Reinforcement Learning Approach to Enhance Grid-Forming Control in Energy Systems
Lists
Only you see this
Abstract
Abstract— Integrating renewable energy sources and transitioning to low-inertia power systems requires innovative grid stability and resilience solutions. Grid-forming inverters (GFMs) are crucial in this shift, enabling voltage and frequency regulation in systems with diminishing synchronous machine-based inertia. As the complexities in this domain increase, controlling energy flows using conventional techniques becomes challenging. This paper reviews Reinforcement Learning (RL) applications and their transformative potential in tackling the dynamic complexities of modern power systems, focusing on virtual synchronous generator-based grid forming inverters (VSG-GFMI) control.
BibTeX
@inproceedings{zaki1996reinforcement,
author = {Mohammed J. Zaki and Haluk Gözde and M. Cengiz Taplamacıoğlu and Özgül Salor and Reyhan Akbarlı},
title = {{Reinforcement Learning Approach to Enhance Grid-Forming Control in Energy Systems}},
booktitle = {Scientific},
year = {1996},
doi = {10.58225/icetea.2024.62-67},
}Loading related content...