Method for controlling operation of a wind turbine

A method for controlling operation of a wind turbine, the method comprising:

• collecting training data, the training data comprising pitch setpoints, tip speed ratio setpoints, and historical data regarding one or more operational conditions of the wind turbine including a power output or a power differential of the wind turbine;
• training a machine learning model by applying the training data to the machine learning model, an output of the machine learning model is an estimated power or estimated power differential of the wind turbine based on the training data, and the machine learning model is stored;
• obtaining recent data regarding one or more operational conditions of the wind turbine;
• applying the machine learning model to the recent data to output a reference power or reference power differential corresponding to the recent data;
• applying the machine learning model to the recent data to output at least one estimated power or estimated power differential corresponding to values of the pitch setpoints and the tip speed ratio setpoints which differ from the recent data;
• determining a wind turbine setting by comparing the estimated power or estimated power differential to the reference power or reference power differential, and applying the wind turbine setting to the wind turbine if the estimated power or estimated power differential is greater than or equal to a threshold amount above the reference power or reference power differential;
• repeating the obtaining, applying and determining steps at a predetermined time interval.