Leveraging mobile positioning data to model building occupant behaviour in a mixed-use district
Bibliographic record
Abstract
OBs are critical inputs for developing an accurate UBEM. Therefore, this paper aims to investigate the different approaches to use mobile positioning data for modelling OB in mixed-use districts and illustrate how the generated profiles can be integrated with other commonly used datasets in UBEMs. A case study is used as the basis of this investigation which focuses on Downtown Montreal. The geometry of the model was created using CityGML data while building characteristics were extracted from the tax assessment rolls (TAR). These characteristics were also used to group the buildings into archetypes, then the configuration of building systems of each archetype was assigned using the DOE available libraries.The investigation started with developing a base model where OBs were represented using standard deterministic profiles. Afterward, location-based mobile positioning data was used to generate data-driven OB profiles for different points of interest (POIs). Then, a probabilistic model was developed combined with clustering analysis to scale-up the generated profiles from POIs to a whole-building scale to match the commonly available LOD of the geometric data while considering the building types given the TAR. The final profiles were integrated into the simulation and the results were compared to the base model results.Urban building energy models (UBEMs) are expected to play a significant role in planning the current and future needs of the energy grid infrastructure. Consequently, researchers have been investigating the deployment of the available rich datasets to represent the different components of UBEMs at different resolutions and evaluate their impact on the accuracy of the model results. The representation of occupants in UBEMs has been one of the key targets of these research efforts, especially with occupant-related inputs being acknowledged as the main reasons behind the unrealistic estimation of the building performance indicators by UBEMs. However, the majority of these efforts focused only on simulating single building types and evaluating the impact of different levels of details (LODs) of occupancy profiles on the simulation results without considering the LODs available for the other UBEMs inputs. This can create a challenge for practitioners to fit the generated occupancy profiles into their simulations. Accordingly, research efforts should be directed to investigate the integration of occupant behaviour (OB) patterns with different resolutions into UBEMs in parallel with investigating the potential of the emerging data sources to represent occupants in the models.The results quantify the deviation between the standard occupancy profiles and the data-driven ones, which will help identify the necessary updates that should be considered in codes and standards for different building types. Moreover, the results will highlight the variation between the simulation results of the baseline with standard deterministic occupant-related profiles versus the data-driven models developed using mobile positioning data. More specifically, the investigations focus on the impact of the data-driven OB profiles on the peak energy demand and the energy use at different temporal and spatial resolutions (i.e., building scale, building sector scale, and district scale). Finally, the results will be used to develop guidelines and recommendations regarding how occupancy should be integrated for different UBEM applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".