Calibrating building energy models using supercomputer trained machine learning agents

Concurrency and Computation: Practice and Experience

Volumn 26, Issue 13, 2014, Pages 2122-2133

  Sanyal, Jibonananda ^a   New, Joshua ^a   Edwards, Richard E ^b   Parker, Lynne ^c  

^a OAK RIDGE NATIONAL LABORATORY   (United States)

^b AMAZON   (United States)

^c UNIVERSITY OF TENNESSEE   (United States)

Author keywords

big data; building energy modeling; calibration; machine learning; parametric ensemble; supercomputer

Indexed keywords

BIG DATA; BOUNDARY ELEMENT METHOD; BUILDINGS; CALIBRATION; COST EFFECTIVENESS; INTELLIGENT AGENTS; LEARNING SYSTEMS; MACHINE LEARNING; SUPERCOMPUTERS;

BUILDING ENERGY MODEL; BUILDING STOCKS; COMPUTATIONAL PROBLEM; DEPARTMENT OF ENERGY; MACHINE LEARNING AGENTS; PARAMETRIC ENSEMBLE; PARAMETRIC SPACES; PUBLIC DOMAINS;

LEARNING ALGORITHMS;

EID: 84905014200     PISSN: 15320626     EISSN: 15320634     Source Type: Journal    
DOI: 10.1002/cpe.3267     Document Type: Conference Paper

References (18)

1. U.S. Dept. of Energy. Building Energy Data Book. D&R International, Ltd.: Silver Spring, MD, 2010.
2. U.S. Dept. of Energy. Building Energy Data Book. D&R International, Ltd.: Silver Spring, MD, 2011.
3. Briggs RS, Lucas RG, Taylor ZT,. Climate classification for building energy codes and standards: part 1-development process. ASHRAE Transactions 2003; 109 (1): 109-121.
4. Briggs RS, Lucas RG, Taylor ZT,. Climate classification for building energy codes and standards: part 2-zone definitions, maps, and comparisons. ASHRAE Transactions 2003; 109 (1): 122-130.
5. Deru M, Field K, Studer D, Benne K, Griffith B, Torcellini P, Liu B, Halverson M, Winiarski D, Rosenberg M, Yazdanian M, Huang J, Crawley D,. US Department of Energy Commercial Reference Building Models of the National Building Stock. NREL Report No. TP-5500-46861, National Renewable Energy Laboratory: Golden, CO, 2011.
6. IECC 2009 and ASHRAE 90.1-2007. Energy code climate zones, 2009.
7. Field K, Deru M, Studer D,. Using DOE commercial reference buildings for simulation studies, 2010.
8. New JR, Sanyal J, Bhandari MS, Shrestha SS,. Autotune E+ building energy models. 5th National SimBuild of IBPSA-USA, Madison, Wisconsin, 2012; 270-278.
9. Sanyal J, New J, Edwards R,. Supercomputer assisted generation of machine learning agents for the calibration of building energy models. Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery, ACM, San Diego, CA, 2013; 22.
10. de Wit MS,. Uncertainty in predictions of thermal comfort in buildings. Ph.D. Thesis, The Delft University, Delft, Netherlands, 2001.
11. Garrett A, New JR, Chandler T,. Evolutionary tuning of building models to monthly electrical consumption, Technical paper DE-13-008. In Proceedings of the ASHRAE Annual Conference and ASHRAE Transactions 2013, Vol. 119, Denver, CO, 2013; 89-100. part 2.
12. Big Ladder Software. EPx, a modified version of energyplus v. 7, 2013.
13. Edwards RE, New JR, Parker LE,. Approximate l-fold cross-validation with least squares SVM and kernel ridge regression. IEEE 12th International Conference on Machine Learning and Applications (ICMLA13), Miami, Florida, USA, 2013.
14. Edwards RE, New JR, Parker LE,. Constructing large scale energyplus surrogates from big data. ORNL Internal Report ORNL/TM-2013/46861, 2013.
15. Edwards RE, New JR, Parker LE,. Estimating building simulation parameters via Bayesian structure learning. In Proceedings of the 2nd International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications (BigMine '13). ACM: New York, NY, USA, 2013; 31-38. DOI: 10.1145/2501221.2501226, http://doi.acm.org/10.1145/ 2501221.2501226.
16. Edwards RE, New JR, Parker LE,. Predicting future hourly residential electrical consumption: a machine learning case study. Energy and Buildings 2012; 49: 591-603.
17. Edwards RE, Parker L,. MLSuite final report fy2012, Oak Ridge National Laboratory, TN, 2013.
18. Edwards RE, Parker L,. Sensor-based energy modeling final report fy2012, Oak Ridge National Laboratory, TN, 2012.