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

被引：3

作者：

Hu C. ^{[1
]}

Qiao R. ^{[1
]}

Zhang Z. ^{[1
]}

Yan X. ^{[1
]}

Li M. ^{[2
]}

机构：

[1] School of Computer Science, China University of Geosciences, Wuhan

[2] California State University, Department of Computer Science, Fresno, 93740, CA

来源：

Complex System Modeling and Simulation | 2022年 / 2卷 / 03期

关键词：

evolutionary reinforcement learning; scheduling problem; water distribution network;

D O I：

10.23919/CSMS.2022.0014

中图分类号：

学科分类号：

摘要：

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. © 2021 TUP.

引用

页码：213 / 223

页数：10