Enhancing Microgrid Performance through Hybrid Energy Storage System Integration: ANFIS and GA Approaches

Abstract

Modeling and stability analysis of a battery energy storage system in the Microgrid (MG) is critical for optimizing performance and efficiency and managing power safely and effectively. In this context, the contribution of this work is to propose the combined efforts of the hybrid energy storage system (HESS) including the photovoltaic (PV), fuel cell (FC), and battery to support the demand load. This article of the contribution is interfaced with the PV, FC, and battery with MG. To gain design evaluation, the method incorporates the phasor workable alternative from advanced power systems. In this direction, an adaptive neuro-fuzzy inference system (ANFIS) and Genetic Algorithm (GA) control strategies are applied to collect the system data in electrical power systems. The process of these data provides important information, and knowledge is the result of analyzing this information, which is a key driver to intelligent behavior or action. To conclude, the application of ANFIS in the HESS-MG system results in an injection value of 99.6% at the Single Line-to-Ground Faults Scenario (SLGFS), and the utilization of GA in the HESS-MG yields an injection value of 98.9% at the SLGFS. The reduction of voltage sag without the use of HESS-MG technology is 76.2%, respectively.