Design of a power system stabilizer using a new recurrent neural network

This paper presents a new two-layer recurrent neural network, (RAW) for the power system stabilizer (PSS) design, which is called the recurrent neural network power system stabilizer (RNNPSS) in order to damp the oscillations of the power system. The RNNPSS consists of a recurrent neural network identifier (RNNI), and a recurrent neural network controller (RNNC). The RAW consists of an input layer and an output layer. Each neuron in the input layer is a recurrent one which is connected to oneself and other neurons, and then connected to the output layer. The simulation results demonstrate that the effectiveness of the proposed RNNPSS and reduce its sensitivity to system disturbances.