The Potential of Harnessing Real-Time Occupancy Data for Improving Energy Performance of Activity-Based Workplaces

Currently, the available studies on the prediction of building energy performance and real occupancy data are typically characterized by aggregated and averaged occupancy patterns or large thermal zones of reference. Despite the increasing diffusion of smart energy management systems and the growing availability of longitudinal data regarding occupancy, these two domains rarely inform each other. This research aims at understanding the potential of employing real-time occupancy data to identify better cooling strategies for activity-based-working (ABW)-supportive offices and reduce the overall energy consumption. It presents a case study comparing the energy performance of the office when different resolutions of occupancy and thermal zoning are applied, ranging from the standard energy certification approach to real-time occupancy patterns. For the first time, one year of real-time occupancy data at the desk resolution, captured through computer logs and Bluetooth devices, is used to investigate this issue. Results show that the actual cooling demand is 9% lower than predicted, unveiling the energy-saving potential to be achieved from HVAC systems for non-assigned seating environments. This research demonstrates that harnessing real-time occupancy data for demand-supply cooling management at a fine-grid resolution is an efficient strategy to reduce cooling consumption and increase workers’ comfort. It also emphasizes the need for more data and monitoring campaigns for the definition of more accurate and robust energy management strategies.

ANALYSES ON OCCUPANT PATTERNS AND ENERGY CONSUMPTION IN RESIDENTIAL BUILDINGS INCLUDING THE COVID-19 PANDEMIC

In the last years, as a result of environmental concerns, changes in lifestyle during the COVID-19 crisis, the role of healthy buildings in addition to the main lighting design principles are highlighted. Therefore, today’s lighting design issues include social well-being, mental well-being, and physical well-being more than we discussed in the last century. Hence, we are familiar with occupant-centric and performance-based metrics for residential and non-domestic buildings. The study analyses the extended occupancy patterns, daylight availability, and annual lighting energy demand through a case study in Bursa, Turkey including the COVID-19 pandemic scenario.

Towards a Living Lab for Enhanced Thermal Comfort and Air Quality: Analyses of Standard Occupancy, Weather Extremes, and COVID-19 Pandemic

Maintaining indoor environmental (IEQ) quality is a key priority in educational buildings. However, most studies rely on outdoor measurements or evaluate limited spatial coverage and time periods that focus on standard occupancy and environmental conditions which makes it hard to establish causality and resilience limits. To address this, a fine-grained, low-cost, multi-parameter IOT sensor network was deployed to fully depict the spatial heterogeneity and temporal variability of environmental quality in an educational building in Sydney. The building was particularly selected as it represents a multi-use university facility that relies on passive ventilation strategies, and therefore suitable for establishing a living lab for integrating innovative IoT sensing technologies. IEQ analyses focused on 15 months of measurements, spanning standard occupancy of the building as well as the Black Summer bushfires in 2019, and the COVID-19 lockdown. The role of room characteristics, room use, season, weather extremes, and occupancy levels were disclosed via statistical analysis including mutual information analysis of linear and non-linear correlations and used to generate site-specific re-design guidelines. Overall, we found that 1) passive ventilation systems based on manual interventions are most likely associated with sub-optimum environmental quality and extreme variability linked to occupancy patterns, 2) normally closed environments tend to get very unhealthy under periods of extreme pollution and intermittent/protracted disuse, 3) the elevation and floor level in addition to room use were found to be significant conditional variables in determining heat and pollutants accumulation, presumably due to the synergy between local sources and vertical transport mechanisms. Most IEQ inefficiencies and health threats could be likely mitigated by implementing automated controls and smart logics to maintain adequate cross ventilation, prioritizing building airtightness improvement, and appropriate filtration techniques. This study supports the need for continuous and capillary monitoring of different occupied spaces in educational buildings to compensate for less perceivable threats, identify the room for improvement, and move towards healthy and future-proof learning environments.

Effectiveness of passive climate change adaptation measures in Switzerland: A climate-based analysis on natural ventilation and overheating risks reduction in dwellings

Building energy codes have been implemented in Switzerland as well as across the world to reduce building energy consumption, however, due to the progressive effect of climate change phenomena and the precipitate change in occupancy patterns due to the global pandemic, their effectiveness and limitations must be constantly re-examined. This paper explores the effectiveness of natural ventilation as a passive cooling strategy, as well as the overheating patterns in dwellings across the Swiss territory. The work is based on a climate-based simulation model at a territorial scale, from which the building performance is further analysed considering the heating energy consumption and overheating risk hours above 26.5°C. The effectiveness of natural ventilation through the operable window operable area in reducing overheating risk was also estimated. The results show the effectiveness across the whole territory of the current regulation (SIA 380/1:2016), which is focused on the performance of the building envelope to reduce heat losses. An unattended alarming overheating pattern was spotted in locations with altitudes below 1500 meters as a direct consequence of the climate change phenomena, hence a series of recommendations are proposed to update and improve the current legal requirements.

Optimizing occupant-centric building controls given stochastic occupant behaviour

Occupant-centric control (OCC) strategies represent a novel approach for indoor climate control in which occupancy patterns and occupant preferences are embedded within control sequences. They aim to improve both occupant comfort and energy efficiency by learning and predicting occupant behaviour, then optimizing building operations accordingly. Previous studies estimate that OCC can increase energy savings by up to 60% while improving occupant comfort. However, their performance is subjected to several factors, including uncertainty due to occupant behaviour, OCC configurational settings, as well as building design parameters. To this end, testing OCCs and adjusting their configurational settings are critical to ensure optimal performance. Furthermore, identifying building design alternatives that can optimize such performance given different occupant preferences is an important step that cannot be investigated during field implementations of OCC due to logistical constraints. This paper presents a framework to optimize OCC performance in a simulation environment, which entails coupling synthetic occupant behaviour models with OCCs that learn their preferences. The genetic algorithm for optimization is then used to identify the configurational settings and design parameters that minimize energy consumption under three different occupant scenarios. To demonstrate the proposed framework, three OCCs were implemented in the building simulation program, EnergyPlus, and executed through a Python package, EPPY to optimize OCC configurational settings and design parameters. Results revealed significant improvement of OCC performance under the identified optimal configurational settings and design parameters for each of the investigated occupant scenarios. This approach would improve OCC performance in actual buildings and avoid discomfort issues that arise during the initial implementation phases.

Imputing Parking Usage on Sparsely Monitored Areas Within Amsterdam Through the Application of Machine Learning

Effective parking policy is essential for cities to reduce the demand their road networks experience and to combat their carbon footprints. Existing research in the application of machine learning to understand parking behavior assumes that cities have prohibitively expensive stationary parking sensors installed, while no research has yet attempted to use machine learning to impute for parking behavior using mobile probe data of sparsely monitored areas. To this end, this paper shows that it is indeed feasible to impute parking pressure (occupation as a percentage). Gradient boosted trees were found to perform the best with an R2 score of 0.20 and root mean squared error (RMSE) score of 0.087. This paper also found that three unique parking occupancy patterns exist in Amsterdam and that this information, in combination with neighborhood characteristics, has an impact on imputation under certain conditions.

Habitat Partitioning and Overlap by Large Lacertid Lizards in Southern Europe

South-western Europe has a rich diversity of lacertid lizards. In this study, we evaluated the occupancy patterns and niche segregation of five species of lacertids, focusing on large-bodied species (i.e., adults having >75 mm snout-vent length) that occur in south-western Europe (Italian to the Iberian Peninsula). We characterized the niches occupied by these species based on climate and vegetation cover properties. We expected some commonality among phylogenetically related species, but also patterns of habitat segregation mitigating competition between ecologically equivalent species. We used multivariate ordination and probabilistic methods to describe the occupancy patterns and evaluated niche evolution through phylogenetic analyses. Our results showed climate niche partitioning, but with a wide overlap in transitional zones, where segregation is maintained by species-specific responses to the vegetation cover. The analyses also showed that phylogenetically related species tend to share large parts of their habitat niches. The occurrence of independent evolutionary lineages contributed to the regional species richness favored by a long history of niche divergence.

Online Implementation of a Soft Actor-Critic Agent to Enhance Indoor Temperature Control and Energy Efficiency in Buildings

Recently, a growing interest has been observed in HVAC control systems based on Artificial Intelligence, to improve comfort conditions while avoiding unnecessary energy consumption. In this work, a model-free algorithm belonging to the Deep Reinforcement Learning (DRL) class, Soft Actor-Critic, was implemented to control the supply water temperature to radiant terminal units of a heating system serving an office building. The controller was trained online, and a preliminary sensitivity analysis on hyperparameters was performed to assess their influence on the agent performance. The DRL agent with the best performance was compared to a rule-based controller assumed as a baseline during a three-month heating season. The DRL controller outperformed the baseline after two weeks of deployment, with an overall performance improvement related to control of indoor temperature conditions. Moreover, the adaptability of the DRL agent was tested for various control scenarios, simulating changes of external weather conditions, indoor temperature setpoint, building envelope features and occupancy patterns. The agent dynamically deployed, despite a slight increase in energy consumption, led to an improvement of indoor temperature control, reducing the cumulative sum of temperature violations on average for all scenarios by 75% and 48% compared to the baseline and statically deployed agent respectively.