SPEED DEVIATION DRIVEN ADAPTIVE NEURAL-NETWORK-BASED POWER-SYSTEM STABILIZER

The paper presents an online adaptive artificial neural network (ANN) based power system stabilizer (PSS). The proposed controller is first trained offline using a pole placement based state feedback gain techn ique at different operating points. The trained ANN parameters (weight s and biases) are updated and tuned online using the speed deviation a s the reinforcement signal. The proposed PSS is tested at different op erating conditions and a variety of regulator gains. The digital resul ts validate the effectiveness and reliability of the new PSS in terms of fast system response under different loading conditions compared wi th the conventional PI controller and the modern control theory approa ch of pole placement.