Artificial neural network-based dynamic power management of a DC microgrid: a hardware-in-loop real-time verification

Abstract

In this paper, the performance of a DC microgrid has been examined among photovoltaics modules, loads and hybrid energy storage system (HESS). The primary goal of this article is to construct and verify the proposed artificial neural network (ANN)-based control system for a DC microgrid (DCMG). To exploit the energy source maximum and to regulate the DC bus voltage of HESS, an ANN-based dynamic power management control system for a DCMG is proposed and implemented to manage power-sharing among photovoltaics, loads, hybrid battery and supercapacitor energy storage to address the demand–generation disparity. The proposed control strategy employed on DC microgrid with HESS has been simulated and compared with the existing techniques in Matlab^® environment. Furthermore, the results have been experimentally verified in hardware-in-loop (HIL) on OPAL-RT real-time simulator.

KEYWORDS:

• Artificial neural network (ANN)
• battery
• bidirectional DC/DC converter (BDDC)
• HESS
• supercapacitor (SC)

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The authors convey their heartfelt gratitude to MHRD, Government of India for offering financial support during this research study.