Two-Phase Risk Hedging Rules for Informing Conservation of Flood Resources in Reservoir Operation Considering Inflow Forecast Uncertainty

Water shortages during dry periods can be successfully mitigated by managing reservoirs in real-time to conserve water as floods recede. The inherent uncertainty in inflow forecasts however means that it remains a challenge to balance the risks of flooding against those of water shortages. Few studies have examined how the risks of floods and water shortages can be managed using reservoir operation rules. In this study, a two-phase stochastic optimization model was built to determine the optimal conservation level for flood water by minimizing the risks from both floods and water shortages. For the optimal condition, hedging rules were analytically derived as a quasi-linear function of the storage capability and the expected water shortage. The rules indicate that the flood water conservation was achieved when the marginal upstream flood risk was equal to the marginal water shortage risk, and that the limits of three operation zones divided by the expected water availability should be used when determining the water release. The results from testing the model with data from the Xianghongdian Reservoir (China) showed that the hedging rules outperformed the capacity-constrained pre-release rules for conserving flood water without increasing the flood risk. This proposed methodology will inform the process for making decisions about how to operate reservoirs to ensure optimal real-time flood water conservation.