Method for evaluating a performance of a wind turbine

A performance evaluation system configured to evaluate the performance of a wind turbine, comprising:

• one or more memories having computer-readable instructions stored therein;
• and
• one or more processors configured to execute the computer-readable instructions to:
• acquire, for each of a plurality of wind turbines, at least one corresponding power production parameter and at least one corresponding site specific parameter for each of a plurality of days;
• prepare a dataset based on the at least one corresponding power production parameter and at least one corresponding site specific parameter;
• train a machine learning algorithm to cluster the plurality of wind turbines into a plurality of clusters of wind turbines with comparable conditions based on the dataset, each of the plurality of clusters of wind turbines comprising at least two wind turbines;
• cluster the plurality of wind turbines with the trained machine learning algorithm into the plurality of clusters of wind turbines;
• identify a specific cluster from the plurality of clusters with comparable conditions to the wind turbine based on corresponding site specific parameters of the wind turbines in the specific cluster and the at least one corresponding site specific parameter of the wind turbine;
• determine a cluster performance index of the specific cluster based on the at least one corresponding power production parameter of the wind turbines in the specific cluster;
• determine a wind turbine performance index of the wind turbine based on the at least one corresponding power production parameter of the wind turbine;
• and
• evaluate a performance of the wind turbine by comparing the wind turbine performance index of the wind turbine to the cluster performance index of the specific cluster.

One or more non-transitory computer-readable media comprising computer-readable instructions, which when executed by one or more processors of a performance evaluation system configured to evaluate the performance of a wind turbine, cause the performance evaluation system to:

• acquire, for each of a plurality of wind turbines, at least one corresponding power production parameter and at least one corresponding site specific parameter for each of a plurality of days;
• prepare a dataset based on the at least one corresponding power production parameter and at least one corresponding site specific parameter;
• train a machine learning algorithm to cluster the plurality of wind turbines into a plurality of clusters of wind turbines with comparable conditions based on the dataset, each of the plurality of clusters of wind turbines comprising at least two wind turbines,
• cluster the plurality of wind turbines with the trained machine learning algorithm into the plurality of clusters of wind turbines,
• identify a specific cluster from the plurality of clusters with comparable conditions to the wind turbine based on corresponding site specific parameters of the wind turbines in the specific cluster and the at least one corresponding site specific parameter of the wind turbine;
• determine a cluster performance index of the specific cluster based on the at least one corresponding power production parameter of the wind turbines in the specific cluster;
• determine a wind turbine performance index of the wind turbine based on the at least one corresponding power production parameter of the wind turbine;
• evaluate a performance of the wind turbine by comparing the wind turbine performance index of the wind turbine to the cluster performance index of the specific cluster.