Back to Search
Start Over
Optimal control towards sustainable wastewater treatment plants based on multi-agent reinforcement learning
- Source :
- Chen, K, Wang, H, Valverde Pérez, B, Zhai, S, Vezzaro, L & Wang, A 2021, ' Optimal control towards sustainable wastewater treatment plants based on multi-agent reinforcement learning ', Chemosphere, vol. 279, 130498 . https://doi.org/10.1016/j.chemosphere.2021.130498
- Publication Year :
- 2020
- Publisher :
- arXiv, 2020.
-
Abstract
- 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/m3-ww, 0.530 kWh/m3-ww, 2.491 kg CO2-eq/m3-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/m3-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.
- Subjects :
- Signal Processing (eess.SP)
FOS: Computer and information sciences
reinforcement learning
Environmental Engineering
Computer Science - Artificial Intelligence
Health, Toxicology and Mutagenesis
0208 environmental biotechnology
Environmental pollution
02 engineering and technology
Wastewater treatment
Systems and Control (eess.SY)
010501 environmental sciences
Environment
Wastewater
01 natural sciences
Multi-objective optimization
Electrical Engineering and Systems Science - Systems and Control
Waste Disposal, Fluid
Water Purification
Greenhouse Gases
FOS: Electrical engineering, electronic engineering, information engineering
Environmental Chemistry
Retrofitting
Reinforcement learning
Humans
SDG 7 - Affordable and Clean Energy
Electrical Engineering and Systems Science - Signal Processing
Baseline (configuration management)
Oxygen saturation
0105 earth and related environmental sciences
Pollutant
Public Health, Environmental and Occupational Health
General Medicine
General Chemistry
Energy consumption
Environmental economics
Eutrophication
sustainability
Pollution
020801 environmental engineering
Artificial Intelligence (cs.AI)
multi-objective optimization
Greenhouse gas
Sustainability
Environmental science
Sewage treatment
SDG 12 - Responsible Consumption and Production
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Chen, K, Wang, H, Valverde Pérez, B, Zhai, S, Vezzaro, L & Wang, A 2021, ' Optimal control towards sustainable wastewater treatment plants based on multi-agent reinforcement learning ', Chemosphere, vol. 279, 130498 . https://doi.org/10.1016/j.chemosphere.2021.130498
- Accession number :
- edsair.doi.dedup.....f00bb0a2e1520522b3e051bb11c842da
- Full Text :
- https://doi.org/10.48550/arxiv.2008.10417