Deep Reinforcement Learning for Optimized Reservoir Operation and Flood Risk Mitigation
Open Access
Abstract
Effective reservoir operation demands a careful balance between flood risk mitigation, water supply reliability, and operational stability, particularly under evolving hydrological conditions. This study applies deep reinforcement learning (DRL) models—Deep Q-Network (DQN), Proximal Policy Optimization (PPO), and Deep Deterministic Policy Gradient (DDPG)—to optimize reservoir operations at the Soyang River Dam, South Korea, using 30 years of daily hydrometeorological data (1993–2022). The DRL framework integrates observed and remotely sensed variables such as precipitation, temperature, and soil moisture to guide adaptive storage decisions. Discharge is computed via mass balance, preserving inflow while optimizing system responses. Performance is evaluated using cumulative reward, action stability, and counts of total capacity and flood control violations. PPO achieved the highest cumulative reward and the most stable actions but incurred six flood control violations; DQN recorded one flood control violation, reflecting larger buffers and strong flood control compliance; DDPG provided smooth, intermediate responses with one violation. No model exceeded the total storage capacity. Analyses show a consistent pattern: retain on the rise, moderate the crest, and release on the recession to keep Flood Risk (FR) < 0. During high-inflow days, DRL optimization outperformed observed operation by increasing storage buffers and typically reducing peak discharge, thereby mitigating flood risk.Keywords
Funding Information
- Korea Environmental Industry and Technology Institute (2022003460001)
This publication has 64 references indexed in Scilit:
- Deep reinforcement learning for multiple reservoir operation planning in the Chao Phraya River BasinModeling Earth Systems and Environment, 2025
- Evaluation of ERA5 and ERA5-Land reanalysis precipitation datasets over Spain (1951–2020)Atmospheric Research, 2023
- Study of the impact of reservoir water level decline on the stability treated landslide on reservoir bankAlexandria Engineering Journal, 2022
- A Review of Reservoir Operation Optimisations: from Traditional Models to Metaheuristic AlgorithmsArchives of Computational Methods in Engineering, 2022
- Identification of preferential target sites for the environmental flow estimation using a simple flowchart in KoreaEnvironmental Monitoring and Assessment, 2022
- Deep Reinforcement Learning for Cascaded Hydropower Reservoirs Considering Inflow ForecastsWater Resources Management, 2020
- Untenable nonstationarity: An assessment of the fitness for purpose of trend tests in hydrologyAdvances in Water Resources, 2018
- Deterministic and probabilistic flood modeling for contemporary and future coastal and inland precipitation inundationApplied Geography, 2014
- Many‐objective reservoir policy identification and refinement to reduce policy inertia and myopia in water managementWater Resources Research, 2014
- A global perspective on environmental flow assessment: emerging trends in the development and application of environmental flow methodologies for riversRiver Research and Applications, 2003