Intelligent Energy Management with ANFIS Based Strategy for Enhancing Battery Performance

The rapid advancement of Renewable Energy Sources (RES) has enhanced their integration into modern power systems, but their inherent intermittency presents significant challenges. To address these fluctuations, Energy Storage Systems (ESS) are increasingly employed; however, managing the complex interactions between multiple RES, flexible loads, and ESS poses a substantial challenge for traditional rule-based control systems. This study evaluates the performance of the Adaptive Neuro-Fuzzy Inference System (ANFIS) in optimizing battery management, comparing it to conventional Fuzzy Logic Control (FLC). An ANFIS controller was designed to manage battery states-specifically charging, discharging, and floating—by leveraging critical input variables such as Battery State of Charge (BSoC), Power Demand (PD), and Generated Power (Pgen). The model exhibited remarkable adaptability through the iterative optimization of its membership functions and rules, in contrast to the static framework of traditional Fuzzy Logic Control (FLC). The obtained simulation outcomes demonstrate that ANFIS substantially outperforms FLC across essential performance in different metrics. The overall findings underscore the considerable potential of ANFIS in advancing adaptive control methodologies within energy systems, ultimately facilitating more efficient management of energy resources.