Prediction of Intraday Electricity Supply Curves
Source abstract
Abstract
The electricity market in Spain, as in many European countries, is organized into daily, intraday, and reserve markets. This project aims to predict the supply curves in the Spanish intraday market that have six sessions with different horizons of application, using information from the market itself. To achieve this, we approximate these curves using a non-uniform grid of points and evaluate the quality of these approximations with a weighted distance, both based on empirical market data. We employ neural network models, including multilayer perceptrons (MLPs), convolutional neural networks (CNNs), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), and a Transformer network alongside a naive model for benchmarking. The MLP and CNN models demonstrated significant improvements in predicting these supply curves for the six market sessions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Electric Power Systems and Control · Integrated Energy Systems Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Campus Puerta de Toledo, Universidad Carlos III de Madrid, 28005 Madrid, Spain
Department of Statistics and Institute Flores de Lemus, Universidad Carlos III de Madrid, 28903 Getafe, Spain
Funding
Ministerio de Ciencia e Innovación
References (37)
Show source-provided references
1. Jefatura del Estado (2024, September 07). Law 54/1997, of November 27, of the Electrical Sector. (In Spanish).
2. Jefatura del Estado (2024, September 06). Law 24/2013, of December 26, of the Electric Sector. (In Spanish).
3. El mercado de generación eléctrica en España: Estructura, funcionamiento y resultados
4. (2024, September 09). The Spanish Electricity Market. (In Spanish).
5. Energía-y-Sociedad (2024, September 06). The Process of Liberalization and Separation of Regulated Activities. (In Spanish).
6. Operador del Mercado Ibérico de Energía (2024, September 06). Daily Market Operation. Available online: https://www.omie.es/sites/default/files/inline-files/mercado_diario.pdf.
7. Operador del Mercado Ibérico de Energía (2024, September 06). Details of How the Intraday Market Works. (In Spanish).
8. Recent advances in electricity price forecasting: A review of probabilistic forecasting10.1016/j.rser.2017.05.234 ↗
9. Energy Forecasting: A Review and Outlook10.1109/OAJPE.2020.3029979 ↗
10. Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark10.1016/j.apenergy.2021.116983 ↗
11. Electricity price forecasting using sale and purchase curves: The X-Model10.1016/j.eneco.2016.08.008 ↗
12. Functional Prediction for the Residual Demand in Electricity Spot Markets10.1109/TPWRS.2013.2258690 ↗
13. X-Model: Further Development and Possible Modifications10.3390/forecast2010002 ↗
14. Forecasting of electricity price through a functional prediction of sale and purchase curves10.1002/for.2624 ↗
15. Efficient Representation of Supply and Demand Curves on Day-Ahead Electricity Markets
16. Pinhão, M., Fonseca, M., and Covas, R. (2022). Electricity Spot Price Forecast by Modelling Supply and Demand Curve. Mathematics, 10.10.3390/math10122012 ↗
17. The arithmetic of stepwise offer curves10.1016/j.energy.2021.122444 ↗
18. Foronda-Pascual, D., and Alonso, A.M. (2023). Prediction of Matching Prices in Electricity Markets through Curve Representation. Energies, 16.10.3390/en16237812 ↗
19. Clustering and forecasting of day-ahead electricity supply curves using a market-based distance10.1016/j.ijepes.2024.109977 ↗
20. European Union (2024, October 01). Overview of European Electricity Markets. Available online: https://energy.ec.europa.eu/system/files/2017-08/overview_of_european_electricity_markets_0.pdf.
21. Evolution and reform of UK electricity market10.1016/j.rser.2022.112317 ↗
22. Comisión Nacional de los Mercados y la Competencia (2024, September 06). Resolution of May 6, 2021, of the National Commission of Markets and Competition, Approving the Operating Rules of the Daily and Intraday Electricity Markets for Their Adaptation of the Supply Limits to the European Matching Limits. (In Spanish).
23. Operador del Mercado Ibérico de Energía (2024, September 06). Evolution of the Electricity Market. Annual Report., (In Spanish).
24. Real Observatorio de la Armada (2024, September 06). Official Time Changes in Spain Since 1918. (In Spanish).
25. Comparing predictive accuracy10.1080/07350015.1995.10524599 ↗
26. Testing the equality of prediction mean squared errors10.1016/S0169-2070(96)00719-4 ↗
27. Hyndman, R., Athanasopoulos, G., Bergmeir, C., Caceres, G., Chhay, L., O’Hara-Wild, M., Petropoulos, F., Razbash, S., Wang, E., and Yasmeen, F. (2024). Forecast: Forecasting Functions for Time Series and Linear Models, The R Foundation. R Package Version 8.23.0.
28. Alpaydin, E. (2014). Multilayer Perceptrons. Introduction to Machine Learning, MIT Press.
29. Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms10.1016/j.energy.2023.128446 ↗
30. O’Shea, K., and Nash, R. (2015). An Introduction to Convolutional Neural Networks. arXiv.
31. Energy demand forecasting using convolutional neural network and modified war strategy optimization algorithm10.1016/j.heliyon.2024.e27353 ↗
32. Staudemeyer, R.C., and Morris, E.R. (2019). Understanding LSTM—A tutorial into Long Short-Term Memory Recurrent Neural Networks. arXiv.
33. Effective energy consumption forecasting using empirical wavelet transform and long short-term memory10.1016/j.energy.2021.121756 ↗
34. Comparing Long Short-Term Memory (LSTM) and bidirectional LSTM deep neural networks for power consumption prediction10.1016/j.egyr.2023.09.175 ↗
35. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2023). Attention Is All You Need. arXiv.
36. A Transformer based approach to electricity load forecasting10.1016/j.tej.2024.107370 ↗
37. Redefine statistical significance10.1038/s41562-017-0189-z ↗