Fuzzy Control System Design Using ANFIS for Power Systems with SVC

In this research, we designed a fuzzy control system using Adaptive Neuro-Fuzzy Inference System (ANFIS) for power systems equipped with Static Var Compensator (SVC). The primary objective is to enhance power system stability and performance while mitigating oscillations and instabilities through ANFIS optimization. ANFIS represents a hybrid approach combining fuzzy logic principles with neural network adaptability, enabling continuous learning and performance optimization for control systems. The implementation typically involves creating a multi-layer ANFIS architecture where: - Layer 1 generates membership functions for input variables - Layer 2 computes firing strengths for fuzzy rules - Layer 3 normalizes these firing strengths - Layer 4 implements adaptive nodes with linear functions - Layer 5 produces the final output through weighted summation By applying ANFIS to SVC control in power systems, we achieve more precise and intelligent regulation, significantly improving system responsiveness and stability. The ANFIS training process utilizes hybrid learning algorithms combining least-squares estimation with backpropagation gradient descent, allowing the system to automatically adjust membership function parameters and rule consequents. This research contributes innovative methodologies and techniques for power system control and optimization, potentially advancing the development of smart grid technologies through intelligent, adaptive control mechanisms. The ANFIS-SVC integration demonstrates practical implementation of machine learning techniques in power system stabilization, featuring real-time adaptability to changing grid conditions.