Using Models to Provide Predicted Ranges for Building-Human Interfaces: Preprint

Research output: Contribution to conferencePaper


Most building energy consumption dashboards provide only a snapshot of building performance; whereas some provide more detailed historic data with which to compare current usage. This paper will discuss the Building Agent(tm) platform, which has been developed and deployed in a campus setting at the National Renewable Energy Laboratory as part of an effort to maintain the aggressive energyperformance achieved in newly constructed office buildings and laboratories. The Building Agent(tm) provides aggregated and coherent access to building data, including electric energy, thermal energy, temperatures, humidity, and lighting levels, and occupant feedback, which are displayed in various manners for visitors, building occupants, facility managers, and researchers. This paper focuseson the development of visualizations for facility managers, or an energy performance assurance role, where metered data are used to generate models that provide live predicted ranges of building performance by end use. These predicted ranges provide simple, visual context for displayed performance data without requiring users to also assess historical information or trends. Several energymodelling techniques were explored including static lookup-based performance targets, reduced-order models derived from historical data using main effect variables such as solar radiance for lighting performance, and integrated energy models using a whole-building energy simulation program.
Original languageAmerican English
Number of pages10
StatePublished - 2013
Event2013 Building Simulation Conference - Chambery, France
Duration: 25 Aug 201328 Aug 2013


Conference2013 Building Simulation Conference
CityChambery, France

NREL Publication Number

  • NREL/CP-5500-58521


  • building agent
  • building energy consumption dashboard
  • electric energy
  • humidity
  • lighting level
  • temperature
  • thermal energy


Dive into the research topics of 'Using Models to Provide Predicted Ranges for Building-Human Interfaces: Preprint'. Together they form a unique fingerprint.

Cite this