guest ::
| Home > Publications database > Principal Component Density Estimation for Scenario Generation Using Normalizing Flows > print |
| Home > Publications database > Principal Component Density Estimation for Scenario Generation Using Normalizing Flows > print |
| 001 | 905464 | ||
| 005 | 20240712112904.0 | ||
| 024 | 7 | _ | |2 arXiv |a arXiv:2104.10410 |
| 024 | 7 | _ | |2 Handle |a 2128/30348 |
| 024 | 7 | _ | |2 altmetric |a altmetric:104444026 |
| 037 | _ | _ | |a FZJ-2022-00705 |
| 100 | 1 | _ | |0 P:(DE-Juel1)179591 |a Cramer, Eike |b 0 |u fzj |
| 245 | _ | _ | |a Principal Component Density Estimation for Scenario Generation Using Normalizing Flows |
| 260 | _ | _ | |c 2021 |
| 336 | 7 | _ | |0 PUB:(DE-HGF)25 |2 PUB:(DE-HGF) |a Preprint |b preprint |m preprint |s 1646223063_5186 |
| 336 | 7 | _ | |2 ORCID |a WORKING_PAPER |
| 336 | 7 | _ | |0 28 |2 EndNote |a Electronic Article |
| 336 | 7 | _ | |2 DRIVER |a preprint |
| 336 | 7 | _ | |2 BibTeX |a ARTICLE |
| 336 | 7 | _ | |2 DataCite |a Output Types/Working Paper |
| 500 | _ | _ | |a 18 pages, 7 figures |
| 520 | _ | _ | |a Neural networks-based learning of the distribution of non-dispatchable renewable electricity generation from sources such as photovoltaics (PV) and wind as well as load demands has recently gained attention. Normalizing flow density models are particularly well suited for this task due to the training through direct log-likelihood maximization. However, research from the field of image generation has shown that standard normalizing flows can only learn smeared-out versions of manifold distributions. Previous works on normalizing flow-based scenario generation do not address this issue, and the smeared-out distributions result in the sampling of noisy time series. In this paper, we exploit the isometry of the principal component analysis (PCA), which sets up the normalizing flow in a lower-dimensional space while maintaining the direct and computationally efficient likelihood maximization. We train the resulting principal component flow (PCF) on data of PV and wind power generation as well as load demand in Germany in the years 2013 to 2015. The results of this investigation show that the PCF preserves critical features of the original distributions, such as the probability density and frequency behavior of the time series. The application of the PCF is, however, not limited to renewable power generation but rather extends to any data set, time series, or otherwise, which can be efficiently reduced using PCA. |
| 536 | _ | _ | |0 G:(DE-HGF)POF4-1121 |a 1121 - Digitalization and Systems Technology for Flexibility Solutions (POF4-112) |c POF4-112 |f POF IV |x 0 |
| 536 | _ | _ | |0 G:(DE-Juel1)HDS-LEE-20190612 |a HDS LEE - Helmholtz School for Data Science in Life, Earth and Energy (HDS LEE) (HDS-LEE-20190612) |c HDS-LEE-20190612 |x 1 |
| 588 | _ | _ | |a Dataset connected to arXivarXiv |
| 700 | 1 | _ | |0 P:(DE-Juel1)172025 |a Mitsos, Alexander |b 1 |u fzj |
| 700 | 1 | _ | |0 P:(DE-HGF)0 |a Tempone, Raul |b 2 |
| 700 | 1 | _ | |0 P:(DE-Juel1)172097 |a Dahmen, Manuel |b 3 |e Corresponding author |u fzj |
| 773 | _ | _ | |a 10.1017/dce.2022.7 |y 2021 |
| 856 | 4 | _ | |u https://juser.fz-juelich.de/record/905464/files/2104.10410.pdf |y OpenAccess |
| 909 | C | O | |o oai:juser.fz-juelich.de:905464 |p openaire |p open_access |p VDB |p driver |p dnbdelivery |
| 910 | 1 | _ | |0 I:(DE-588b)5008462-8 |6 P:(DE-Juel1)179591 |a Forschungszentrum Jülich |b 0 |k FZJ |
| 910 | 1 | _ | |0 I:(DE-588b)36225-6 |6 P:(DE-Juel1)179591 |a RWTH Aachen |b 0 |k RWTH |
| 910 | 1 | _ | |0 I:(DE-588b)5008462-8 |6 P:(DE-Juel1)172025 |a Forschungszentrum Jülich |b 1 |k FZJ |
| 910 | 1 | _ | |0 I:(DE-588b)36225-6 |6 P:(DE-Juel1)172025 |a RWTH Aachen |b 1 |k RWTH |
| 910 | 1 | _ | |0 I:(DE-588b)36225-6 |6 P:(DE-HGF)0 |a RWTH Aachen |b 2 |k RWTH |
| 910 | 1 | _ | |0 I:(DE-HGF)0 |6 P:(DE-HGF)0 |a KAUST |b 2 |
| 910 | 1 | _ | |0 I:(DE-588b)5008462-8 |6 P:(DE-Juel1)172097 |a Forschungszentrum Jülich |b 3 |k FZJ |
| 913 | 1 | _ | |0 G:(DE-HGF)POF4-112 |1 G:(DE-HGF)POF4-110 |2 G:(DE-HGF)POF4-100 |3 G:(DE-HGF)POF4 |4 G:(DE-HGF)POF |9 G:(DE-HGF)POF4-1121 |a DE-HGF |b Forschungsbereich Energie |l Energiesystemdesign (ESD) |v Digitalisierung und Systemtechnik |x 0 |
| 914 | 1 | _ | |y 2021 |
| 915 | _ | _ | |0 StatID:(DE-HGF)0510 |2 StatID |a OpenAccess |
| 920 | _ | _ | |l yes |
| 920 | 1 | _ | |0 I:(DE-Juel1)IEK-10-20170217 |k IEK-10 |l Modellierung von Energiesystemen |x 0 |
| 980 | 1 | _ | |a FullTexts |
| 980 | _ | _ | |a preprint |
| 980 | _ | _ | |a VDB |
| 980 | _ | _ | |a I:(DE-Juel1)IEK-10-20170217 |
| 980 | _ | _ | |a UNRESTRICTED |
| 981 | _ | _ | |a I:(DE-Juel1)ICE-1-20170217 |
| Library | Collection | CLSMajor | CLSMinor | Language | Author |
|---|