A novel power system stabilizer based on neural network inverse system

A novel power system stabilizer (PSS) based on the neural network α-th order inverse system (called NNIPSS) is proposed in this paper. The reversibility of an excitation system with PSS in power systems is proved firstly. Then with the power angle of the generators as the output variable, the structure of the NNIPSS is given. The designing and training methods of the neural network inverse system are described in detail. In order to improve the dynamic performance and robustness of the neural network inverse system, a fuzzy-PID controller is employed. Simulations of one machine infinite bus system show that the proposed NNIPSS can provide better performances and robustness compared with a conventional PSS (CPSS).