Sensorless Control of DC Microgrid Based on Artificial Intelligence

Abstract

Nowadays, DC microgrids are preferred in the field of renewable energy. The autonomous DC microgrids aim to provide smooth power flow from renewables to loads. While satisfying certain load profiles and sustaining the power as the desired level, the control of power converters is considerable. To ascend the resilience of DC microgrids, battery storage systems (BSSs) are also used as a backup unit for supplying uninterrupted power. The main task of BSSs is to compensate for the lack of power when the load is higher than supplied power or store the surplus of power in case that the load demand is less than the extracted power. In other words, by draining and storing the power, BSSs help to increase the flexibility of the system and keep the main DC bus voltage within acceptable bounds. This study introduces artificial intelligence (AI)-based method to diminish the number of implemented sensors and control power converters without reducing efficiency. In this paper, artificial neural networks (ANNs) as a subset of AI are exploited. Diminishing the number of sensors in the control layer makes the system more reliable. To validate the effectiveness of the proposed system, phases of ANNs' simulations are performed in MATLAB/Simulink.