An Automated Building Energy Model Calibration Workflow to Improve Indoor Climate Controls
Bibliographic record
Abstract
White-box building energy models (BEM) are employed to optimize building operation and controls.Calibration improves the models' credibility by reducing the discrepancy between simulated and measured energy consumption data.However, calibrating a BEM is time-consuming and prohibitively expensive due to the large number of required model inputs and the limited availability of measurements.Moreover, this process remains challenging due to the lack of clear guidelines and a consensus on the calibration methodology.Therefore, the industry needs an efficient, low-cost, and accurate way to calibrate BEMs to actualize the benefits of operational optimization in commercial and industrial buildings.This research aims to increase the calibration efficiency by proposing an improved workflow to obtain a quick, lightweight, and parsimonious model that only requires building automation system (BAS) and energy meter data as well as simple geometric drawings.To this end, a deeper understanding of the uncertainty inherent in the BEM calibration process and the calibrated model's predictive performance on operational decisions were explored.The proposed method was demonstrated with a case study building in Ottawa, Canada, using metered energy use and actual meteorological year (AMY) data and operational parameters (e.g., HVAC system setpoints and schedules)extracted from the BAS.The results indicated more accurate parameters estimates and significantly more reliable energy consumption projections when the model is calibrated using energy meter data at a higher temporal resolution (i.e., hourly instead of monthly).Applying control interventions to calibrated case study BEM showed that up to 34% of energy could be saved through the optimized operation.Furthermore, leveraging BAS data not only overcame the overparameterization issue by reducing the number of unknown model inputs but was also found useful to detect operational anomalies to support the operational decision-making process.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 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) | 0.003 | 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".