Electrical power system (EPS) is becoming more complex and non-linear due to its varying operating conditions. In order to keep EPS in the steady state condition, active power (P) or terminal voltage (Vt) and reactive power (Q) or frequency (f) must be controlled and maintained continuously. The response of the transient stability (terminal voltage) can be improved by adopting suitable controller as an additional voltage controller with the automatic voltage regulator (AVR) in the excitation system, whereas the dynamic stability (frequency deviations i.e 6ω) can be enhanced with governing system. In power system networks, low frequency oscillations have become a major concern for many years. In order to depress low frequency oscillation, the power system stabilizer (PSS) parameters must be adjusted when there are changes in power system network conditions. This paper presents the application of multilayer perceptron feed forward neural network (MLPFFNN) as a controller to tune PSS parameters for achieving better enhancement in stability. For training MLP neural network, real power (P) and reactive power (Q) of synchronous machine are chosen as the input signals and the output are the desired power network stabilizer parameters. The proposed controller is implemented as single machine connected at infinite bus (SMIB) and compared with conventional controllers using Matlab/Simulink. The results obtained show the promising results due to the improvement in terminal voltage (Vt) as well as frequency deviation (6ω).