Reinforcement Learning\unicodex2013Based Transient Response Shaping for Microgrids

2022/07/11 by Venkataramanan, Ashwin, Mehrizi-Sani, Ali
#FOS: Electrical engineering #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2207.05020

Abstract

This work explores the usage of a supplementary controller for improving the transient performance of inverter\unicodex2013based resources (IBR) in microgrids. The supplementary controller is trained using a reinforcement learning (RL)\unicodex2013based algorithm to minimize transients in a power converter connected to a microgrid. The controller works autonomously to issue adaptive, intermediate set points based on the current state and trajectory of the observed or tracked variable. The ability of the designed controller to mitigate transients is verified on a medium voltage test system using PSCAD/EMTDC.

Related

• A Reinforcement Learning Approach for Fast Frequency Control in Low-Inertia Power Systems
• Deep Reinforcement Learning for Optimizing Inverter Control: Fixed and Adaptive Gain Tuning Strategies for Power System Stability
• Offline Reinforcement Learning for Microgrid Voltage Regulation
• Adaptive Intelligent Secondary Control of Microgrids Using a Biologically-Inspired Reinforcement Learning
• SAVER: Safe Learning-Based Controller for Real-Time Voltage Regulation