An adaptive frame and intelligent control approach for an autonomous hybrid renewable energy technology consisting of PV, wind, and fuel cell innovation

The goal of this study is to look into a control approach for a micro-grid hybrid power conversion system that integrates multiple power sources and transformers to meet continuous load requirements under a variety of naturalistic settings. The study's key discoveries include the construction of an autonomous model with intelligent control methodologies, as well as a dynamic framework for a hybrid renewable energy system that includes photovoltaic (PV), fuel cells (FC), and wind turbines (WT). This study is unique in that it integrates alternate energy sources with FC devices using short- and long-term storage methods made possible by adaptive- intelligent power controllers. The research also focuses on improving mathematical and electrical models, which are developed in the MATLAB, Simulink, and Sim Power Systems environments. The study's key result is that an Adaptive Neuro-Fuzzy Inference System (ANFIS) is effective at adjusting load voltage in response to changing environmental and load conditions. In comparison to conventional Proportional-Integral-Derivative (PID) control, ANFIS reduces settling time by 68 %. In addition, when compared to an optimal PID controller based on the Cuckoo Search Algorithm (CSA), ANFIS reduces settling time by 60 %. In general, the study advances the area by presenting an intelligent control method for optimizing the performance of hybrid renewable energy systems, increasing efficiency, and minimizing settling time using ANFIS-based control mechanisms.