Improvement of multimachine power system stability using adaptive PSS

The excitation controllers, such as automatic voltage regulator (AVR) and power system stabilizer (PSS) for improving electric power systems transient stability, have been installed on synchronous generators. A design procedure is shown for the controller parameter-tuning applying a genetic algorithm (GA). The PSS optimized by 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 an adaptive power system stabilizer (APSS) based on a recurrent neural network (RNN) to enhance the dynamic stability of a power system. The proposed APSS is applied in parallel with a conventional PSS (CPSS) to enhance the performance of power system stability. Both the APSS and CPSS is used for stabilizing signals. The APSS is constructed by a three-layered (8-9-1) RNN, of which inputs are DeltaP(e) and Deltaomega. The weights of APSS are adjusted online to maintain electrical output power deviation to zero. By applying the proposed APSS, good damping characteristics over a wide range of operating conditions can be realized. The ability of the proposed APSS has been investigated in a three-machine power system.