Large-scale load profiling for energy flexibility in residential buildings: A data-driven approach for load aggregation through representative clusters
Bibliographic record
Abstract
This paper presents a data-driven methodology to characterize the flexibility potential of a large number of residential buildings within energy aggregators. Smart thermostat data from numerous homes—along with ambient temperature and heating power measurements—are used to calibrate reduced-order grey-box thermal models for each dwelling. An economic Model Predictive Control framework is then applied to quantify the building energy flexibility of these homes within a day-ahead coordination market. The resulting power demand forecasts are analysed using a time-series k -means clustering algorithm to group homes by representative flexibility profiles. A Monte Carlo estimation is then performed on these clusters to: a) identify the optimal penetration level of demand-side management strategies, b) estimate uncertainty in aggregated demand, and c) evaluate the need for strategy diversification. To demonstrate the feasibility of the proposed approach, the methodology is implemented through simulations involving a substantial number of houses in two Canadian metropolitan areas: Toronto, Ontario, and Montreal, Québec. Out of the 2,031 load profiles considered, six customer clusters were identified. At an aggregated level, coordinated participation in demand response led to a 94% increase in daily load factor (ratio of average to maximum demand) and a 20% reduction in system ramping in both locations. The methodology ultimately enables the prioritization of customer groups based on their demand response potential and demonstrates the importance of refining participation approaches within the building portfolio.
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 | 0.001 | 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 | 0.001 |
| 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".