Large-scale load profiling for energy flexibility in residential buildings: A data-driven approach for load aggregation through representative clusters

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.