Real-time stability enhancement based on neural fuzzy networks and genetic algorithms

This papers presents an adaptive power system stabilizers (PSS) using an adaptive network based fuzzy inference systems (ANFIS) and the second version of non-dominated sorting genetic algorithms (NSGA-II). Firstly genetic algorithms are used to tune stabilizer parameters on a wide range of loading conditions to create a data base. Two eigenvalue-based objective functions are considered to place the closed-loop system eigenvalues in the D-shape sector. Then, ANFIS is employed to establish the relationship between these operating points and the corresponding stabilizer parameters. The proposed stabilizer has been tested by performing non linear simulations and eigenvalue analysis using single machine infinite bus (SMIB) model. The results show the effectiveness and the robustness of the proposed stabilizer to provide efficient damping in real-time.