Uncertainty-aware Decision Support in Power Grid Demand Forecasting

Tuwe Löfström, Johan Hallberg Szabadváry, Kristoffer Pettersson, Madalina Aldea, Helena Löfström
Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 329:1029-1042, 2026.

Abstract

Effective management of modern power grids requires accurate demand forecasting and interpretable decision support for fluctuations in electricity consumption. This study extends the Calibrated Explanations method with online calibration support for uncertainty-aware probabilistic regression in offline, semi-online, and fully online settings. Since the application is a temporal forecasting problem, the proposed workflow should be understood as an empirically updated online decision-support procedure rather than as a new finite-sample conformal-validity theorem for arbitrary dependent time series. We apply Long Short-Term Memory (LSTM) networks and online ridge regression to an electricity-demand dataset to provide calibrated forecasts with quantified uncertainty. These forecasts provide threshold-risk information and support operator interpretation through Calibrated Explanations, including sensitivity analysis of key variables that affect energy demand. The proposed approach illustrates the practical use of online calibrated explanations in power-grid decision support.

Cite this Paper

BibTeX
@InProceedings{pmlr-v329-lofstrom26c, title = {Uncertainty-aware Decision Support in Power Grid Demand Forecasting}, author = {L{\"o}fstr{\"o}m, Tuwe and Hallberg Szabadv{\'a}ry, Johan and Pettersson, Kristoffer and Aldea, Madalina and L{\"o}fstr{\"o}m, Helena}, booktitle = {Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {1029--1042}, year = {2026}, editor = {Ahlberg, Ernst and Johansson, Ulf and Boström, Henrik and Carlevaro, Alberto and Hallberg Szabadváry, Johan and Carlsson, Lars}, volume = {329}, series = {Proceedings of Machine Learning Research}, month = {02--04 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v329/main/assets/lofstrom26c/lofstrom26c.pdf}, url = {https://proceedings.mlr.press/v329/lofstrom26c.html}, abstract = {Effective management of modern power grids requires accurate demand forecasting and interpretable decision support for fluctuations in electricity consumption. This study extends the Calibrated Explanations method with online calibration support for uncertainty-aware probabilistic regression in offline, semi-online, and fully online settings. Since the application is a temporal forecasting problem, the proposed workflow should be understood as an empirically updated online decision-support procedure rather than as a new finite-sample conformal-validity theorem for arbitrary dependent time series. We apply Long Short-Term Memory (LSTM) networks and online ridge regression to an electricity-demand dataset to provide calibrated forecasts with quantified uncertainty. These forecasts provide threshold-risk information and support operator interpretation through Calibrated Explanations, including sensitivity analysis of key variables that affect energy demand. The proposed approach illustrates the practical use of online calibrated explanations in power-grid decision support.} }
Endnote
%0 Conference Paper %T Uncertainty-aware Decision Support in Power Grid Demand Forecasting %A Tuwe Löfström %A Johan Hallberg Szabadváry %A Kristoffer Pettersson %A Madalina Aldea %A Helena Löfström %B Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2026 %E Ernst Ahlberg %E Ulf Johansson %E Henrik Boström %E Alberto Carlevaro %E Johan Hallberg Szabadváry %E Lars Carlsson %F pmlr-v329-lofstrom26c %I PMLR %P 1029--1042 %U https://proceedings.mlr.press/v329/lofstrom26c.html %V 329 %X Effective management of modern power grids requires accurate demand forecasting and interpretable decision support for fluctuations in electricity consumption. This study extends the Calibrated Explanations method with online calibration support for uncertainty-aware probabilistic regression in offline, semi-online, and fully online settings. Since the application is a temporal forecasting problem, the proposed workflow should be understood as an empirically updated online decision-support procedure rather than as a new finite-sample conformal-validity theorem for arbitrary dependent time series. We apply Long Short-Term Memory (LSTM) networks and online ridge regression to an electricity-demand dataset to provide calibrated forecasts with quantified uncertainty. These forecasts provide threshold-risk information and support operator interpretation through Calibrated Explanations, including sensitivity analysis of key variables that affect energy demand. The proposed approach illustrates the practical use of online calibrated explanations in power-grid decision support.
APA
Löfström, T., Hallberg Szabadváry, J., Pettersson, K., Aldea, M. & Löfström, H.. (2026). Uncertainty-aware Decision Support in Power Grid Demand Forecasting. Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 329:1029-1042 Available from https://proceedings.mlr.press/v329/lofstrom26c.html.

Related Material