Fully Adaptive Recurrent Neuro-Fuzzy Control for Power System Stability Enhancement in Multi Machine System

Voltage instability in a power system produces low-frequency oscillations (LFOs), causing adverse effects distribution. Intelligent control schemes can overcome the limitations of fixed-parameter structures stabilizers (PSS). Flexible alternating current transmission (FACTS) along with some supplementary have remarkable potential damping oscillations. This paper proposes an adaptive neurofuzzy based recurrent wavelet (ANRWC) scheme to enhance stability. The proposed utilizes Gaussian as antecedent part’s membership function and consequent parts. Our uses gradient descent, adadelta, moment estimation (ADAM) proximal descent algorithms for optimization which parameters are updated using back-propagation algorithm. A multi-machine is used testing controller. We evaluate comparison conventional lead-lag takagi sugeno kang (ANFTSK) scheme. For comparison, we calculate performance indices (PIs) different controllers. Both quantitative qualitative evaluations assert effectiveness compared other schemes.