International Journal of Electrical and Electronics Research ISSN 2348-6988 (online) Vol. 9, Issue 4, pp: (1-7), Month: October - December 2021, Available at: www.researchpublish.com
Neural Network and Its Application in Electric Power System Damping Controller: A Review Ade Elbani1, Rudy Gianto2 1,2
Department of Electrical Engineering, Tanjungpura University, Pontianak, Indonesia
Abstract: Neural network-based controller is one of the techniques of adaptive control. The adaptive controller is developed to overcome the shortcomings of the non-adaptive controllers. This control technique is very popular, and has been implemented in many important engineering applications. One important application of neural network-based controller is in the field of electrical power engineering, where the neural network-based controller concept has been employed to design the intelligent stabilizer for damping of power oscillation. This paper provides an overview on the neural network and its application in improving dynamic performance of an electrical power system. Keywords: Neural network, adaptive control, dynamic performance, damping, power system.
I. INTRODUCTION Interest in neural networks has made a comeback after a period of relative inactivity following the shortcomings of early neural networks (the single-layer perceptron), which was publicized in the late 1960s. The renewed interest was due, in part, to powerful new neural models, the multilayer perceptron and the feedback model of Hopfield, and to learning methods such as back-propagation; but it was also due to advances in hardware that have brought within reach the realization of neural networks with very large number of nodes [1]. The use of neural networks in control system can be seen as a natural step in the evolution of control methodology to meet new challenges. Looking back, the evolution in the control area has been fuelled by three major needs: the need to deal with increasing complex system, the need to accomplish demanding design requirement, and the need to attain these requirements with less precise advanced knowledge of the plant and its environment-that is, the need to control under increased uncertainty. Today, the need to control, in a better way, increasingly complex dynamical systems under significant uncertainty has led to a re-evaluation of the conventional control methods, and it has made the need for new methods quite apparent [1]. The application of neural networks in feedback control systems was first proposed by Werbos (1989). Since then, the neural networks control has been studied by many researchers. Recently, neural networks have entered the mainstream of control theory as a natural extension of adaptive control to systems that are nonlinear in the tuneable parameters. Therefore, it can be said that the neural network-based controller is one of the techniques of adaptive control. This adaptive controller is developed to overcome the shortcomings of the non-adaptive controllers. The non-adaptive (fixedparameter) controller is, in general, based on one particular system operating condition. The key disadvantage of this controller is that the possibility of the controller performance deterioration under other operating conditions. Furthermore, it is not possible to achieve maximum performance for each and every operating condition when the controller parameters are fixed. More recently, adaptive control techniques have been proposed to overcome the disadvantage of fixed-parameter controllers design. In this adaptive controller design, the controller parameters are determined online and adaptive to the changing in system operating conditions. This paper provides an overview on the neural network [2-8]. Previous works published in the area of adaptive damping controller designs using neural network-based controller concept are also presented in this paper [9-24].
Page | 1 Research Publish Journals