Autonomous in-situ modeling for virtual building models in digital twins

Abstract

A virtual building model (VBM) is a mathematical representation that serves as a virtual replica, depicting the physical behavior of real building systems in a building digital twin (DT). DT-enabled building operations leveraging VBMs have contributed to reducing energy consumption during building operations. In-situ modeling approaches strive to develop accurate VBMs; however, the autonomous development of VBMs using these approaches remains unexplored. To address this gap, this study introduces an autonomous in-situ modeling (AIM) method, representing the first attempt to autonomously develop an unobserved virtual model. AIM aims to calibrate pre-built models using autonomously developed virtual models. This method was applied to predict evaporator inlet temperatures in a real operating heating, ventilating, and air conditioning (HVAC) system, as well as the secondary-side supply water pressure in a district heating substation (DHS) system. The effectiveness of the AIM-developed virtual evaporator inlet temperature model was evaluated by comparing the results with expert-developed virtual models. The AIM-driven target virtual model achieved a root mean squared error (RMSE) accuracy of 0.40 °C, compared to 0.73 °C when expert intervention was involved. The AIM-driven virtual secondary-side supply water pressure model achieved an RMSE of 0.16 Pa, indicating that AIM can serve as a generalizable algorithm applicable to various building energy systems. These results validate AIM’s feasibility and highlight its potential to extend the virtual model infrastructure within a DT environment. This advancement paves the way for DT-enabled autonomous building operation.