A data-driven approach to support the automation of thermostats in residential buildings
Bibliographic record
Abstract
Programmable thermostats represent a significant advancement in home automation technology, offering the potential for maintaining comfort and energy efficiency. However, the frequent overriding of default schedules indicates the necessity of flexibility to accommodate the dynamic occupant behavior and requirements. This thesis delves into this challenge, leveraging data-driven insights to understand thermostat override behaviors and hence develop supportive automation strategies that minimize human interaction. The introductory focus of this research lies in examining how individual comfort preferences, outdoor conditions, and daily schedules influence thermostat override behaviors. The data set for this exploration comprises thermostat and occupancy data from two residential buildings in Quebec, Canada, equipped with ecobee smart thermostats from the heating and cooling seasons of 2017 to 2019. The research subsequently explores the frequency of override behaviors across different Heating, ventilation, and air conditioning (HVAC) modes, schedules, temperatures, and years. \nA key novelty of this research lies in its extensive exploration of occupancy, temperature, and setpoint trends over specific periods, facilitating the identification of patterns in thermostat override cycles and daily adjustments. Machine learning algorithms, such as decision trees and random forests, are employed to ascertain the importance of various features influencing thermostat override behaviors. Association rule mining techniques then reveal the relationship between variables, suggesting adaptive automation strategies based on temperature, occupancy, time, and outdoor conditions. \nAfter conducting a comparative data analysis for two households, we identified significant shifts in occupant behavior and temperature preferences. From these insights, we have derived four various automation strategies: temperature-based, occupancy-based, outdoor temperature-based, and time-of-day and weekday-based. These strategies exemplify the adaptability in occupant behaviors. Recognizing the factors that influence thermostat overrides makes it possible to equip smart thermostats with more intuitive automation strategies. These strategies can proactively adjust settings in line with user behavior and prevailing outdoor conditions, enhancing comfort and energy efficiency. To further fine-tune and widen the applicability of these strategies, it would be beneficial to conduct additional research with more extensive and diverse datasets.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 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".