Publication:

Forecasting What Matters: DecisionFocused RL for Controlled EV Charging with Unknown Departure Times

Date

 
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
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.orcid0000-0001-8072-4532
cris.virtual.orcid0000-0003-2707-4176
cris.virtualsource.department3a02f10b-34a0-4aad-bf38-0cd86e77ef0e
cris.virtualsource.department0888a712-4dcf-4c7f-b0c9-3747dd0787bc
cris.virtualsource.department85b4733f-a9ef-4085-a12d-030ac887f5ff
cris.virtualsource.department620b024a-fd0a-4fbf-9967-6a13307ced87
cris.virtualsource.orcid3a02f10b-34a0-4aad-bf38-0cd86e77ef0e
cris.virtualsource.orcid0888a712-4dcf-4c7f-b0c9-3747dd0787bc
cris.virtualsource.orcid85b4733f-a9ef-4085-a12d-030ac887f5ff
cris.virtualsource.orcid620b024a-fd0a-4fbf-9967-6a13307ced87
dc.contributor.authorGabriele, Giuseppe
dc.contributor.authorPavirani, Fabio
dc.contributor.authorMadahi, Seyed Soroush Karimi
dc.contributor.authorDevelder, Chris
dc.date.accessioned2026-11-10T09:35:15Z
dc.date.available2026-11-10T09:35:15Z
dc.date.createdwos2026
dc.date.issued2026
dc.description.abstractThe recent growth of EV adoption poses challenges for power systems, including increased peak demand and potential grid instability. Smart control of EV charging — e.g., based on reinforcement learning (RL) — can alleviate these issues by learning temporal and contextual patterns from historical data. Yet, in real-world scenarios, key features, such as departure time, often are unavailable. This, in turn, makes it harder for an RL agent to learn and execute an effective charging policy. To mitigate this uncertainty, a trained forecaster can approximate the unknown features from available data. However, since these forecasting models are typically trained for accuracy (rather than their impact on a downstream agent’s decision quality), their errors may propagate and hinder the overall performance of a controller that is using the forecasts. To avoid this, we propose a decision‑focused RL (DF-RL) framework in which the forecaster is trained end‑to‑end, i.e., with feedback from the charging policy actions taken by the RL agent. Such joint training of both the forecaster and controller ultimately results in higher‑quality actions: our proposed DF-RL method yields superior charging decisions compared to other baselines, achieving up to a 14% improvement in total reward and a 55% reduction of unsupplied energy (i.e., charging that failed to happen because the EV already left), relative to the RL method without departure time forecasting.
dc.description.wosFundingTextThis research was partly funded by the Flemish Government through the "Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen" programme, and by the EU through the Horizon Europe project BlueBird (https://bluebirdproject.eu/ - grant agreement no. 101192452)
dc.identifier.doi10.1145/3744255.3811736
dc.identifier.isbn979-8-4007-2011-6
dc.identifier.issn/
dc.identifier.urihttps://imec-publications.be/handle/20.500.12860/60786
dc.language.isoeng
dc.provenance.editstepusergreet.vanhoof@imec.be
dc.publisherASSOC COMPUTING MACHINERY
dc.source.beginpage235
dc.source.conference17th ACM International Conference on Future and Sustainable Energy Systems
dc.source.conferencedate2026-06-22
dc.source.conferencelocationBanff, Canada
dc.source.endpage239
dc.source.journalPROCEEDINGS OF THE 17TH ACM INTERNATIONAL CONFERENCE ON FUTURE AND SUSTAINABLE ENERGY, E-ENERGY
dc.source.numberofpages5
dc.title

Forecasting What Matters: DecisionFocused RL for Controlled EV Charging with Unknown Departure Times

dc.typeProceedings paper
dspace.entity.typePublication
imec.internal.crawledAt2026-06-17
imec.internal.sourcecrawler
imec.internal.wosCreatedAt2026-11-07
Files

Original bundle

Name:
3744255.3811736.pdf
Size:
587.53 KB
Format:
Adobe Portable Document Format
Description:
Published
Publication available in collections: