Short-term density forecasting of low-voltage load using bernstein-polynomial normalizing flows

Arpogaus, Marcel; Voss, Marcus; Sick, Beate; Nigge-Uricher, Mark; Dürr, Oliver

doi:10.1109/TSG.2023.3254890

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	Short-term density forecasting of low-voltage load using bernstein-polynomial normalizing flows
Authors:	Arpogaus, Marcel Voss, Marcus Sick, Beate Nigge-Uricher, Mark Dürr, Oliver
et. al:	No
DOI:	10.1109/TSG.2023.3254890
Published in:	IEEE Transactions on Smart Grid
Volume(Issue):	14
Issue:	6
Page(s):	4902
Pages to:	4911
Issue Date:	15-Jun-2023
Publisher / Ed. Institution:	IEEE
ISSN:	1949-3053 1949-3061
Language:	English
Subjects:	Computer Science; Statistics; Machine learning; Methodology; Application
Subject (DDC):	006: Special computer methods 510: Mathematics
Abstract:	The transition to a fully renewable energy grid requires better forecasting of demand at the low-voltage level to increase efficiency and ensure reliable control. However, high fluctuations and increasing electrification cause huge forecast variability, not reflected in traditional point estimates. Probabilistic load forecasts take uncertainties into account and thus allow more informed decision-making for the planning and operation of low-carbon energy systems. We propose an approach for flexible conditional density forecasting of short-term load based on Bernstein polynomial normalizing flows, where a neural network controls the parameters of the flow. In an empirical study with 3639 smart meter customers, our density predictions for 24h-ahead load forecasting compare favorably against Gaussian and Gaussian mixture densities. Furthermore, they outperform a non-parametric approach based on the pinball loss, especially in low-data scenarios.
URI:	https://doi.org/10.48550/arXiv.2204.13939 https://digitalcollection.zhaw.ch/handle/11475/30097
Fulltext version:	Published version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Institute of Data Analysis and Process Design (IDP)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

There are no files associated with this item.

Show full item record

Arpogaus, M., Voss, M., Sick, B., Nigge-Uricher, M., & Dürr, O. (2023). Short-term density forecasting of low-voltage load using bernstein-polynomial normalizing flows. IEEE Transactions on Smart Grid, 14(6), 4902–4911. https://doi.org/10.1109/TSG.2023.3254890

Arpogaus, M. et al. (2023) ‘Short-term density forecasting of low-voltage load using bernstein-polynomial normalizing flows’, IEEE Transactions on Smart Grid, 14(6), pp. 4902–4911. Available at: https://doi.org/10.1109/TSG.2023.3254890.

M. Arpogaus, M. Voss, B. Sick, M. Nigge-Uricher, and O. Dürr, “Short-term density forecasting of low-voltage load using bernstein-polynomial normalizing flows,” IEEE Transactions on Smart Grid, vol. 14, no. 6, pp. 4902–4911, Jun. 2023, doi: 10.1109/TSG.2023.3254890.

ARPOGAUS, Marcel, Marcus VOSS, Beate SICK, Mark NIGGE-URICHER und Oliver DÜRR, 2023. Short-term density forecasting of low-voltage load using bernstein-polynomial normalizing flows. IEEE Transactions on Smart Grid [online]. 15 Juni 2023. Bd. 14, Nr. 6, S. 4902–4911. DOI 10.1109/TSG.2023.3254890. Verfügbar unter: https://doi.org/10.48550/arXiv.2204.13939

Arpogaus, Marcel, Marcus Voss, Beate Sick, Mark Nigge-Uricher, and Oliver Dürr. 2023. “Short-Term Density Forecasting of Low-Voltage Load Using Bernstein-Polynomial Normalizing Flows.” IEEE Transactions on Smart Grid 14 (6): 4902–11. https://doi.org/10.1109/TSG.2023.3254890.

Arpogaus, Marcel, et al. “Short-Term Density Forecasting of Low-Voltage Load Using Bernstein-Polynomial Normalizing Flows.” IEEE Transactions on Smart Grid, vol. 14, no. 6, June 2023, pp. 4902–11, https://doi.org/10.1109/TSG.2023.3254890.