TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Arpogaus, Marcel
A1  - Voß, Marcus
A1  - Sick, Beate
A1  - Nigge-Uricher, Mark
A1  - Dürr, Oliver
T1  - Probabilistic Short-Term Low-Voltage Load Forecasting using Bernstein-Polynomial Normalizing Flows
T2  - ICML 2021, Workshop Tackling Climate Change with Machine Learning, June 26, 2021, virtual
N2  - The transition to a fully renewable energy grid requires better forecasting of demand at the low-voltage level. 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.
KW  - Power and energy
KW  - Deep Learning
KW  - Probabilistic forecasting
KW  - Generative modeling
KW  - Uncertainty quantification and robustness
Y1  - 2021
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:kon4-opus4-29255
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:kon4-opus4-29255
UR  - https://www.climatechange.ai/papers/icml2021/20/paper.pdf
SP  - 6
S1  - 6
ER  -