Power systems damping enhancement by a hybrid neuro-fuzzy SVC stabilizers

摘要

An adaptive network based fuzzy inference system (ANFIS) for SVC stabilizer is presented in this paper to improve the damping of power systems in the presence of load model parameters uncertainty. This control method is shown to offer a better damping. It is widely known that Static Var compensator (SVC) stabilizers traditionally assume that the system loads are voltage dependent with fixed parameters, however, the load parameters are generally uncertain. This uncertain behavior of load parameters can de-tune the stabilizer gain-settings; consequently SVC stabilizer with fixed gains can be adequate for some load parameters but contrarily reduce system damping and contribute to system instability with loads having othe parameters. Takagi and Sugeno's fuzzy if-then rules and an adaptive feed-forward neural network with superivsed learning capability are used in the ANFIS. The proposed ANFIS is trained over a wide range of typical load parameters in order to adapt the gains of the SVC stabilizer. A MATLAB computer simulation is used to show the effectiveness of the proposed ANFIS SVC stabilizer. The simulation results show that the tuned gains of the SVC stabilizer using the ANFIS can provide better damping that the conventional fixed-gains SVC stabilizer.