Conformal prediction techniques for electricity price forecasting

Thumbnail Image
Files
Date
2025
Authors
O'Connor, Ciaran
Prestwich, Steven D.
Visentin, Andrea
Journal Title
Journal ISSN
Volume Title
Publisher
Springer Nature Switzerland AG
Published Version
https://doi.org/10.1007/978-3-031-77066-1_1
Research Projects
Organizational Units
Journal Issue
Abstract
Integrating the erratic production of renewable energy into the electricity grid poses numerous challenges. One approach to stabilising market prices and reducing energy losses due to curtailments is the deployment of batteries. Efficient electricity arbitrage is crucial to make investments in storage systems financially viable; trading solutions to achieve this rely on price forecasting techniques. This study delves into the application of Conformal Prediction (CP) techniques, including Ensemble Batch Prediction Intervals (EnbPI) and Sequential Predictive Conformal Inference for Time Series (SPCI), for generating probabilistic forecasts in the Irish electricity market. Recent advancements in CP have addressed temporal considerations inherent in time series forecasting, eliminating the need for exchangeability assumptions. Our study demonstrates that despite potential efficiency trade-offs, CP methods consistently yield precise and reliable prediction intervals, ensuring comprehensive coverage. We assess the impact of CP on the financial results of a simulated trading algorithm. Monetary outcomes achieved with EnbPI and SPCI outperform those of both split CP and traditional quantile regression models, highlighting the practical superiority of CP in electricity price forecasting.
Description
Keywords
Prediction techniques , Electricity price forecasting
Citation
O’Connor, C., Prestwich, S. and Visentin, A. (2025) ‘Conformal prediction techniques for electricity price forecasting’, in V. Lemaire, G. Ifrim, A. Bagnall, T. Guyet, S. Malinowski, P. Schäfer, and R. Tavenard (eds) Advanced Analytics and Learning on Temporal Data. Cham: Springer Nature Switzerland, pp. 1–17. https://doi.org/10.1007/978-3-031-77066-1_1
Link to publisher’s version
URI
https://hdl.handle.net/10468/16878
Collections
Computer Science - Conference Items
Copyright
© 2025, the Authors, under exclusive license to Springer Nature Switzerland AG. This version of the paper has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-77066-1_1