Scalable tuning of building models to hourly data

• We survey guidelines and calibration requirements for energy models of buildings.
• We apply evolutionary computation for calibrating software to measured data.
• We showcase abbreviated schedules for speeding up autonomous calibration.
• We demonstrate an island-model for parallelizing multi-parameter optimization.
• We analyze automatic calibration to hourly data with comparison to manual effort.

Energy models of existing buildings are unreliable unless calibrated so that they correlate well with actual energy usage. Manual tuning requires a skilled professional and is prohibitively expensive for small projects, imperfect, non-repeatable, and not scalable to the dozens of sensor channels that smart meters, smart appliances, and sensors are making available. A scalable, automated methodology is needed to quickly, intelligently calibrate building energy models to all available data, increase the usefulness of those models, and facilitate speed-and-scale penetration of simulation-based capabilities into the marketplace for actualized energy savings. The “Autotune” project is a novel, model-agnostic methodology that leverages supercomputing, large simulation ensembles, and big data mining with multiple machine learning algorithms to allow automatic calibration of simulations that match measured experimental data in a way that is deployable on commodity hardware. This paper shares several methodologies employed to reduce the combinatorial complexity to a computationally tractable search problem for hundreds of input parameters. Accuracy metrics are provided that quantify model error to measured data for either monthly or hourly electrical usage from a highly instrumented, emulated-occupancy research home.