Wide-Area-Based Adaptive Neuro-Fuzzy SVC Controller for Damping Interarea Oscillations

Abstract

Low-frequency interarea oscillation is a major problem in interconnected power systems with weak tie-lines that causes several stability problems if not damped. Fuzzy logic controller can generate human knowledge-based control rules to solve complex nonlinear problems. Unlike a neural network, fuzzy systems cannot learn from data, and it takes a long time to modify the membership functions. The adaptive neuro-fuzzy inference system (ANFIS) is a robust and intelligent system that integrates the capabilities of fuzzy logic and neural networks with several advantages such as adaptability, robustness, rapidity, and flexibility. In this paper, an ANFIS-based controller is proposed for controlling the reactive power provided by static var compensator to damp interarea oscillations. The controller input is a remote signal provided by a wide-area measurement system, and it is calculated as the center-of-inertia difference of generator rotor speed deviations. Moreover, a proportional-plus-derivative time-delay compensator with adaptive parameters is added to the controller to reduce the influence of time delay. A two-area four-machine test system is used and simulated with a Simulink-based package developed for the work of this paper. The time-domain simulations and frequency response analysis demonstrate the capability of the proposed controller to effectively damp interarea oscillations, under a small- and large-scale disturbances and against a wide range of time delays and load uncertainty.