INTERNATIONAL JOURNAL OF TECHNOLOGY ENHANCEMENTS AND EMERGING ENGINEERING RESEARCH, VOL 4, ISSUE 4 14 ISSN 2347-4289 Copyright © 2016 IJTEEE. Ann Based Mrac Controller For Transient Stability Enhancement Of Smib Dr. Majli N. Hawas, Dr. Raaed K. Ibrahim, Ahmed J. Sultan Department of Electrical Power Engineering Technique, College of Electrical & Electronic Engineering Techniques, Baghdad, Iraq; Department of Computer Engineering Technique, College of Electrical & Electronic Engineering Techniques, Baghdad, Iraq; Department of Electrical Power Engineering Technique, College of Electrical & Electronic Engineering Techniques, Baghdad, Iraq, ABSTRACT: In this paper, an artificial neural network ANN is presented to enhance the transient stability of a single machine infinite bus based on model reference adaptive controller MRAC. Critical clearing time CCT is a main factor in analysis of transient stability that indicates of maximum permissible time period of fault in power system. Increment value of CCT has important issue to improve system stability. The simulation results using MATLAB / SIMULINK package show that the proposed ANN-MRAC can dramatically improve the dynamic system behavior and force the system to track the reference model and reduce the error between them. The comparison between conventional Range-Kutta method and the ANN-MRAC is demonstrated that the proposed controller scheme is increasing of CCT and damping of electromechanical power oscillations. Keywords: Transient Stability; Model Reference Adaptive Control; single Machine to Infinite Bus; Neural Network. 1. INTRODUCTION: Present the increasing demand of electricity has significantly increment and power systems reconstruction make system work closer to their stability limits. Transient stability involves the response to large disturbance and is associated with appreciable change of rotor speeds, power angle and power transformer. System response to such a disturbance is usually considered within one second [1, 2]. Recently sophistication and complexities of the control of nonlinear systems has been an important research area due to the difficulties in modeling and nonlinearities. Adaptive control is one of the widely approach of control schemes to deal with nonlinear system. MRAC is point out to certain class of adaptive systems. In this class, the controller is designed to achieve system output converges to reference model output having the same reference input. Recently, an ANN has broad opportunities for identification, estimation, and control due to their ability to process the higher mathematical rate like nonlinear functions. The ANN application in power system stability has been taken a wide research area which has fast and parallel data processing, highly accurate solution. Many reports were published on TSA, in references [3- 5] were used an artificial intelligent techniques including FACTs devices to assess of transient stability for SMIB. In this work, the ANN-MRAC was used to improve transient stability of SMIB through increasing of CCT of system. 2. MODELING OF SMIB: Figure (1) shows that a SMIB system used to demonstrate the fundamental concepts and the principles of transient stability when subject into disturbance. The equation of motion or the swing equation describing the SMIB system is as below [1, 2]: ʹ                    (1) Where: P : Mechanical power input, in pu. P is the generator's electrical power output P  : Maximum electrical power input, in pu. H: Inertia constant, in MW.S/MVA. δ: Rotor angle, in electrical rad. t: Time, in sec. D: Coefficient of damping power. Equation (1) may be written in terms of the two first-order equations:               (2)      (3) Any of the numerical integration may be used to solve equations 2 and 3. In this paper we used fourth-order Runge-Kutta (R-K) method [1, 2]. The general formula giving the values of w ,δ and t for the (n+1) first step of integration are as follows:        (4)       (5)      (6) Where:      (7)       (8) Figure 1: Single line diagram of SMIB