An artificial neural network based power system stabilizer for multi-machine power system

An adaptive power system stabilizer (PSS) over a wide range of operating conditions and typical local load models is proposed, using an artificial neural network ANN. The PSS with fixed parameters, which improves the power system damping for one operating point, may become unsatisfactory for another one especially for a wide range of operating conditions and load models. To improve the damping of the system over a wide range of operating conditions, it is desirable to adapt the parameters of the PSS in real time, based on operating points and load models. In order to do this, on-line measurement of operating points and load model parameters are chosen as the input signals to the neural network. The outputs of the neural network are the desired parameters of the PSS. The neural network, once trained by a set of input-output patterns in the training set, can yield proper PSS parameters under any operating conditions and local load model. Simulation results show that the tuning parameters of the PSS using the ANN approach can provide better damping than a fixed-parameters PSS over a wide range of operating points and typical load models. The proposed PSS is implemented for a multi-machine system.