Mathematical methods for SCADA data mining of onshore wind farms: Performance evaluation and wake analysis

Abstract

Supervisory control and data acquisition (SCADA) systems have become widely diffuse in modern wind energy technology. The slowdown of new installations and the increasing percentage of energy entering the grid from renewable stochastic sources has diverted attention to the careful optimization of operating farms. Elaborating the complex data stream from SCADA systems into knowledge poses technological and scientific challenges. SCADA data analysis therefore lies at the crossroads of mechanical engineering, applied mathematics, statistics and physics. In the present work, mathematical methods are proposed for tackling the complexity of SCADA data. This idea is to elaborate simplified and more powerful data sets through one action: discretization of continuous quantities. The approach is employed for two very different issues: performance evaluation and wake effects analysis, which is investigated from the point of view of power losses, due to the difficulties associated with optimal turbine alignment with the wind. Two indexes for performance evaluation are formulated. Recurrent non-trivial orientation patterns of clusters of turbines are individuated, and the efficiency associated to them is analyzed. The methods are tested on two wind farms situated in southern Italy.