Multi-Task Reinforcement Learning for Distribution System Voltage Control With Topology Changes
IEEE Transactions on Smart Grid · 2023-05 · 14 (3) · 2481-2484
DOI: 10.1109/tsg.2022.3233766 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Smart Grid, 2023-05. Verfasst von Yansong Pei und 3 weiteren Autor:innen. Die Arbeit wurde bisher 74-mal zitiert (Crossref) und nennt 12 Literaturangaben. Gefördert von: U.S. Department of Energy’s Solar Energy Technologies Office.
Abstract (Originalsprache)
This letter proposes a multi-task deep reinforcement learning (DRL) approach for distribution system voltage regulation considering topology changes via PV smart inverter control. The key idea is to encode the topology as an additional state for the DRL and leverage the multi-task learning scheme for joint learning of all task control policies. Unlike other DRL-based methods, our approach is robust to different topologies. Comparison results on the modified IEEE 123-node system demonstrate the enhanced robustness of the proposed method.
Förderung
- U.S. Department of Energy’s Solar Energy Technologies Office
Zitieren
APA
Pei, Y., Zhao, J., Yao, Y., & Ding, F. (2023). Multi-Task Reinforcement Learning for Distribution System Voltage Control With Topology Changes. IEEE Transactions on Smart Grid, 14(3), 2481-2484. https://doi.org/10.1109/tsg.2022.3233766
Vancouver
Pei Y, Zhao J, Yao Y, Ding F. Multi-Task Reinforcement Learning for Distribution System Voltage Control With Topology Changes. IEEE Transactions on Smart Grid. 2023;14(3):2481-2484. doi:10.1109/tsg.2022.3233766
BibTeX
@article{Pei2023,
author = {Pei, Yansong and Zhao, Junbo and Yao, Yiyun and Ding, Fei},
title = {Multi-Task Reinforcement Learning for Distribution System Voltage Control With Topology Changes},
journal = {IEEE Transactions on Smart Grid},
year = {2023},
volume = {14},
number = {3},
pages = {2481--2484},
doi = {10.1109/tsg.2022.3233766}
}
EUVIMED