Design of a neural adaptive power system stabilizer using dynamic back-propagation method

A neural adaptive power system stabilizer (NAPSS) is described in this paper. The proposed structure consists of a neuro-identifier to track and identify the nonlinear plant in real-time, and a neuro-controller to damp the power plant oscillations. These two subnetworks are trained in an on-line mode utilizing the dynamic back-propagation method. The performance and effectiveness of the proposed controller are demonstrated by simulation studies for a variety of operating conditions and disturbances.