Application of Lyapunov-based adaptive neural network upfc damping controllers for transient stability enhancement

Abstract

A Lyapunov-based adaptive neural network unified power flow controller (UPFC) is developed for improving transient stability of power systems. A simple UPFC dynamical model, composed of a controllable shunt susceptance on the shunt side and an ideal complex transformer on the series side, is utilized to analyze UPFC dynamical characteristics and control parameters. The corresponding energy function and the damping control strategy of a classical generator embedded with a UPFC is derived analytically. This energy-based damping control strategy can also be extended into the interconnected power systems by considering the associated two-machine equivalent model. In order to consider more detailed power system models and model uncertainty issues, we incorporate the adaptive recurrent neural network into our UPFC damping controller. This controller can be treated as neural network approximations of Lyapunov control actions in real time and can adjust the corresponding weights in the neural network by the built-in back propagation algorithm. Simulation results demonstrate that the proposed control strategy is very effective for suppressing power swing even under severe system conditions.