Dimensions of superiority: How deep reinforcement learning excels in urban drainage system real-time control
Reducing combined sewer overflows and flooding is crucial for the efficient operation of urban drainage systems. Traditional real-time control (RTC) methods often fall short in efficiency and performance, which prompts the exploration of innovative approaches. Deep reinforcement learning (DRL) has r...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Water Research X |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S258991472500012X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823864276203339776 |
|---|---|
| author | Zhenyu Huang Yiming Wang Xin Dong |
| author_facet | Zhenyu Huang Yiming Wang Xin Dong |
| author_sort | Zhenyu Huang |
| collection | DOAJ |
| description | Reducing combined sewer overflows and flooding is crucial for the efficient operation of urban drainage systems. Traditional real-time control (RTC) methods often fall short in efficiency and performance, which prompts the exploration of innovative approaches. Deep reinforcement learning (DRL) has recently emerged as a promising technique to enhance RTC performance. This study evaluates the effectiveness of RTC using a multi-agent-based DRL approach. We developed a comprehensive evaluation framework incorporating multiple quantitative indicators, including control objectives, decision time, robustness, and adaptability. To validate our framework, we conducted a case study on an urban drainage system in Suzhou, China, analyzing 31 historical rainfall events. Our findings reveal that DRL can reduce flooding and overflow risks by 15.1 % to 43.5 % on average compared to conventional RTC methods. Additionally, DRL demonstrates superior efficiency, robustness, and adaptability. This study not only highlights the potential of DRL in urban drainage management but also provides insights into its broader application in enhancing the resilience of urban infrastructure systems. |
| format | Article |
| id | doaj-art-cd6c23f0e40c4b44ab0d9ced111728ac |
| institution | Kabale University |
| issn | 2589-9147 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Water Research X |
| spelling | doaj-art-cd6c23f0e40c4b44ab0d9ced111728ac2025-02-09T05:01:01ZengElsevierWater Research X2589-91472025-09-0128100313Dimensions of superiority: How deep reinforcement learning excels in urban drainage system real-time controlZhenyu Huang0Yiming Wang1Xin Dong2School of Environment, Tsinghua University, Beijing 10084, PR ChinaSchool of Environment, Tsinghua University, Beijing 10084, PR ChinaSchool of Environment, Tsinghua University, Beijing 10084, PR China; Environmental Simulation and Pollution Control State Key Joint Laboratory, School of Environment, Tsinghua University, Beijing 100084, PR China; Corresponding author.Reducing combined sewer overflows and flooding is crucial for the efficient operation of urban drainage systems. Traditional real-time control (RTC) methods often fall short in efficiency and performance, which prompts the exploration of innovative approaches. Deep reinforcement learning (DRL) has recently emerged as a promising technique to enhance RTC performance. This study evaluates the effectiveness of RTC using a multi-agent-based DRL approach. We developed a comprehensive evaluation framework incorporating multiple quantitative indicators, including control objectives, decision time, robustness, and adaptability. To validate our framework, we conducted a case study on an urban drainage system in Suzhou, China, analyzing 31 historical rainfall events. Our findings reveal that DRL can reduce flooding and overflow risks by 15.1 % to 43.5 % on average compared to conventional RTC methods. Additionally, DRL demonstrates superior efficiency, robustness, and adaptability. This study not only highlights the potential of DRL in urban drainage management but also provides insights into its broader application in enhancing the resilience of urban infrastructure systems.http://www.sciencedirect.com/science/article/pii/S258991472500012XUrban drainage systemsReal-time controlDeep reinforcement learningMulti-agentEvaluation framework |
| spellingShingle | Zhenyu Huang Yiming Wang Xin Dong Dimensions of superiority: How deep reinforcement learning excels in urban drainage system real-time control Water Research X Urban drainage systems Real-time control Deep reinforcement learning Multi-agent Evaluation framework |
| title | Dimensions of superiority: How deep reinforcement learning excels in urban drainage system real-time control |
| title_full | Dimensions of superiority: How deep reinforcement learning excels in urban drainage system real-time control |
| title_fullStr | Dimensions of superiority: How deep reinforcement learning excels in urban drainage system real-time control |
| title_full_unstemmed | Dimensions of superiority: How deep reinforcement learning excels in urban drainage system real-time control |
| title_short | Dimensions of superiority: How deep reinforcement learning excels in urban drainage system real-time control |
| title_sort | dimensions of superiority how deep reinforcement learning excels in urban drainage system real time control |
| topic | Urban drainage systems Real-time control Deep reinforcement learning Multi-agent Evaluation framework |
| url | http://www.sciencedirect.com/science/article/pii/S258991472500012X |
| work_keys_str_mv | AT zhenyuhuang dimensionsofsuperiorityhowdeepreinforcementlearningexcelsinurbandrainagesystemrealtimecontrol AT yimingwang dimensionsofsuperiorityhowdeepreinforcementlearningexcelsinurbandrainagesystemrealtimecontrol AT xindong dimensionsofsuperiorityhowdeepreinforcementlearningexcelsinurbandrainagesystemrealtimecontrol |