Hybrid-neuro-fuzzy UPFC for improving transient stability performance of power system

This article presents a new technique of combining the advantages of both conventional proportional and integral (PI) controller with a radial basis function neural network (RBFNN) with Takagi-Sugeno (TS) fuzzy updating of its parameters. The error is given as input to the RBFNN, which in turn outputs a modified error to be used by the PI controller. This control scheme is used for controlling the series voltage injection through unified power flow controller (UPFC) to improve the modal oscillations of a multi-machine power system. Further, a new local auxiliary signal derived from phase angle difference across the UPFC series transformer is added to the real power error to improve the damping performance. This eliminates the need of generator speed mostly used for improving modal oscillation damping. Besides, all the machines are being equipped with conventional power system stabilizer (PSS) to study the coordinated effect of UPFC and PSS in the system. Digital simulation of a four machine power system subjected to a wide variety of disturbances validates the efficiency of the new approach.