Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Probabilistic Forecasting of Real-Time Electricity Market Signals via Interpretable Generative AI (2403.05743v5)

Published 9 Mar 2024 in eess.SP, cs.LG, econ.GN, and q-fin.EC

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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. E. Ni, P. Luh, and S. Rourke, “Optimal integrated generation bidding and scheduling with risk management under a deregulated power market,” IEEE Transactions on Power Systems, vol. 19, no. 1, pp. 600–609, 2004.
  2. R. Jabr, “Robust self-scheduling under price uncertainty using conditional value-at-risk,” IEEE Transactions on Power Systems, vol. 20, no. 4, pp. 1852–1858, 2005.
  3. M. Zhou, Z. Yan, Y. X. Ni, G. Li, and Y. Nie, “Electricity price forecasting with confidence-interval estimation through an extended arima approach,” IEE Proc.-Gener.Transmiss.Distrib, vol. 153, no. 2, pp. 187–195, 2006.
  4. J. P. González, A. M. S. Muñoz San Roque, and E. A. Pérez, “Forecasting functional time series with a new hilbertian armax model: Application to electricity price forecasting,” IEEE Transactions on Power Systems, vol. 33, no. 1, pp. 545–556, 2018.
  5. G. Dudek, “Multilayer perceptron for GEFCom2014 probabilistic electricity price forecasting,” International Journal of Forecasting, vol. 32, no. 3, pp. 1057–1060, Jul. 2016. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0169207015001442
  6. D. Lee, H. Shin, and R. Baldick, “Bivariate probabilistic wind power and real-time price forecasting and their applications to wind power bidding strategy development,” IEEE Transactions on Power Systems, vol. 33, no. 6, pp. 6087–6097, 2018.
  7. J. Nowotarski and R. Weron, “Recent advances in electricity price forecasting: A review of probabilistic forecasting,” Renewable and Sustainable Energy Reviews, vol. 81, pp. 1548–1568, Jan. 2018.
  8. C. Zhang and Y. Fu, “Probabilistic electricity price forecast with optimal prediction interval,” IEEE Transactions on Power Systems, vol. 39, no. 1, pp. 442–452, 2024.
  9. J. Bottieau, Y. Wang, Z. De Grève, F. Vallée, and J.-F. Toubeau, “Interpretable transformer model for capturing regime switching effects of real-time electricity prices,” IEEE Transactions on Power Systems, vol. 38, no. 3, pp. 2162–2176, 2023.
  10. W. Härdle, H. Lütkepohl, and R. Chen, “A review of nonparametric time series analysis,” International Statistical Review / Revue Internationale de Statistique, vol. 65, no. 1, pp. 49–72, 1997, publisher: [Wiley, International Statistical Institute (ISI)]. [Online]. Available: https://www.jstor.org/stable/1403432
  11. J. Nowotarski and R. Weron, “Computing electricity spot price prediction intervals using quantile regression and forecast averaging,” Computational Statistics, vol. 30, no. 3, pp. 791–803, Sep. 2015. [Online]. Available: https://doi.org/10.1007/s00180-014-0523-0
  12. R. Weron and A. Misiorek, “Forecasting spot electricity prices: A comparison of parametric and semiparametric time series models,” International Journal of Forecasting, vol. 24, no. 4, pp. 744–763, 2008. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0169207008000952
  13. B. Uniejewski and R. Weron, “Regularized quantile regression averaging for probabilistic electricity price forecasting,” Energy Economics, vol. 95, p. 105121, 2021. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0140988321000268
  14. L. M. Lima, P. Damien, and D. W. Bunn, “Bayesian predictive distributions for imbalance prices with time-varying factor impacts,” IEEE Transactions on Power Systems, vol. 38, no. 1, pp. 349–357, 2023.
  15. S. Chai, Z. Xu, and Y. Jia, “Conditional density forecast of electricity price based on ensemble elm and logistic emos,” IEEE Transactions on Smart Grid, vol. 10, no. 3, pp. 3031–3043, 2019.
  16. P. Gaillard, Y. Goude, and R. Nedellec, “Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting,” International Journal of Forecasting, vol. 32, no. 3, pp. 1038–1050, Jul. 2016. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0169207015001545
  17. C. Zhang and Y. Fu, “Probabilistic electricity price forecast with optimal prediction interval,” IEEE Transactions on Power Systems, pp. 1–10, 2023.
  18. J.-F. Toubeau, T. Morstyn, J. Bottieau, K. Zheng, D. Apostolopoulou, Z. De Grève, Y. Wang, and F. Vallée, “Capturing spatio-temporal dependencies in the probabilistic forecasting of distribution locational marginal prices,” IEEE Transactions on Smart Grid, vol. 12, no. 3, pp. 2663–2674, 2021.
  19. N. Nguyen and B. Quanz, “Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecasting,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 10, pp. 9117–9125, May 2021, number: 10. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/17101
  20. Z. Zheng, L. Wang, L. Yang, and Z. Zhang, “Generative Probabilistic Wind Speed Forecasting: A Variational Recurrent Autoencoder Based Method,” IEEE Transactions on Power Systems, vol. 37, no. 2, pp. 1386–1398, Mar. 2022, conference Name: IEEE Transactions on Power Systems. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9516991
  21. L. Li, J. Zhang, J. Yan, Y. Jin, Y. Zhang, Y. Duan, and G. Tian, “Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 10, pp. 8420–8428, May 2021, number: 10. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/17023
  22. M. Khodayar, S. Mohammadi, M. E. Khodayar, J. Wang, and G. Liu, “Convolutional Graph Autoencoder: A Generative Deep Neural Network for Probabilistic Spatio-Temporal Solar Irradiance Forecasting,” IEEE Transactions on Sustainable Energy, vol. 11, no. 2, pp. 571–583, Apr. 2020, conference Name: IEEE Transactions on Sustainable Energy. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8663347
  23. K. Rasul, A.-S. Sheikh, I. Schuster, U. M. Bergmann, and R. Vollgraf, “Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows,” Feb. 2022. [Online]. Available: https://openreview.net/forum?id=WiGQBFuVRv
  24. Y. Li, X. Lu, Y. Wang, and D. Dou, “Generative time series forecasting with diffusion, denoise, and disentanglement,” in Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, Eds., vol. 35.   Curran Associates, Inc., 2022, pp. 23 009–23 022. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2022/file/91a85f3fb8f570e6be52b333b5ab017a-Paper-Conference.pdf
  25. A. Koochali, P. Schichtel, A. Dengel, and S. Ahmed, “Probabilistic Forecasting of Sensory Data With Generative Adversarial Networks – ForGAN,” IEEE Access, vol. 7, pp. 63 868–63 880, 2019, conference Name: IEEE Access. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8717640
  26. K. Yeo, Z. Li, and W. Gifford, “Generative Adversarial Network for Probabilistic Forecast of Random Dynamical Systems,” SIAM Journal on Scientific Computing, vol. 44, no. 4, pp. A2150–A2175, Aug. 2022, publisher: Society for Industrial and Applied Mathematics. [Online]. Available: https://epubs.siam.org/doi/abs/10.1137/21M1457448
  27. Y. Li, Y. Ding, Y. Liu, T. Yang, P. Wang, J. Wang, and W. Yao, “Dense skip attention based deep learning for day-ahead electricity price forecasting,” IEEE Transactions on Power Systems, vol. 38, no. 5, pp. 4308–4327, 2023.
  28. H. Xu, F. Hu, X. Liang, and M. A. Gunmi, “Attention mechanism multi-size depthwise convolutional long short-term memory neural network for forecasting real-time electricity prices,” IEEE Transactions on Power Systems, pp. 1–12, 2024.
  29. H. Zhou, S. Zhang, J. Peng, S. Zhang, J. Li, H. Xiong, and W. Zhang, “Informer: Beyond efficient transformer for long sequence time-series forecasting,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 12, pp. 11 106–11 115, May 2021. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/17325
  30. S. Liu, H. Yu, C. Liao, J. Li, W. Lin, A. X. Liu, and S. Dustdar, “Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting,” Mar. 2022. [Online]. Available: https://openreview.net/forum?id=0EXmFzUn5I
  31. M. Rosenblatt, “Stationary Processes as Shifts of Functions of Independent Random Variables,” Journal of Mathematics and Mechanics, vol. 8, no. 5, pp. 665–681, 1959.
  32. X. Wang and L. Tong, “Innovations Autoencoder and its Application in One-class Anomalous Sequence Detection,” Journal of Machine Learning Research, vol. 23, no. 49, pp. 1–27, 2022. [Online]. Available: http://jmlr.org/papers/v23/21-0735.html
  33. M. Arjovsky, S. Chintala, and L.Bottou, “Wasserstein GAN,” Jan. 2017, arXiv:1701.07875.
  34. X. Wang, L. Tong, and Q. Zhao, “Generative probabilistic time series forecasting and applications in grid operations,” arXiv preprint arXiv:2402.13870, 2024.
  35. M. White, R. Pike, C. Brown, R. Coutu, B. Ewing, S. Johnson, and C. Mendrala, “White paper: Inter-regional interchange scheduling analysis and options,” ISO New England and New York ISO, Tech. Rep., January 2011.
  36. D. Salinas, M. Bohlke-Schneider, L. Callot, R. Medico, and J. Gasthaus, “High-dimensional multivariate forecasting with low-rank gaussian copula processes,” in Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, Eds., vol. 32.   Curran Associates, Inc., 2019. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2019/file/0b105cf1504c4e241fcc6d519ea962fb-Paper.pdf
  37. D. Salinas, V. Flunkert, and J. Gasthaus, “DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks,” Feb. 2019, arXiv:1704.04110 [cs, stat]. [Online]. Available: http://arxiv.org/abs/1704.04110
  38. T. Gneiting and M. Katzfuss, “Probabilistic forecasting,” Annual Review of Statistics and Its Application, vol. 1, no. 1, pp. 125–151, 2014. [Online]. Available: https://doi.org/10.1146/annurev-statistics-062713-085831
  39. P. F. Christoffersen, “Evaluating Interval Forecasts,” International Economic Review, vol. 39, no. 4, pp. 841–862, Nov. 1998.
  40. E. Tómasson, M. R. Hesamzadeh, and F. A. Wolak, “Optimal offer-bid strategy of an energy storage portfolio: A linear quasi-relaxation approach,” Applied Energy, vol. 260, p. 114251, 2020. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0306261919319385
  41. NERC, “Balancing and frequency control,” NERC Resource Subcommittee, Priceton,NJ, Tech. Rep., January 2011. [Online]. Available: https://www.nerc.com/comm/OC/BAL0031_Supporting_Documents_2017_DL/NERC%20Balancing%20and%20Frequency%20Control%20040520111.pdf
  42. E. Stroe-Kunold, T. Stadnytska, J. Werner, and S. Braun, “Estimating long-range dependence in time series: An evaluation of estimators implemented in r,” Behavior Research Methods, vol. 41, no. 3, pp. 909–923, 2009.
  43. M. A. Montemurro and P. A. Pury, “Long-range fractal correlations in literary corpora,” Fractals, vol. 10, no. 4, pp. 451–461, 2002.
  44. J. Bhan, S. Kim, J. Kim, Y. Kwon, S. il Yang, and K. Lee, “Long-range correlations in korean literary corpora,” Chaos, Solitons & Fractals, vol. 29, no. 1, pp. 69–81, 2006. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0960077905008131
  45. G. Klæboe, A. L. Eriksrud, and S.-E. Fleten, “Benchmarking time series based forecasting models for electricity balancing market prices,” Energy Systems, vol. 6, no. 1, pp. 43–61, 2015.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now