ANN-BASED STATIC SYNCHRONOUS COMPENSATOR FOR IMPROVING TRANSIENT STABILITY PERFORMANCE

Abstract

Static synchronous compensator (STATCOM) is a shunt connected voltage source converter (VSC), which can affect rapid control of reactive flow in the transmission line by controlling the generated a.c. voltage. The main aim of the paper is to design artificial neural network (ANN) based STATCOM for power system damping. The proposed controllers are designed to coordinate two control inputs, voltage of the injection bus and capacitor voltage of the STATCOM, to improve the transient stability of a single machine infinite bus (SMIB) system and multi-machine system. The three different STATCOM controllers namely: (1) conventional PI controller (PI), (2) multilayer feed forward network (MFFN) based controller and (3) radial basis function network (RBFN) are considered for their comparative studies. The ANN models are trained by the voltage of injection bus and capacitor voltage. The proposed controllers are tested under various system conditions. The power oscillation damping (POD) control and power system stabilizer (PSS), and their coordinated action with proposed controllers are tested. The simulation results show that the proposed controller provides satisfactory performance in terms of improvements of transient stability of the system. The results indicate that the coordinated POD and PSS action further improves the dynamic performance of the system. The RBFN-based STATCOM controller provides superior dynamic performance than other controllers.