Vaes, Julien;
Charitopoulos, Vassilis M;
(2023)
A data-driven uncertainty modelling and reduction approach for energy optimisation problems.
In: Kokossis, Antonios C and Georgiadis, Michael C and Pistikopoulos, Efstratios, (eds.)
Computer Aided Chemical Engineering.
(pp. 1161-1167).
Elsevier: Amsterdam, The Netherlands.
![]() |
Text
escape_paper.pdf - Accepted Version Access restricted to UCL open access staff Download (7MB) |
Abstract
Taking uncertainty into account is crucial when making strategic decisions. To guard against the risk of adverse scenarios, traditional optimisation techniques incorporate uncertainty based on prior knowledge on its distribution. In this paper, we show how, based on limited historical data, we can generate from a low-dimensional space the underlying structure of uncertainty. To this end, we first exploit the correlation between the sources of uncertainty through a principal component analysis (PCA) to reduce dimensionality. Next, we perform clustering to reveal the typical uncertainty patterns, and finally we generate polyhedral uncertainty sets based on a kernel density estimation (KDE) of marginal probability functions.
Type: | Book chapter |
---|---|
Title: | A data-driven uncertainty modelling and reduction approach for energy optimisation problems |
ISBN-13: | 978-0-443-15274-0 |
DOI: | 10.1016/B978-0-443-15274-0.50185-2 |
Publisher version: | http://dx.doi.org/10.1016/b978-0-443-15274-0.50185... |
Language: | English |
Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
Keywords: | Polyhedral Uncertainty Set, Robust Optimisation (RO), PCA, Kernel density estimation (KDE), Dimensionality Reduction, Data scarcity |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Chemical Engineering |
URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10194774 |
Archive Staff Only
![]() |
View Item |