2000 character limit reached
Learning to Bid in Forward Electricity Markets Using a No-Regret Algorithm (2404.03314v1)
Published 4 Apr 2024 in cs.GT, cs.SY, and eess.SY
Abstract: It is a common practice in the current literature of electricity markets to use game-theoretic approaches for strategic price bidding. However, they generally rely on the assumption that the strategic bidders have prior knowledge of rival bids, either perfectly or with some uncertainty. This is not necessarily a realistic assumption. This paper takes a different approach by relaxing such an assumption and exploits a no-regret learning algorithm for repeated games. In particular, by using the \emph{a posteriori} information about rivals' bids, a learner can implement a no-regret algorithm to optimize her/his decision making. Given this information, we utilize a multiplicative weight-update algorithm, adapting bidding strategies over multiple rounds of an auction to minimize her/his regret. Our numerical results show that when the proposed learning approach is used the social cost and the market-clearing prices can be higher than those corresponding to the classical game-theoretic approaches. The takeaway for market regulators is that electricity markets might be exposed to greater market power of suppliers than what classical analysis shows.
- X. Hu and D. Ralph, “Using EPECs to model bilevel games in restructured electricity markets with locational prices,” Operations Research, vol. 55, no. 5, pp. 809–827, 2007.
- B. F. Hobbs, C. B. Metzler, and J. S. Pang, “Strategic gaming analysis for electric power systems: An MPEC approach,” IEEE Transactions on Power Systems, vol. 15, no. 2, pp. 638–645, 2000.
- S. Martín, Y. Smeers, and J. A. Aguado, “A stochastic two settlement equilibrium model for electricity markets with wind generation,” IEEE Transactions on Power Systems, vol. 30, no. 1, pp. 233–245, 2015.
- C. Ruiz and A. J. Conejo, “Pool strategy of a producer with endogenous formation of locational marginal prices,” IEEE Transactions on Power Systems, vol. 24, no. 4, pp. 1855–1866, 2009.
- P. Auer, N. Cesa-Bianchi, and P. Fischer, “Finite-time analysis of the multiarmed bandit problem,” Machine Learning, vol. 47, pp. 235–256, 2002.
- Y. Wang, B. Zhang, J. Ma, and Q. Jin, “Earning while learning: An adversarial multi-armed bandit based real-time bidding scheme in deregulated electricity market,” IEEE Transactions on Network Science and Engineering, vol. 9, no. 6, pp. 3991–4000, 2022.
- J. H. Nachbar, “Prediction, optimization, and learning in repeated games,” Econometrica, vol. 65, no. 2, pp. 275–309, 1997.
- F. Orabona, “A modern introduction to online learning,” arXiv preprint arXiv:1912.13213, 2022.
- S. Shalev-Shwartz et al., “Online learning and online convex optimization,” Foundations and Trends® in Machine Learning, vol. 4, no. 2, pp. 107–194, 2012.
- Y. Ye, D. Qiu, M. Sun, D. Papadaskalopoulos, and G. Strbac, “Deep reinforcement learning for strategic bidding in electricity markets,” IEEE Transactions on Smart Grid, vol. 11, no. 2, pp. 1343–1355, 2020.
- Y. Du, F. Li, H. Zandi, and Y. Xue, “Approximating Nash equilibrium in day-ahead electricity market bidding with multi-agent deep reinforcement learning,” Journal of Modern Power Systems and Clean Energy, vol. 9, no. 3, pp. 534–544, 2021.
- O. Karaca, P. G. Sessa, A. Leidi, and M. Kamgarpour, “No-regret learning from partially observed data in repeated auctions,” IFAC-PapersOnLine, vol. 53, no. 2, pp. 14–19, 2020.
- Z. Zhao, A. L. Liu, and Y. Chen, “Electricity demand response under real-time pricing: A multi-armed bandit game,” in Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2018, pp. 748–756.
- S. Baltaoglu, L. Tong, and Q. Zhao, “Algorithmic bidding for virtual trading in electricity markets,” IEEE Transactions on Power Systems, vol. 34, no. 1, pp. 535–543, 2018.
- European Energy Exchange. (2023) EPEX Spot aggregate curves. [Online]. Available: https://www.epexspot.com/en/market-data
- Nord Pool. (2024) Aggregate market data: Nord Pool day-ahead aggregate curves. [Online]. Available: https://data.nordpoolgroup.com/auction/day-ahead/aggregated-bid-curves?deliveryDate=latest&bidCurveArea=BALTIC
- Y. Freundand and R. E. Schapire, “Adaptive game playing using multiplicative weights,” Games and Economic Behavior, vol. 29, pp. 79–103, 1999.
- B. H. Ahn and W. W. Hogan, “On convergence of the PIES algorithm for computing equilibria,” Operations Research, vol. 30, pp. 281–300, 1982.
- P. G. Sessa, I. Bogunovic, M. Kamgarpour, and A. Krause, “No-regret learning in unknown games with correlated payoffs,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 32, 2019.
- Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of Computer and System Sciences, vol. 55, no. 1, pp. 119–139, 1997.
- S. Leyffer and T. Munson, “Solving multi-leader–common-follower games,” Optimisation Methods & Software, vol. 25, no. 4, pp. 601–623, 2010.
- V. Conitzer and D. Korzhyk, “Commitment to correlated strategies,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 25, no. 1, 2011, pp. 632–637.
- N. Basilico, S. Coniglio, N. Gatti, A. Marchesi et al., “Bilevel programming approaches to the computation of optimistic and pessimistic single-leader-multi-follower equilibria,” Leibniz International Proceedings in Informatics, vol. 75, pp. 1–14, 2017.
- D. Pozo, E. Sauma, and J. Contreras, “Basic theoretical foundations and insights on bilevel models and their applications to power systems,” Annals of Operations Research, vol. 254, pp. 303–334, 2017.
- R. Chen, I. C. Paschalidis, M. C. Caramanis, and P. Andrianesis, “Learning from past bids to participate strategically in day-ahead electricity markets,” IEEE Transactions on Smart Grid, vol. 10, no. 5, pp. 5794–5806, 2019.
- Arega Getaneh Abate (5 papers)
- Dorsa Majdi (2 papers)
- Jalal Kazempour (47 papers)
- Maryam Kamgarpour (86 papers)