Power System Stabilizer for Multi-Machine Using Genetic Algorithms Based on Recurrent Neural Network

This paper presents a novel approach to combine genetic algorithm (GA) with a new recurrent neural network (RNN) to design a genetic algorithm based on recurrent neural networks power system stabilizer (GARNNPSS) for multi machine power system. The GARNNPSS consists of a recurrent neural network identifier (RNNI) that tracks and identifies the power generator and a recurrent neural network controller (RNNC) that supplies an adaptive signal to the governor and exciter to damp the power system oscillation. Both RNNI and RNNC are firstly trained offline by GA to find the optimal learning rates, and then online to damp the oscillations of multi-machine power system. The proposed GARNNPSS is simulated for three-generator power system. The simulation results demonstrate the effectiveness of the proposed GARNNPSS and its optimal performance. The operating range of the proposed control scheme was demonstrated as better than that of the conventional PSS.