A SCADA data mining method for precision assessment of performance enhancement from aerodynamic optimization of wind turbine blades

The target of improving efficiency of wind kinetic energy extraction has stimulated a certain attention to wind turbine retrofitting. This kind of interventions has material and labor costs and producible energy is lost during installation. Further, the estimation of the energy enhancement is commonly provided under the hypothesis of ideal conditions that can be very different from real ones. Therefore, a precise estimation of performance improvement is fundamental. In this work, a SCADA-based method is formulated for estimating the improvement in energy production of multi-megawatt wind turbines, sited in Italy in a very complex terrain. The blades of one wind turbine in the farm have been optimized by installing vortex generators and passive flow control devices. An Artificial Neural Network (ANN) model is employed: the output is the power of the retrofitted wind turbine and the inputs are the powers of some reference nearby wind turbines. The production increase is estimated by observing how the difference between simulated and measured power output changes after the installation of the aerodynamic upgrade. The average improvement is estimated as the 3.9% of the total energy produced below rated power.