Optimal control towards sustainable wastewater treatment plants based on multi-agent reinforcement learning
文献类型：期刊论文
| 作者 | Chen, Kehua; Wang, Hongcheng ; Valverde-Perez, Borja; Zhai, Siyuan; Vezzaro, Luca; Wang, Aijie
|
| 刊名 | CHEMOSPHERE
 |
| 出版日期 | 2021-09 |
| 卷号 | 279页码:- |
| 关键词 | Wastewater treatment Reinforcement learning Multi-objective optimization Sustainability |
| ISSN号 | 0045-6535 |
| 英文摘要 | Wastewater treatment plants (WWTPs) are designed to eliminate pollutants and alleviate environmental pollution resulting from human activities. However, the construction and operation of WWTPs consume resources, emit greenhouse gases (GHGs) and produce residual sludge, thus require further optimization. WWTPs are complex to control and optimize because of high non-linearity and variation. This study used a novel technique, multi-agent deep reinforcement learning (MADRL), to simultaneously optimize dissolved oxygen (DO) and chemical dosage in a WWTP. The reward function was specially designed from life cycle perspective to achieve sustainable optimization. Five scenarios were considered: baseline, three different effluent quality and cost-oriented scenarios. The result shows that optimization based on LCA has lower environmental impacts compared to baseline scenario, as cost, energy consumption and greenhouse gas emissions reduce to 0.890 CNY/m(3)-ww, 0.530 kWh/m(3)-ww, 2.491 kg CO2-eq/m(3)-ww respectively. The cost-oriented control strategy exhibits comparable overall performance to the LCA-driven strategy since it sacrifices environmental benefits but has lower cost as 0.873 CNY/m(3)-ww. It is worth mentioning that the retrofitting of WWTPs based on resources should be implemented with the consideration of impact transfer. Specifically, LCA-SW scenario decreases 10 kg PO4-eq in eutrophication potential compared to the baseline within 10 days, while significantly increases other indicators. The major contributors of each indicator are identified for future study and improvement. Last, the authors discussed that novel dynamic control strategies required advanced sensors or a large amount of data, so the selection of control strategies should also consider economic and ecological conditions. In a nutshell, there are still limitations of this work and future studies are required. (C) 2021 Elsevier Ltd. All rights reserved. |
| WOS研究方向 | Environmental Sciences |
| 源URL | [http://ir.rcees.ac.cn/handle/311016/46138]  |
| 专题 | 生态环境研究中心_中国科学院环境生物技术重点实验室 |
| 作者单位 | 1.Chinese Acad Sci, Res Ctr Ecoenvironm Sci, Key Lab Environm Biotechnol, 18 Shuangqing Rd, Beijing 100085, Peoples R China 2.Harbin Inst Technol Shenzhen, Sch Civil & Environm Engn, Shenzhen 518055, Peoples R China 3.Harbin Inst Technol, State Key Lab Urban Water Resource & Environm, Harbin 150001, Peoples R China 4.Tech Univ Denmark, DTU Environm, Bldg 115, DK-2800 Lyngby, Denmark 5.Univ Chinese Acad Sci, Sino Danish Ctr Educ & Res, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chen, Kehua,Wang, Hongcheng,Valverde-Perez, Borja,et al. Optimal control towards sustainable wastewater treatment plants based on multi-agent reinforcement learning[J]. CHEMOSPHERE,2021,279:-. |
| APA | Chen, Kehua,Wang, Hongcheng,Valverde-Perez, Borja,Zhai, Siyuan,Vezzaro, Luca,&Wang, Aijie.(2021).Optimal control towards sustainable wastewater treatment plants based on multi-agent reinforcement learning.CHEMOSPHERE,279,-. |
| MLA | Chen, Kehua,et al."Optimal control towards sustainable wastewater treatment plants based on multi-agent reinforcement learning".CHEMOSPHERE 279(2021):-. |
入库方式： OAI收割
来源：生态环境研究中心
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。