A Dynamic Semantic Data Modeling Approach: Application to Flexible HVAC Zones

Shoya Marumoto, Shohei Miyata, Keiichiro Taniguchi, Yasunori Akashi
EIA Nordic 2025, Lecture Notes in Computer Science, vol 16096, Nov. 2025
https://doi.org/10.1007/978-3-032-03098-6_8

Abstract
The semantic data model (SDM), which is considered a foundation for uniting data that are currently dispersed individually, was not envisioned to change intrinsically during daily use. Thus, the SDM needs to adapt to spatial flexibility for more advanced data-driven control using dynamically changing spatial information. Based on this issue, this study proposes a dynamic description approach of the SDM with examples. Specifically, a method for describing an SDM that reflects the changes in the HVAC zones of each air conditioner owing to the movement of partitions and the operation status of the air conditioners is proposed. The changes in the SDM are classified into two types: addition of telemetry data and changes in the graph structure. As an example of application which associates with the dynamic SDM, a method for estimating each changing HVAC zone was proposed and the results were analyzed. Although the changes were observed in the HVAC zones, some cases were difficult to consider in practically. However, the results show the possibilities for more sophisticated estimation methods and its applicability to the dynamic SDM. As a case study in constructing an information system incorporating a dynamic SDM, a prototype was developed using a physical model. The system encompasses the sensing of partitions and occupants within the model, data integration to the SDM, and display of application outputs. The system was analyzed in comparison with previously proposed system architectures to demonstrate the potential use of dynamic SDM in smart building operations.