Multivariate Scenario Generation of Day-Ahead Electricity Prices using Normalizing Flows

Hilger, Hannes; Gorjao, Leonardo Rydin; Dahmen, Manuel; Cramer, Eike; Witthaut, Dirk; Trebbien, Julius

doi:10.48550/ARXIV.2311.14033

Preprint

FZJ-2024-00902

Multivariate Scenario Generation of Day-Ahead Electricity Prices using Normalizing Flows

Hilger, H.FZJ* ; Witthaut, D.FZJ* ; Dahmen, M.FZJ* ; Gorjao, L. R. ; Trebbien, J.FZJ* ; Cramer, E. (Corresponding author)RWTH*FZJ*

2023
arXiv

arXiv (2023) [10.48550/ARXIV.2311.14033]

This record in other databases:

Please use a persistent id in citations: doi:10.48550/ARXIV.2311.14033 doi:10.34734/FZJ-2024-00902

Abstract: Trading on electricity markets requires accurate information about the realization of electricity prices and the uncertainty attached to the predictions. We present a probabilistic forecasting approach for day-ahead electricity prices using the fully data-driven deep generative model called normalizing flows. Our modeling approach generates full-day scenarios of day-ahead electricity prices based on conditional features such as residual load forecasts. Furthermore, we propose extended feature sets of prior realizations and a periodic retraining scheme that allows the normalizing flow to adapt to the changing conditions of modern electricity markets. In particular, we investigate the impact of the energy crisis ensuing from the Russian invasion of Ukraine. Our results highlight that the normalizing flow generates high-quality scenarios that reproduce the true price distribution and yield highly accurate forecasts. Additionally, our analysis highlights how our improvements towards adaptations in changing regimes allow the normalizing flow to adapt to changing market conditions and enables continued sampling of high-quality day-ahead price scenarios.

Keyword(s): Machine Learning (cs.LG) ; FOS: Computer and information sciences

Contributing Institute(s):