The wind turbine power curve (WTPC) shows the relationship between the wind speed and power output of the turbine. Power curves, which are provided by the manufacturers, are mainly used in planning, forecasting, performance monitoring and control of the wind turbines. Hence an accurate WTPC model is very important in predictive control and monitoring. This paper presents comparative analysis of various parametric and non-parametric techniques for modeling of wind turbine power curves, with reference to three commercial wind turbines; 330, 800 and 900 kW, respectively. Firstly, these WTPCs were used to evaluate the accuracy of several previously developed mathematical models by utilizing error measurement techniques such as normalized root mean square error (NRMSE) and r-square. Later on, the most accurate model was selected and the genetic algorithm (GA) was utilized to improve the model's accuracy by optimizing its coefficients. Finally, WTPCs were modeled using artificial neural network (ANN) and the result was compared with the GA optimized model.