Semantic Inference-Based Control Strategies for Building HVAC Systems Using Modelica-Based Physical Models
Parastoo Delgoshaei, Mohammad Heidarinejad, Mark A. Austin · Procedia Engineering · 2017
The focus of this paper is on an integrated approach for HVAC modeling (semantic and physical), optimization, and control. It utilizes the Building Control Virtual Test Bed (BCVTB) platform to integrate ontologies along with rule sets into Model Predictive Control (MPC) routines and Modelica-based simulations. The ontologies represent the data in the form of semantic models of the domain. They include concepts and the relationships between them, i.e., mechanical equipment, zones, and sensors. While the MPC ensures optimized physical control, the ontologies and rule sets are responsible for data-driven and inference-based semantic control. The Web Ontology Language (OWL) is used to describe the ontologies, and Jena API was used as the framework to create the ontologies and define the rule sets.