A COMPARISON OF GAUSSIAN PROCESS REGRESSION AND CHANGE-POINT REGRESSION FOR THE BASELINE MODEL IN INDUSTRIAL FACILITIES
This study compares the effectiveness of Gaussian
Process (GP) models to three-parameter cooling change
point (3PC) models for establishing baseline energy
usage models in industrial facilities using utility bill
data. Several different methods of creating baseline
models for commercial and residential buildings have
been developed; however, few attempts have been
made to create baseline energy models in industrial
facilities. Industrial facilities account for 33% of annual
energy usage within the United States, so industrial
energy usage needs to be analyzed in order to identify
energy saving opportunities. Creating a baseline energy
model is important to understanding an industrial
facility’s energy usage. An analysis of the
effectiveness of using GP regression to develop a
baseline energy usage models in industrial facilities
from utility bill data and ambient outdoor dry bulb
temperature is presented. Two case studies are
presented: using utility bill data and average monthly
temperatures to create a GP regression model and 3PC
model. In both cases the baseline regression models
gave a CV-RMSE of 15% or lower and NMBE of 5%
or lower showing that either a GP regression model or
3PC model using utility bill data is capable of
producing acceptable baseline energy models by
ASHRAE Guidelines. In both cases GP regression
models had slightly lower CV-RMSE values than 3PC
ASHRAE Guideline 14: Measurement of Energy and Demand Savings, ASHRAE Inc, Atlanta, GA, 2002.
ASHRAE Handbook of Fundamentals, ASHRAE, Inc., 2013
Brueske, S. and Sabouni, R. 2014. U.S. Manufacturing Energy Use and Loss, the Big Picture. Industrial Energy Technology Conference 2014.
EIA. February 2015 Monthly Energy Review, US Energy Information Administration (2015). www.eia.gov/mer.
Fels, M. F. (1986). PRISM: An Introduction. Energy and Buildings, 9, 5-18.
Galitsky, C and Ernst, W. (2008) “Energy Efficiency Improvement and Cost Saving Opportunities for the Vehicle Assembly Industry”, Ernest Orlando Lawrence Berkeley National Laboratory Report, LBNL-50939-Revision.
Golden, A. (2014), Analyzing Industrial Energy Use through Ordinary Least Squares Regression Models. Thesis from University of Alabama.
Heo, Y., and Zavala, V.M (2012). Gaussian Process modeling for measurement and verification of building energy savings. Energy and Buildings. 53, 7-18
Heo, Y., Graziano, D., Zavala, V.M., Dickinson, P., Kamrath, M., and Kirshenbaum, M., (2013). CosteffectiveMeasurement and Verificaton Method for Determing Energy Savings under Uncertainty. ASHRAE Transctions
Kissock, J. K., & Seryak, J. (2004). Understanding Manufacturing Energy Use through Statistical Analysis. Twenty-Sixth Industrial Energy Technology Conference. Houston, TX.
Kissock, J. K., & Eger, C. (2008). Measuring Industrial Energy Savings. Applied Energy, 85, 347-361. Rabl, A., Norfor, L., and Spadaro, J. (1992). Steady State Models for Analysis of Commercial Building Energy Data. ACEEE Summer Study on Energy Efficiency in Buildings, (pp. 9.239-9.261).
Rasmussen, C. and Williams, C. (2006). Gaussian Processes for Machine Learning. MIT Press. Rossiter A.P. and Jones, B. (2015). Comprehensive Energy Efficieny in the Process Industries. Industrial Energy Technology Conference 2015.
Sever, F., Kissock, J. K., Brown, D., & Mulqueen, S. (2011). Estimating Industrial Building Energy Savings using Inverse Simulation. ASHRAE Transactions, 117(1), 348-355.
Sonderegger, R. C. (1998). A Baseline Model for Utility Bill Analysis Using Both Weather and NonWeather Related Variables. ASHRAE Summer Meeting. Toronto.
Srivastav, A. Tewari, A, and Dong, B. (2013). Baseline building energy modeling and localized uncertainy quantification using Gaussian mixture models. Energy and Buildings. 65, 438-447.
U.S. Department of Energy Office of Energy Efficiency & Renewable Energy. http://energy.gov/eere/amo/better-plants
U.S. House. Committee on Appropriations. Energy and Water Development Appropriations Bill, 2013 (to Accompany H.R. 5325) Together with Additional Views. 112th Congress. 2d Session. Report 112462. Washington: GPO, 2012. GPO. U.S.
Government Printing Office. Web. 2 May 2012. (85). http://www.gpo.gov
Weather Underground. www.weatherunderground.com 2015
Wilson, J. K. (1998). The Significant Role of Energy Calculations in the Success of Long-Term Energy Guarantees. ASHRAE Transactions, 104(2), 880894.5,no. 9, pp. 781–798, Dec. 1991.
Zhang, Y., O’Neill, Z., Wagner, T., & Augenbroe, G. (2013). An Inverse Model with Uncertainty Quantification to Estimate the Energy Performance of an Office Building. Proceedings of BS2013: 13th Conference of International Building Performance Simulation Association (pp. 614621). Chambery, France: IBPSA.
Zhang, Y., O’Neill, Z., Dong, B., Augenbroe, G. (2015), Comparisons of Inverse Modeling Approaches for Predicting Building Energy Performance. Building and Environment, 86, 177190.
- There are currently no refbacks.