Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges
- Creators
-
Chen, Xin
-
Qu, Guannan
-
Tang, Yujie
-
Low, Steven
-
Li, Na
Abstract
With large-scale integration of renewable generation and distributed energy resources, 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. This paper provides a comprehensive review of various RL techniques and how they can be applied to decision-making and control in power systems. In particular, we select three key applications, i.e., frequency regulation, voltage control, and energy management, as examples to illustrate RL-based models and solutions. We then present the critical issues in the application of RL, i.e., safety, robustness, scalability, and data. Several potential future directions are discussed as well.
Additional Information
© 2022 IEEE. Manuscript received February 9, 2021; revised July 27, 2021 and November 17, 2021; accepted February 18, 2022. Date of publication February 25, 2022; date of current version June 21, 2022. This work was supported in part by NSF CAREER under Grant ECCS-1553407; in part by the NSF AI Institute under Grant 2112085; in part by NSF under Grant ECCS-1931662, Grant AitF- 1637598, and Grant CNS-1518941; in part by Cyber-Physical Systems (CPS) under Grant ECCS-1932611; in part by Resnick Sustainability Institute; in part by PIMCO Fellowship; in part by Amazon AI4Science Fellowship; and in part by the Caltech Center for Autonomous Systems and Technologies (CAST). Paper no. TSG-00195-2021.Attached Files
Accepted Version - 2102.01168.pdf
Files
Name | Size | Download all |
---|---|---|
md5:fdca7bda29e5a213b5790af0f35f0a75
|
3.5 MB | Preview Download |
Additional details
- Eprint ID
- 113762
- Resolver ID
- CaltechAUTHORS:20220307-188369000
- NSF
- ECCS-1553407
- NSF
- CBET-2112085
- NSF
- ECCS-1931662
- NSF
- CCF-1637598
- NSF
- CNS-1518941
- NSF
- ECCS-1932611
- Resnick Sustainability Institute
- PIMCO
- Amazon AI4Science Fellowship
- Center for Autonomous Systems and Technologies
- Created
-
2022-03-08Created from EPrint's datestamp field
- Updated
-
2022-07-12Created from EPrint's last_modified field
- Caltech groups
- Center for Autonomous Systems and Technologies (CAST), Resnick Sustainability Institute