Flood mitigation in coastal urban catchments using real-time stormwater infrastructure control and reinforcement learning
| Autor: | Madhur Behl, Jonathan L. Goodall, Peter A. Beling, Cheng Wang, Arash Tavakoli, Arsalan Heydarian, Benjamin D. Bowes |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
reinforcement learning
Atmospheric Science 010504 meteorology & atmospheric sciences Stormwater Control (management) 0207 environmental engineering Information technology 02 engineering and technology Environmental technology. Sanitary engineering 01 natural sciences smart stormwater systems Reinforcement learning Flood mitigation 020701 environmental engineering TD1-1066 0105 earth and related environmental sciences Civil and Structural Engineering Water Science and Technology urban flooding T58.5-58.64 Geotechnical Engineering and Engineering Geology 6. Clean water 13. Climate action Environmental science real-time control Water resource management |
| Zdroj: | Journal of Hydroinformatics, Vol 23, Iss 3, Pp 529-547 (2021) |
| ISSN: | 1465-1734 1464-7141 |
| DOI: | 10.2166/hydro.2020.080 |
| Popis: | Flooding in coastal cities is increasing due to climate change and sea-level rise, stressing the traditional stormwater systems these communities rely on. Automated real-time control (RTC) of these systems can improve performance, and creating control policies for smart stormwater systems is an active area of study. This research explores reinforcement learning (RL) to create control policies to mitigate flood risk. RL is trained using a model of hypothetical urban catchments with a tidal boundary and two retention ponds with controllable valves. RL's performance is compared to the passive system, a model predictive control (MPC) strategy, and a rule-based control strategy (RBC). RL learns to proactively manage pond levels using current and forecast conditions and reduced flooding by 32% over the passive system. Compared to the MPC approach using a physics-based model and genetic algorithm, RL achieved nearly the same flood reduction, just 3% less than MPC, with a significant 88× speedup in runtime. Compared to RBC, RL was able to quickly learn similar control strategies and reduced flooding by an additional 19%. This research demonstrates that RL can effectively control a simple system and offers a computationally efficient method that could scale to RTC of more complex stormwater systems. HIGHLIGHTS Reinforcement learning (RL) creates policies for real-time coastal stormwater system control.; RL's ability to mitigate flooding and manage ponds is compared to a passive system, model predictive control, and rule-based control.; RL was more efficient than model predictive control using a physics-based model and genetic algorithm.; RL's ability to mitigate flooding exceeded the passive system and rule-based control. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|