EUROPEAN TRANSACTIONS ON ELECTRICAL POWER Euro. Trans. Electr. Power 16:629–646 Published online 26 July 2006 in Wiley InterScience (www.interscience.wiley.com). DOI: 10.1002/etep.109 The application of neural network controller to power system with SMES for transient stability enhancement A. Demiro ¨ren* ,y , H. L. Zeynelgil and S. N. Sengo ¨r Istanbul Technical University, Electrical-Electronic Faculty, 80626 Istanbul, Turkey SUMMARY In this paper, a synchronous generator including power system stabilizer (PSS), voltage regulator, and governor is considered. This generator also has a superconducting magnetic energy storage (SMES) unit at its terminal bus. The investigation of the transient stability enhancement for the whole system is done using SMES unit and neural network (NN) controllers, while one of the controllers affects the mechanical input; the other affects the exciter input. Thus, non-linear power system control is provided by a control application of layered neural networks. The back propagation-through-time algorithm is used as a control rule for the NN controller. Copyright # 2006 John Wiley & Sons, Ltd. key words: power system; PSS; NN; SMES 1. INTRODUCTION Control and transient stability enhancement problem of generator has a major importance in power system investigations. As most papers in the literature mentioned, conventional controllers can disturb steady state operation although they provide sufficient regulation during transient phenomena [1–4]. The generators are equipped with high gain, fast acting automatic voltage regulators that enhance large- scale stability by keeping the generator synchronized with the power system during large transient fault conditions. An adverse effect of excitation system with the high gain causes a decrease in damping torque of generators, leading the system to oscillation instability [2]. The stabilizing methods such as power system stabilizer (PSS), static Var compensators (SVC), or phase shifter have been suggested for maintaining stability [1]. Sometimes, these methods alone are not sufficient to control the system oscillations. Recently, superconducting magnetic energy storage (SMES) is proposed to damp the system oscillations. Due to the development of the high-temperature superconductive materials, the SMES application to power systems is becoming an important issue in the electrical engineering. The SMES unit is developed to store electric power in the superconducting magnetic inductor. According to system power requirements, the power can be absorbed or released from the superconducting inductor. SMES unit can be applied for different cases such as load-frequency control, transmission line Copyright # 2006 John Wiley & Sons, Ltd. *Correspondence to: A. Demiro ¨ren, Istanbul Technical University, Electrical-Electronic Faculty, 80626 Istanbul, Turkey. y E-mail: aysen@triton.elk.itu.edu.tr