of poor power curve fitting effect and improves the accuracy of yaw-to-wind detection.

A system and method are provided for controlling a wind turbine of a wind farm. Accordingly, a controller implements a first model to determine a modeled performance parameter for the first wind turbine. The modeled performance parameter is based, at least in part, on an operation of a designated grouping of wind turbines of the plurality of wind turbines, which is exclusive of the first wind turbine. The controller then determines a performance parameter differential for the first wind turbine at multiple sampling intervals. The performance parameter differential is indicative of a difference between the modeled performance parameter and a monitored performance parameter for the first wind turbine. A second model is implemented to determine a predicted performance parameter of the first wind turbine at each of a plurality of setpoint combinations based, at least in part, on the performance parameter differential the first wind turbine. A setpoint combination is then selected based on the predicted performance parameter and an operating state of the first wind turbine is changed based on the setpoint combination.

A system and method are provided for controlling a wind farm during low wind speeds. Accordingly, the farm controller designates at least one of the plurality of wind turbines of the wind farm as a designated turbine. The designated turbine is operating in a full auxiliary mode when the speed of the wind acting on the wind farm is below a wind speed threshold. The remaining wind turbines are operated in a reduced auxiliary mode. The reduced auxiliary mode includes the disabling of at least one of pitching and yawing of the remaining wind turbines. When a power output for the designated wind turbine exceeds a power threshold, the farm controller directs at least one group of the remaining wind turbines to transition from the reduced auxiliary mode to the full auxiliary mode. During certain grid conditions, the transition between auxiliary modes may be delayed.

The present disclosure is directed to a system and method for assessing farm-level performance of a wind farm. The method includes operating the wind farm in a first operational mode and identifying one or more pairs of wind turbines having wake interaction. The method also includes generating a pairwise dataset for the wind turbines pairs. Further, the method includes generating a first wake model based on the pairwise dataset and predicting a first farm-level performance parameter based on the first wake model. The method also includes operating the wind farm in a second operational mode and collecting operational data during the second operational mode. Moreover, the method includes predicting a first farm-level performance parameter for the second operational mode using the first wake model and the operational data from the second operational mode. The method further includes determining a second farm-level performance parameter during the second operational mode. Thus, the method includes determining a difference in the farm-level performance of the wind farm as a function of the first and second farm-level performance parameters.

A method for compensating the output power of wind turbine generator set includes acquiring the average values of the first ambient temperature of environments where the wind turbine generator set is located in various periods; collecting the output power of the wind turbine generator set at the end time of various periods; compensating the set output power collected at the end time of current period according to difference value between the average value of the first ambient temperature in the current period and that in the previous period so as to guarantee the stability of the set output power if the average value of the first ambient temperature in the current period and the average value of the first ambient temperature in the previous period both are higher than a preset temperature threshold value.

A method is provided for controlling the operation of a wind turbine, the wind turbine including a generator, a converter, a converter control unit, a wind turbine controller and a connection device to an external electrical power grid, wherein electrical power generated by the generator is input into the power grid via the converter, wherein the wind turbine controller is configured to determine a fault condition according to a fault condition signal and to active a safe operating mode in response to the fault condition signal indicating a fault condition, wherein the fault condition signal is determined by evaluating changes in an available output power signal generated by the converter control unit, the available output power signal describing the active output power available from the converter.

A method and corresponding arrangement are provided for determining pitch angle adjustment signals for adjusting a pitch angle of a rotor blade connected to a rotation shaft of a wind turbine. The method includes obtaining a first maximal speed signal indicative of a first desired maximal rotational speed of the rotation shaft. The method also includes deriving a first pitch angle adjustment signal based on the first maximal speed signal. The method further includes obtaining a second maximal speed signal indicative of a second desired maximal rotational speed of the rotation shaft different from the first desired maximal rotational speed of the rotation shaft. Further, the method includes deriving a second pitch angle adjustment signal based on the second maximal speed signal. The second pitch angle adjustment signal is different from the first pitch angle adjustment signal.

Embodiments of the present invention provide methods and apparatus for increasing turbulent mixing in the wake of at least one wind turbine. Doing so, increases efficiency of a wind turbine located in the wake by transferring energy to the wake that was lost when the wind passed through the upwind turbine. Turbulent mixing may be increased by changing the induction factor for a rotor by, for example, altering the pitch of the blades, the RPMs of the rotor, or the yaw of the nacelle. These techniques may be static or dynamically changing. Further, the different induction factors for a plurality of wind turbines may be synchronized according to a predetermined pattern to further increase turbulent mixing.

A computer-implemented method for determining wind turbine performance. The computer-implemented method includes generating a digital image based on operation data of a wind turbine. The operation data includes wind speed data and associated power output data. The computer-implemented method also includes processing the digital image using a convolutional neural network to obtain processed digital image, and processing the processed digital image to determine a representation of a wind turbine power curve associated with operation of the wind turbine.