Power system stabilizer based on artificial neural network

Abstract

This paper describes a systematic approach for designing a self-tuning adaptive power system stabilizer (PSS) based on artificial neural network (ANN). An ANN is used for self-tuning the parameters of PSS e.g. stabilizing gain Kstab and time constant (T1) for Lead PSS in realtime. The inputs to the ANN are generator terminal active power (P) and reactive power (Q). Investigations are carried out to assess the dynamic performance of the system with self-tuning PSS based on ANN (ST-ANNPSS) over a wide range of loading conditions. The simulations are performed using Matlab/Simulink's neural network toolbox. The simulation and experimental results demonstrate the effective dynamic performance of the proposed system.