Photovoltaic power prediction for solar micro-grid optimal control

In a solar micro-grid, hybrid renewable energy system generates electricity for building’s onsite use. The battery storage and the main power grid connection are used to facilitate matching between demand production. To control flows optimally, an accurate day-ahead prediction of photovoltaic (PV) panels output is required. However, this challenging task due fluctuating nature radiation availability. accuracy influenced by modelling method input parameters. study, measured weather data gathered from experimental installation PV predict 24-hours horizon in 15 min intervals. multiple linear regression (MLR) artificial neural network (ANN) methods considered compared using performance indicators. micro-inverter technology gather individual panel addition overall output. results show that have different performances ANN model built with highest accuracy. Utilizing leads advantage having more purpose.