A method for predicting a day-ahead wind power of wind farms, comprising: constructing a raw data set based on a correlation between the to-be-predicted daily wind power, the numerical weather forecast meteorological feature and a historical daily wind power; obtaining a clustered data set and performing k-means clustering, obtaining a raw data set with cluster labels, and generating massive labeled scenes based on robust auxiliary classifier generative adversarial networks; determining the cluster label category of the to-be-predicted day based on the known historical daily wind power and numerical weather forecast meteorological feature, and screening out multiple scenes with high similarity to the to-be-predicted daily wind power based on the cluster label category; and obtaining the prediction results of the to-be-predicted daily wind power at a plurality of set times based on an average value, an upper limit value and a lower limit value of the to-be-predicted daily wind power.

Aspects of the present invention relate to controlling a wind turbine having a tower damping system actuable to control components of vibrational movement of the tower, a side-side component of a vibrational movement of the tower in a horizontal plane; and a fore-aft component of the vibrational movement of the tower in the horizontal plane are determined; and a control signal based on the side-side and fore-aft components is determined such that the tower damping system produces a force that increases or decreases the vibrational movement of the tower such that the side-side and fore-aft components are substantially equal.

Provided is a method of controlling at least one wind turbine in case of a rotational overspeed situation, the method including: determining a current state related to the wind turbine; providing data related to the current state as input to a turbine model; predicting a load of at least one wind turbine component and power output of the wind turbine using the turbine model provided with the input for plural control strategies; comparing the predicted load and power output for the plural control strategies; and selecting that control strategy among the plural control strategies that satisfies a target criterion including the load and the power output.

A method for controlling noise generated by a wind farm with a plurality of wind turbines is disclosed. In the event that a predicted noise level exceeds a predefined threshold noise value, one or more wind turbines are selected using a noise propagation model and respective wind turbine models for the selected one or more wind turbines, and by performing an optimisation process to reduce the predicted noise level at the predefined evaluation position to a level below the predefined threshold noise value while maximising the total power production of the wind farm.

Disclosed herein are methods, systems, and devices for utilizing distributed reinforcement learning and consensus control to most effectively generate and utilize energy. In some embodiments, individual turbines within a wind farm may communicate to reach a consensus as to the desired yaw angle based on the wind conditions.

A method of operating a wind turbine. The wind turbine is operated over an operating period in accordance with a control strategy. A sensor signal is received over the operating period from a sensor measuring an operational parameter of the turbine. A model is used to obtain a modelled fatigue value based on the sensor signal. The modelled fatigue value provides an estimate of fatigue loading applied to a component of the turbine over the operating period. The control strategy is modified based on the modelled fatigue value.

A wind turbine control apparatus, method and non-transitory computer-readable medium are disclosed. The wind turbine control apparatus comprises a generator connected to a wind turbine with a drive train. The drive train comprises a rotor, a low speed shaft, a gear box, a high speed shaft, and a controller module. The controller module is configured to obtain a maximum power within a large range of varying wind velocities by operating the rotor at a neural network determined optimal angular speed for the current wind velocity.

A method for computer-implemented determination of control parameters of a turbine in case of a component malfunction is provided. The method considers the impact of individual turbine characteristic values on the turbine performance in a turbine model in order to determine control parameters for the turbine without damaging it. The following includes the steps of: receiving, by an interface, an information indicating a component malfunction; identifying, by a processing unit, as to what power level the turbine is operated at, by a simulation of the operation of the turbine, the simulation being made with a given turbine model in which the identified component is set to be operated with a reduced function and in which one or more characteristic values characteristic values of the wind turbine are used as input parameter; and deriving, by the processing unit, the control parameters for the wind turbine from the identified power level.

A method for determining improved control parameters of a turbine by consideration of a lifetime information is provided. The method considers the impact of individual turbine manufacturing tolerances on the turbine performance, thereby avoiding under-utilization of those wind turbines. The invention includes the steps of: receiving, by an interface, actual operation parameters of the turbine and/or ambient condition information; determining, by a processing unit, a lifetime information about a residual lifetime of the turbine or a turbine component by a simulation of the operation of the turbine, the simulation being made with a given turbine model in which the actual operation parameters of the turbine and/or ambient condition information and one or more characteristic values of the turbine are used as input parameters; and deriving, by the processing unit, the control parameters for the turbine from lifetime information.

A method for determining control parameters of a turbine by consideration of component-relevant temperature limits is provided. The method considers the impact of individual turbine manufacturing tolerances on the turbine performance in a turbine model to determine control parameters for the turbine without damaging it. The method includes the steps of: receiving, by an interface, one or more measurement values of turbine sensors; determining, by a processing unit, at components or turbine places being equipped or not with turbine sensors, one or more virtual parameters and/or temperatures by a simulation of the operation of the turbine, the simulation being made with a given turbine model in which the one or more measurement values and one or more characteristic values of the wind turbine are used as input parameters; and deriving, by the processing unit, the control parameters for the wind turbine from the one or more virtual parameters and/or temperatures.