Reinforcement Learning Model for Real Time Voltage Control in a Hybrid Microgrid

In contemporary hybrid microgrids that incorporate renewable energy sources like solar and wind, sustaining appropriate voltage levels is a significant difficulty due to the intermittent and variable characteristics of these power sources. Power quality concerns, particularly voltage variations, provide a significant challenge in hybrid (solar-wind) microgrid systems. This system requires real-time voltage regulation to operate efficiently and reliably. This work introduces an innovative method for real-time voltage regulation in a hybrid microgrid, employing a reinforcement learning (RL) model combined with HOMER software for simulation purposes. Real-time grid circumstances, including power generation and load demand, guide the reinforcement learning-based controller's voltage level adjustments. We can model complex interactions between renewable energy sources, battery storage, and grid loads using HOMER to mimic the microgrid's physical components and operating environment. Interaction with the simulated microgrid teaches the reinforcement learning model to maintain voltage stability, minimize power losses, and improve system efficiency. Real-time input lets the system adapt to renewable energy fluctuations and sudden demand swings. Simulation results demonstrate the effectiveness of the RL-based control strategy in improving voltage regulation compared to traditional control methods. The system shows enhanced resilience to disturbances and superior adaptability to variable renewable energy generation. This technology helps hybrid microgrids construct more advanced, self-learning control systems for dependability and energy efficiency. Its multi-agent system supports decentralized decision-making and efficient coordination of dispersed energy resources while accounting for generation and load dynamics uncertainty. This reduces voltage variations and improves system robustness. The results show that reinforcement learning can revolutionize hybrid microgrid real-time voltage regulation, improving energy system sustainability and efficiency.

Authors

Institutions

Publication Details

Published
2024-12-18
DOI
https://doi.org/10.1109/i-coste63786.2024.11025035
Primary Topic
Microgrid Control and Optimization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Reinforcement Learning Model for Real Time Voltage Control in a Hybrid Microgrid

R. Srimathi, A. Sahaya Sudha, P Renugadevi
Microgrid Control and Optimization
article

Reinforcement Learning Model for Real Time Voltage Control in a Hybrid Microgrid

R. Srimathi, A. Sahaya Sudha, P Renugadevi
article en

Abstract

In contemporary hybrid microgrids that incorporate renewable energy sources like solar and wind, sustaining appropriate voltage levels is a significant difficulty due to the intermittent and variable characteristics of these power sources. Power quality concerns, particularly voltage variations, provide a significant challenge in hybrid (solar-wind) microgrid systems. This system requires real-time voltage regulation to operate efficiently and reliably. This work introduces an innovative method for real-time voltage regulation in a hybrid microgrid, employing a reinforcement learning (RL) model combined with HOMER software for simulation purposes. Real-time grid circumstances, including power generation and load demand, guide the reinforcement learning-based controller's voltage level adjustments. We can model complex interactions between renewable energy sources, battery storage, and grid loads using HOMER to mimic the microgrid's physical components and operating environment. Interaction with the simulated microgrid teaches the reinforcement learning model to maintain voltage stability, minimize power losses, and improve system efficiency. Real-time input lets the system adapt to renewable energy fluctuations and sudden demand swings. Simulation results demonstrate the effectiveness of the RL-based control strategy in improving voltage regulation compared to traditional control methods. The system shows enhanced resilience to disturbances and superior adaptability to variable renewable energy generation. This technology helps hybrid microgrids construct more advanced, self-learning control systems for dependability and energy efficiency. Its multi-agent system supports decentralized decision-making and efficient coordination of dispersed energy resources while accounting for generation and load dynamics uncertainty. This reduces voltage variations and improves system robustness. The results show that reinforcement learning can revolutionize hybrid microgrid real-time voltage regulation, improving energy system sustainability and efficiency.

Vellore Institute of Technology University (IN)
Affordable and clean energy
Openalex Percentile: Top 62%
Microgrid Control and Optimization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.