Abstract
EnergyPlus is the flagship building energy simulation
software used to model whole building energy consumption for
residential and commercial establishments. A typical input to the
program often has hundreds, sometimes thousands of parameters
which are typically tweaked by a buildings expert to “get it
right”. This process can sometimes take months. “Autotune” is an
ongoing research effort employing machine learning techniques
to automate the tuning of the input parameters for an EnergyPlus
input description of a building. Even with automation, the
computational challenge faced to run the tuning simulation
ensemble is daunting and requires the use of supercomputers to
make it tractable in time. In this proposal, we describe the scope
of the problem, the technical challenges faced and overcome, the
machine learning techniques developed and employed, and the
software infrastructure developed/in development when taking
the EnergyPlus engine, which was primarily designed to run on
desktops, and scaling it to run on shared memory supercomputers
(Nautilus) and distributed memory supercomputers (Frost and
Titan). The parametric simulations produce data in the order of
tens to a couple of hundred terabytes.We describe the approaches
employed to streamline and reduce bottlenecks in the workflow
for this data, which is subsequently being made available for the
tuning effort as well as made available publicly for open-science.
