Dataset for Comparative Evaluation and Enhancement of Fuzzy Logic-Based Battery Control in Microgrids Using Genetic Algorithm Optimization

Designing efficient control systems for microgrids involves not only handling non-linear dynamics but also optimizing control parameters to balance supply, demand, and storage under uncertain and variable conditions. This paper investigates a hybrid microgrid configuration composed of photovoltaic (PV) panels, a wind turbine, a battery energy storage system (BESS), and a grid connection with bidirectional energy exchange. The study is structured in two phases. In the first phase, a fuzzy logic controller (FLC) is implemented using previously established system parameters and tuned via Genetic Algorithm (FL-GA) to evaluate its effectiveness compared to other commonly used optimization strategies. In the second phase, the fuzzy control structure is enhanced through a redefinition of its input and output variables to improve decision-making accuracy and system responsiveness. Results indicate that the modified GA-tuned fuzzy controller achieves competitive performance, with improved robustness, better SOC use, and reduced reliance on grid imports.