Normalizing Flow-based Day-Ahead Wind Power Scenario Generation for Profitable and Reliable Delivery Commitments by Wind Farm Operators

Cramer, Eike; Paeleke, Leonard; Mitsos, Alexander; Dahmen, Manuel

doi:10.48550/arxiv.2204.02242

Cited by 1 publication

(1 citation statement)

References 44 publications

(87 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed four-dimensional distribution of price differences is modeled using normalizing flows Papamakarios et al, 2021), a non-parametric, i.e., fully data-driven, distribution model. Normalizing flows learn complex distributions without a priori assumptions about the data and can include external impact factors for probabilistic regression (Winkler et al, 2019;Cramer et al, 2022b). For scenario generation of other energy time series, such as renewable electricity generation and electricity demand, normalizing flows have already shown promising results (Dumas et al, 2022;Cramer et al, 2022a,b;Arpogaus et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Multivariate Probabilistic Forecasting of Intraday Electricity Prices using Normalizing Flows

Cramer¹,

Witthaut²,

Mitsos³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Electricity is traded on various markets with different time horizons and regulations. Short-term trading becomes increasingly important due to higher penetration of renewables. In Germany, the intraday electricity price typically fluctuates around the day-ahead price of the EPEX spot markets in a distinct hourly pattern. This work proposes a probabilistic modeling approach that models the intraday price difference to the day-ahead contracts. The model captures the emerging hourly pattern by considering the four 15 min intervals in each day-ahead price interval as a four-dimensional joint distribution. The resulting nontrivial, multivariate price difference distribution is learned using a normalizing flow, i.e., a deep generative model that combines conditional multivariate density estimation and probabilistic regression. The normalizing flow is compared to a selection of historical data, a Gaussian copula, and a Gaussian regression model. Among the different models, the normalizing flow identifies the trends most accurately and has the narrowest prediction intervals. Notably, the normalizing flow is the only approach that identifies rare price peaks. Finally, this work discusses the influence of different external impact factors and finds that, individually, most of these factors have negligible impact. Only the immediate history of the price difference realization and the combination of all input factors lead to notable improvements in the forecasts.

show abstract

Section: Introductionmentioning

confidence: 99%