Islanded micro-grid under variable load conditions for local distribution network using artificial neural network

This research proposes an intelligent artificial neural network (ANN) controller designed for a micro-grid featuring solar photovoltaic, wind, and Battery Energy Storage (BES) systems, integrated with a shunt voltage source converter. The primary goal of this proposed method is to minimize Total Harmonic Distortion (THD) and ensure a stable Distribution Line Commutation Voltage (DLCV) amidst load variations, achieving a rapid settling period. The STF not only facilitates phase synchronization but also effectively separates harmonic and fundamental components. This research contributes to advancing micro-grid control strategies, particularly in enhancing stability and reducing distortion during variable operating conditions. Based on an analysis of the four test cases, it is evident that the proposed strategy lowered the THDs to 4.63%, 3.45%, 3.05%, and 4.70% for each test case, as well as the PF to a level that was similar. The proposed controller shows better results compared with other controllers like Sliding Mode Controller (SMC) and the Proportional-Integral Controller (PIC).