Abstract
An adaptive neuro-fuzzy inference system (ANFIS) based supplementary Unified Power Flow Controller (UPFC) to superimpose the damping function on the control signal of UPFC is proposed. By using a hybrid learning procedure, the proposed ANFIS construct an input -output mapping based on stipulated input-output data pairs. The linguistic rules, considering the dependence of the plant output on the controlling signal are used to build the initial fuzzy inference structure. On the basis of linearized Philips-Hefron model of power system installed with UPFC, the damping function of the UPFC with various alternative UPFC control signals are investigated. In the simulations under widely varying operating conditions and system parameters, ANFIS based controller yields improved performance when compared with constant gain controller, based on phase compensation technique. To validate the robustness of the proposed technique, the approach is integrated to a multi-machine power system and the nonlinear simulation results are presented.