EUVIMEDEUVIMED entdecken
Crossref

Knowledge-Enhanced Configuration of Energy Scheduling Models in Multi-Building Energy Communities

Stepan Gagin, Hermann De Meer

ACM SIGEnergy Energy Informatics Review · 01.09.2026 · 6 (3) · 179-193

DOI: 10.1145/3861130.3861144 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM SIGEnergy Energy Informatics Review, online erschienen am 11.11.2026. Verfasst von Stepan Gagin und 1 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The growing deployment of distributed energy resources in buildings has introduced new challenges in managing building energy systems. Modern buildings often integrate diverse devices, such as photovoltaic panels, heat pumps, and storage units, across multiple energy vectors. To efficiently optimize the operation of these interconnected systems, an energy scheduler service is often implemented. However, the configuration of such a service requires extensive knowledge about modeled building systems. The paper presents the architecture of a replicable and interoperable energy scheduling solution. The main contributions are two novel methods for automating energy scheduler model configuration and an ontology for formal energy scheduler model description. The first configuration approach is based on predefined rules to extract relevant information from the semantic descriptions of devices installed in buildings. In the experiments, it is demonstrated that this approach can correctly configure up to 62 % of device parameters, resulting in the representation of 77 % of devices installed in buildings (69 % of the devices have all parameters correctly configured). The second configuration approach does not require the manual creation of the rules and relies on large language models to process semantic descriptions or natural language descriptions of buildings and corresponding devices. It can identify up to 60 % of device parameters correctly, representing 90 % of devices. However, only up to 37 % of the devices are fully configured without missing or incorrect properties. The results of the configuration services are expressed according to the proposed ontology, which is designed to represent all concepts relevant to energy scheduling. This allows for integration with the existing systems and other energy management services.

Zitieren

APA

Gagin, S., & Meer, H. D. (2026). Knowledge-Enhanced Configuration of Energy Scheduling Models in Multi-Building Energy Communities. ACM SIGEnergy Energy Informatics Review, 6(3), 179-193. https://doi.org/10.1145/3861130.3861144

Vancouver

Gagin S, Meer HD. Knowledge-Enhanced Configuration of Energy Scheduling Models in Multi-Building Energy Communities. ACM SIGEnergy Energy Informatics Review. 2026;6(3):179-193. doi:10.1145/3861130.3861144

BibTeX
@article{Gagin2026,
  author = {Gagin, Stepan and Meer, Hermann De},
  title = {Knowledge-Enhanced Configuration of Energy Scheduling Models in Multi-Building Energy Communities},
  journal = {ACM SIGEnergy Energy Informatics Review},
  year = {2026},
  volume = {6},
  number = {3},
  pages = {179--193},
  doi = {10.1145/3861130.3861144}
}
Kostenlos starten →