Optimizing Hybrid Microgrids in Real-time: A Comparative Analysis of Two Reinforcement Learning Training Methods

Authors

  • khawaja Haider ali Electrical Engineering department, Sukkur IBA University,65200 Airport Road Sukkur, Pakistan
  • Mohammed Alharbi 2Department of Electrical Engineering, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia
  • Asif Ali Tahir Environment and Sustainability Institute (ESI), University of Exeter, Penryn Campus, Cornwall, TR10 9FE, United Kingdom

DOI:

https://doi.org/10.24949/njes.v16i2.757

Abstract

Reinforcement learning has been employed in recent research articles to optimize the energy storage system scheduling in microgrids, aiming to reduce overall system costs. However, applying reinforcement learning in real-time scenarios introduces uncertainties and delays due to the extensive training required to develop the optimal policy for the storage system. This work addresses these challenges and explores potential solutions for real-time dispatch control actions of the battery in a grid-tied microgrid. The study considers different approaches for training the agent, distinguishing between online and offline scheduling of the energy storage system. The limitations of these approaches and their implications on real-time performance are also analyzed. By developing a comprehensive microgrid model and comparing two training approaches, this research contributes to novel insights for efficient real-time scheduling of energy storage systems in grid-tied microgrids. The proposed approach presents a promising path towards addressing uncertainties and achieving optimal operation in grid-tied microgrids. In terms of average cost per year, the difference between the two approaches is 4% if foresight of the real data is perfect, otherwise the real-time approach is more cost-effective.

Author Biographies

Mohammed Alharbi, 2Department of Electrical Engineering, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia

 Mohammed Alharbi received the B.S. degree in electrical engineering from King Saud University, Riyadh, Saudi Arabia, in 2010, and the M.S. degree in electrical engineering from the Missouri University of Science and Technology, Rolla, MO, USA, in 2014, the Ph.D. degree in electrical engineering from the North Carolina State University, Raleigh, NC, USA, in 2020. He was a Teaching Assistant with King Saud University from September 2010 till May 2011. He was a project engineer at the Freedom Systems Center in the North Carolina State University, Raleigh, NC, USA from January 2016 till December 2019, where he was involved in designing and constructing a modular multi-level converter for control validations. In August 2020, he joined the Department of Electrical Engineering, King Saud University, Riyadh, Saudi Arabia, where he is currently an Assistant Professor. His research interests include medium voltage and high-power converters, modular multi-level converter (MMC) controls, multi-terminal HVdc systems, and grid integration of renewable energy systems

Asif Ali Tahir, Environment and Sustainability Institute (ESI), University of Exeter, Penryn Campus, Cornwall, TR10 9FE, United Kingdom

Prof. Asif Tahir received his PhD degree in Inorganic Chemistry from Quaid-I-Azam University Islamabad Pakistan in 2009.Currently he is Associate Professor and Director of Research in Renewable Energy at Department of Engineering, University of Exeter (UoE). He has secured research funding (>10m) as PI and CoI for various research projects. He is specialized in the fabrication of nanomaterials using state-of-the-art techniques for solar energy conversion and building energy efficiency. His research focus on energy material design, green hydrogen production, electrochemical energy storage, thermal energy storage, device characterisation and optimisation of device for high performance. He has published 115 peer-reviewed research papers in high impact journals and one book chapter. His publication has received an overall citation of 5630 and his h-index is 38

Downloads

Published

2023-11-05

Issue

Section

Engineering Sciences