Against the background of increasing cost pressure, condition monitoring is becoming increasingly relevant to the wind energy industry. The present study examines the role of wind turbulence and the non-constant variance of residuals in power curve monitoring. Power curve monitoring methods are classified and compared by means of Monte Carlo simulations. It is found that adjusting for the non-constant variance of residuals using standardisation may considerably improve the performance of control charts, no matter what method is used to generate them. Additionally, turbulence is found to be an important factor, and including it may further increase the performance of control charts. (C) 2019 Elsevier Ltd. All rights reserved.