Development of Energy Disaggregation Algorithms for Commercial Buildings
Bibliographic record
Abstract
Energy management in commercial buildings requires accurate measurement of enduses, which is crucial for sustainability and cost reduction.However, a common challenge is the lack of high-resolution energy submetering, hindering effective energy management.To this end, a suite of load disaggregation algorithms suitable for buildings with and without building automation systems (BASs) is developed in this study.The thesis consists of four parts.The Ąrst part uses multiple linear regression models estimated by the genetic algorithm and a least-square solver to disaggregate heating and electricity data using BAS data as predictors.The method was tested on data from an Ottawa office building and showed accurate disaggregation into end-use categories, such as occupant-controlled loads and distribution loads for electricity, air handling unit (AHU) heating coils, and perimeter heating devices for heating.The second part explores the impact of submeter density and conĄguration on the disaggregation strategy using BAS trend data as predictors.Findings highlighted factors affecting the minimum number of submeters needed for accurate disaggregation, providing insights for building design codes, energy consultants, and policymakers.The third part proposed a time-series decomposition-based method to disaggregate major energy end-uses without BAS trend data.Data from ten office buildings in Ottawa were used to break down total energy use into three major end-uses.Disaggregation results were compared with actual submeter data, and insights into lighting and thermal scheduling were assessed.The proposed method showed promising performance, suggesting potential for quick and low-cost auditing of commercial buildings with limited submeter data access.The fourth part of this thesis utilized the developed disaggregation algorithms integrated into a visualization tool for end-users to interact with disaggregated data.Additionally, preliminary recommendations for thermal submetering requirements were incorporated based on the Ąndings presented in the second part of the thesis.This thesis enhances energy management in commercial buildings by developing practical energy disaggregation iii I extend my gratitude to Dr. Burak Gunay and Dr. Araz Ashouri, my Ph.D. supervisors, for their outstanding guidance and dedicated support.Their enthusiasm, motivation, patience, and expertise signiĄcantly contributed to the enhancement of both my research and technical writing abilities.IŠd also like to acknowledge the examination committee-Ian Beausoleil-Morrison, Dr. Elie Azar
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.002 | 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".