International Review of Automatic Control (I.RE.A.CO.), Vol. 5, N. 2 ISSN 1974-6059 March 2012 Manuscript received and revised February 2012, accepted March 2012 Copyright © 2012 Praise Worthy Prize S.r.l. - All rights reserved 179 Frequency Control of Isolated Network with Wind and Diesel Generators by Using Adaptive Artificial Neural Network Controller Syed Q. Ali 1 , Hany M. Hasanien 2 Abstract – Due to increasing interest in renewable energy applications, wind energy conversion systems have gained a lot of significance worldwide. Wind generators produce unpredictable output fluctuations which result in variations of the network frequency thereby affecting the power system. This results in a degraded power quality and restricts the penetration of wind energy, especially for microgrid or island network applications. This problem needs to be addressed to ensure the expansion of the wind energy component in the overall world energy mix. This paper addresses the aforementioned problem by the application of an adaptive artificial neural network (ANN) controller for controlling the frequency of an islanded network with a high penetration no storage wind diesel (HPNSWD) system. The proposed controller is validated by computer simulation analysis using MATLAB-Simulink. The effectiveness of the proposed controller is then compared with a PID controller. Copyright © 2012 Praise Worthy Prize S.r.l. - All rights reserved. Keywords: Adaptive Artificial Neural Network (ANN) Controller, Wind Turbine, Isolated Network, Network Frequency, High Penetration No Storage Wind Diesel (HPNSWD) System Nomenclature ANN Artificial Neural Network CAN Controller Area Network GTO Gate Turn Off PID Proportional, Integral and Derivative PLL Phase Locked Loop A Area covered by the rotor in meter squared (m 2 ) C Capacitance in Farad(F) C p Power coefficient K p Proportional gain K i Integral gain K d Derivative gain L Inductance in Henry (H) M Magnetizing inductance in Henry (H) P Power in Watts (W) T Electromagnetic torque in Newton meters (Nm) e(t) Error f Frequency in Hz f i Activation function of the ANN controller i Instantaneous current in Ampers (A) m(t) Controller output signal r Resistance in Ohms ( ) u Wind speed in meter per second (m/s) v Instantaneous voltage in Volts (V) w ij Weighting factor of the ANN neurons x j Input signal for each neuron of the ANN controller Step change in error for the ANN controller Wind turbine blade pitch angle in degrees ( o ) Tip speed ratio Air density in Kilogram per meter cubed (kg/m 3 ) Flux linkage in Weber (Wb) Electrical rotor speed in radians per second (rad/s) I. Introduction As a result of conventional energy sources consumption and increasing environmental concern, efforts have been made to generate electricity from renewable sources, such as wind, solar, biomass etc. Institutional support for wind energy sources, together with the wind energy potential and improvement of wind energy conversion technologies, has led to a fast development of wind power generation in recent years [1]-[3]. However, the frequency variation of power system due to wind generator output fluctuations is a serious problem. If installations of wind farms continue to increase, frequency control of power system by the main sources, that is, hydraulic and thermal power stations will be difficult in the near future, especially in an isolated network like a small island which has weak capability of power regulation. In such a case, the installation may be restricted even though it is a small wind farm. Though there is such a difficulty, an introduction of the wind energy utilization is much effective in an isolated power system, because main