A Lagrangian-Informed Long-Term Dispatch Policy for Coupled Hydropower and Photovoltaic Systems

2025-03-03 · Eliza Cohn, Ning Qi, Upmanu Lall, Bolun Xu

This paper presents a long-term dispatch framework for coupled hydropower and floating photovoltaic systems. We introduce a temporal decomposition algorithm based on partial Lagrangian relaxation to address long-term water contract constraints. We derive a real-time, non-anticipatory dispatch policy based on water contract pricing. Our framework is evaluated with a case study using real-world hydrology and power system data from Lake Mead and Lake Powell, on the Colorado River, demonstrating competitive performance against commercial solvers for both linearized and nonlinear reservoir models. We conduct a sensitivity analysis on transmission capacity, electricity price and uncertainty scenarios, showing that the operational performance is significantly impacted by the transmission capacity and electricity prices while remaining relatively robust under uncertainty scenarios.

📄 PDF Abstract BibTeX arXiv:2503.01690

Code (0)

등록된 구현이 없습니다.

History-informed Lagrangian Neural Networks

2026-08-13 · Tianshuo Zhang, Xianglei Xing, Wenzhe Zhai, Jia Gao 외 arxiv

Forecasting the long-horizon evolution of mechanical systems from position-only observations is a pivotal yet difficult task, as hidden velocities and trajectory-specific physical properties must be inferred simultaneous…

Efficiently Training Deep-Learning Parametric Policies using Lagrangian Duality

2024-05-23 · Andrew Rosemberg, Alexandre Street, Davi M. Valladão, Pascal Van Hentenryck

Constrained Markov Decision Processes (CMDPs) are critical in many high-stakes applications, where decisions must optimize cumulative rewards while strictly adhering to complex nonlinear constraints. In domains such as p…

Decision Making Decision Making Under Uncertainty Deep Learning Reinforcement Learning (RL)+3

Learning a Discrete Set of Optimal Allocation Rules in a Queueing System with Unknown Service Rate

2022-02-04 · Saghar Adler, Mehrdad Moharrami, Vijay Subramanian

Motivated by the wide range of modern applications of the Erlang-B blocking model beyond communication networks and call centers to sizing and pricing in design production systems, messaging systems, and app-based parkin…

Blocking

Machine Learning for Electricity Market Clearing

2022-05-23 · Laurent Pagnier, Robert Ferrando, Yury Dvorkin, Michael Chertkov

This paper seeks to design a machine learning twin of the optimal power flow (OPF) optimization, which is used in market-clearing procedures by wholesale electricity markets. The motivation for the proposed approach stem…

BIG-bench Machine Learning

Look-Ahead AC Optimal Power Flow: A Model-Informed Reinforcement Learning Approach

2023-03-04 · Xinyue Wang, Haiwang Zhong, Guanglun Zhang, Guangchun Ruan 외

With the increasing proportion of renewable energy in the generation side, it becomes more difficult to accurately predict the power generation and adapt to the large deviations between the optimal dispatch scheme and th…

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1