Urban Building Energy Stock Datasets

This dataset comprises over 1 million records of residential urban building stock, including types such as terraced houses, detached houses, semi-detached houses, and bungalows. It utilizes jEPlus as a parametric tool for physics-based simulations, combined with EnergyPlus for thermal simulation, and integrates DesignBuilder construction templates for generation. The dataset encompasses various building features, such as HVAC systems and building fabric properties (including U-values for walls, roofs, floors, doors, and windows). It also contains parameters related to heating, lighting, equipment, photovoltaic systems, and hot water energy demand.

For citation:
Usman Ali, Sobia Bano, Mohammad Haris Shamsi, Divyanshu Sood, Cathal Hoare, Wangda Zuo, Neil Hewitt, James O'Donnell. “Urban building energy performance prediction and retrofit analysis using data-driven machine learning approach”. Energy and Buildings, Volume 303, https://doi.org/10.1016/j.enbuild.2023.113768