Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 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

Any-Quantile Probabilistic Forecasting of Short-Term Electricity Demand (2404.17451v2)

Published 26 Apr 2024 in cs.LG and stat.ML

Abstract: Power systems operate under uncertainty originating from multiple factors that are impossible to account for deterministically. Distributional forecasting is used to control and mitigate risks associated with this uncertainty. Recent progress in deep learning has helped to significantly improve the accuracy of point forecasts, while accurate distributional forecasting still presents a significant challenge. In this paper, we propose a novel general approach for distributional forecasting capable of predicting arbitrary quantiles. We show that our general approach can be seamlessly applied to two distinct neural architectures leading to the state-of-the-art distributional forecasting results in the context of short-term electricity demand forecasting task. We empirically validate our method on 35 hourly electricity demand time-series for European countries. Our code is available here: https://github.com/boreshkinai/any-quantile.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. The use of probabilistic forecasts: Applying them in theory and practice, IEEE Power and Energy Magazine 17 (2019) 46–57. doi:10.1109/MPE.2019.2932639.
  2. Balancing needs assessment using advanced probabilistic forecasts, in: 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), 2018, pp. 1–6. doi:10.1109/PMAPS.2018.8440392.
  3. Quantifying the value of probabilistic forecasting for power system operation planning, Applied Energy 343 (2023) 121254. URL: https://www.sciencedirect.com/science/article/pii/S0306261923006189. doi:10.1016/j.apenergy.2023.121254.
  4. Enhancing power systems operational flexibility with ramp products from flexible resources, Electric Power Systems Research 202 (2022) 107599. URL: https://www.sciencedirect.com/science/article/pii/S0378779621005800. doi:10.1016/j.epsr.2021.107599.
  5. A probabilistic security assessment approach to power systems with integrated wind resources, Renewable Energy 85 (2016) 114–123. URL: https://www.sciencedirect.com/science/article/pii/S0960148115300598. doi:10.1016/j.renene.2015.06.035.
  6. 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), 2022, pp. 1–6. doi:10.1109/PMAPS53380.2022.9810632.
  7. T. Hong, S. Fan, Probabilistic electric load forecasting: A tutorial review, International Journal of Forecasting 32 (2016) 914–938. URL: https://www.sciencedirect.com/science/article/pii/S0169207015001508. doi:10.1016/j.ijforecast.2015.11.011.
  8. H. Khajeh, H. Laaksonen, Applications of probabilistic forecasting in smart grids: A review, Applied Sciences 12 (2022). URL: https://www.mdpi.com/2076-3417/12/4/1823. doi:10.3390/app12041823.
  9. B. Li, J. Zhang, A review on the integration of probabilistic solar forecasting in power systems, Solar Energy 210 (2020) 68–86. URL: https://www.sciencedirect.com/science/article/pii/S0038092X20307982. doi:10.1016/j.solener.2020.07.066, special Issue on Grid Integration.
  10. R. J. Hyndman, S. Fan, Density forecasting for long-term peak electricity demand, IEEE Transactions on Power Systems 25 (2010) 1142–1153. doi:10.1109/TPWRS.2009.2036017.
  11. J. W. Taylor, R. Buizza, Neural network load forecasting with weather ensemble predictions, IEEE Transactions on Power Systems 17 (2002) 626 – 632. URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-0036699869&doi=10.1109%2fTPWRS.2002.800906&partnerID=40&md5=019f35fba591b6a47c11ac1e27c6fdbe. doi:10.1109/TPWRS.2002.800906.
  12. A. Khoshrou, E. J. Pauwels, Short-term scenario-based probabilistic load forecasting: A data-driven approach, Applied Energy 238 (2019) 1258–1268. URL: https://www.sciencedirect.com/science/article/pii/S0306261919301412. doi:10.1016/j.apenergy.2019.01.155.
  13. J. Xie, T. Hong, Temperature scenario generation for probabilistic load forecasting, IEEE Transactions on Smart Grid 9 (2018) 1680–1687. doi:10.1109/TSG.2016.2597178.
  14. On normality assumption in residual simulation for probabilistic load forecasting, IEEE Transactions on Smart Grid 8 (2017) 1046–1053. doi:10.1109/TSG.2015.2447007.
  15. Daily load forecasting and maximum demand estimation using arima and garch, in: 2006 International Conference on Probabilistic Methods Applied to Power Systems, 2006, pp. 1–6. doi:10.1109/PMAPS.2006.360237.
  16. Hybrid ensemble deep learning for deterministic and probabilistic low-voltage load forecasting, IEEE Transactions on Power Systems 35 (2020) 1881–1897. doi:10.1109/TPWRS.2019.2946701.
  17. Probabilistic load forecasting via quantile regression averaging on sister forecasts, IEEE Transactions on Smart Grid 8 (2017) 730–737. doi:10.1109/TSG.2015.2437877.
  18. Power load probability density forecasting using gaussian process quantile regression, Applied Energy 213 (2018) 499–509. URL: https://www.sciencedirect.com/science/article/pii/S0306261917316100. doi:10.1016/j.apenergy.2017.11.035.
  19. Electricity consumption probability density forecasting method based on lasso-quantile regression neural network, Applied Energy 233-234 (2019) 565–575. URL: https://www.sciencedirect.com/science/article/pii/S0306261918316301. doi:10.1016/j.apenergy.2018.10.061.
  20. Short-term probabilistic building load forecasting based on feature integrated artificial intelligent approach, Electric Power Systems Research 206 (2022) 107802. URL: https://www.sciencedirect.com/science/article/pii/S0378779622000323. doi:10.1016/j.epsr.2022.107802.
  21. Nonparametric probabilistic load forecasting based on quantile combination in electrical power systems, Applied Energy 322 (2022) 119507. URL: https://www.sciencedirect.com/science/article/pii/S0306261922008273. doi:10.1016/j.apenergy.2022.119507.
  22. Short-term probabilistic load forecasting method based on uncertainty estimation and deep learning model considering meteorological factors, Electric Power Systems Research 225 (2023) 109804. URL: https://www.sciencedirect.com/science/article/pii/S0378779623006934. doi:10.1016/j.epsr.2023.109804.
  23. Short-term power load probability density forecasting method using kernel-based support vector quantile regression and copula theory, Applied Energy 185 (2017) 254–266. URL: https://www.sciencedirect.com/science/article/pii/S0306261916315239. doi:10.1016/j.apenergy.2016.10.079.
  24. Short-term power load probability density forecasting based on GLRQ-stacking ensemble learning method, International Journal of Electrical Power & Energy Systems 142 (2022) 108243. URL: https://www.sciencedirect.com/science/article/pii/S0142061522002721. doi:10.1016/j.ijepes.2022.108243.
  25. G. Dudek, Stacking for probabilistic short-term load forecasting, in: Int. Conf. on Computational Science, ICCS 2024 (in print), 2024.
  26. Energy forecasting: A review and outlook, IEEE Open Access Journal of Power and Energy 7 (2020) 376–388. doi:10.1109/OAJPE.2020.3029979.
  27. Probabilistic individual load forecasting using pinball loss guided lstm, Applied Energy 235 (2019) 10–20. URL: https://www.sciencedirect.com/science/article/pii/S0306261918316465. doi:10.1016/j.apenergy.2018.10.078.
  28. An improved quantile regression neural network for probabilistic load forecasting, IEEE Transactions on Smart Grid 10 (2019) 4425–4434. doi:10.1109/TSG.2018.2859749.
  29. Probabilistic forecasting method for mid-term hourly load time series based on an improved temporal fusion transformer model, International Journal of Electrical Power & Energy Systems 146 (2023) 108743. URL: https://www.sciencedirect.com/science/article/pii/S0142061522007396. doi:10.1016/j.ijepes.2022.108743.
  30. Es-drnn: A hybrid exponential smoothing and dilated recurrent neural network model for short-term load forecasting, IEEE Transactions on Neural Networks and Learning Systems (2023) 1–13. doi:10.1109/TNNLS.2023.3259149.
  31. L. Alfieri, P. De Falco, Wavelet-based decompositions in probabilistic load forecasting, IEEE Transactions on Smart Grid 11 (2020) 1367–1376. doi:10.1109/TSG.2019.2937072.
  32. Probabilistic forecasting of electricity consumption, photovoltaic power generation and net demand of an individual building using gaussian processes, Applied Energy 213 (2018) 195–207. URL: https://www.sciencedirect.com/science/article/pii/S0306261917318275. doi:10.1016/j.apenergy.2017.12.104.
  33. Gluonts: Probabilistic and neural time series modeling in python, The Journal of Machine Learning Research 21 (2020) 4629–4634.
  34. Probabilistic electric load forecasting through bayesian mixture density networks, Applied Energy 309 (2022) 118341. URL: https://www.sciencedirect.com/science/article/pii/S0306261921015907. doi:10.1016/j.apenergy.2021.118341.
  35. Linear convergence of gradient and proximal-gradient methods under the polyak-łojasiewicz condition, in: P. Frasconi, N. Landwehr, G. Manco, J. Vreeken (Eds.), Machine Learning and Knowledge Discovery in Databases, Springer International Publishing, Cham, 2016, pp. 795–811. doi:10.1007/978-3-319-46128-1_50.
  36. T. Gneiting, R. Ranjan, Comparing density forecasts using threshold-and quantile-weighted scoring rules, Journal of Business & Economic Statistics 29 (2011) 411–422. doi:10.1198/jbes.2010.08110.
  37. ES-dRNN with dynamic attention for short-term load forecasting, in: 2022 International Joint Conference on Neural Networks (IJCNN), 2022, pp. 1–8. doi:10.1109/IJCNN55064.2022.9889791.
  38. N-BEATS: Neural basis expansion analysis for interpretable time series forecasting, in: ICLR, 2020.
  39. N-BEATS neural network for mid-term electricity load forecasting, Applied Energy 293 (2021) 116918. doi:10.1016/j.apenergy.2021.116918.
  40. Film: Visual reasoning with a general conditioning layer, in: AAAI, 2018. doi:10.1609/aaai.v32i1.11671.
  41. Forecasting methods for balancing energy market in Poland, International Journal of Electrical Power and Energy Systems 65 (2015) 94–101. doi:10.1016/j.ijepes.2014.09.029.
  42. Pytorch: An imperative style, high-performance deep learning library, in: NeurIPS, 2019, pp. 8024–8035.
  43. G. Dudek, Pattern similarity-based methods for short-term load forecasting – Part 2: Models, Applied Soft Computing 36 (2015) 422–441. doi:10.1016/j.asoc.2015.07.035.
  44. G. Dudek, Short-term load forecasting using Theta method, in: 14th Int. Conf. on Forecasting in Power Engineering 2018, E3S Web Conf., volume 84, 2019. doi:10.1051/e3sconf/20198401004.
  45. G. Dudek, Pattern-based local linear regression models for short-term load forecasting, Electric Power Systems Research 130 (2016) 139–147. doi:10.1016/j.epsr.2015.09.001.
  46. Deepar: Probabilistic forecasting with autoregressive recurrent networks, International Journal of Forecasting 36 (2020) 1181–1191. doi:10.1016/j.ijforecast.2019.07.001.
  47. Attention is all you need, in: Proceedings of 31st Conference on Neural Information Processing Systems (NIPS 2017), 2017, pp. 5998–6008.
  48. Temporal fusion transformers for interpretable multi-horizon time series forecasting, International Journal of Forecasting 37 (2021) 1748–1764. doi:10.1016/j.ijforecast.2021.03.012.
  49. Models for optimising the theta method and their relationship to state space models, International Journal of Forecasting 32 (2016) 1151–1161. doi:10.1016/j.ijforecast.2016.02.005.
  50. F. X. Diebold, R. S. Mariano, Comparing predictive accuracy, Journal of Business & Economic Statistics 13 (1995) 253–263. doi:10.1080/07350015.1995.10524599.
  51. The m5 uncertainty competition: Results, findings and conclusions, International Journal of Forecasting 38 (2022) 1365–1385. URL: https://www.sciencedirect.com/science/article/pii/S0169207021001722. doi:10.1016/j.ijforecast.2021.10.009, special Issue: M5 competition.
  52. T. Gneiting, A. E. Raftery, Strictly proper scoring rules, prediction, and estimation, Journal of the American Statistical Association 102 (2007) 359–378. doi:10.1198/016214506000001437.
  53. Quantile and probability curves without crossing, Econometrica 78 (2010) 1093–1125. URL: http://dx.doi.org/10.3982/ECTA7880. doi:10.3982/ecta7880.

Summary

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

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

Tweets