ADAPTIVE FUZZY–ANN CONTROL STRATEGY FOR ENHANCING VOLTAGE STABILITY IN REMOTE SOLAR–BATTERY MICROGRIDS

The growing penetration of renewable energy sources into isolated microgrid frameworks necessitates advanced control methodologies capable of ensuring dependable voltage stability and superior power quality.This research introduces an adaptive fuzzy-artificial neural network (Fuzzy-ANN) control approach specifically designed for voltage regulation within a solar-battery based microgrid operating in remote settings, devoid of auxiliary grid support.The proposed strategy harmonises the interpretive nature of fuzzy logic with the adaptive learning faculties of artificial neural networks, thereby enabling real-time adjustment of control parameters in response to dynamic fluctuations in load profiles, solar irradiance, and battery state-of-charge.Through rigorous simulation analyses, the adaptive Fuzzy-ANN controller is demonstrated to effectively mitigate voltage instabilities such as sags and swells, whilst concurrently reducing total harmonic distortion at the point of common coupling.Moreover, when subjected to comparative scrutiny against conventional proportional-integral and standalone fuzzy schemes, the proposed controller exhibits superior transient response, diminished steady-state errors, and heightened operational reliability.The empirical evidence affirms the potential of this intelligent control architecture to enhance both resilience and stability within remote microgrid environments reliant upon inherently intermittent renewable energy sources, thus contributing meaningfully towards the broader pursuit of sustainable and autonomous energy systems.