Genetically Optimized Neuro-Fuzzy IPFC for Damping Modal Oscillations of Power Systems

An integrated approach of the radial basis function neural network (RBFNN) and Takagi-Sugeno (TS) fuzzy scheme with genetic optimization of their parameters has been developed in this paper to design intelligent adaptive controllers for improving the transient stability performance of power system. At the outset this concept is applied to a simple device such as the thyristor controlled series capacitor (TCSC) connected in a single-machine infinite bus power system and is then extended to the interline power flow controller (IPFC) connected in a multimachine power system. The RBFNN uses single neuron architecture and its parameters are dynamically updated in an online fashion with the TS-fuzzy scheme designed with only four rules and triangular membership function. The rules of the TS-fuzzy scheme are derived from the real or reactive power error and their derivatives either at the TCSC or IPFC buses depending on the device. Further, to implement this combined scheme only one coefficient in the TS-fuzzy rules needs to be optimized. The optimization of this coefficient, as well as the coefficient for auxiliary signal generation, is performed through genetic algorithm. The performance of the new controller is evaluated both in single-machine and multimachine power systems subjected to various transient disturbances. The new genetic-neuro-fuzzy control scheme exhibits a superior damping performance as well as a greater critical clearing time in comparison to the existing PI as well as RBFNN controller with updating of its parameters through the extended Kalman filter (EKF).