Evolutionary Tuning of Building Models to Monthly Electrical Consumption

Abstract

Building energy models of existing buildings are unreliable unless calibrated so they correlate well with actual energy usage. Calibrating models is costly because it is currently an “art” which requires significant manual effort by an experienced and skilled professional. An automated methodology could significantly decrease this cost and facilitate greater adoption of energy simulation capabilities into the marketplace. The “Autotune” project is a novel methodology which leverages supercomputing, large databases of simulation data, and machine learning to allow automatic calibration of simulations to match measured experimental data on commodity hardware. This paper shares initial results from the automated methodology applied to the calibration of building energy models (BEM) for EnergyPlus (E+) to reproduce measured monthly electrical data.