This study investigates how ordinary atmospheric conditions induce systematic deviations from the nominal manufacturer's power curve of a modern wind turbine using a residual-based comparative power curve analysis. The approach directly compares theoretical power values with turbine-level SCADA measurements. It evaluates the difference between predicted and measured power as a continuous indicator of relative underperformance rather than as a classified anomaly. The dataset comprises wind speed, wind direction, air density, ambient temperature, cloud cover, solar irradiance, and measured electrical power from a Nordex N117/3600 wind turbine over a full annual period, complemented by temporally synchronized atmospheric data. Power residuals are analyzed as functions of wind speed and paired meteorological variables to reveal recurring deviation patterns and their physical context. The cumulative integration of positive residuals indicates an annual energy production loss of approximately 244,481 kWh, demonstrating that small but persistent power-curve departures accumulate into a substantial long-term deficit. The results show that performance deviations concentrate primarily in the partially loaded operating region and are strongly associated with variations in air density and wind regime. At the same time, temperature and radiative variables play a secondary role. The main contribution of this study is the presentation of a physically interpretable, residual-based performance deviation analysis that links power curve departures directly to atmospheric conditions and quantifies their cumulative energy impact without relying on predictive models or formal anomaly detection algorithms
Gökhan Yüksek (Tue,) studied this question.