Recurrent Neural Network Supplementary Stabilization Controller for Automatic Voltage Regulator and Governor

摘要

Excitation controllers such as automatic voltage regulators (AVRs) and power system stabilizers (PSSs) are normally installed on synchronous generators for improving electric power systems' transient stability. The PSS optimized by the genetic algorithm (GA) has a certain robustness. However, since the power system is nonlinear, drastic changes in the system caused by faults and circuit switching may cause control performance to become unsatisfactory. Then a method using a nonlinear neural network can be used to tune the control systems. This method of using neural networks has been reported in recent years. This paper presents a recurrent neural network (RNN) stabilization controller to improve the transient stability of power systems. The proposed controller is constructed by a three-layer (8-9-1) RNN, of which inputs are ΔP_e and Δ_ω. The weights of the proposed controller are adjusted online to maintain electrical output power deviation equal to zero. By applying the proposed controller, good damping characteristics over a wide range of operating conditions can be realized. The ability of the proposed controller has been investigated in a single-machine infinite-bus system.