Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 7.16 MB
Add to list
  1. Search results
  2. Risk-sensitive reinforcement learning...

Risk-sensitive reinforcement learning-based strategies for dutch implicit balancing

Seyedsoroush Karimi Madahi (UGent) , Fabio Pavirani (UGent) , Bert Claessens (UGent) and Chris Develder (UGent)
(2025) 2025 21ST INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET, EEM. In International Conference on the European Energy Market p.1-6
Author
Organization
Project
Abstract
Adopting renewable energy sources (RES) can pave the way toward reaching net-zero carbon emissions. However, the intermittent nature of RES can pose significant challenges to balance responsible parties (BRPs) and transmission system operators (TSOs) in maintaining the balance of the electricity grid. BRPs can assist TSOs in balancing the grid by occasionally deviating from their nomination to help reduce the system imbalance, which is called implicit balancing. In this paper, we propose data-driven implicit balancing strategies for BRPs in the Dutch imbalance settlement mechanism. Dutch implicit balancing is challenging due to the Dutch imbalance pricing calculation, which is a combination of single and dual pricing methods. To cope with this challenge, a risk management perspective is incorporated into the proposed method through distributional reinforcement learning. Distributional reinforcement learning agents are trained to manage a BRP's battery in the presence of wind farm generation stochasticity to reduce its imbalance cost. Dutch imbalance data of 2024 are used to assess the performance of the learned implicit strategies. The proposed method is benchmarked against deterministic model predictive control and a rule-based controller. The results show that both risk-neutral and risk-averse agents improve daily profit by 29.3% and 20.7 %, respectively, compared to the rule-based controller. Moreover, the risk-averse agent decreases the average portfolio deviation during dual pricing situations by 19.2% compared to the risk-neutral agent, resulting in a lower imbalance cost for the BRP in these situations.
Keywords
Battery, Imbalance settlement mechanism, Implicit balancing, Reinforcement learning, Risk-sensitive arbitrage

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.59 MB
  • Download
    8856 acc.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 3.57 MB

Citation

Please use this url to cite or link to this publication:

MLA
Karimi Madahi, Seyedsoroush, et al. “Risk-Sensitive Reinforcement Learning-Based Strategies for Dutch Implicit Balancing.” 2025 21ST INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET, EEM, IEEE, 2025, pp. 1–6, doi:10.1109/eem64765.2025.11050202.
APA
Karimi Madahi, S., Pavirani, F., Claessens, B., & Develder, C. (2025). Risk-sensitive reinforcement learning-based strategies for dutch implicit balancing. 2025 21ST INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET, EEM, 1–6. https://doi.org/10.1109/eem64765.2025.11050202
Chicago author-date
Karimi Madahi, Seyedsoroush, Fabio Pavirani, Bert Claessens, and Chris Develder. 2025. “Risk-Sensitive Reinforcement Learning-Based Strategies for Dutch Implicit Balancing.” In 2025 21ST INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET, EEM, 1–6. IEEE. https://doi.org/10.1109/eem64765.2025.11050202.
Chicago author-date (all authors)
Karimi Madahi, Seyedsoroush, Fabio Pavirani, Bert Claessens, and Chris Develder. 2025. “Risk-Sensitive Reinforcement Learning-Based Strategies for Dutch Implicit Balancing.” In 2025 21ST INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET, EEM, 1–6. IEEE. doi:10.1109/eem64765.2025.11050202.
Vancouver
1.
Karimi Madahi S, Pavirani F, Claessens B, Develder C. Risk-sensitive reinforcement learning-based strategies for dutch implicit balancing. In: 2025 21ST INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET, EEM. IEEE; 2025. p. 1–6.
IEEE
[1]
S. Karimi Madahi, F. Pavirani, B. Claessens, and C. Develder, “Risk-sensitive reinforcement learning-based strategies for dutch implicit balancing,” in 2025 21ST INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET, EEM, Lisbon, Portugal, 2025, pp. 1–6.
@inproceedings{01K1FX089N5BTJ8BNBH6FTW5J2,
  abstract     = {{Adopting renewable energy sources (RES) can pave the way toward reaching net-zero carbon emissions. However, the intermittent nature of RES can pose significant challenges to balance responsible parties (BRPs) and transmission system operators (TSOs) in maintaining the balance of the electricity grid. BRPs can assist TSOs in balancing the grid by occasionally deviating from their nomination to help reduce the system imbalance, which is called implicit balancing. In this paper, we propose data-driven implicit balancing strategies for BRPs in the Dutch imbalance settlement mechanism. Dutch implicit balancing is challenging due to the Dutch imbalance pricing calculation, which is a combination of single and dual pricing methods. To cope with this challenge, a risk management perspective is incorporated into the proposed method through distributional reinforcement learning. Distributional reinforcement learning agents are trained to manage a BRP's battery in the presence of wind farm generation stochasticity to reduce its imbalance cost. Dutch imbalance data of 2024 are used to assess the performance of the learned implicit strategies. The proposed method is benchmarked against deterministic model predictive control and a rule-based controller. The results show that both risk-neutral and risk-averse agents improve daily profit by 29.3% and 20.7 %, respectively, compared to the rule-based controller. Moreover, the risk-averse agent decreases the average portfolio deviation during dual pricing situations by 19.2% compared to the risk-neutral agent, resulting in a lower imbalance cost for the BRP in these situations.}},
  articleno    = {{646}},
  author       = {{Karimi Madahi, Seyedsoroush and Pavirani, Fabio and Claessens, Bert and Develder, Chris}},
  booktitle    = {{2025 21ST INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET, EEM}},
  isbn         = {{9798331512798}},
  issn         = {{2165-4077}},
  keywords     = {{Battery,Imbalance settlement mechanism,Implicit balancing,Reinforcement learning,Risk-sensitive arbitrage}},
  language     = {{eng}},
  location     = {{Lisbon, Portugal}},
  pages        = {{646:1--646:6}},
  publisher    = {{IEEE}},
  title        = {{Risk-sensitive reinforcement learning-based strategies for dutch implicit balancing}},
  url          = {{http://doi.org/10.1109/eem64765.2025.11050202}},
  year         = {{2025}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: