Publication:

S3TS: Stochastic Scenario-Structured Tree Search for advanced planning under uncertainty

Date

 
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid0009-0005-7904-099X
cris.virtual.orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid0000-0003-2707-4176
cris.virtualsource.department3a02f10b-34a0-4aad-bf38-0cd86e77ef0e
cris.virtualsource.departmentb1ed2720-3619-440a-8c4f-be92499407bc
cris.virtualsource.department620b024a-fd0a-4fbf-9967-6a13307ced87
cris.virtualsource.orcid3a02f10b-34a0-4aad-bf38-0cd86e77ef0e
cris.virtualsource.orcidb1ed2720-3619-440a-8c4f-be92499407bc
cris.virtualsource.orcid620b024a-fd0a-4fbf-9967-6a13307ced87
dc.contributor.authorPavirani, Fabio
dc.contributor.authorClaessens, Bert
dc.contributor.authorPinson, Pierre
dc.contributor.authorDevelder, Chris
dc.date.accessioned2026-11-16T12:56:08Z
dc.date.available2026-11-16T12:56:08Z
dc.date.createdwos2026
dc.date.issued2026
dc.description.abstractEffective scheduling is essential to the reliable operation of electrical grids and their connected assets. An effective planning strategy must accommodate advanced, potentially non-linear system models while explicitly handling the uncertainties arising from the integration of renewable energy sources. Existing approaches can address either non-linearity (e.g., Monte Carlo Tree Search) or uncertainty (e.g., stochastic mathematical optimization), but rarely both simultaneously. To bridge this gap, we propose a Stochastic Scenario-Structured Tree Search (S3TS) algorithm that explicitly represents uncertainty through scenario trees while enabling the integration of advanced non-linear models. We evaluate S3TS on a simulated demand response signal publication problem, largely mimicking the imbalance settlement mechanism in Belgium. In linear, analytically tractable settings, its costs are within 14% of the mathematically optimal solution conditioned on the scenario trees. In highly non-linear scenarios, S3TS reduces cost by up to 51% and 5.3% compared to a myopic algorithm and deterministic MCTS, respectively, and consistently outperforms three online-sampling tree searches. Sensitivity studies over the tree configuration, the search parameters, and a misspecified scenario distribution confirm the robustness of S3TS.
dc.description.wosFundingTextThis research was partly funded by the Flemish Government through the "Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen" programme as well as a travel grant from the Research Foundation-Flanders, by the Energy Transition Fund.
dc.identifier.doi10.1016/j.egyai.2026.100920
dc.identifier.issn2666-5468
dc.identifier.urihttps://imec-publications.be/handle/20.500.12860/60805
dc.language.isoeng
dc.provenance.editstepusergreet.vanhoof@imec.be
dc.publisherELSEVIER
dc.source.beginpage100920
dc.source.endpage16
dc.source.journalENERGY AND AI
dc.source.numberofpages16
dc.source.volume26
dc.title

S3TS: Stochastic Scenario-Structured Tree Search for advanced planning under uncertainty

dc.typeJournal article review
dspace.entity.typePublication
imec.internal.crawledAt2026-11-05
imec.internal.sourcecrawler
imec.internal.wosCreatedAt2026-11-05
Files

Original bundle

Name:
1-s2.0-S2666546826002466-main.pdf
Size:
2.88 MB
Format:
Adobe Portable Document Format
Description:
Published
Publication available in collections: