ENERtune: Automated Building Energy Model Calibration
More accurate energy model calibration that requires less money, effort, and time!
Calibration Process in ENERtune
ENERlite Consulting, Inc. was awarded the SBIR/STTR 2021 Small Business grant from the Department of Energy for the advancement of Building Energy Modeling and improvement of the quality and reliability of models for existing buildings. Our team has developed a multi-stage calibration tool, ENERtune, that uses machine-learning algorithms to increase the model's accuracy and meta-modeling techniques to increase the efficiency of the calibration process.
Building energy modeling (BEM) is increasingly used in building industries for various purposes, such as quantifying savings from energy retrofit projects. Building energy models without proper validation and calibration will lead to significant discrepancies between projected and actual building energy consumption. Deficiencies in predictive accuracy and consistency of BEM were identified as barriers to using BEM in the industry.
The goal of ENERtune is to improve the predictive accuracy and consistency of building energy models by providing an educated and automated multi-stage calibration tool.
How ENERtune works:
ENERtune is an innovative solution that streamlines building energy model calibration by automating multiple stages. It fine-tunes them based on the building's actual weather data and monthly utility data. ENERtune’s machine-learning techniques increase model accuracy and its gray-box modeling technique uses both data and physics models, which often results in a faster and more efficient calibration process.
What is ENERtune:
Based on sensitivity analysis, meta-modeling, and gradient-based optimization, ENERTUNE identifies a subset of model inputs that has the greatest influence on the model output and optimizes this subset by minimizing the error between model output and monthly utility data.
Compared with the existing model calibration tools and processes, ENERtune has a higher level of automation while enabling human-computer interaction for model input screening, measured data screening, and post-calibration sanity checks. This process will add physical insight and reduce the number of parameters and uncertainty bounds in the calibration process. The complexity reduction through meta-modeling in ENERtune can also make the calibration process less computationally expensive.
ENERtune has been tested and validated in multiple real buildings including office buildings and institutional buildings.
