Two-stage voltage regulation in power distribution system using graph convolutional network-based deep reinforcement learning in real time

•A two-stage voltage regulation framework is proposed to alleviate voltage violations.•A mixed-integer second order cone optimization programming (MISOCP) model is proposed for day-head hourly voltage regulation.•A graph reinforcement learning (GRL) method is novelty proposed for intraday voltage re...

Celý popis

Podrobná bibliografia

Vydané v:	International journal of electrical power & energy systems Ročník 151; s. 109158
Hlavní autori:	Wu, Huayi, Xu, Zhao, Wang, Minghao, Zhao, Jian, Xu, Xu
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier Ltd 01.09.2023
Predmet:	Deep deterministic policy gradient Graph convolutional network Reinforcement learning Renewable energy Voltage regulation Deep deterministic policy gradient Graph convolutional network Renewable energy Voltage regulation Reinforcement learning
ISSN:	0142-0615, 1879-3517
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!