The transition toward energy-efficient and smart buildings requires Digital Twins (DTs) that can couple real-time data with physics-based Building Energy Models (BEMs) for predictive and adaptive operation. Yet, despite rapid digitalisation, there remains a lack of practical guidance and real-world implementations demonstrating how calibrated BEMs can be effectively integrated into Building Management Systems (BMSs). This study addresses that gap by presenting a complete and reproducible end-to-end framework for embedding physics-based BEMs into operational DTs using two setups: (i) encapsulation as Functional Mock-up Units (FMUs) and (ii) containerisation via Docker. Both approaches were deployed and tested in a real educational building in Cáceres (Spain), equipped with a LoRaWAN-based sensing and actuation infrastructure. A systematic comparison highlights their respective trade-offs: FMUs offer faster execution but limited weather inputs and higher implementation effort, whereas Docker-based workflows provide full portability, scalability, and native interoperability with Internet of Things (IoT) and BMS architectures. To enable real-time operation, a surrogate modelling framework was embedded within the Docker architecture to replicate the optimisation logic of the calibrated BEM and generate predictive blind control schedules in milliseconds—bypassing simulation overhead and enabling continuous actuation. The combined Docker + surrogate setup achieved 10–15% heating energy savings during winter operation without any HVAC retrofit. Beyond the case study, this work provides a step-by-step, in-depth guideline for practitioners to integrate calibrated BEMs into real-time control loops using existing toolchains. The proposed approach demonstrates how hybrid physics- and data-driven DTs can transform building management into a scalable, energy-efficient, and operationally deployable reality.

The current climate and energy crises demand innovative approaches to operating buildings more sustainably. HVAC systems, which significantly contribute to a building’s energy consumption, have been a major focus of research aimed at improving operational efficiency. However, a critical factor often overlooked is the seasonal and hourly variation in solar radiation and the resulting solar heat gain, which heats specific rooms differently depending on their orientation, type, and location within the building. This study proposes a simulation-based strategy to reduce HVAC energy use in hotels by allocating guests to rooms with more favorable thermal characteristics depending on the season. A high-resolution building energy model (BEM) was developed to represent a real 17-floor hotel tower in Madrid, incorporating detailed geometry and surrounding shading context. The model includes 439 internal thermal zones and simulates solar radiation using EnergyPlus’ Radiance module. The simulation results revealed large room-by-room differences in thermal energy demand. When applying an energetically optimized guest allocation strategy based on these simulations and using real occupancy data, potential reductions in HVAC energy demand were estimated to reach around 6% during summer and up to 20% in winter. These findings demonstrate that data-driven guest allocation, informed by physics-based building simulations, can provide substantial energy savings without requiring physical renovations or equipment upgrades, offering a promising approach for more sustainable hotel operation.