• Home
  • Search
  • Real-Time Control of A2O Process in Wastewater Treatment Through Fast Deep Reinforcement Learning Based on Data-Driven Simulation Model
  • Cite Icon16
  • https://doi.org/10.3390/w16243710Copy DOI Icon

Real-Time Control of A2O Process in Wastewater Treatment Through Fast Deep Reinforcement Learning Based on Data-Driven Simulation Model

  • Dec 22, 2024
  • Water
  • Fukang Hu +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Real-time control (RTC) can be applied to optimize the operation of the anaerobic–anoxic–oxic (A2O) process in wastewater treatment for energy saving. In recent years, many studies have utilized deep reinforcement learning (DRL) to construct a novel AI-based RTC system for optimizing the A2O process. However, existing DRL methods require the use of A2O process mechanistic models for training. Therefore they require specified data for the construction of mechanistic models, which is often difficult to achieve in many wastewater treatment plants (WWTPs) where data collection facilities are inadequate. Also, the DRL training is time-consuming because it needs multiple simulations of mechanistic model. To address these issues, this study designs a novel data-driven RTC method. The method first creates a simulation model for the A2O process using LSTM and an attention module (LSTM-ATT). This model can be established based on flexible data from the A2O process. The LSTM-ATT model is a simplified version of a large language model (LLM), which has much more powerful ability in analyzing time-sequence data than usual deep learning models, but with a small model architecture that avoids overfitting the A2O dynamic data. Based on this, a new DRL training framework is constructed, leveraging the rapid computational capabilities of LSTM-ATT to accelerate DRL training. The proposed method is applied to a WWTP in Western China. An LSTM-ATT simulation model is built and used to train a DRL RTC model for a reduction in aeration and qualified effluent. For the LSTM-ATT simulation, its mean squared error remains between 0.0039 and 0.0243, while its R-squared values are larger than 0.996. The control strategy provided by DQN effectively reduces the average DO setpoint values from 3.956 mg/L to 3.884 mg/L, with acceptable effluent. This study provides a pure data-driven RTC method for the A2O process in WWTPs based on DRL, which is effective in energy saving and consumption reduction. It also demonstrates that purely data-driven DRL can construct effective RTC methods for the A2O process, providing a decision-support method for management.

Similar Papers
  • PDF
  • Research Article
  • Citations5

Deep imitation reinforcement learning with expert demonstration data

  • Oct 31, 2018
  • The Journal of Engineering
  • Menglong Yi +3
  • Research Article
  • Citations50

CH4 emission and conversion from A2O and SBR processes in full-scale wastewater treatment plants

  • Jan 01, 2014
  • Journal of Environmental Sciences
  • Yan Liu +3
  • PDF
  • Research Article
  • Citations31

Exploiting Biofilm Characteristics to Enhance Biological Nutrient Removal in Wastewater Treatment Plants

  • Jul 27, 2022
  • Applied Sciences
  • Ncumisa Mpongwana +1
  • Research Article
  • Citations149

Life cycle assessment and economic efficiency analysis of integrated management of wastewater treatment plants

  • Nov 19, 2015
  • Journal of Cleaner Production
  • Wenhua Piao +4
  • Research Article
  • Citations119

Bioaerosols emission and exposure risk of a wastewater treatment plant with A2O treatment process

  • Nov 14, 2018
  • Ecotoxicology and Environmental Safety
  • Yunping Han +4
  • Research Article
  • Citations25

Deep learning based simulators for the phosphorus removal process control in wastewater treatment via deep reinforcement learning algorithms

  • Feb 06, 2024
  • Engineering Applications of Artificial Intelligence
  • Esmaeel Mohammadi +5
  • PDF
  • Research Article
  • Citations10

Sustainable Energy Management Benchmark at Wastewater Treatment Plant

  • Nov 21, 2021
  • Sustainability
  • Andrey Kiselev +5
  • Research Article
  • Citations127

Antibiotic resistant bacteria and genes in wastewater treatment plants: From occurrence to treatment strategies

  • Jun 06, 2022
  • Science of The Total Environment
  • Shengnan Li +4
  • PDF
  • Research Article
  • Citations6

Measurement report: Per- and polyfluoroalkyl substances (PFAS) in particulate matter (PM 10 ) from activated sludge aeration

  • Jun 13, 2025
  • Atmospheric Chemistry and Physics
  • Jishnu Pandamkulangara Kizhakkethil +3
  • Research Article
  • Citations13

Changes in the composition of bacterial communities and pathogen levels during wastewater treatment.

  • Aug 01, 2022
  • Environmental Science and Pollution Research
  • Shuangfei Li +6
  • Research Article
  • Citations72

The application of footprints for assessing the sustainability of wastewater treatment plants: A review

  • Sep 06, 2020
  • Journal of Cleaner Production
  • Ke-Hua Chen +6
  • Research Article
  • Citations91

Stepwise impact of urban wastewater treatment on the bacterial community structure, antibiotic contents, and prevalence of antimicrobial resistance

  • Sep 28, 2017
  • Environmental Pollution
  • Mingyu Wang +4
  • Research Article

Contribution Analysis of Life Cycle Assessment Factors for Potential Environmental Impact of Wastewater Treatment Process

  • Sep 30, 2018
  • Journal of the Korean Society of Urban Environment
  • Soongoo Kim +1
  • Research Article
  • Citations25

Fate processes of Parabens, Triclocarban and Triclosan during wastewater treatment: assessment via field measurements and model simulations.

  • May 08, 2021
  • Environmental Science and Pollution Research
  • Zi-Feng Zhang +6
  • Research Article
  • Citations5

OmniDRL: An Energy-Efficient Deep Reinforcement Learning Processor With Dual-Mode Weight Compression and Sparse Weight Transposer

  • Apr 01, 2022
  • IEEE Journal of Solid-State Circuits
  • Juhyoung Lee +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.