{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T21:17:20Z","timestamp":1773868640796,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2020,10,16]],"date-time":"2020-10-16T00:00:00Z","timestamp":1602806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["773960"],"award-info":[{"award-number":["773960"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Energies"],"abstract":"<jats:p>The importance of price forecasting has gained attention over the last few years, with the growth of aggregators and the general opening of the European electricity markets. Market participants manage a tradeoff between, bidding in a lower price market (day-ahead), but with typically higher volume, or aiming for a lower volume market but with potentially higher returns (balance energy market). Companies try to forecast the extremes of revenues or prices, in order to manage risk and opportunity, assigning their assets in an optimal way. It is thought that in general, electricity markets have quasi-deterministic principles, rather than being based on speculation, hence the desire to forecast the price based on variables that can describe the outcome of the market. Many studies address this problem from a statistical approach or by performing multiple-variable regressions, but they very often focus only on the time series analysis. In 2019, the Loss of Load Probability (LOLP) was made available in the UK for the first time. Taking this opportunity, this study focusses on five LOLP variables (with different time-ahead estimations) and other quasi-deterministic variables, to explain the price behavior of a multi-variable regression model. These include base production, system load, solar and wind generation, seasonality, day-ahead price and imbalance volume contributions. Three machine-learning algorithms were applied to test for performance, Gradient Boosting (GB), Random Forest (RF) and XGBoost. XGBoost presented higher performance and so it was chosen for the implementation of the real time forecast step. The model returns a Mean Absolute Error (MAE) of 7.89 \u00a3\/MWh, a coefficient of determination (R2 score) of 76.8% and a Mean Squared Error (MSE) of 124.74. The variables that contribute the most to the model are the Net Imbalance Volume, the LOLP (aggregated), the month and the De-rated margins (aggregated) with 28.6%, 27.5%, 14.0%, and 8.9% of weight on feature importance respectively.<\/jats:p>","DOI":"10.3390\/en13205420","type":"journal-article","created":{"date-parts":[[2020,10,17]],"date-time":"2020-10-17T05:45:51Z","timestamp":1602913551000},"page":"5420","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["Price Forecasting for the Balancing Energy Market Using Machine-Learning Regression"],"prefix":"10.3390","volume":"13","author":[{"given":"Alexandre","family":"Lucas","sequence":"first","affiliation":[{"name":"Directorate C\u2014Energy, Transport and Climate, Joint Research Centre (JRC), European Commission, Via E. Fermi 2749, 21027 Ispra (V.A.), Italy"}]},{"given":"Konstantinos","family":"Pegios","sequence":"additional","affiliation":[{"name":"Kiwi Power, Innovation and Grants Programme, 3 London Wall Buildings, London Wall, London EC2M 5PD, UK"}]},{"given":"Evangelos","family":"Kotsakis","sequence":"additional","affiliation":[{"name":"Directorate C\u2014Energy, Transport and Climate, Joint Research Centre (JRC), European Commission, Via E. Fermi 2749, 21027 Ispra (V.A.), Italy"}]},{"given":"Dan","family":"Clarke","sequence":"additional","affiliation":[{"name":"Kiwi Power, Innovation and Grants Programme, 3 London Wall Buildings, London Wall, London EC2M 5PD, UK"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,16]]},"reference":[{"key":"ref_1","unstructured":"Communication from the Commission to the European Parliament, and The European Council (2019). The European Economic and Social Committee and the Committee of the Regions, Office for Official Publications of the European Communities. The European Green Deal COM\/2019\/640 final."},{"key":"ref_2","unstructured":"International Energy Agency (2020). European Union 2020 Energy Policy Review, Paris, IEA\/OECD Publications."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1017\/S0020782900004253","article-title":"Paris Agreement","volume":"55","author":"Horowitz","year":"2016","journal-title":"Int. Leg. Mater."},{"key":"ref_4","unstructured":"European Commission (2020, June 26). Clean Energy for All Europeans Package\u2014European Commission. Available online: https:\/\/ec.europa.eu\/energy\/en\/topics\/energy-strategy\/clean-energy-all-europeans."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kuo, P.H., and Huang, C.J. (2018). An electricity price forecasting model by hybrid structured deep neural networks. Sustainability, 10.","DOI":"10.3390\/su10041280"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1016\/j.engappai.2012.12.012","article-title":"A hybrid intelligent model based on recurrent neural networks and excitable dynamics for price prediction in deregulated electricity market","volume":"26","author":"Sharma","year":"2013","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.ijepes.2008.09.003","article-title":"Electricity price forecasting in deregulated markets: A review and evaluation","volume":"31","author":"Aggarwal","year":"2009","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1109\/5.823996","article-title":"Forecasting loads and prices in competitive power markets","volume":"88","author":"Bunn","year":"2000","journal-title":"Proc. IEEE"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1030","DOI":"10.1016\/j.ijforecast.2014.08.008","article-title":"Electricity price forecasting: A review of the state-of-the-art with a look into the future","volume":"30","author":"Weron","year":"2014","journal-title":"Int. J. Forecast."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1859","DOI":"10.1109\/TPWRS.2005.857272","article-title":"Supply function equilibrium bidding strategies with fixed forward contracts","volume":"20","author":"Niu","year":"2005","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1109\/TPWRS.2007.913195","article-title":"Forecasting the Mean and the Variance of Electricity Prices in Deregulated Markets","volume":"23","author":"Ruibal","year":"2008","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1007\/s00186-008-0252-7","article-title":"Stochastic models for bidding strategies on oligopoly electricity market","volume":"69","author":"Weron","year":"2009","journal-title":"Math. Methods Oper. Res."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chatzidimitriou, K.C., Chrysopoulos, A.C., Symeonidis, A.L., and Mitkas, P.A. (2012). Enhancing Agent Intelligence through Evolving Reservoir Networks for Predictions in Power Stock Markets, Springer. BT\u2014Agents and Data Mining Interaction.","DOI":"10.1007\/978-3-642-27609-5_15"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.1016\/j.jet.2013.04.020","article-title":"Supply function equilibria: Step functions and continuous representations","volume":"148","author":"Holmberg","year":"2013","journal-title":"J. Econ. Theory"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.enpol.2014.04.021","article-title":"Turning green: Agent-based modeling of the adoption of dynamic electricity tariffs","volume":"72","author":"Maciejowska","year":"2014","journal-title":"Energy Policy"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.ijepes.2013.11.045","article-title":"Nash Equilibrium in a two-settlement electricity market using competitive coevolutionary algorithms","volume":"57","author":"Ladjici","year":"2014","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1007\/978-3-540-25944-2_111","article-title":"Modeling electricity prices with regime switching models","volume":"3039","author":"Bierbrauer","year":"2004","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1080\/13504860500117503","article-title":"Pricing in Electricity Markets: A Mean Reverting Jump Diffusion Model with Seasonality","volume":"12","author":"Cartea","year":"2005","journal-title":"Appl. Math. Financ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3462","DOI":"10.1016\/j.jbankfin.2007.04.011","article-title":"Spot and derivative pricing in the EEX power market","volume":"31","author":"Bierbrauer","year":"2007","journal-title":"J. Bank. Financ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1016\/j.ijforecast.2008.09.008","article-title":"Forecasting electricity prices: The impact of fundamentals and time-varying coefficients","volume":"24","author":"Karakatsani","year":"2008","journal-title":"Int. J. Forecast."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1016\/j.eneco.2010.05.008","article-title":"An empirical comparison of alternate regime-switching models for electricity spot prices","volume":"32","author":"Janczura","year":"2010","journal-title":"Energy Econ."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.ejor.2012.04.030","article-title":"A numerical algorithm for pricing electricity derivatives for jump-diffusion processes based on continuous time lattices","volume":"222","author":"CAlbanese","year":"2012","journal-title":"Eur. J. Oper. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.eneco.2014.03.007","article-title":"Revisiting the relationship between spot and futures prices in the Nord Pool electricity market","volume":"44","author":"Weron","year":"2014","journal-title":"Energy Econ."},{"key":"ref_24","first-page":"1","article-title":"Point and Interval Forecasting of Spot Electricity Prices: Linear vs. Non-Linear Time Series Models","volume":"10","author":"Misiorek","year":"2006","journal-title":"Stud. Nonlinear Dyn. Econ."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1016\/j.ijforecast.2008.08.004","article-title":"Forecasting spot electricity prices: A comparison of parametric and semiparametric time series models","volume":"24","author":"Weron","year":"2008","journal-title":"Int. J. Forecast."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.jedc.2009.08.002","article-title":"Structural vector autoregressions with Markov switching","volume":"34","author":"Lanne","year":"2010","journal-title":"J. Econ. Dyn. Control"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Weron, R. (2006). Modeling and Forecasting Electricity Loads and Prices: A Statistical Approach, Wiley.","DOI":"10.1002\/9781118673362"},{"key":"ref_28","unstructured":"Tr\u00fcck, S., Weron, R., and Wolff, R. (2007). Outlier Treatment and Robust Approaches for Modeling Electricity Spot Prices. Munich Pers. RePEc Arch., 4711. Available online: https:\/\/mpra.ub.uni-muenchen.de\/4711\/."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1109\/TPWRS.2008.920731","article-title":"When Supply Meets Demand: The Case of Hourly Spot Electricity Prices","volume":"23","author":"Boogert","year":"2008","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.eneco.2011.12.006","article-title":"The case of negative day-ahead electricity prices","volume":"35","author":"Fanone","year":"2013","journal-title":"Energy Econ."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.eneco.2013.03.013","article-title":"Identifying spikes and seasonal components in electricity spot price data: A guide to robust modeling","volume":"38","author":"Janczura","year":"2013","journal-title":"Energy Econ."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Shahidehpour, M., Yamin, H., and Li, Z. (2002). Market Operations in Electric Power Systems, Wiley.","DOI":"10.1002\/047122412X"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1086\/500675","article-title":"Understanding the Fine Structure of Electricity Prices","volume":"79","author":"Geman","year":"2006","journal-title":"J. Bus."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.apenergy.2016.03.089","article-title":"Day-ahead electricity price forecasting via the application of artificial neural network based models","volume":"172","author":"Panapakidis","year":"2016","journal-title":"Appl. Energy"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.apenergy.2015.09.087","article-title":"Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks","volume":"162","author":"Keles","year":"2016","journal-title":"Appl. Energy"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Karabiber, O.A., and Xydis, G. (2019). Electricity price forecasting in the Danish day-ahead market using the TBATS, ANN and ARIMA methods. Energies, 12.","DOI":"10.3390\/en12050928"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1109\/TPWRS.2008.920046","article-title":"Modeling Real-Time Balancing Power Market Prices Using Combined SARIMA and Markov Processes","volume":"23","author":"Olsson","year":"2008","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3710","DOI":"10.3390\/en7063710","article-title":"Exponential smoothing approaches for prediction in real-time electricity markets","volume":"7","author":"Pinson","year":"2014","journal-title":"Energies"},{"key":"ref_39","unstructured":"Kratochv\u00edl, \u0160., and Bejbl, J. (2015, January 14). The system imbalance prediction. Proceedings of the 19th International Student Conference on Electrical Engineering, Prague, Czech Republic."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Dumas, J., Boukas, I., de Villena, M.M., Mathieu, S., and Cornelusse, B. (2019). Probabilistic Forecasting of Imbalance Prices in the Belgian Context. Int. Conf. Eur. Energy Mark. EEM, 2019.","DOI":"10.1109\/EEM.2019.8916375"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.renene.2015.01.059","article-title":"Statistical analysis of negative prices in European balancing markets","volume":"80","author":"Brijs","year":"2015","journal-title":"Renew. Energy"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.eneco.2014.10.012","article-title":"Efficient modeling and forecasting of electricity spot prices","volume":"47","author":"Ziel","year":"2015","journal-title":"Energy Econ."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Maciejowska, K. (2014, January 28\u201330). Fundamental and speculative shocks, what drives electricity prices?. Proceedings of the 11th International Conference on the European Energy Market (EEM14), Krakow, Poland.","DOI":"10.1109\/EEM.2014.6861289"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/MPAE.2006.1597990","article-title":"Energy price forecasting\u2014Problems and proposals for such predictions","volume":"4","author":"Amjady","year":"2006","journal-title":"IEEE Power Energy Mag."},{"key":"ref_45","unstructured":"ELEXON (2020, June 27). Available online: https:\/\/www.ELEXON.co.uk\/."},{"key":"ref_46","unstructured":"ELEXON (2020, June 27). Available online: https:\/\/www.ELEXON.co.uk\/about\/about-ELEXON\/."},{"key":"ref_47","unstructured":"European Commission (2016). Final Report of the Sector Inquiry on Capacity Mechanisms, Office for Official Publications of the European Communities."},{"key":"ref_48","unstructured":"ELEXON Limited (2019). Loss of Load Probability Calculation Statement, ELEXON Limited. Balancing and Settlement Code Version 2.0."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forest","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD16), San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_52","unstructured":"SKlearn (2018, October 31). Available online: http:\/\/scikit-learn.org\/stable\/."}],"container-title":["Energies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1996-1073\/13\/20\/5420\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:22:51Z","timestamp":1760178171000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1996-1073\/13\/20\/5420"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,16]]},"references-count":52,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2020,10]]}},"alternative-id":["en13205420"],"URL":"https:\/\/doi.org\/10.3390\/en13205420","relation":{},"ISSN":["1996-1073"],"issn-type":[{"value":"1996-1073","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,16]]}}}