This content will become publicly available on Thu Jul 04 00:00:00 EDT 2024
Stochastic Unit Commitment: Model Reduction via Learning
Abstract
As weather-dependent renewable generation increases its share in the generation mix of most electric energy systems, a stochastic unit commitment becomes the natural day-ahead scheduling tool. However, such a tool is generally computationally intractable if a detailed uncertainty description is considered. Taking this into account, we proposed a learning method to make the stochastic unit commitment problem tractable. Here, recent advances in statistical learning and machine learning to address optimization problems can be advantageously applied to the rather intractable stochastic unit commitment problem. Considering these advances, we explore simple learning techniques to drastically reduce the size of a stochastic unit commitment problem without significantly altering its optimal solution. The considered stochastic unit commitment problem is formulated as a two-stage stochastic programming problem. The first stage represents commitment decisions, while the second one represents the operation conditions under different scenarios. Taking into account historical solved instances (or proxies for them), we reduce the size (measured by numbers of constraints and variables) of the stochastic unit commitment problem by (i) fixing unchanged binary variables and by (ii) eliminating inactive inequality constraints. Our numerical results show that the reduced problem generally requires significantly less time to solve while obtaining high-quality solutions, which aremore »
- Authors:
-
- The Ohio State University, Columbus, OH (United States)
- Purdue University, West Lafayette, IN (United States)
- Publication Date:
- Research Org.:
- Duke Univ., Durham, NC (United States)
- Sponsoring Org.:
- USDOE Advanced Research Projects Agency - Energy (ARPA-E)
- OSTI Identifier:
- 1988713
- Grant/Contract Number:
- AR0001283
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Current Sustainable/Renewable Energy Reports
- Additional Journal Information:
- Journal Volume: 10; Journal Issue: 2; Journal ID: ISSN 2196-3010
- Publisher:
- Springer
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 42 ENGINEERING; Stochastic unit commitment; learning; stochastic programming; mixed-integer linear programming
Citation Formats
Liu, Xuan, Conejo, Antonio J., and Constante Flores, Gonzalo E. Stochastic Unit Commitment: Model Reduction via Learning. United States: N. p., 2023.
Web. doi:10.1007/s40518-023-00209-2.
Liu, Xuan, Conejo, Antonio J., & Constante Flores, Gonzalo E. Stochastic Unit Commitment: Model Reduction via Learning. United States. https://doi.org/10.1007/s40518-023-00209-2
Liu, Xuan, Conejo, Antonio J., and Constante Flores, Gonzalo E. Tue .
"Stochastic Unit Commitment: Model Reduction via Learning". United States. https://doi.org/10.1007/s40518-023-00209-2.
@article{osti_1988713,
title = {Stochastic Unit Commitment: Model Reduction via Learning},
author = {Liu, Xuan and Conejo, Antonio J. and Constante Flores, Gonzalo E.},
abstractNote = {As weather-dependent renewable generation increases its share in the generation mix of most electric energy systems, a stochastic unit commitment becomes the natural day-ahead scheduling tool. However, such a tool is generally computationally intractable if a detailed uncertainty description is considered. Taking this into account, we proposed a learning method to make the stochastic unit commitment problem tractable. Here, recent advances in statistical learning and machine learning to address optimization problems can be advantageously applied to the rather intractable stochastic unit commitment problem. Considering these advances, we explore simple learning techniques to drastically reduce the size of a stochastic unit commitment problem without significantly altering its optimal solution. The considered stochastic unit commitment problem is formulated as a two-stage stochastic programming problem. The first stage represents commitment decisions, while the second one represents the operation conditions under different scenarios. Taking into account historical solved instances (or proxies for them), we reduce the size (measured by numbers of constraints and variables) of the stochastic unit commitment problem by (i) fixing unchanged binary variables and by (ii) eliminating inactive inequality constraints. Our numerical results show that the reduced problem generally requires significantly less time to solve while obtaining high-quality solutions, which are very close to or indistinguishable from the one obtained by solving the original problem. We use an Illinois 200-bus system to illustrate and characterize the performance of the proposed problem-reduction method.},
doi = {10.1007/s40518-023-00209-2},
journal = {Current Sustainable/Renewable Energy Reports},
number = 2,
volume = 10,
place = {United States},
year = {Tue Jul 04 00:00:00 EDT 2023},
month = {Tue Jul 04 00:00:00 EDT 2023}
}
Works referenced in this record:
Optimization-Driven Scenario Grouping
journal, July 2020
- Ryan, Kevin; Ahmed, Shabbir; Dey, Santanu S.
- INFORMS Journal on Computing, Vol. 32, Issue 3
Learning to Solve Large-Scale Security-Constrained Unit Commitment Problems
journal, October 2020
- Xavier, Álinson S.; Qiu, Feng; Ahmed, Shabbir
- INFORMS Journal on Computing
Learning optimization proxies for large-scale Security-Constrained Economic Dispatch
journal, December 2022
- Chen, Wenbo; Park, Seonho; Tanneau, Mathieu
- Electric Power Systems Research, Vol. 213
Grid Structural Characteristics as Validation Criteria for Synthetic Networks
journal, July 2017
- Birchfield, Adam B.; Xu, Ti; Gegner, Kathleen M.
- IEEE Transactions on Power Systems, Vol. 32, Issue 4
System Advisor Model, SAM 2014.1.14: General Description
report, February 2014
- Blair, Nate; Dobos, Aron P.; Freeman, Janine
Learning-Accelerated ADMM for Distributed DC Optimal Power Flow
journal, January 2022
- Biagioni, David; Graf, Peter; Zhang, Xiangyu
- IEEE Control Systems Letters, Vol. 6
JuMP: A Modeling Language for Mathematical Optimization
journal, January 2017
- Dunning, Iain; Huchette, Joey; Lubin, Miles
- SIAM Review, Vol. 59, Issue 2
Power systems optimization under uncertainty: A review of methods and applications
journal, January 2023
- Roald, Line A.; Pozo, David; Papavasiliou, Anthony
- Electric Power Systems Research, Vol. 214
Stochastic Security-Constrained Unit Commitment
journal, May 2007
- Wu, Lei; Shahidehpour, Mohammad; Li, Tao
- IEEE Transactions on Power Systems, Vol. 22, Issue 2
Warm-starting constraint generation for mixed-integer optimization: A Machine Learning approach
journal, October 2022
- Jiménez-Cordero, Asunción; Morales, Juan Miguel; Pineda, Salvador
- Knowledge-Based Systems, Vol. 253
Electricity Markets
book, January 2010
- Conejo, Antonio J.; Carrión, Miguel; Morales, Juan M.
- International Series in Operations Research & Management Science
Applying High Performance Computing to Transmission-Constrained Stochastic Unit Commitment for Renewable Energy Integration
journal, May 2015
- Papavasiliou, Anthony; Oren, Shmuel S.; Rountree, Barry
- IEEE Transactions on Power Systems, Vol. 30, Issue 3
Topology-Aware Learning Assisted Branch and Ramp Constraints Screening for Dynamic Economic Dispatch
journal, September 2022
- Hasan, Fouad; Kargarian, Amin
- IEEE Transactions on Power Systems, Vol. 37, Issue 5
Emulating AC OPF Solvers With Neural Networks
journal, November 2022
- Baker, Kyri
- IEEE Transactions on Power Systems, Vol. 37, Issue 6
Modeling Approaches for Computational Cost Reduction in Stochastic Unit Commitment Formulations
journal, February 2010
- Ruiz, P. A.; Philbrick, C. R.; Sauer, P. W.
- IEEE Transactions on Power Systems, Vol. 25, Issue 1
Data-Driven Screening of Network Constraints for Unit Commitment
journal, September 2020
- Pineda, Salvador; Morales, Juan Miguel; Jimenez-Cordero, Asuncion
- IEEE Transactions on Power Systems, Vol. 35, Issue 5
Learning for Constrained Optimization: Identifying Optimal Active Constraint Sets
journal, January 2022
- Misra, Sidhant; Roald, Line; Ng, Yeesian
- INFORMS Journal on Computing, Vol. 34, Issue 1