PSS Design Using Adaptive Recurrent Neural Network Controller

This paper presents an adaptive power system stabilizer (PSS) which consists of a recurrent neural network controller (RNNC) and a compensator to damp the oscillations of power system. The function of RNNC is to supply an adaptive control signal to the exciter or governor with the adaptive law, which can damp most of the power system´s oscillations. The function of compensator is to delete the extra disturbance or uncertainty. The principle and equation derivation of the adaptive neural network control PSS are introduced and analyzed. Simulations for the power system are demonstrated their performance and compare with the conventional PSS does.