Esther Borkowski

Last Name

Borkowski

First Name

Esther

ORCID

0000-0003-3631-7651

Show all metadata

Search Results

Publications1 - 10 of 12

Developing a weighting scheme for building operational performance: A case study from the Netherlands
Luo , Wei; Johra , Hicham; Borkowski, Esther; et al. (2025)
Building and Environment
Building operations must balance the often-competing performance objectives of occupants’ needs, energy efficiency, and power grid demand, posing a complex multi-criteria decision-making problem. Tailored weighting schemes offer practical approaches to synthesize these diverse performance aspects onto a common scale, effectively informing building operations and overall performance evaluations. However, such schemes remain underdeveloped. To address this gap, a stakeholder ontology was first developed to analyze power dynamics and information flows among stakeholders involved in building operational performance. Building managers were identified as key stakeholders to determine weights of such a scheme. Subsequently, building on the Smart Readiness Indicator (SRI) framework, a survey was conducted to calculate the weights for commercial buildings using the Analytic Hierarchy Process (AHP). Inputs from 27 building managers in the Netherlands were collected, along with 13 building owners and 13 international researchers. Results showed that performance aspects were not equally weighted. Building managers prioritized occupants’ health and wellbeing, building service downtime, and occupant comfort, while assigning the lowest weight to operational cost. Building owners and researchers also agreed with these top three priorities. However, considerable individual variation in priorities was observed, even after accounting for stakeholder roles, building types, and country. These findings suggest that the SRI weighting scheme should be adapted to regional contexts and highlight the necessity for customizable building management dashboards tailored to specific building conditions. Finally, the proposed weighting scheme offers pragmatic insights to support decision making in building operations, policy development, certification systems development, and smart building control and management.
A scalable approach for real-world implementation of deep reinforcement learning controllers in buildings based on online transfer learning: The HiLo case study
Coraci, Davide; Silvestri, Alberto; Razzano, Giuseppe; et al. (2025)
Energy and Buildings
In recent years, Transfer Learning (TL) has emerged as a promising solution to scale Deep Reinforcement Learning (DRL) controllers for building energy management, addressing challenges related to DRL implementation as high data requirements and reliance on surrogate models. Moreover, most TL applications are limited to simulations, not revealing their real performance in actual buildings. This paper explores the implementation of an online TL methodology combining imitation learning and fine-tuning to transfer a DRL controller between two real office environments. Pre-trained in simulation using a calibrated digital twin, the DRL controller reduces energy consumption and improves indoor temperature control when managing the operation of a Thermally Activated Building System in one of the two offices both in simulation and in the real field. Afterwards, the DRL controller is transferred to the other office following the online TL methodology. The proposed approach outperforms a DRL controller implemented without pre-training, and Rule-Based and Proportional-Integral controllers, achieving energy savings between 6 and 40% and improving indoor temperature control between 30 and 50%. These findings underscore the efficacy of the online TL methodology as a viable solution to enhance the scalability of DRL controllers in real buildings.
Overview of occupant-centric KPIs for building performance and their value to various building stakeholders
Sleiman, Sleiman; Ouf, Mohamed; Luo, Wei; et al. (2024)
Energy and Buildings
Recognizing the significance of occupants and their interactions with the building's operational systems, various occupant-related key performance indicators (KPIs) have been established. However, there remains a notable gap concerning the practical utilization of these indicators by building stakeholders. Therefore, this study provides a comprehensive overview of the occupant-related building performance KPIs and how various building stakeholders influence them through their decision-making. The study assessed: (1) roles of various building stakeholders; (2) stakeholders’ requirement for occupant-centric KPIs in their decision-making process; (3) factors demonstrating effective occupant-centric KPIs along with data requirements to evaluate them; and (4) stakeholders’ decisions and actions that affect occupant-centric KPIs. Key stakeholders identified involved investors, building owners, designers, building occupants, building managers and operators, as well as utility providers. Effective occupant-centric KPIs were characterised by their fit-for-purpose, actionability, quantifiability, comparability, reproducibility, integrability, feasibility, and usability. Results indicated that building managers and operators primarily affect thermal, air quality, and visual KPIs. Building occupants, public authorities, investors, building owners, and designers influence all categories of occupant-centric KPIs. Utility providers particularly impact thermal KPIs. In conclusion, findings of this study contribute to shaping the way in which stakeholders consider occupants in their decision-making to achieve building performance objectives by data-driven occupant-centric KPIs.
Mediating effects of ventilation on the impacts of temperature on human comfort, health and cognitive performance: A living lab study
Fan, Xiaojun; Wargocki , Pawel; Silvestri , Alberto; et al. (2025)
Building and Environment
The independent effects of increased temperature and reduced ventilation on human comfort, health, and cognitive performance are well documented. However, how ventilation moderates the impacts of temperature on humans remains underexplored. This living lab study investigated thermal comfort, acute health symptoms, physiological responses and cognitive performance under three experimental conditions: two temperatures (24 and 27 °C) and two ventilation scenarios (mechanical ventilation on at 215 m³/h and off). Sixteen subjects were exposed to each condition for 125 min in a balanced order. At 27 °C, when the ventilation system was turned off, the mean CO₂ concentration increased from 800 ppm to 1900 ppm. Subjects felt warmer and rated the thermal environment as less acceptable compared to the ventilated condition. The increase in mean skin temperature and decrease in core body temperature were further significantly aggravated. Compared to 24 °C with ventilation, subjects reported greater fatigue and sleepiness and rated the air quality even worse, along with a declining trend in cognitive performance (P < 0.05, d < 0.5), even though no significant independent effects of increased temperature or reduced ventilation were observed within the short exposure duration. These findings suggest that ventilation mediates the effects of temperature, even within typical indoor ranges, and highlight noteworthy interactions between temperature and ventilation. These results support the revision of the current temperature and ventilation requirements in existing standards, particularly in the context of a warming world.
Challenges in modelling thermo-optical performance of 3D-printed facades: a cross-domain review
Piccioni, Valeria; Leschok, Matthias; Borkowski, Esther; et al. (2023)
Building Simulation Conference Proceedings ~ Proceedings of Building Simulation 2023: 18th Conference of IBPSA
Thanks to large-scale 3D printing, it is possible to fabricate performance-integrated building facades, contributing to the building sector's decarbonisation. The assessment of thermo-optical performance in 3D-printed facades (3DPF) is still at an early stage. The main challenges are related to the specificity of such components: the geometrical complexity, the interaction of multiple physical effects and the influence of the fabrication process on their properties. This focused review examines the aspects of performance indicators, multiphysics and multiscale modelling by reviewing recent efforts in the fields of advanced facades and process engineering. Learnings from the reviewed studies guided the development of a novel approach for modelling the thermo-optical properties of polymer 3DPF and informing their design.
Thermal and uncertainty analysis of a lightweight floor with integrated TABS and ventilation system
Borkowski, Esther; Lydon, Gearóid; Schlueter, Arno (2023)
Building Simulation Conference Proceedings ~ Proceedings of Building Simulation 2023: 18th Conference of IBPSA
The HiLo living lab combines numerous novel multifunctional building elements, including a floor system that integrates TABS and ventilation system into complex geometry and lightweight structural components. The purpose of this study is to investigate the operational performance of the floor system and to compare it with the performance predicted by a white-box model in TRNSYS. Although the model can accurately and reliably predict the actual performance of the floor system with a median CV-RMSE index of 3.35%, the limited variability in the data and the unique conditions of the living lab may limit the generalisability of the model.
Comparison of two deep reinforcement learning algorithms towards an optimal policy for smart building thermal control
Silvestri, Alberto; Coraci, Davide; Wu, Duan; et al. (2023)
Journal of Physics: Conference Series ~ CISBAT International Conference 2023: Predictive & adaptive control
Heating, Ventilation, and Air Conditioning (HVAC) systems are the main providers of occupant comfort, and at the same time, they represent a significant source of energy consumption. Improving their efficiency is essential for reducing the environmental impact of buildings. However, traditional rule-based and model-based strategies are often inefficient in real-world applications due to the complex building thermal dynamics and the influence of heterogeneous disturbances, such as unpredictable occupant behavior. In order to address this issue, the performance of two state-of-the-art model-free Deep Reinforcement Learning (DRL) algorithms, Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC), has been compared when the percentage valve opening is managed in a thermally activated building system, modeled in a simulated environment from data collected in an existing office building in Switzerland. Results show that PPO reduced energy costs by 18% and decreased temperature violations by 33%, while SAC achieved a 14% reduction in energy costs and 64% fewer temperature violations compared to the onsite Rule-Based Controller (RBC).
Real building implementation of a deep reinforcement learning controller to enhance energy efficiency and indoor temperature control
Silvestri, Alberto; Coraci, Davide; Brandi, Silvio; et al. (2024)
Applied Energy
Deep Reinforcement Learning (DRL) has emerged as a promising approach to address the trade-off between energy efficiency and indoor comfort in buildings, potentially outperforming conventional Rule-Based Controllers (RBC). This paper explores the real-world application of a Soft-Actor Critic (SAC) DRL controller in a building’s Thermally Activated Building System (TABS), focusing on optimising energy consumption and maintaining comfortable indoor temperatures. Our approach involves pre-training the DRL agent using a simplified Resistance-Capacitance (RC) model calibrated with real building data. The study first benchmarks the DRL controller against three RBCs, two Proportional-Integral (PI) controllers and a Model Predictive Controller (MPC) in a simulated environment. In the simulation study, DRL reduces energy consumption by 15% to 50% and decreases temperature violations by 25% compared to RBCs, reducing also energy consumption and temperature violations compared to PI controllers by respectively 23% and 5%. Moreover, DRL achieves comparable performance in terms of temperature control but consuming 29% more energy than an ideal MPC. When implemented in a real building during a two-month cooling season, the DRL controller performances were compared with those of the best-performing RBC, enhancing indoor temperature control by 68% without increasing energy consumption. This research demonstrates an effective strategy for training and deploying DRL controllers in real building energy systems, highlighting the potential of DRL in practical energy management applications.
Teaching architecture through an energy and climate lens
Hischier, Illias; Grobe, Lars Oliver; Waibel, Christoph; et al. (2025)
ETH Learning and Teaching Journal
Despite the increasing societal awareness of the climate crisis, considerations of outdoor and indoor climate, energy consumption and generation, and the environmental impact of material choices still represent a niche in architectural practice. Given the urgency of the issue, addressing these topics needs to be integrated in architectural design. In this work, we first describe a build-up of teaching formats and position them in view of learners’ competence development in architectural design through an energy and climate lens. We identify opportunities to refine our teaching instruments further and improve the learners' ability to independently integrate topics related to energy, emissions, climate, and comfort in the practice of design projects. We end with an outlook of an idealized build-up of these competencies across an architecture curriculum.
The GHG Emission Timeline – Integrating sustainability assessment into the early building design stage
Hischier, Illias; Walker, Linus; Piccioni, Valeria; et al. (2023)
Journal of Physics: Conference Series ~ CISBAT International Conference 2023: Life-Cycle Analysis
To address the challenges of integrating sustainability assessment such as life cycle assessment (LCA) in the early building design stage, we propose a new concept: The Greenhouse gas (GHG) Emission Timeline. The concept is derived from researching robustness assessment methods and personal experiences from teaching. Rather than aggregating environmental aspects into a single number, with the Timeline we want to highlight the temporality of GHG emissions in the context of ongoing transformation processes. Similarly to the previously proposed Material Pyramid for comparing the CO2 footprint of different materials, the Timeline is a pedagogical tool to visualize quantities, dynamics, and uncertainties aiming to provide a common ground for discussing sustainability in the early building design stage. The Timeline is compiled in a few simple steps with readily available resources. Hence, it does not need prior expert knowledge. The concept, as well as the first application examples of the Timeline from an architectural design studio at ETH Zurich are presented and discussed. By using GHG emission calculations for the compilation of a historic timeline, students created new lenses that addressed sustainability from a holistic viewpoint beyond GHG emissions.

Publications1 - 10 of 12

Esther Borkowski

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results