Probabilistic short-term low-voltage load forecasting using bernstein-polynomial normalizing flows

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

Publication type:	Conference paper
Type of review:	Peer review (publication)
Title:	Probabilistic short-term low-voltage load forecasting using bernstein-polynomial normalizing flows
Authors:	Arpogaus, Marcel Voss, Marcus Sick, Beate Nigge-Uricher, Mark Dürr, Oliver
et. al:	No
Published in:	International Conference on Machine Learning (ICML) Workshop Tackling Climate Change with Machine Learning, online, 26 June 2021
Issue Date:	2021
Publisher / Ed. Institution:	ICML
Language:	English
Subjects:	Deep learning; Forecast; Energieversorgung; Netzstabilität
Subject (DDC):	006: Special computer methods 333.79: Energy
Abstract:	The transition to a fully renewable energy grid requires better forecasting of demand at the lowvoltage level to increase efficiency and ensure a reliable control. However, high fluctuations and increasing electrification cause huge forecast errors with traditional point estimates. Probabilistic load forecasts take future uncertainties into account and thus enables various applications in 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 363 smart meter customers, our density predictions compare favorably against Gaussian and Gaussian mixture densities and also outperform a non-parametric approach based on the pinball loss for 24h-ahead load forecasting for two different neural network architectures.
URI:	https://www.climatechange.ai/papers/icml2021/20 https://digitalcollection.zhaw.ch/handle/11475/27563
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. (2021). Probabilistic short-term low-voltage load forecasting using bernstein-polynomial normalizing flows. International Conference on Machine Learning (ICML) Workshop Tackling Climate Change with Machine Learning, Online, 26 June 2021. https://www.climatechange.ai/papers/icml2021/20

Arpogaus, M. et al. (2021) ‘Probabilistic short-term low-voltage load forecasting using bernstein-polynomial normalizing flows’, in International Conference on Machine Learning (ICML) Workshop Tackling Climate Change with Machine Learning, online, 26 June 2021. ICML. Available at: https://www.climatechange.ai/papers/icml2021/20.

M. Arpogaus, M. Voss, B. Sick, M. Nigge-Uricher, and O. Dürr, “Probabilistic short-term low-voltage load forecasting using bernstein-polynomial normalizing flows,” in International Conference on Machine Learning (ICML) Workshop Tackling Climate Change with Machine Learning, online, 26 June 2021, 2021. [Online]. Available: https://www.climatechange.ai/papers/icml2021/20

ARPOGAUS, Marcel, Marcus VOSS, Beate SICK, Mark NIGGE-URICHER und Oliver DÜRR, 2021. Probabilistic short-term low-voltage load forecasting using bernstein-polynomial normalizing flows. In: International Conference on Machine Learning (ICML) Workshop Tackling Climate Change with Machine Learning, online, 26 June 2021 [online]. Conference paper. ICML. 2021. Verfügbar unter: https://www.climatechange.ai/papers/icml2021/20

Arpogaus, Marcel, Marcus Voss, Beate Sick, Mark Nigge-Uricher, and Oliver Dürr. 2021. “Probabilistic Short-Term Low-Voltage Load Forecasting Using Bernstein-Polynomial Normalizing Flows.” Conference paper. In International Conference on Machine Learning (ICML) Workshop Tackling Climate Change with Machine Learning, Online, 26 June 2021. ICML. https://www.climatechange.ai/papers/icml2021/20.

Arpogaus, Marcel, et al. “Probabilistic Short-Term Low-Voltage Load Forecasting Using Bernstein-Polynomial Normalizing Flows.” International Conference on Machine Learning (ICML) Workshop Tackling Climate Change with Machine Learning, Online, 26 June 2021, ICML, 2021, https://www.climatechange.ai/papers/icml2021/20.