An online adaptive PSS based on RBF neural network identifier

The design of a conventional power system stabilizer (PSS) based on linearized model cannot guarantee its performance in practical operating, so some intelligent techniques have been used. However, the parameters cannot update online in most of these mehods, thus the performance cannot be further improved. This paper adopts the design method of adaptive neural-fuzzy based power system stabilizer (ANFPSS). It consists of two separate neural networks, namely radial basis function neural network (RBFNN) identifier and adaptive neuro-fuzzy controller (ANFC). Meanwhile, particle swarm optimization (PSO) algorithm is used to obtain appropriate initial parameters of the RBFNN identifier. Based on the optimized initial parameters, the RBFNN online identifier provides a dynamic model of controlled plant and updates the adaptive link weights of the ANFC. Simulation results on a single machine infinite bus power system demonstrate that the proposed stabilizer is effective in damping low-frequency oscillations as well as improving system dynamic stability. In addition, the proposed approach provides superior performance when compared to IEEE PSS2B. Key-Words: power system stabilizers, particle swarm optimization, neural network identifier, neuro-fuzzy controller.