An online adaptive PID-PSS based on RBF neural network identifier

The Fixed-Gain PID (FG-PID) controller based Power System Stabilizers (PSS) cannot be flexible enough to damp the low-frequency power system oscillations. In order to overcome the problem, an Online Adaptive PID (OLA-PID) controller is developed for power system stability enhancement. The OLA-PID controller parameters are updated based on the information provided by the Radial Basis Function Neural Network (RBFNN) identifier. Meanwhile, Particle Swarm Optimization (PSO) algorithm is used to obtain appropriate initial parameters of the RBFNN identifier. Using the optimized initial parameters, the RBFNN online identifier provides a dynamic model of controlled plant and updates the OLA-PID controller parameters. Simulation results on a single machine infinite bus power system demonstrate that the proposed stabilizer performs well in damping and quicker response when compared with the FG-PID controller.