Abstract--This paper is a part of a research project to study the dynamics and control of horizontal axis wind turbines. The main objective of this work is to give contribution to the control problem of horizontal axis wind power plants using neural network. This work presents a new methodology to control wind power plants. It employs an adaptive neural networks self-tuning control system to control medium scale wind turbine system, during different operating conditions. The proposed control system consists of neural networks inverse and forward identifiers, which are used to model the inverse and forward dynamics of the system, respectively, and to adapt neural controller parameters, and reference model that are used to enhance trajectory training, and neural controller which is used to generate control signal to the pitch angle actuator. The proposed control system performed good simulation results, and the latter show that the proposed control system is really a new contribution in the area of control of horizontal axis wind turbine power generation systems. Keywords—Control, Identification, Neural Networks, Wind Turbine, Wind Power. I. INTRODUCTION The main sources of electric power have been fuel-burning power generators which use the energy from non-renewable fuels to rotate a shaft connected to an electric generator. These systems have seen vast improvements in the areas of efficiency, emissions, and controllability because they have always been the primary power sources. The integration of wind power into utility systems is an area that is attracting growing interest. The development of renewable natural energy has attracted considerable interest in recent years primarily due to concern about environment pollution caused by the burning of fossils, and its continually diminishing reserves [1]. Wind turbine generator system provides an environmentally friendly, economically, competitive and socially beneficial means of electricity generation. Much attention has been paid in recent times to the generation of clean energy. These natural and clean sources of energy need to have no by-products associated with their operation [2]. Wind energy is gaining momentum in this field of clean energy due to its relatively low cost. Wind turbines complement the use of other electric power sources by providing a least cost approach under certain conditions. In addition, wind turbines need minimum maintenance. The most special feature about wind turbines is the fact that, unlike other generation systems, the power inflow rate is not controllable [8]. In most generation systems, the fuel flow rate, or the amount of energy, applied to the generator controls the output voltage and frequency. The power fluctuates with the variation of winds. The fact that one has no control over the energy source input, the unpredictability of wind and the varying power demand are more than enough concerns to justify the need for a control system, which will regulate the parameters of the wind energy conversion system that need to be controlled for matched operation of the wind turbine. II. WIND TURBINE CHARACTERISTICS The kinetic energy, U of a parcel of air of mass m flowing at upstream speed u in the axial direction (x-direction) of the wind turbine is given by: 2 2 1 1 2 2 U mu Ax u (1) where, A is the cross–sectional (swept) area of the wind turbine in square meters, is the air density in kg/m3, and x is the thickness of the wind parcel in meters. The power in the wind P w , is the time derivative of the kinetic energy and is given in (2), which represents the total power available for extraction. 3 1 2 w P Au (2) As the wind passes over the turbine, the wind will lose power equal to the power extracted by the turbine. The extracted power is usually expressed in terms of the wind turbine swept area A, because the upstream cross-sectional area is not physically measurable as the cross-sectional area of the wind turbine. 3 3 , 2 1 2 1 8 2 16 1 2 9 3 27 2 w ideal P A u Au (3) The factor 16/27 = 0.59 is called Betz coefficient. It shows that an actual turbine cannot extract more than 59 percent of the total power in an undistributed tube of air of the same area (the cross-sectional area equal to the wind turbine swept area). The fraction of power P m extracted from the available power in the wind by practical turbines is expressed by the coefficient of performance C p . The actual mechanical power extracted can be written as: 3 1 2 m p p w P C Au CP (4) The value of Cp is highly non-linear and varies with the wind speed, the rotational speed of the turbine, and the turbine blade parameters such as pitch angle. The variable that combines the effects of the rotational speed and the wind speed is called tip speed ratio. The tip speed ratio , is defined as the ratio between the rectilinear speed of the turbine tip, t R, and the wind speed u as given in (5). NN Self-Tuning Pitch Angle Controller of Wind Power Generation Unit A. F. Bati, and S. K. Leabi 2019 142440178X/06/$20.00 ©2006 IEEE PSCE 2006