Building Energy Calibration based on Parameter Estimation and Machine Learning

Buildings rarely perform as designed/simulated and there are numerous tangible benefits if this gap is reconciled. Building energy simulations are essential not only during the design phase but also offer a number of benefits during building operation. Examples are commissioning, fault detection and diagnostics, identifying and evaluating retrofit opportunities, and especially optimal predictive control especially in the context of electrical grid services meant to assure/enhance to assure reliability and flexibility with increasing renewable penetration. This project develops a scientific yet pragmatic methodology that focusses on parametric estimation rather than a blind forced-fit to energy use data. It starts with rapidly and inexpensively created simulation inputs and reconciles simulated energy and indoor temperatures with actual performance using readily available hourly or sub-hourly performance data from smart meters, building automation systems and local weather stations. Current calibration methods providing little physical insight into actual parameters and often over-promise accuracy. Rather than subjectively adjusting a large number of inputs based on Monte Carlo-type of random massive simulations, the new method will scientifically identify and estimate a small number of parameters and uncertainty bounds using a multi-stage process. The parameters will have direct physical significance. The residual error in energy balance is related to forcing functions using machine learning to enhance the accuracy of calibration. Thus the burden of arriving at a good final model is shared between initial inputs, calibration and machine learning. In Phase I, the development advances the state of the art by developing and applying the methodology to at least one synthetic building and one actual building. This proposal will perform major improvements especially in integrating the HVAC systems into the earlier methodology which has been applied to office buildings as large as 130,000 sq.ft. The project will also develop guidelines for next generation simulations to facilitate incorporation of calibration. In subsequent phases, the methodology and tool will be refined and coded to be ready for field deployment not only by the building energy services community, but also by utility services community facilitating creation of new markets and dispatch of flexibility services to the electrical grid.