IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v377y2025ipds030626192401715x.html
   My bibliography  Save this article

Data-augmentation acceleration framework by graph neural network for near-optimal unit commitment

Author

Listed:
  • Wei, Lishen
  • Ai, Xiaomeng
  • Fang, Jiakun
  • Cui, Shichang
  • Gao, Liqian
  • Li, Kun
  • Wen, Jinyu

Abstract

The acceleration of large-scale unit commitment (UC) problems has been a long-standing challenge in the power industry. Independent system operators are required to find a near-optimal solution within a short timeframe, which is a challenging task in practice. In this paper, to obtain near-optimal commitments rapidly, we develop a data-augmentation acceleration framework by neural network. First, a data augmentation technique is developed to enrich the training dataset with numerous near-optimal solutions instead of just incorporating the optimal one. Secondly, we employ the graph neural network (GNN) to learn the commitments, where the UC problems are treated as graphs to represent the relationship between variables and constraints. Last, a repair method is introduced to address potential inaccuracies caused by GNN, converting infeasible or suboptimal solutions into near-optimal ones. The proposed framework was validated on the RTS-GMLC and Jiangsu province systems. Numerical experiments with the Gurobi solver demonstrated a remarkable acceleration in finding near-optimal solutions, achieving speed-ups of 10.7× and 15.9×, respectively. The quickly obtained near-optimal solutions also greatly aid in finding optimal solutions. Furthermore, integrating the proposed framework into the open-source solver significantly outperformed the Gurobi solver in finding near-optimal commitments.

Suggested Citation

  • Wei, Lishen & Ai, Xiaomeng & Fang, Jiakun & Cui, Shichang & Gao, Liqian & Li, Kun & Wen, Jinyu, 2025. "Data-augmentation acceleration framework by graph neural network for near-optimal unit commitment," Applied Energy, Elsevier, vol. 377(PD).
    • Handle: RePEc:eee:appene:v:377:y:2025:i:pd:s030626192401715x
    DOI: 10.1016/j.apenergy.2024.124332
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S030626192401715X
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2024.124332?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. de Mars, Patrick & O’Sullivan, Aidan, 2021. "Applying reinforcement learning and tree search to the unit commitment problem," Applied Energy, Elsevier, vol. 302(C).
    2. Bengio, Yoshua & Lodi, Andrea & Prouvost, Antoine, 2021. "Machine learning for combinatorial optimization: A methodological tour d’horizon," European Journal of Operational Research, Elsevier, vol. 290(2), pages 405-421.
    3. Álinson S. Xavier & Feng Qiu & Shabbir Ahmed, 2021. "Learning to Solve Large-Scale Security-Constrained Unit Commitment Problems," INFORMS Journal on Computing, INFORMS, vol. 33(2), pages 739-756, May.
    4. Bernard Knueven & James Ostrowski & Jean-Paul Watson, 2020. "On Mixed-Integer Programming Formulations for the Unit Commitment Problem," INFORMS Journal on Computing, INFORMS, vol. 32(4), pages 857-876, October.
    5. Zhang, Menghan & Yang, Zhifang & Lin, Wei & Yu, Juan & Dai, Wei & Du, Ershun, 2021. "Enhancing economics of power systems through fast unit commitment with high time resolution," Applied Energy, Elsevier, vol. 281(C).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. O’Malley, Cormac & de Mars, Patrick & Badesa, Luis & Strbac, Goran, 2023. "Reinforcement learning and mixed-integer programming for power plant scheduling in low carbon systems: Comparison and hybridisation," Applied Energy, Elsevier, vol. 349(C).
    2. Fajemisin, Adejuyigbe O. & Maragno, Donato & den Hertog, Dick, 2024. "Optimization with constraint learning: A framework and survey," European Journal of Operational Research, Elsevier, vol. 314(1), pages 1-14.
    3. Kai Pan & Ming Zhao & Chung-Lun Li & Feng Qiu, 2022. "A Polyhedral Study on Fuel-Constrained Unit Commitment," INFORMS Journal on Computing, INFORMS, vol. 34(6), pages 3309-3324, November.
    4. Koutecká, Pavlína & Šůcha, Přemysl & Hůla, Jan & Maenhout, Broos, 2025. "A machine learning approach to rank pricing problems in branch-and-price," European Journal of Operational Research, Elsevier, vol. 320(2), pages 328-342.
    5. Luis Montero & Antonio Bello & Javier Reneses, 2022. "A Review on the Unit Commitment Problem: Approaches, Techniques, and Resolution Methods," Energies, MDPI, vol. 15(4), pages 1-40, February.
    6. Brammer, Janis & Lutz, Bernhard & Neumann, Dirk, 2022. "Permutation flow shop scheduling with multiple lines and demand plans using reinforcement learning," European Journal of Operational Research, Elsevier, vol. 299(1), pages 75-86.
    7. Shen, Yunzhuang & Sun, Yuan & Li, Xiaodong & Eberhard, Andrew & Ernst, Andreas, 2023. "Adaptive solution prediction for combinatorial optimization," European Journal of Operational Research, Elsevier, vol. 309(3), pages 1392-1408.
    8. Aliakbari Sani, Sajad & Bahn, Olivier & Delage, Erick, 2022. "Affine decision rule approximation to address demand response uncertainty in smart Grids’ capacity planning," European Journal of Operational Research, Elsevier, vol. 303(1), pages 438-455.
    9. Skolfield, J. Kyle & Escobedo, Adolfo R., 2022. "Operations research in optimal power flow: A guide to recent and emerging methodologies and applications," European Journal of Operational Research, Elsevier, vol. 300(2), pages 387-404.
    10. Awol Seid Ebrie & Chunhyun Paik & Yongjoo Chung & Young Jin Kim, 2023. "Environment-Friendly Power Scheduling Based on Deep Contextual Reinforcement Learning," Energies, MDPI, vol. 16(16), pages 1-12, August.
    11. Zhao, Zhonghao & Lee, Carman K.M. & Huo, Jiage, 2023. "EV charging station deployment on coupled transportation and power distribution networks via reinforcement learning," Energy, Elsevier, vol. 267(C).
    12. Sun, Yanshuo & Kirtonia, Sajeeb & Chen, Zhi-Long, 2021. "A survey of finished vehicle distribution and related problems from an optimization perspective," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 149(C).
    13. Zhao, Shihao & Li, Kang & Yang, Zhile & Xu, Xinzhi & Zhang, Ning, 2022. "A new power system active rescheduling method considering the dispatchable plug-in electric vehicles and intermittent renewable energies," Applied Energy, Elsevier, vol. 314(C).
    14. Li, Mingjie & Hao, Jin-Kao & Wu, Qinghua, 2024. "A flow based formulation and a reinforcement learning based strategic oscillation for cross-dock door assignment," European Journal of Operational Research, Elsevier, vol. 312(2), pages 473-492.
    15. Long He & Sheng Liu & Zuo‐Jun Max Shen, 2022. "Smart urban transport and logistics: A business analytics perspective," Production and Operations Management, Production and Operations Management Society, vol. 31(10), pages 3771-3787, October.
    16. Bootaki, Behrang & Zhang, Guoqing, 2024. "A location-production-routing problem for distributed manufacturing platforms: A neural genetic algorithm solution methodology," International Journal of Production Economics, Elsevier, vol. 275(C).
    17. Panagiotis Andrianesis & Dimitris Bertsimas & Michael C. Caramanis & William W. Hogan, 2020. "Computation of Convex Hull Prices in Electricity Markets with Non-Convexities using Dantzig-Wolfe Decomposition," Papers 2012.13331, arXiv.org, revised Oct 2021.
    18. Linxin Zhang & Zuobin Ying & Zhile Yang & Yuanjun Guo, 2024. "Dynamic Multi-Energy Optimization for Unit Commitment Integrating PEVs and Renewable Energy: A DO3LSO Algorithm," Mathematics, MDPI, vol. 12(24), pages 1-28, December.
    19. Juho Lauri & Sourav Dutta & Marco Grassia & Deepak Ajwani, 2023. "Learning fine-grained search space pruning and heuristics for combinatorial optimization," Journal of Heuristics, Springer, vol. 29(2), pages 313-347, June.
    20. Ahmet Herekoğlu & Özgür Kabak, 2024. "Crew recovery optimization with deep learning and column generation for sustainable airline operation management," Annals of Operations Research, Springer, vol. 342(1), pages 399-427, November.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:appene:v:377:y:2025:i:pd:s030626192401715x. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.