An Explainable Day-Ahead Electricity Price Forecasting Framework with Temporal Decoupling and Cross-Market Validation
Keywords:
Electricity price forecasting, Sustainable energy systems, Renewable energy integration, Temporal decouplingAbstract
Accurate day-ahead electricity price forecasting is important for electricity market operation, risk assessment, and renewable energy integration. Under increasing variable renewable energy penetration, strong intraday cycles and co-movement between renewable generation and demand-related activity can obscure marginal relationships between explanatory variables and prices. This study proposes an explainable day-ahead electricity price forecasting framework with temporal decoupling and cross-market validation. Using hourly records from Denmark West, Great Britain, and Northern Italy, we construct a 12-dimensional feature vector covering demand-side, supply-side, and market-side information. Hourly de-meaning is introduced for PV-related variables before Pearson and hourly-correlation screening. A Transformer--BiLSTM hybrid model captures long-range dependence and local sequential dynamics, while SHAP-based attribution examines whether learned feature contributions remain aligned with expected market mechanisms. The framework obtains lower MAE and RMSE than the compared benchmark models in all three markets. Ablation results indicate that hourly de-meaning, feature screening, the Transformer module, and the BiLSTM module each contribute to forecasting performance.
References
Maciejowska, K.; Uniejewski, B.; Weron, R. Forecasting electricity prices. arXiv 2022, arXiv:2204.11735. https://doi.org/10.48550/arXiv.2204.11735
Weron, R. Electricity price forecasting: A review of the state-of-the-art with a look into the future. International Journal of Forecasting 2014, 30(4), 1030–1081. https://doi.org/10.1016/j.ijforecast.2014.08.008
Arantegui, R.L.; Jäger-Waldau, A. Photovoltaics and wind status in the European Union after the Paris Agreement. Renewable and Sustainable Energy Reviews 2018, 81, 2460–2471. https://doi.org/10.1016/j.rser.2017.06.052
Wang, Y.; Wang, R.; Tanaka, K.; Ciais, P.; Penuelas, J.; Balkanski, Y.; Sardans, J.; Hauglustaine, D.; Cao, J.; Chen, J.; et al. Global Spatiotemporal Optimization of Photovoltaic and Wind Power to Achieve the Paris Agreement Targets. Nature Communications 2025, 16, 2127. https://doi.org/10.1038/s41467-025-57292-w
ENTSO-E. System Flexibility Needs for the Energy Transition. ENTSO-E: Brussels, Belgium, 2024. Available online: https://www.entsoe.eu/system-flexibility/ (accessed on 15 November 2025).
Cavus, M. Advancing Power Systems with Renewable Energy and Intelligent Technologies: A Comprehensive Review on Grid Transformation and Integration. Electronics 2025, 14, 1159. https://doi.org/10.3390/electronics14061159
Conejo, A.J.; Morales, J.M.; Baringo, L. Real-time demand response model. IEEE Transactions on Smart Grid 2010, 1(3), 236–242. https://doi.org/10.1109/TSG.2010.2076840
Contreras, J.; Espínola, R.; Nogales, F.J.; Conejo, A.J. ARIMA models to predict next-day electricity prices. IEEE Transactions on Power Systems 2003, 18, 1014–1020. https://doi.org/10.1109/TPWRS.2002.804943
Garcia, R.C.; Contreras, J.; van Akkeren, M.; Garcia, J.B.C. A GARCH forecasting model to predict day-ahead electricity prices. IEEE Transactions on Power Systems 2005, 20, 867–874. https://doi.org/10.1109/TPWRS.2005.846044
Liu, H.; Shi, J. Applying ARMA–GARCH approaches to forecasting short-term electricity prices. Energy Economics 2013, 37, 152–166. https://doi.org/10.1016/j.eneco.2013.02.006
Tan, Z.; Zhang, J.; Wang, J.; Xu, J. Day-ahead electricity price forecasting using wavelet transform combined with ARIMA and GARCH models. Applied Energy 2010, 87, 3606–3610. https://doi.org/10.1016/j.apenergy.2010.05.012
Gupta, S.; Chakrabarty, D.; Kumar, R. Predicting Indian electricity exchange-traded market prices: SARIMA and MLP approach. OPEC Energy Review 2023, 47, 271–286. https://doi.org/10.1111/opec.12287
Chai, S.; Li, Q.; Abedin, M.Z.; Lucey, B.M. Forecasting electricity prices from the state-of-the-art modeling technology and the price determinant perspectives. Research in International Business and Finance 2024, 67, 102132. https://doi.org/10.1016/j.ribaf.2023.102132
Saini, D.; Saxena, A.; Bansal, R.C. Electricity price forecasting by linear regression and SVM. In Proceedings of the 2016 International Conference on Recent Advances and Innovations in Engineering (ICRAIE 2016), Jaipur, India, 23–25 December 2016; pp. 1–7. https://doi.org/10.1109/ICRAIE.2016.7939509
Tschora, L.; Pierre, E.; Plantevit, M.; Robardet, C. Electricity price forecasting on the day-ahead market using machine learning. Applied Energy 2022, 313, 118752. https://doi.org/10.1016/j.apenergy.2022.118752
Lago, J.; De Ridder, F.; De Schutter, B. Forecasting Spot Electricity Prices: Deep Learning Approaches and Empirical Comparison of Traditional Algorithms. Applied Energy 2018, 221, 386–405. https://doi.org/10.1016/j.apenergy.2018.02.069
Zhou, S.; Zhou, L.; Mao, M.; Tai, H.-M.; Wan, Y. An optimized heterogeneous structure LSTM network for electricity price forecasting. IEEE Access 2019, 7, 108161–108173. https://doi.org/10.1109/ACCESS.2019.2932999
Yang, H.; Schell, K.R. HFNet: Forecasting real-time electricity price via novel GRU architectures. In Proceedings of the 2020 International Conference on Probabilistic Methods Applied to Power Systems (PMAPS 2020), Liège, Belgium, 18–21 August 2020; pp. 1–6. https://doi.org/10.1109/PMAPS47429.2020.9183697
Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L.; Polosukhin, I. Attention is all you need. In Proceedings of Advances in Neural Information Processing Systems (NeurIPS 2017), Long Beach, CA, USA, 4–9 December 2017; pp. 5998–6008. https://doi.org/10.48550/arXiv.1706.03762
Wang, H. Prediction of Electricity Price Intervals Using Dynamic Bayesian Networks. Energy Informatics 2025, 8, 127. https://doi.org/10.1186/s42162-025-00578-6
Lago, J.; Marcjasz, G.; De Schutter, B.; Weron, R. Forecasting Day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-source benchmark. Applied Energy 2021, 293, 116983. https://doi.org/10.1016/j.apenergy.2021.116983
Cu, Y.; Wang, K.; Zhang, L.; Liu, Z.; Liu, Y.; Mo, L. A Time Series Decomposition-Based Interpretable Electricity Price Forecasting Method. Energies 2025, 18, 664. https://doi.org/10.3390/en18030664
Blyth, C.R. On Simpson’s paradox and the sure-thing principle. Journal of the American Statistical Association 1972, 67, 364–366. https://doi.org/10.1080/01621459.1972.10482387
Sensfuß, F.; Ragwitz, M.; Genoese, M. The merit-order effect: A detailed analysis of the price effect of renewable electricity generation on spot market prices in Germany. Energy Policy 2008, 36, 3086–3094. https://doi.org/10.1016/j.enpol.2008.03.035
Jónsson, T.; Pinson, P.; Madsen, H. On the market impact of wind energy forecasts. Energy Economics 2010, 32, 313–320. https://doi.org/10.1016/j.eneco.2009.10.018
Hogan, W.W. Electricity scarcity pricing through operating reserves. Economics of Energy & Environmental Policy 2013, 2, 65–86. https://doi.org/10.5547/2160-5890.2.2.4
Clò, S.; Cataldi, A.; Zoppoli, P. The merit-order effect in the Italian power market: The impact of solar and wind generation on national wholesale electricity prices. Energy Policy 2015, 77, 79–88. https://doi.org/10.1016/j.enpol.2014.11.038
Khan, A.A.A.; Ullah, M.H.; Tabassum, R.; Kabir, M.F. Enhanced Transformer–BiLSTM deep learning framework for day-ahead energy price forecasting. IEEE Transactions on Industry Applications 2025, Early Access. https://doi.org/10.1109/TIA.2025.3599812
Marcjasz, G.; Narajewski, M.; Weron, R.; Ziel, F. Distributional neural networks for electricity price forecasting. Energy Economics 2023, 125, 106843. https://doi.org/10.1016/j.eneco.2023.106843
Jørgensen, B.H.; Wolter, C.; Moreno, C. IEA Wind TCP Annual Report 2024: Denmark. International Energy Agency Wind Technology Collaboration Programme: Paris, France, 2025. Available online: https://iea-wind.org/about-iea-wind-tcp/annual-reports/ (accessed on 8 February 2026).
Energinet. Annual Report 2018: Energy across borders. Energinet: Fredericia, Denmark, 2018. Available online: https://en.energinet.dk/media/fjnfkw54/annual-report-2018.pdf (accessed on 8 February 2026).
Rintamäki, T.; Siddiqui, A.S.; Salo, A. Does renewable energy generation decrease the volatility of electricity prices – An analysis of Denmark and Germany. Energy Economics 2017, 62, 270–282. https://doi.org/10.1016/j.eneco.2016.12.019
Newbery, D. Missing money and missing markets: Reliability, capacity auctions and interconnectors. Energy Policy 2016, 94, 401–410. https://doi.org/10.1016/j.enpol.2015.10.028
Ganepola, C.N.; Shubita, M.; Lee, L. The electric shock: Causes and consequences of electricity prices in the United Kingdom. Energy Economics 2023, 126, 107030. https://doi.org/10.1016/j.eneco.2023.107030
Elexon. System Prices Analysis Report: January 2025. Elexon: London, UK, 2025. Available online: https://assets.elexon.co.uk/wp-content/uploads/sites/11/2025/02/21160740/System-Prices-Analysis-Report_-January-2025-Elexon-BSC.pdf (accessed on 8 February 2026).
Durán-Castillo, G.; Weis, T.; Leach, A.; Fleck, B.A. Toward Sustainable Electricity Markets: Merit-Order Dynamics on Photovoltaic Energy Price Duck Curve and Emissions Displacement. Sustainability 2025, 17, 4618. https://doi.org/10.3390/su17094618
Pierro, M.; Moser, D.; Perez, R.; Cornaro, C. The value of PV power forecast and the paradox of the single pricing scheme: The Italian case study. Energies 2020, 13, 3945. https://doi.org/10.3390/en13153945
Hosseini Imani, M.; Bompard, E.; Colella, P.; Huang, T. Impact of wind and solar generation on the Italian zonal electricity price. Energies 2021, 14, 5858. https://doi.org/10.3390/en14185858
Kath, C.; Ziel, F. Quantifying the economic gains of accurate quarter-hourly electricity price forecasts. Energy Economics 2018, 76, 411–423. https://doi.org/10.1016/j.eneco.2018.10.005
Sioshansi, R.; Denholm, P.; Jenkin, T.; Weiss, J. Estimating the value of electricity storage in PJM: Arbitrage and some welfare effects. Energy Economics 2009, 31, 269–277. https://doi.org/10.1016/j.eneco.2008.10.005
Schill, W.-P. Residual load, renewable surplus generation and storage requirements in Germany. Energy Policy 2014, 73, 65–79. https://doi.org/10.1016/j.enpol.2014.05.032
Prokhorov, A.; Dreisbach, N. The impact of renewable energy generation on electricity price volatility in European markets. Renewable and Sustainable Energy Reviews 2022, 153, 111819. https://doi.org/10.1016/j.rser.2021.111819
Green, R.; Vasilakos, N. Market behaviour with large amounts of intermittent generation. Energy Policy 2010, 38, 3211–3220. https://doi.org/10.1016/j.enpol.2009.07.038
