Journal Home > Volume 13 , Issue 6
Building Simulation 2020, 13(6): 1205-1220 https://doi.org/10.1007/s12273-020-0661-y
Research Article | Issue | Published: 04 June 2020

Generation and representation of synthetic smart meter data

Show Author's Information Tianzhen Hong1( ),  Daniel Macumber2,  Han Li1,  Katherine Fleming2,  Zhe Wang1
Lawrence Berkeley National Laboratory, Berkeley, California, USA
National Renewable Energy Laboratory, Golden, Colorado, USA
Keywords:
data representation, EnergyPlus, smart meter data, building energy modeling, synthetic data, occupant modeling
Cite this article:
Hong T, Macumber D, Li H, et al. Generation and representation of synthetic smart meter data. Building Simulation, 2020, 13(6): 1205-1220. https://doi.org/10.1007/s12273-020-0661-y
Download citation
EndNote(RIS)
BibTeX

595

Views

40

Downloads

Citations

10

Crossref

N/A

WoS

9

Scopus

0

CSCD

Abstract Full text About this article

Advanced energy algorithms running at big-data scale will be necessary to identify, realize, and verify energy savings to meet government and utility goals of building energy efficiency. Any algorithm must be well characterized and validated before it is trusted to run at these scales. Smart meter data from real buildings will ultimately be required for the development, testing, and validation of these energy algorithms and processes. However, for initial development and testing, smart meter data are difficult to work with due to privacy restrictions, noise from unknown sources, data accessibility, and other concerns which can complicate algorithm development and validation. This study describes a new methodology to generate synthetic smart meter data of electricity use in buildings using detailed building energy modeling, which aims to capture the variability and stochastics of real energy use in buildings. The methodology can create datasets tailored to represent specific scenarios with known truth and controllable amounts of synthetic noise. Knowledge of ground truth also allows the development and validation of enhanced processes which leverage building metadata, such as building type or size (floor area), in addition to smart meter data. The methodology described in this paper includes the key influencing factors of real-world building energy use including weather data, occupant-driven loads, building operation and maintenance practices, and special events. Data formats to support workflows leveraging both synthetic meter data and associated metadata are proposed and discussed. Finally, example use cases of the synthetic meter data are described to illustrate potential applications.


menu
Abstract
Full text
Outline
About this article

Generation and representation of synthetic smart meter data

Show Author's information Tianzhen Hong1( ), Daniel Macumber2, Han Li1, Katherine Fleming2, Zhe Wang1
Lawrence Berkeley National Laboratory, Berkeley, California, USA
National Renewable Energy Laboratory, Golden, Colorado, USA

Abstract

Advanced energy algorithms running at big-data scale will be necessary to identify, realize, and verify energy savings to meet government and utility goals of building energy efficiency. Any algorithm must be well characterized and validated before it is trusted to run at these scales. Smart meter data from real buildings will ultimately be required for the development, testing, and validation of these energy algorithms and processes. However, for initial development and testing, smart meter data are difficult to work with due to privacy restrictions, noise from unknown sources, data accessibility, and other concerns which can complicate algorithm development and validation. This study describes a new methodology to generate synthetic smart meter data of electricity use in buildings using detailed building energy modeling, which aims to capture the variability and stochastics of real energy use in buildings. The methodology can create datasets tailored to represent specific scenarios with known truth and controllable amounts of synthetic noise. Knowledge of ground truth also allows the development and validation of enhanced processes which leverage building metadata, such as building type or size (floor area), in addition to smart meter data. The methodology described in this paper includes the key influencing factors of real-world building energy use including weather data, occupant-driven loads, building operation and maintenance practices, and special events. Data formats to support workflows leveraging both synthetic meter data and associated metadata are proposed and discussed. Finally, example use cases of the synthetic meter data are described to illustrate potential applications.

Keywords: data representation, EnergyPlus, smart meter data, building energy modeling, synthetic data, occupant modeling

References(54)

Andersen RK (2012). The influence of occupants’ behaviour on energy consumption investigated in 290 identical dwellings and in 35 apartments. In: Proceedings of the 10th International Conference on Healthy Buildings.
Bartz K (2019). Record wildfires push 2018 disaster costs to $91 billion. Center for Climate and Energy Solutions. Available at https://www.c2es.org/2019/02/record-wildfires-push-2018-disaster-costs-to-91-billion/. Accessed 1 Nov 2019.
BEDES (n.d.). Building Energy Data Exchange Specification (BEDES). Available at https://bedes.lbl.gov/. Accessed 23 Sept 2019.
BrickSchema (n.d.). Available at https://brickschema.org/. Accessed 29 Sept 2019.
DOI
BuildingSync (n.d.). Available at https://buildingsync.net/. Accessed 29 Sept 2019.
DOI
Chao CYH, Hu JS (2004). Development of a dual-mode demand control ventilation strategy for indoor air quality control and energy saving. Building and Environment, 39: 385-397.
DOI Google Scholar
Chen Y, Hong T, Luo X (2018). An agent-based stochastic Occupancy Simulator. Building Simulation, 11: 37-49.
DOI Google Scholar
D’Oca S, Hong T, Langevin J (2018). The human dimensions of energy use in buildings: A review. Renewable and Sustainable Energy Reviews, 81: 731-742.
DOI Google Scholar
Dahmen J, Cook D (2019). SynSys: A synthetic data generation system for healthcare applications. Sensors, 19: 1181.
DOI Google Scholar
de Bakker C, Aries M, Kort H, Rosemann A (2017). Occupancy-based lighting control in open-plan office spaces: A state-of-the-art review. Building and Environment, 112: 308-321.
DOI Google Scholar
de Dear RJ (1998). A global database of thermal comfort field experiments. ASHRAE Transactions, 104(1b): 1141-2252.
Google Scholar
Deme Belafi Z, Hong T, Reith A (2019). A library of building occupant behaviour models represented in a standardised schema. Energy Efficiency, 12: 637-651.
DOI Google Scholar
Deru M, Field K, Studer D, Benne K, Griffith B, et al. (2011). U.S. Department of Energy Commercial Reference Building Models of the National Building Stock. Office of Scientific and Technical Information (OSTI).
DOI
Dickinson R (2016). Morphing Weather Files: An Overview of the Weathershift Tool. Available at https://www.iesve.com/website/var/assets/support/weather-files/weathershift/weathershift-white-paper.pdf.
Dunn G, Knight I (2005). Small power equipment loads in UK office environments. Energy and Buildings, 37: 87-91.
DOI Google Scholar
Fernandes LL, Lee ES, DiBartolomeo DL, McNeil A (2014). Monitored lighting energy savings from dimmable lighting controls in The New York Times Headquarters Building. Energy and Buildings, 68: 498-514.
DOI Google Scholar
Field K, Deru M, Studer D (2010). Using DoE Commercial Reference Buildings for Simulation Studies. In: Proceedings of SimBuild. Available at Retrieved from http://www.nrel.gov/docs/fy10osti/ 48588.pdf.
Földváry Ličina V, Cheung T, Zhang H, de Dear R, Parkinson, et al. (2018). Development of the ASHRAE Global Thermal Comfort Database II. Building and Environment, 142: 502-512.
Google Scholar
Guglielmetti R, Macumber D, Long N (n.d.). OpenStudio: An Open Source Integrated Analysis Platform.
Guideline A (2014). Guideline 14-2014. Measurement of Energy, Demand, and Water Savings.
Gunay HB, O’Brien W, Beausoleil-Morrison I, Gilani S (2016). Modeling plug-in equipment load patterns in private office spaces. Energy and Buildings, 121: 234-249.
DOI Google Scholar
Guo X, Tiller DK, Henze GP, Waters CE (2010). The performance of occupancy-based lighting control systems: A review. Lighting Research & Technology, 42: 415-431.
DOI Google Scholar
Haves P, Parker A, Jegi S, Garg V, Ravache B (2017). Development of automated procedures to generate reference building models for ASHRAE Standard 90.1 and India’s building energy code and implementation in OpenStudio.
DOI
Hong T, Chang W-K, Lin H-W (2013). A fresh look at weather impact on peak electricity demand and energy use of buildings using 30-year actual weather data. Applied Energy, 111: 333-350.
DOI Google Scholar
Hong T, Lin H-W (2013). Occupant behavior: impact on energy use of private offices. LBNL Report, LBNL-6128E. Lawrence Berkeley National Laboratory.
Hong T, Yan D, D’Oca S, Chen CF (2017). Ten questions concerning occupant behavior in buildings: The big picture. Building and Environment, 114: 518-530.
DOI Google Scholar
Kim Y-S, Heidarinejad M, Dahlhausen M, Srebric J (2017). Building energy model calibration with schedules derived from electricity use data. Applied Energy, 190: 997-1007.
DOI Google Scholar
Kim Y-S, Srebric J (2017). Impact of occupancy rates on the building electricity consumption in commercial buildings. Energy and Buildings, 138: 591-600.
DOI Google Scholar
Knight W (2016). Self-driving cars can learn a lot by playing grand theft auto. MIT Technology Review, Available at https://www.technologyreview.com/s/602317/self-driving-cars-can-learn-a-lot-by-playing-grand-theft-auto/. Accessed 23 Sept 2019.
Google Scholar
Li H, Macumber D (2019). Open studio-Occupant-Variability-Gem: Pre-release of OpenStudio-Occupant-Variability-Gem. Available at .
DOI
Luo X, Lam KP, Chen Y, Hong T (2017). Performance evaluation of an agent-based occupancy simulation model. Building and Environment, 115: 42-53.
DOI Google Scholar
Mahdavi A, Tahmasebi F, Kayalar M (2016). Prediction of plug loads in office buildings: Simplified and probabilistic methods. Energy and Buildings, 129: 322-329.
DOI Google Scholar
Marr B (2018). Does synthetic data hold the secret to artificial intelligence? Forbes, Available at https://bit.ly/2ne9bSE. Accessed 23 Sept 2019.
Google Scholar
Martani C, Lee D, Robinson P, Britter R, Ratti C (2012). ENERNET: Studying the dynamic relationship between building occupancy and energy consumption. Energy and Buildings, 47: 584-591.
DOI Google Scholar
Masoso OT, Grobler LJ (2010). The dark side of occupants’ behaviour on building energy use. Energy and Buildings, 42: 173-177.
DOI Google Scholar
Mathew P, Wallace N, Issler P, Ravache B, Sun K, Coleman P, Zhu C (2018). Do energy costs really affect commercial mortgage default risk? New results and implications for energy efficiency investments.
Motegi N, Piette MA, Watson DS, Kiliccote S, Xu P (2007). Introduction to commercial building control strategies and techniques for demand response—Appendices. Office of Scientific and Technical Information (OSTI).
DOI
Nikolaev EI, Dvoryaninov PV, Lensky YY, Drozdovsky NS (2018). Using virtual data for training deep model for hand gesture recognition. Journal of Physics: Conference Series, 1015: 042045.
DOI Google Scholar
Project Haystack (n.d.). Available at https://project-haystack.org/. Accessed 29 Sept 2019.
Ranson M, Tarquinio L, Lew A (2016). Modeling the impact of climate change on extreme weather losses. Available at .
DOI
Roth A, Goldwasser D, Parker A (2016). There's a measure for that!. Energy and Buildings, 117: 321-331.
DOI Google Scholar
Ruiz G, Bandera C (2017). Validation of calibrated energy models: common errors. Energies, 10: 1587.
DOI Google Scholar
Sarkar T (2018). Synthetic data generation—A must-have skill for new data scientists. Available at https://towardsdatascience.com/synthetic-data-generation-a-must-have-skill-for-new-data-scientists-915896c0c1ae. Accessed 23 Sept 2019.
Shrivastava A, Pfister T, Tuzel O, Susskind J, Wang W, Webb R (2017). Learning from simulated and unsupervised images through adversarial training. In: Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition.
DOI
Thomas D, Butry D, Gilbert S, Webb D, Fung J (2016). The costs and losses of wildfires: a literature survey. National Institute of Standards and Technology. Available at .
DOI
Tian Y, Li X, Wang K, Wang F (2018). Training and testing object detectors with virtual images. CAA Journal of Automatica Sinica, 5: 539-546.
DOI Google Scholar
Toole J (2019). Synthetic data: A bridge over the data moat—Jameson Toole—Medium. Available at https://heartbeat.fritz.ai/synthetic-data-a-bridge-over-the-data-moat-29f392a52f27. Accessed 23 Sept 2019.
Wang Z, de Dear R, Luo M, Lin B, He Y, Ghahramani A, Zhu Y (2018). Individual difference in thermal comfort: A literature review. Building and Environment, 138: 181-193.
DOI Google Scholar
Wang N, Vlachokostas A, Borkum M, Bergmann H, Zaleski S (2019). Unique Building Identifier: A natural key for building data matching and its energy applications. Energy and Buildings, 184: 230-241.
DOI Google Scholar
Wang Z, Hong T (2020). Learning occupants’ indoor comfort temperature through a Bayesian inference approach for office buildings in United States. Renewable and Sustainable Energy Reviews, 119: 109593.
DOI Google Scholar
Wehner MF, Arnold JR, Knutson T, Kunkel KE, LeGrande AN (2017). Ch. 8: Droughts, floods, and wildfires. In: Climate Science Special Report: Fourth National Climate Assessment, Volume I. U.S. Global Change Research Program. Available at .
DOI
Wilcox S, Marion W (2008). Users Manual for TMY3 Data Sets (Revised). Office of Scientific and Technical Information (OSTI). Available at .
DOI
Yan D, Hong T, Dong B, Mahdavi A, D’Oca S, Gaetani I, Feng X (2017). IEA EBC Annex 66: Definition and simulation of occupant behavior in buildings. Energy and Buildings, 156: 258-270.
DOI Google Scholar
Yoshino H, Hong T, Nord N (2017). IEA EBC annex 53: Total energy use in buildings—Analysis and evaluation methods. Energy and Buildings, 152: 124-136.
DOI Google Scholar
Publication history
Copyright
Acknowledgements

Publication history

Received: 02 February 2020
Accepted: 13 May 2020
Published: 04 June 2020
Issue date: December 2020

Copyright

This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply 2020

Acknowledgements

This research was supported by the Assistant Secretary for Energy Efficiency and Renewable Energy, Office of Building Technologies of the United States Department of Energy, under Contract No. DE-AC02-05CH11231.

Return