However, during the application, correct selection of turbine
parameters is critical for estimating the wind power generation by using PID since it depends only on exact mathematical modeling. Subsequently, power generation in wind turbine device is a complex phenomenon with many other interacting
factors such as wind velocity, climate condition, natural disaster, rotor drag, turbulence flow, roughness and wind shear, etc.
Hence, there is a need for a more efficient and easier to use a system that could be employed in modeling such a complex
management of air flow mechanics. Various techniques have been proposed in the literature [7-9] to predict the wind power
by performing field testing, which could be expensive and time consuming as well as using theoretical data based on
assumptions. This in turn would affect the accuracy of the developed models in the prediction of wind power. To confront
this issue, researchers explored the use of neural network, genetic algorithms and so on, which have been used successfully
in numerous engineering fields [10-11]. In this regard, a fuzzy expert system (FES) has become a popular model that offers
nonlinear system, and it has the advantage of fuzzy experts not requiring a precise mathematical model. Therefore, the
inappropriate and inexact nature of the wind velocity-nonlinear system for a wind turbine could be effectively captured
using fuzzy logic, which is considered as a logical system closer to human knowledge and machine language [12].
Therefore, an integrated intelligent model for wind turbine power management scheme is proposed in this study by using an
adaptive neuro-fuzzy inference system (ANFIS). In this model, an artificial neural network is employed to develop the
fuzzy expert system in order to achieve a more realistic evaluation of wind power extraction. In addition, demonstration is
performed to investigate the effect of control strategy parameters on the system performance of the wind turbine and its
power extraction.