Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published January 27, 2021 | Submitted
Report Open

Reinforcement Learning for Decision-Making and Control in Power Systems: Tutorial, Review, and Vision

Abstract

With large-scale integration of renewable generation and distributed energy resources (DERs), modern power systems are confronted with new operational challenges, such as growing complexity, increasing uncertainty, and aggravating volatility. Meanwhile, more and more data are becoming available owing to the widespread deployment of smart meters, smart sensors, and upgraded communication networks. As a result, data-driven control techniques, especially reinforcement learning (RL), have attracted surging attention in recent years. In this paper, we provide a tutorial on various RL techniques and how they can be applied to decision-making in power systems. We illustrate RL-based models and solutions in three key applications, frequency regulation, voltage control, and energy management. We conclude with three critical issues in the application of RL, i.e., safety, scalability, and data. Several potential future directions are discussed as well.

Additional Information

Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)

Attached Files

Submitted - 2102.01168.pdf

Files

2102.01168.pdf
Files (864.2 kB)
Name Size Download all
md5:ee6bab8684e3bd5ef4be0be122429e8d
864.2 kB Preview Download

Additional details

Created:
August 20, 2023
Modified:
August 20, 2023