ISSN: 2319-5967 ISO 9001:2008 Certified International Journal of Engineering Science and Innovative Technology (IJESIT) Volume 3, Issue 1, January 2014 159 Neural Network based FACTS Controller for Enhancement of Power System Dynamic Stability Mithilesh Das, Dr. Ramesh Kumar, Rajib Kumar Mandal Abstract: This paper presents a Hybrid method for power system dynamic stability enhancement. Hybrid method consists of Interline Power flow Controller with RBFNN and Lead- Lag as a supplementary Controller. Here for Power system dynamic stability prospect low power frequency oscillation has been kept into the consideration. For modelling purposes SMIB System is being used and also for analysis purposes Phillip Heffron model of equivalent SMIB System has been used. Matlab Simulation provides the time domain analysis of the System. Keywords: IPFC, RBFNN, SMIB, Lead-Lag Controller and Phillip Heffron Model. I. INTRODUCTION Power systems are subjected to low frequency disturbances that might cause loss of synchronism and an eventual breakdown of entire system. The oscillations, which are typically in the frequency range of 0.2 to 3.0 Hz, might be excited by the disturbances in the system or, in some cases, might even build up spontaneously. These oscillations limit the power transmission capability of a network and, sometimes, even cause a loss of synchronism and an eventual breakdown of the entire system. For this purpose, Power system stabilizers (PSS) are used to generate supplementary control signals for the excitation system in order to damp these low frequency power system oscillations. The use of power system stabilizers has become popular in the form of POD controller. By the virtue of advancement in Technology FACTS controller replaces the Conventional Power System Stabilizer [1]. In this work, we deal with damping out the low power frequency oscillations. Small deviation (0.01 p.u.) in the mechanical power (Mechanical Torque) has been taken into consideration for the purposes of analysis. A model of Power System named as “Phillip- Heffron Model” has been implemented for the time domain analysis. An Interline Power Flow Controller (IPFC) has been used here as a FACTS controller. A Radial Basis Function Neural Network (RBFNN) controller and Lead- Lag controller have been used as supplementary controller for the FACTS controller. Result obtained from RBFNN based FACTS controller and Lead-Lag based FACTS controller are compared. II. POWER SYSTEM MODELLING Fig.1: Single Machine Infinite Bus installed with IPFC