IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2403.05743.html
   My bibliography  Save this paper

Probabilistic Forecasting of Real-Time Electricity Market Signals via Interpretable Generative AI

Author

Listed:
  • Xinyi Wang
  • Qing Zhao
  • Lang Tong

Abstract

This paper introduces a generative AI approach to probabilistic forecasting of real-time electricity market signals, including locational marginal prices, interregional price spreads, and demand-supply imbalances. We present WIAE-GPF, a Weak Innovation AutoEncoder-based Generative Probabilistic Forecasting architecture that generates future samples of multivariate time series. Unlike traditional black-box models, WIAE-GPF offers interpretability through the Wiener-Kallianpur innovation representation for nonparametric time series, making it a nonparametric generalization of the Wiener/Kalman filter-based forecasting. A novel learning algorithm with structural convergence guarantees is proposed, ensuring that, under ideal training conditions, the generated forecast samples match the ground truth conditional probability distribution. Extensive tests using publicly available data from U.S. independent system operators under various point and probabilistic forecasting metrics demonstrate that WIAE-GPF consistently outperforms classical methods and cutting-edge machine learning techniques.

Suggested Citation

  • Xinyi Wang & Qing Zhao & Lang Tong, 2024. "Probabilistic Forecasting of Real-Time Electricity Market Signals via Interpretable Generative AI," Papers 2403.05743, arXiv.org, revised Sep 2024.
    • Handle: RePEc:arx:papers:2403.05743
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2403.05743
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Wolfgang Härdle & Helmut Lütkepohl & Rong Chen, 1997. "A Review of Nonparametric Time Series Analysis," International Statistical Review, International Statistical Institute, vol. 65(1), pages 49-72, April.
    2. Gaillard, Pierre & Goude, Yannig & Nedellec, Raphaël, 2016. "Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting," International Journal of Forecasting, Elsevier, vol. 32(3), pages 1038-1050.
    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. Ayse Yilmaz & Ufuk Yolcu, 2022. "Dendritic neuron model neural network trained by modified particle swarm optimization for time‐series forecasting," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 41(4), pages 793-809, July.
    2. Shao, Zhen & Zheng, Qingru & Yang, Shanlin & Gao, Fei & Cheng, Manli & Zhang, Qiang & Liu, Chen, 2020. "Modeling and forecasting the electricity clearing price: A novel BELM based pattern classification framework and a comparative analytic study on multi-layer BELM and LSTM," Energy Economics, Elsevier, vol. 86(C).
    3. Uniejewski, Bartosz & Maciejowska, Katarzyna, 2023. "LASSO principal component averaging: A fully automated approach for point forecast pooling," International Journal of Forecasting, Elsevier, vol. 39(4), pages 1839-1852.
    4. Monika Zimmermann & Florian Ziel, 2024. "Efficient mid-term forecasting of hourly electricity load using generalized additive models," Papers 2405.17070, arXiv.org.
    5. Jonathan Berrisch & Florian Ziel, 2023. "Multivariate Probabilistic CRPS Learning with an Application to Day-Ahead Electricity Prices," Papers 2303.10019, arXiv.org, revised Feb 2024.
    6. Patrick Saart & Jiti Gao & Nam Hyun Kim, 2014. "Semiparametric methods in nonlinear time series analysis: a selective review," Journal of Nonparametric Statistics, Taylor & Francis Journals, vol. 26(1), pages 141-169, March.
    7. Grzegorz Marcjasz & Tomasz Serafin & Rafał Weron, 2018. "Selection of Calibration Windows for Day-Ahead Electricity Price Forecasting," Energies, MDPI, vol. 11(9), pages 1-20, September.
    8. Rolf Tschernig & Lijian Yang, 2000. "Nonparametric Estimation of Generalized Impulse Response Functions," Econometric Society World Congress 2000 Contributed Papers 1417, Econometric Society.
    9. Marcjasz, Grzegorz & Uniejewski, Bartosz & Weron, Rafał, 2019. "On the importance of the long-term seasonal component in day-ahead electricity price forecasting with NARX neural networks," International Journal of Forecasting, Elsevier, vol. 35(4), pages 1520-1532.
    10. Smyl, Slawek & Hua, N. Grace, 2019. "Machine learning methods for GEFCom2017 probabilistic load forecasting," International Journal of Forecasting, Elsevier, vol. 35(4), pages 1424-1431.
    11. Weron, Rafal & Misiorek, Adam, 2008. "Forecasting spot electricity prices: A comparison of parametric and semiparametric time series models," International Journal of Forecasting, Elsevier, vol. 24(4), pages 744-763.
    12. Uniejewski, Bartosz & Weron, Rafał, 2021. "Regularized quantile regression averaging for probabilistic electricity price forecasting," Energy Economics, Elsevier, vol. 95(C).
    13. Michael Wegener & Göran Kauermann, 2017. "Forecasting in nonlinear univariate time series using penalized splines," Statistical Papers, Springer, vol. 58(3), pages 557-576, September.
    14. Sami MESTIRI, 2022. "Modeling the volatility of Bitcoin returns using Nonparametric GARCH models," Journal of Academic Finance, RED research unit, university of Gabes, Tunisia, vol. 13(1), pages 2-16, June.
    15. Tomasz Serafin & Bartosz Uniejewski & Rafał Weron, 2019. "Averaging Predictive Distributions Across Calibration Windows for Day-Ahead Electricity Price Forecasting," Energies, MDPI, vol. 12(13), pages 1-12, July.
    16. Nowotarski, Jakub & Weron, Rafał, 2018. "Recent advances in electricity price forecasting: A review of probabilistic forecasting," Renewable and Sustainable Energy Reviews, Elsevier, vol. 81(P1), pages 1548-1568.
    17. Jürgen Franke & Peter Mwita & Weining Wang, 2015. "Nonparametric estimates for conditional quantiles of time series," AStA Advances in Statistical Analysis, Springer;German Statistical Society, vol. 99(1), pages 107-130, January.
    18. Wang, Shengjie & Kang, Yanfei & Petropoulos, Fotios, 2024. "Combining probabilistic forecasts of intermittent demand," European Journal of Operational Research, Elsevier, vol. 315(3), pages 1038-1048.
    19. Cordoni, Francesco & Dorémus, Nicolas & Moneta, Alessio, 2024. "Identification of vector autoregressive models with nonlinear contemporaneous structure," Journal of Economic Dynamics and Control, Elsevier, vol. 162(C).
    20. Lütkepohl,Helmut & Krätzig,Markus (ed.), 2004. "Applied Time Series Econometrics," Cambridge Books, Cambridge University Press, number 9780521547871, January.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    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:arx:papers:2403.05743. 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: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    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.