Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 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

Multivariate Scenario Generation of Day-Ahead Electricity Prices using Normalizing Flows (2311.14033v2)

Published 23 Nov 2023 in cs.LG

Abstract: Trading on the day-ahead electricity markets requires accurate information about the realization of electricity prices and the uncertainty attached to the predictions. Deriving accurate forecasting models presents a difficult task due to the day-ahead price's non-stationarity resulting from changing market conditions, e.g., due to changes resulting from the energy crisis in 2021. We present a probabilistic forecasting approach for day-ahead electricity prices using the fully data-driven deep generative model called normalizing flow. Our modeling approach generates full-day scenarios of day-ahead electricity prices based on conditional features such as residual load forecasts. Furthermore, we propose extended feature sets of prior realizations and a periodic retraining scheme that allows the normalizing flow to adapt to the changing conditions of modern electricity markets. Our results highlight that the normalizing flow generates high-quality scenarios that reproduce the true price distribution and yield accurate forecasts. Additionally, our analysis highlights how our improvements towards adaptations in changing regimes allow the normalizing flow to adapt to changing market conditions and enable continued sampling of high-quality day-ahead price scenarios.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (58)
  1. European Network of Transmission System Operators for Electricity. Transparency platform RESTful API – user guide. https://transparency.entsoe.eu/content/static_content/Staticcontent/webapi/Guide.html, 2023.
  2. Understanding electricity prices beyond the merit order principle using explainable AI. Energy and AI, 13:100250, 2023.
  3. Short-term dynamics of day-ahead and intraday electricity prices. International Journal of Energy Sector Management, 11:557–573, 2017.
  4. Short term fluctuations of wind and solar power systems. New Journal of Physics, 18(6):063027, 2016.
  5. The increasing impact of weather on electricity supply and demand. Energy, 145:65–78, 2018.
  6. Energy crisis: five questions that must be answered in 2023. Nature, 612(7941):627–630, 2022.
  7. Initial analysis of the impact of the ukrainian power grid synchronization with continental europe. Energy Advances, 2(1):91–97, 2023.
  8. Complexity and persistence of price time series of the european electricity spot market. PRX Energy, 1(1):013002, 2022.
  9. Learning likelihoods with conditional normalizing flows. arXiv preprint arXiv:1912.00042, 2019.
  10. Multivariate probabilistic time series forecasting via conditioned normalizing flows. In 2021 International Conference on Learning Representations, 2021.
  11. Normalizing flow-based day-ahead wind power scenario generation for profitable and reliable delivery commitments by wind farm operators. Computers & Chemical Engineering, 166:107923, 2022.
  12. Multivariate probabilistic forecasting of intraday electricity prices using normalizing flows. Applied Energy, 346:121370, 2023.
  13. Deep learning. MIT press, 2016.
  14. Normalizing flows for probabilistic modeling and inference. The Journal of Machine Learning Research, 22(1):2617–2680, 2021.
  15. Principal component density estimation for scenario generation using normalizing flows. Data-Centric Engineering, 3:e7, 2022.
  16. Bidding and scheduling in energy markets: Which probabilistic forecast do we need? In 2022 17th International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), pages 1–6. IEEE, 2022.
  17. Prabha Kundur. Power System Stability, volume 10. CRC Press New York, 2007.
  18. Bundesnetzagentur. Definitionen der Marktakteuere und deren Daten. https://www.bundesnetzagentur.de/SharedDocs/Downloads/DE/Sachgebiete/Energie/Unternehmen_Institutionen/DatenaustauschUndMonitoring/MaStR/DefinitionenMarktakteuere.pdf, 2023.
  19. Hourly electricity prices in day-ahead markets. Energy Economics, 29(2):240–248, 2007.
  20. A literature review of intraday electricity markets and prices. In 2019 IEEE Milan PowerTech, pages 1–6, 2019.
  21. European Network of Transmission System Operators for Electricity. ENTSO-E transparency platform. https://transparency.entsoe.eu, 2023.
  22. Rafał Weron. Electricity price forecasting: A review of the state-of-the-art with a look into the future. International Journal of Forecasting, 30(4):1030–1081, 2014.
  23. Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark. Applied Energy, 293:116983, 2021.
  24. Electricity price forecasting: The dawn of machine learning. IEEE Power and Energy Magazine, 20(3):24–31, 2022.
  25. Electricity price forecasting in new zealand: A comparative analysis of statistical and machine learning models with feature selection. Applied Energy, 347:121446, 2023.
  26. Probabilistic forecasting of day-ahead electricity prices and their volatility with LSTMs. In 2023 IEEE PES Innovative Smart Grid Technologies Europe (ISGT EUROPE), pages 1–5, 2023.
  27. Recent advances in electricity price forecasting: A review of probabilistic forecasting. Renewable and Sustainable Energy Reviews, 81:1548–1568, 2018.
  28. Ensemble forecasting for intraday electricity prices: Simulating trajectories. Applied Energy, 279:115801, 2020.
  29. Quantifying uncertainties of neural network-based electricity price forecasts. Applied Energy, 112:120–129, 2013.
  30. Regularized quantile regression averaging for probabilistic electricity price forecasting. Energy Economics, 95:105121, 2021.
  31. Probabilistic electricity price forecasting with narx networks: Combine point or probabilistic forecasts? International Journal of Forecasting, 36(2):466–479, 2020.
  32. A novel probabilistic forecasting system based on quantile combination in electricity price. Computers & Industrial Engineering, 187:109834, 1 2024.
  33. An optimized deep learning approach for forecasting day-ahead electricity prices. Electric Power Systems Research, 229:110129, 4 2024.
  34. Distributional neural networks for electricity price forecasting. Energy Economics, 125:106843, 9 2023.
  35. Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks. Energy Economics, 70:396–420, 2018.
  36. From point forecasts to multivariate probabilistic forecasts: The schaake shuffle for day-ahead electricity price forecasting. Energy Economics, 120:106602, 2023.
  37. Deep distributional time series models and the probabilistic forecasting of intraday electricity prices. Journal of Applied Econometrics, 38(4):493–511, 3 2023.
  38. Model-free renewable scenario generation using generative adversarial networks. IEEE Transactions on Power Systems, 33(3):3265–3275, 2018.
  39. Optimal configuration of concentrating solar power in multienergy power systems with an improved variational autoencoder. Applied Energy, 274:115124, 2020.
  40. An adaptive standardisation model for day-ahead electricity price forecasting. arXiv preprint arXiv:2311.02610, 2023.
  41. Electricity price forecasting on the day-ahead market using machine learning. Applied Energy, 313:118752, 2022.
  42. Density estimation by dual ascent of the log-likelihood. Communications in Mathematical Sciences, 8(1):217–233, 2010.
  43. A family of nonparametric density estimation algorithms. Communications on Pure and Applied Mathematics, 66(2):145–164, 2013.
  44. Auto-encoding variational bayes. In Yoshua Bengio and Yann LeCun, editors, 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings, 2014.
  45. Generative adversarial nets. In Advances in Neural Information Processing Systems, pages 2672–2680. MIT Press, Cambridge, MA, USA, 2014.
  46. Density estimation using realNVP. arXiv preprint arXiv:1605.08803, 2016.
  47. Flows for simultaneous manifold learning and density estimation. Advances in Neural Information Processing Systems, 33:442–453, 2020.
  48. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467, 2016.
  49. Keras Team. Keras documentation: Density estimation using real NVP. https://keras.io/examples/generative/real_nvp, 2023.
  50. Scikit-learn: Machine learning in Python. The Journal of Machine Learning Research, 12:2825–2830, 2011.
  51. Philipp Thörnig. JURECA: Data Centric and Booster Modules implementing the Modular Supercomputing Architecture at Jülich Supercomputing Centre. Journal of Large-Scale Research Facilities, 7:A182, 2021.
  52. Julius Trebbien. Explainable artificial intelligence and deep learning for analysis and forecasting of complex time series: Applications to electricity prices. https://kups.ub.uni-koeln.de/70766/, 2023. MSc. Thesis, University of Cologne.
  53. Validation methods for energy time series scenarios from deep generative models. IEEE Access, 10:8194–8207, 2022.
  54. Amani Joas. Energy price cap in Germany & curtailment of renewables. https://flex-power.energy/energyblog/energy-price-cap-tax-renewables-curtailment, 2022.
  55. Amani Joas. The economics of curtailing renewables like wind & solar. https://flex-power.energy/energyblog/the-economics-of-curtailing-renewables, 2023.
  56. Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102, 2007.
  57. P. Pinson and R. Girard. Evaluating the quality of scenarios of short-term wind power generation. Applied Energy, 96:12–20, 8 2012.
  58. Variogram-based proper scoring rules for probabilistic forecasts of multivariate quantities. Monthly Weather Review, 143(4):1321–1334, 3 2015.
Citations (3)
View on Semantic Scholar

Summary

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

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