A novel power system stabilizer based on neural network inverse system

Abstract

A novel power system stabilizer (PSS) based on the neural networks /spl alpha/-th order inverse system (called NNIPSS) is proposed in this paper. The reversibility of excitation system with PSS in power systems is proved firstly. Then selecting the power angle as the output variable, the control structure of the NNIPSS is given and the sample selection and training methods of the neural network inverse system are described in detail. In order to improve the dynamics performance and robustness of the pseudo-linear system, a fuzzy-PID controller is employed. Simulations of one machine infinite bus system show the effectiveness of the NNIPSS.