TY  - JOUR
U1  - Zeitschriftenartikel, wissenschaftlich - begutachtet (reviewed)
A1  - Arpogaus, Marcel
A1  - Voss, Marcus
A1  - Sick, Beate
A1  - Nigge-Uricher, Mark
A1  - Dürr, Oliver
T1  - Short-Term Density Forecasting of Low-Voltage Load using Bernstein-Polynomial Normalizing Flows
JF  - IEEE Transactions on Smart Grid
N2  - 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.
KW  - Normalizing Flows
KW  - Probabilistic Regression
KW  - Deep Learning
KW  - Probabilistic Load Forecasting
KW  - Low-Voltage
Y1  - 2023
UR  - https://doi.org/10.1109/TSG.2023.3254890
SN  - 1949-3053
SS  - 1949-3053
SN  - 1949-3061
SS  - 1949-3061
U6  - https://doi.org/10.48550/arXiv.2204.13939
DO  - https://doi.org/10.48550/arXiv.2204.13939
N1  - Volltextzugriff für Angehörige der Hochschule Konstanz via Datenbank IEEE Xplore möglich
VL  - Vol. 14
IS  - No. 6, November 2023
SP  - 4902
EP  - 4911
PB  - Institute of Electrical and Electronics Engineers (IEEE)
ER  -