Analysis of power system network using neural network

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