Adaptive Control of Three-Level UPQC via ANFIS for Enhanced Power Quality: A MATLAB/Simulink-Based Evaluation

Abstract

This paper presents a comprehensive study of a three-level Unified Power Quality Conditioner (UPQC) controlled by Adaptive Neuro-Fuzzy Inference System (ANFIS) and its simulation in MATLAB/Simulink. The UPQC is designed to enhance power quality by simultaneously mitigating voltage sags, swells, and harmonic distortions while providing voltage regulation. The proposed ANFIS controller leverages the advantages of both fuzzy logic and neural networks, allowing for adaptive learning and improved performance in dynamic environments. Simulation results demonstrate the effectiveness of the ANFIS controller in comparison to traditional Proportional-Integral (PI) and fuzzy controllers. Key performance metrics, including response time, settling time, and steady-state error, are evaluated across various operating conditions. The findings indicate that the ANFIS-controlled UPQC outperforms both the PI and fuzzy controllers in terms of rapid response and robustness, making it a promising solution for advanced power quality management in modern electrical systems. This research contributes to the growing body of knowledge on intelligent control strategies for power quality enhancement, emphasizing the potential of ANFIS in improving the performance of UPQC systems.