U.S. Synthetic Residential Building Telemetry Dataset Generated with EnergyPlus

This dataset provides national-scale synthetic residential building telemetry generated using EnergyPlus. It includes representative detached and attached residential models developed from the statistical distributions of actual ecobee DYD homes and the U.S. residential building stock. The dataset covers 48 contiguous U.S. states and 13 ASHRAE climate zones. The dataset contains 540 unique EnergyPlus models and their corresponding full-year simulation-output files in Parquet format. Each model is assigned a statistical weight in case_description.csv; expanding the 540 unique cases according to these weights produces a population-weighted sample of 1,200 representative residential cases. The released dataset includes three components for each simulated case: Case description file (case_description.csv): summarizes building characteristics and simulation metadata, including location, housing type, construction vintage, envelope properties, infiltration, HVAC configuration, and case weight. A common case identifier links the case-description records, IDF files, and Parquet outputs. EnergyPlus input files (.idf): contain the complete model definitions and simulation assumptions and were created using EnergyPlus version 9.5. Synthetic telemetry (.gz.parquet): contains full-year EnergyPlus simulation outputs at 5-minute intervals, including indoor and outdoor environmental conditions, thermostat setpoints, HVAC operation and runtime, infiltration and ventilation, and energy consumption variables. Comparisons with ecobee field telemetry and evaluations across detached and attached building forms demonstrate that the dataset captures broad climate-dependent and physically consistent patterns observed in actual homes. The dataset is intended to support the development and benchmarking of surrogate and telemetry-based building energy models, evaluation of retrofit and HVAC-sizing scenarios, climate-zone and state-level analyses, and validation of modeling methods against known physical parameters before their application to field data.