Deep learning and wbg devices combining to improve pv system efficiency: anfis-based mppt controller

Abstract

With the escalating demand for renewable energy sources, photovoltaic (PV) systems have emerged as a pivotal solution for sustainable power generation. The efficacy of these systems is paramount for their widespread implementation. This research article delves into the efficiency assessment of silicon carbide (SiC) components within a boost converter integrated into a PV system. Notably, the boost converter switch is under the intelligent control of an adaptive neuro-fuzzy inference system (ANFIS) based maximum power point tracking (MPPT) controller. This innovative approach leverages AI to optimize energy extraction from PV panels, thereby enhancing overall system efficiency. The cooperation of SiC components and AI-driven control presents a novel perspective on robust and efficient PV systems. To substantiate the research, data collected from the Sidi Bel-Abès PV central is utilized to train the ANFIS. The utilization of real-world data enhances the accuracy of the predictive model, thereby increasing its applicability to practical scenarios. Integrating AI technologies with PV systems marks a significant advancement toward intelligent and adaptive energy systems