No Detail Found!

Deep reinforcement learning for control of microgrids: a review

Author(s)
Muhammad Waheed ul Hassan Department of Electrical Engineering and Technology, Government College University, Faisalabad/ Lahore GarrisoUniversity, Pakistan
Muhammad Farhan Department of Electrical Engineering and Technology, Government College University, Faisalabad/ Lahore GarrisoUniversity, Pakistan
Zahoor Ahmed Department of Control Engineering, Shanghai Jiao-tong University, China
Toseef Abid Department of Electrical Engineering and Technology, Government College University,Pakistan
Muhammad Saqib Ashraf Department of Electrical Engineering and Technology, Government College University, Pakistan
Muhammad Azeem Iqbal Department of Electrical Engineering and Technology, Government College University, Pakistan
Abstract
A Microgrid is widely recognized as a prominent solution to enhance the resilience and performance of distributed power systems. Microgrids offer a unique advantage in quickly incorporating distributed energy resources into the existing electrical networks. The unpredictable nature of distributed energy resources (DERs) makes it difficult to coordinate their activities, so control techniques are employed to bring them into synchronization. Recently techniques based on artificial intelligence have been applied to the problems that arise in the operation and control of the latest generation Microgrid. Machine learning and deep learning are two of the most commonly used techniques in artificial intelligence. Both of these approaches are effective in providing intelligent solutions to complex problems. This research aims to survey the latest strategies of control in microgrids using the deep reinforcement learning approach (DRL). Other techniques of artificial intelligence have already been reviewed extensively, but the use of DRL has increased in recent years. This survey paper aims to provide an overview of the current strategies for controlling Microgrids using DRL. It focuses on voltage control and frequency regulation with distributed, cooperative and multi-agent approaches.
Publication Details
Page(s) 8-23
Published Journal: Lahore Garrison University Research Journal of Computer Science and Information Technology, Volume: 6, Issue: 4, Year: 2022

Request the full text from PASTIC

Keywords
Control, Multi-Agents, Deep Reinforcement Learning Approach (DRL), Microgrids
0

Citations

0

Downloads

56

Views