Skip to main navigation Skip to search Skip to main content

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

  • National Institute of Technology Kurukshetra

Research output: Contribution to journalArticleScientificpeer-review

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.

Original languageEnglish
Pages (from-to)1730-1738
JournalInternational Journal of Ambient Energy
Volume43
Issue number1
DOIs
Publication statusPublished - 2022
MoE publication typeA1 Journal article-refereed

Funding

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

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 7 - Affordable and Clean Energy
    SDG 7 Affordable and Clean Energy

Keywords

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

Fingerprint

Dive into the research topics of 'Artificial neural network-based dynamic power management of a DC microgrid: a hardware-in-loop real-time verification'. Together they form a unique fingerprint.

Cite this