Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

An adaptive standardisation methodology for Day-Ahead electricity price forecasting (2311.02610v3)

Published 5 Nov 2023 in stat.AP, cs.LG, and stat.ME

Abstract: The study of Day-Ahead prices in the electricity market is one of the most popular problems in time series forecasting. Previous research has focused on employing increasingly complex learning algorithms to capture the sophisticated dynamics of the market. However, there is a threshold where increased complexity fails to yield substantial improvements. In this work, we propose an alternative approach by introducing an adaptive standardisation to mitigate the effects of dataset shifts that commonly occur in the market. By doing so, learning algorithms can prioritize uncovering the true relationship between the target variable and the explanatory variables. We investigate five distinct markets, including two novel datasets, previously unexplored in the literature. These datasets provide a more realistic representation of the current market context, that conventional datasets do not show. The results demonstrate a significant improvement across all five markets using the widely accepted learning algorithms in the literature (LEAR and DNN). In particular, the combination of the proposed methodology with the methodology previously presented in the literature obtains the best results. This significant advancement unveils new lines of research in this field, highlighting the potential of adaptive transformations in enhancing the performance of forecasting models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Kalman recursions aggregated online. Statistical Papers , 1–36.
  2. Algorithms for hyper-parameter optimization. Advances in neural information processing systems 24.
  3. A review study of functional autoregressive models with application to energy forecasting. Wiley Interdisciplinary Reviews: Computational Statistics 13, e1525.
  4. An adaptive functional autoregressive forecast model to predict electricity price curves. Journal of Business & Economic Statistics 35, 371–388.
  5. Comparing predictive accuracy. Journal of Business & economic statistics 20, 134–144.
  6. Bootstrap methods: another look at the jackknife. Springer.
  7. A second-order bound with excess losses, in: Conference on Learning Theory, PMLR. pp. 176–196.
  8. Conditional normalization in time series analysis. arXiv preprint arXiv:2305.12651 .
  9. Tests of conditional predictive ability. Econometrica 74, 1545–1578.
  10. Applied time series modelling and forecasting. Wiley.
  11. Generalized Additive Models. Chapman & Hall/CRC Monographs on Statistics & Applied Probability, Taylor & Francis.
  12. Energy forecasting: A review and outlook. IEEE Open Access Journal of Power and Energy 7, 376–388.
  13. Short-term electricity prices forecasting using functional time series analysis. Energies 15, 3423.
  14. Arx-garch probabilistic price forecasts for diversification of trade in electricity markets—variance stabilizing transformation and financial risk-minimizing portfolio allocation. Energies 16, 807.
  15. Conformal prediction interval estimation and applications to day-ahead and intraday power markets. International Journal of Forecasting 37, 777–799.
  16. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 .
  17. Regression quantiles. Econometrica: journal of the Econometric Society , 33–50.
  18. Techniques for verifying the accuracy of risk measurement models. volume 95-24. Division of Research and Statistics, Division of Monetary Affairs, Federal Reserve Board.
  19. Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms. Applied Energy 221, 386–405.
  20. Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark. Applied Energy 293, 116983.
  21. Distributional neural networks for electricity price forecasting. Energy Economics 125, 106843.
  22. Assessing the performance of deep learning models for multivariate probabilistic energy forecasting. Applied Energy 285, 116405.
  23. Optimal bidding on hourly and quarter-hourly day-ahead electricity price auctions: trading large volumes of power with market impact and transaction costs. arXiv preprint arXiv:2104.14204 .
  24. Calibration window selection based on change-point detection for forecasting electricity prices, in: Computational Science–ICCS 2022: 22nd International Conference, London, UK, June 21–23, 2022, Proceedings, Part III, Springer. pp. 278–284.
  25. Computing electricity spot price prediction intervals using quantile regression and forecast averaging. Computational Statistics 30, 791–803.
  26. Adaptive normalization: A novel data normalization approach for non-stationary time series, in: The 2010 International Joint Conference on Neural Networks (IJCNN), IEEE. pp. 1–8.
  27. Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with nbeatsx. International Journal of Forecasting 39, 884–900.
  28. N-beats: Neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:1905.10437 .
  29. Price forecasting and validation in the spanish electricity market using forecasts as input data. International Journal of Electrical Power & Energy Systems 77, 123–127.
  30. Deep adaptive input normalization for time series forecasting. IEEE transactions on neural networks and learning systems 31, 3760–3765.
  31. Scikit-learn: Machine learning in python. the Journal of machine Learning research 12, 2825–2830.
  32. Forecasting: theory and practice. International Journal of Forecasting 38, 705–871.
  33. Dataset shift in machine learning. Mit Press, Cambridge, Massachusetts.
  34. A feature selection method based on shapley values robust to concept shift in regression. arXiv preprint arXiv:2304.14774 .
  35. Electricity price forecasting using support vector machines by considering oil and natural gas price impacts, in: 2015 IEEE international conference on smart energy grid engineering (SEGE), IEEE. pp. 1–5.
  36. Automated variable selection and shrinkage for day-ahead electricity price forecasting. Energies 9, 621.
  37. Efficient forecasting of electricity spot prices with expert and lasso models. Energies 11, 2039.
  38. Regularized quantile regression averaging for probabilistic electricity price forecasting. Energy Economics 95, 105121.
  39. Variance stabilizing transformations for electricity spot price forecasting. IEEE Transactions on Power Systems 33, 2219–2229.
  40. Algorithmic learning in a random world. volume 29. Springer.
  41. Optimal learning with bernstein online aggregation. Machine Learning 106, 119–141.
  42. Electricity price forecasting using sale and purchase curves: The x-model. Energy Economics 59, 435–454.
  43. Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks. Energy Economics 70, 396–420.

Summary

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

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