Projecting and estimating HVAC energy savings from correcting control faults: Comparison between physical and virtual metering approaches
Bibliographic record
Abstract
Fault-impact analysis (FIA) in heating, ventilation, and air conditioning (HVAC) systems involves forecasting system loads in the absence of equipment malfunction and inappropriate sequences of operations with the intention of setting a target for optimal operating energy use and encouraging and augmenting fault correction. Fault correction is an ongoing and resource-intensive endeavor for operations personnel, often motivated by occupant complaints rather than to mitigate excessive operating energy use. Thus, projecting the energy-use impact of faults is imperative to improving building energy efficiency as it leverages the potential to reduce energy use for real-time operational decision-making. Thermal energy meters (i.e., physical meters) can provide post-correction validation by quantifying the energy-use impact of faults, though are incapable of projecting this information before faults are corrected and providing motivation. Additionally, their installation and maintenance costs in existing buildings are often prohibitive. Virtual meters (VMs) which leverage HVAC controls data offer a cost-effective alternative to physical meters. Furthermore, inverse-model (IM)-based VMs enable scalable FIA by employing derived IMs at the system and zone level to emulate alternative control scenarios. This paper presents the first ever field implementation of FIA-capable VM algorithms. An automated and BAS-integrated VM algorithm was deployed in a living-lab facility in Ottawa, Canada, and the VM-estimated energy-use impact of correcting common soft faults is presented and compared with savings reported by thermal meters and savings projected by the FIA. For combined system- and zone-level heating, VMs estimated 85% of the measured energy-use savings, and a 65% reduction in energy use was projected prior to correcting faults where a 62% reduction was realized after faults were corrected. VMs can appropriately assess and project energy savings for fault correction so long as the method to baseline pre-correction energy use persists after correction.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".