Dynamic Scheduling Algorithm Based on Evolutionary Reinforcement Learning for Sudden Contaminant Events Under Uncertain Environment

For sudden drinking water pollution event, reasonable opening or closing valves and hydrants in a water distribution network (WDN), which ensures the isolation and discharge of contaminant as soon as possible, is considered as an effective emergency measure. In this paper, we propose an emergency sc...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Complex System Modeling and Simulation Ročník 2; číslo 3; s. 213 - 223
Hlavní autoři:	Hu, Chengyu, Qiao, Rui, Zhang, Zhe, Yan, Xuesong, Li, Ming
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Tsinghua University Press 01.09.2022
Témata:	evolutionary reinforcement learning scheduling problem water distribution network
ISSN:	2096-9929, 2096-9929
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	For sudden drinking water pollution event, reasonable opening or closing valves and hydrants in a water distribution network (WDN), which ensures the isolation and discharge of contaminant as soon as possible, is considered as an effective emergency measure. In this paper, we propose an emergency scheduling algorithm based on evolutionary reinforcement learning (ERL), which can train a good scheduling policy by the combination of the evolutionary computation (EC) and reinforcement learning (RL). Then, the optimal scheduling policy can guide the operation of valves and hydrants in real time based on sensor information, and protect people from the risk of contaminated water. Experiments verify our algorithm can achieve good results and effectively reduce the impact of pollution events.
ISSN:	2096-9929 2096-9929
DOI:	10.23919/CSMS.2022.0014