Building Energy Consumption
Description
The dataset contains simulated building‑design configurations together with the resulting heating energy‑use intensity (EUI Heating). It is generated through a parametric building‑energy simulation workflow that systematically varies architectural and operational features. The data are intended to illustrate how causal dependencies among design variables can influence energy‑performance outcomes, and how ignoring these dependencies may lead to misleading inferences even when predictive accuracy appears satisfactory. The target variable is the heating Energy Usage Intensity (EUI) measured in [kWh/m²·a], and the feature set reflects typical parameters used in building‑performance and occupant‑behavior studies.
Task: The dataset can be used to study causal discovery methods.
Summary:
- Size of dataset: 918 x 31
- Task: Causal Discovery Problem
- Data Type: Mixed Data
- Dataset Scope: Standalone Dataset
- Ground Truth: Unknown Graph
- Temporal Structure: Static Data
- License: MIT
- Missing Values: No Missing Values
Features:
- Simulation: Simulation number
- Terrain: Surrounding terrain. (Suburbs / Urban / Country / City)
- Orientation: Building rotation angle [°]
- NumberOfFloors: Number of storeys
- FloorHeight: Floor-to-floor height [m]
- Shading: Shading type (Low-SHGC-Value / External-Shading)
- EnergyStandard: Insulation standard (GEG / NZEB / Passive)
- HVAC-System: Heating system type (ASHPBaseboard / BoilerBaseboard / DHWBaseboard). ASHP = air-source heat pump; DH = district heating.
- ServiceHotWater: Hot water system (Electric_TanklessHeater / Electric_WaterHeater / Gas_TanklessHeater / Gas_WaterHeater)
- BuildingSystemVintage: Year of building system (pre_1980 / 1980_2004 / 2004 / 2007 / 2010 / 2013 / 2016 / 2019)
- Open Office: Heating Setpoint: Heating thermostat setpoint, open office [°C]
- Open Office: Cooling Setpoint: Cooling thermostat setpoint, open office [°C]
- Open Office: ACH: Air change rate, open office [1/h]
- Open Office: PPA: Occupant density, open office [people/m²]
- Meeting: Heating Setpoint: Heating thermostat setpoint, meeting room [°C]
- Meeting: Cooling Setpoint: Cooling thermostat setpoint, meeting room [°C]
- Meeting: ACH: Air change rate, meeting room [1/h]
- Meeting: PPA Volume [m³]: Occupant density, meeting room [people/m²]
- Area [m²]: Gross floor area
- Construction Area [%]: Areas covered by walls, columns, or any structural elements.
- Window to Wall Ratio North [%]: Glazing fraction, north façade
- Window to Wall Ratio East [%]: Glazing fraction, east façade
- Window to Wall Ratio South [%]: Glazing fraction, south façade
- Window to Wall Ratio West [%]: Glazing fraction, west façade
- Window to Wall Ratio [%]: Aggregated glazing fraction, all façades
- HVAC-System Capacity [kW]: Total installed HVAC capacity
- Baseboard Capacity Sum [kW]: Total installed baseboard heater capacity
- EUI [kWh/m²a]: Total energy use intensity
- EUI Heating [kWh/m²a]: Heating energy use intensity
- EUI Electricity [kWh]: Total electricity consumption
Files:
- dibe_2023_occupant_behavior_raw.csv: Raw simulation dataset
- dibe_2023_occupant_behavior_analysis.csv: Processed dataset used in the paper’s analysis
Files
dibe_2023_occupant_behavior_analysis.csv
Files
(444.7 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:d3bef7905c3b398f0be38c3164d83fdf
|
218.3 kB | Preview Download |
|
md5:1e4e30907a111896329ea004f6112f6c
|
226.4 kB | Preview Download |
Additional details
Software
- Repository URL
- https://github.com/chenxiachan/causal-inference-occupant-behavior.git
- Programming language
- Python
References
- Xia Chen, Ruiji Sun, Ueli Saluz, Stefano Schiavon, Philipp Geyer Using causal inference to avoid fallouts in data-driven parametric analysis: A case study in the architecture, engineering, and construction industry Developments in the Built Environment, 2024.