A Hybrid AI-Optimization Framework for Resilient Hydropower Operations to Support Grid Stability, Extreme Weather Management, and Large-Scale Industrial Loads
This white paper supports a two-stage decision-support framework that links fast, probabilistic inflow forecasts from modern machine learning and generative AI with multistage stochastic optimization for hydropower scheduling. By propagating uncertainty from prediction into operations, the approach co-optimizes energy and non-energy objectives to strengthen grid reliability, hedge against floods and droughts, and deliver more reliable, resilient generation. The framework targets measurable gains in ramping capacity, forecast-to-dispatch latency, and risk reduction.
Citation Formats
TY - DATA
AB - This white paper supports a two-stage decision-support framework that links fast, probabilistic inflow forecasts from modern machine learning and generative AI with multistage stochastic optimization for hydropower scheduling. By propagating uncertainty from prediction into operations, the approach co-optimizes energy and non-energy objectives to strengthen grid reliability, hedge against floods and droughts, and deliver more reliable, resilient generation. The framework targets measurable gains in ramping capacity, forecast-to-dispatch latency, and risk reduction.
AU - Ploussard, Quentin
A2 - Ganguli, Arkaprabha
A3 - Feinstein, Jeremy
DB - Energy-Water Resilience
DP - Open EI | National Laboratory of the Rockies
DO -
KW - grid reliability
KW - flexible hydropower
KW - probabilistic forecasting
KW - extreme-weather resilience
KW - drought and flood management
KW - reservoir operations
KW - risk-informed scheduling
KW - real-time decision support
LA - English
DA - 2026/01/16
PY - 2026
PB - ANL
T1 - A Hybrid AI-Optimization Framework for Resilient Hydropower Operations to Support Grid Stability, Extreme Weather Management, and Large-Scale Industrial Loads
UR - https://ewr.openei.org/submissions/59
ER -
Ploussard, Quentin, et al. A Hybrid AI-Optimization Framework for Resilient Hydropower Operations to Support Grid Stability, Extreme Weather Management, and Large-Scale Industrial Loads. ANL, 16 January, 2026, Energy-Water Resilience. https://ewr.openei.org/submissions/59.
Ploussard, Q., Ganguli, A., & Feinstein, J. (2026). A Hybrid AI-Optimization Framework for Resilient Hydropower Operations to Support Grid Stability, Extreme Weather Management, and Large-Scale Industrial Loads. [Data set]. Energy-Water Resilience. ANL. https://ewr.openei.org/submissions/59
Ploussard, Quentin, Arkaprabha Ganguli, and Jeremy Feinstein. A Hybrid AI-Optimization Framework for Resilient Hydropower Operations to Support Grid Stability, Extreme Weather Management, and Large-Scale Industrial Loads. ANL, January, 16, 2026. Distributed by Energy-Water Resilience. https://ewr.openei.org/submissions/59
@misc{EWR_Dataset_59,
title = {A Hybrid AI-Optimization Framework for Resilient Hydropower Operations to Support Grid Stability, Extreme Weather Management, and Large-Scale Industrial Loads},
author = {Ploussard, Quentin and Ganguli, Arkaprabha and Feinstein, Jeremy},
abstractNote = {This white paper supports a two-stage decision-support framework that links fast, probabilistic inflow forecasts from modern machine learning and generative AI with multistage stochastic optimization for hydropower scheduling. By propagating uncertainty from prediction into operations, the approach co-optimizes energy and non-energy objectives to strengthen grid reliability, hedge against floods and droughts, and deliver more reliable, resilient generation. The framework targets measurable gains in ramping capacity, forecast-to-dispatch latency, and risk reduction.},
url = {https://ewr.openei.org/submissions/59},
year = {2026},
howpublished = {Energy-Water Resilience, ANL, https://ewr.openei.org/submissions/59},
note = {Accessed: 2026-11-16}
}
Details
Data from Jan 16, 2026
Last updated Jan 16, 2026
Submitted Jan 16, 2026
Contact
Quentin Ploussard
Authors
Keywords
grid reliability, flexible hydropower, probabilistic forecasting, extreme-weather resilience, drought and flood management, reservoir operations, risk-informed scheduling, real-time decision supportDOE Project Details
Project Name White Papers on Ideas to Advance Energy-Water Resilience
Project Lead
Project Number WP-059
