Abstract
New and emerging data streams, from public databases to smart meter infrastructure, contain valuable information that presents an opportunity to develop more robust data-driven models for benchmarking energy use in buildings. In this paper, we propose a new Data-driven, Multi-metric, and Time-varying (DMT) energy benchmarking framework that utilizes these new data streams to benchmark building energy use across multiple metrics at the daily time scale. High fidelity data from smart meters enables the DMT benchmarking framework to produce daily benchmarking scores and use daily weather data to understand seasonally adjusted performance. Intra-day building efficiency is also investigated by benchmarking buildings across several metrics (e.g., total energy usage, operational energy usage, non-operational energy usage) thereby enabling deeper insights into building operations than traditional yearly benchmarking models. By using quantile regression modeling, the DMT framework can differentiate and understand the main drivers of energy consumption between low and high performing buildings and between building operational states. To illustrate the insights that can be gleaned from the proposed DMT framework, we apply the framework to understand building performance for over 500 schools throughout the state of California. The DMT framework provided insights into how various drivers impacted energy usage for both high and low performing buildings, and results indicated that schools had consistent drivers of energy usage. Overall the DMT framework was designed to be highly interpretable such that it could help bridge the gap between data science and engineering methods thus enabling better decision-making in respect to energy efficiency.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Nowak, S., Baatz, B., Gilleo, A., Kushler, M., Molina, M., York, D.: Beyond carrots for utilities: a national review of performance incentives for energy efficiency, Washington, DC (2015). http://kms.energyefficiencycentre.org/sites/default/files/u1504.pdf. Accessed 31 May 31 2017
U.S. Department of Energy, Buildings energy databook, Silver Spring (2012). http://buildingsdatabook.eren.doe.gov/DataBooks.aspx. Accessed 24 Sept 2017
Ramesh, T., Prakash, R., Shukla, K.K.: Life cycle energy analysis of buildings: an overview. Energy Build. 42, 1592–1600 (2010). https://doi.org/10.1016/j.enbuild.2010.05.007
National Academy of Sciences, Real Prospects for Energy Efficiency in the United States: America’s Energy Future Panel on Energy Efficiency Technologies, National Academies Press, Washington, D.C. (2010). https://doi.org/10.17226/12621
How many smart meters are installed in the United States, and who has them? U.S. Energy Information Administration (EIA) (2017). https://www.eia.gov/tools/faqs/faq.php?id=108&t=3. Accessed 10 Jan 2018
Map: U.S. Building Benchmarking and Transparency Policies, Institute for Market Transformation (2017). http://www.imt.org/resources/detail/map-u.s.-building-benchmarking-policies. Accessed 10 May 2017
Lutzenhiser, L., Moezzi, M., Hungerford, D., Commission, C.E., Friedmann, R., Gas, P., Company, E.: Sticky points in modeling household energy consumption defining the problem. In: 2010 ACEEE Summer Study on Energy Efficiency in Buildings, pp. 167–182. (2010) https://www.pdx.edu/cus/sites/www.pdx.edu.cus/files/Lutzenhiseret al (2010) Sticky Points in Modeling Household Energy Consumption.pdf. Accessed 14 Sept 14 2017
Russell, R., Guerry, A.D., Balvanera, P., Gould, R.K., Basurto, X., Chan, K.M.A., Klain, S., Levine, J., Tam, J.: Humans and nature: how knowing and experiencing nature affect well-being. Annu. Rev. Environ. Resour. 38, 473–502 (2013). https://doi.org/10.1146/annurev-environ-012312-110838
Karlin, B., Zinger, J.F., Ford, R.: The effects of feedback on energy conservation: a meta-analysis. Psychol. Bull. 141, 1205–1227 (2015). https://doi.org/10.1037/a0039650
Jain, R.K., Taylor, J.E., Culligan, P.J.: Investigating the impact eco-feedback information representation has on building occupant energy consumption behavior and savings. Energy Build. 64, 408–414 (2013). https://doi.org/10.1016/j.enbuild.2013.05.011
Filippín, C.: Benchmarking the energy efficiency and greenhouse gases emissions of school buildings in central Argentina. Build. Environ. 35, 407–414 (2000). https://doi.org/10.1016/S0360-1323(99)00035-9
Chung, W.: Review of building energy-use performance benchmarking methodologies. Appl. Energy 88, 1470–1479 (2011). https://doi.org/10.1016/j.apenergy.2010.11.022
Xuchao, W., Priyadarsini, R., SiewEang, L.: Benchmarking energy use and greenhouse gas emissions in Singapore’s hotel industry. Energy Policy 38, 4520–4527 (2010). https://doi.org/10.1016/j.enpol.2010.04.006
U.S.E.P. Agency, ENERGY STAR score technical reference, pp. 1–14 (2014). https://portfoliomanager.energystar.gov/pdf/reference/ENERGY STAR Score.pdf. Accessed 7 Sept 2017
Farrell, M.J.: The measurement of productive efficiency. J. R. Stat. Soc. Ser. A (General) 120, 253–290 (1957). https://doi.org/10.1016/S0377-2217(01)00022-4
Zhou, P., Ang, B.W., Poh, K.L.: A survey of data envelopment analysis in energy and environmental studies. Eur. J. Oper. Res. 189, 1–18 (2008). https://doi.org/10.1016/j.ejor.2007.04.042
Schmidt, P.: Frontier production functions. Econom. Rev. 4, 289–328 (1985). https://doi.org/10.1080/07474938608800089
Lee, W.L., Burnett, J.: Benchmarking energy use assessment of HK-BEAM, BREEAM and LEED. Buil. Environ. 43, 1882–1891 (2008). https://doi.org/10.1016/j.buildenv.2007.11.007
Kavousian, A., Rajagopal, R.: Data-driven benchmarking of building energy efficiency utilizing statistical frontier models. J. Comput. Civil Eng. 28, 79–88 (2014). https://doi.org/10.1061/(ASCE)CP.1943-5487.0000327
Filippini, M., Hunt, L.C.: US residential energy demand and energy efficiency: a stochastic demand frontier approach. Energy Econ. 34, 1484–1491 (2012). https://doi.org/10.1016/j.eneco.2012.06.013
Buck, J., Young, D.: The potential for energy efficiency gains in the Canadian commercial building sector: a stochastic frontier study. Energy 32, 1769–1780 (2007). https://doi.org/10.1016/j.energy.2006.11.008
Yang, Z., Roth, J., Jain, R.K.: DUE-B: Data-driven urban energy benchmarking of buildings using recursive partitioning and stochastic frontier analysis. Energy Build. 163, 58–69 (2018). https://doi.org/10.1016/J.ENBUILD.2017.12.040
Arora, D., Malik, P.: Analytics: key to go from generating big data to deriving business value. In: 2015 IEEE First International Conference on Big Data Computing Service and Applications, pp. 446–452. IEEE (2015). https://doi.org/10.1109/bigdataservice.2015.62
Kavousian, A., Rajagopal, R., Fischer, M.: Determinants of residential electricity consumption: using smart meter data to examine the effect of climate, building characteristics, appliance stock, and occupants’ behavior. Energy 55, 184–194 (2013). https://doi.org/10.1016/j.energy.2013.03.086
Haben, S., Singleton, C., Grindrod, P.: Analysis and clustering of residential customers energy behavioral demand using smart meter data. IEEE Trans. Smart Grid 7, 136–144 (2016). https://doi.org/10.1109/TSG.2015.2409786
Kwac, J., Flora, J., Rajagopal, R.: Household energy consumption segmentation using hourly data. IEEE Trans. Smart Grid 5, 420–430 (2014). https://doi.org/10.1109/TSG.2013.2278477
Alahakoon, D., Yu, X.: Smart electricity meter data intelligence for future energy systems: a survey. IEEE Trans. Industr. Inf. 12, 425–436 (2016). https://doi.org/10.1109/TII.2015.2414355
Chicco, G.: Overview and performance assessment of the clustering methods for electrical load pattern grouping. Energy 42, 68–80 (2012). https://doi.org/10.1016/j.energy.2011.12.031
Zhao, F., Wang, G., Deng, C., Zhao, Y.: A real-time intelligent abnormity diagnosis platform in electric power system. In: International Conference on Advanced Communication Technology, ICACT, Global IT Research Institute (GIRI), pp. 83–87 (2014). https://doi.org/10.1109/icact.2014.6778926
Albert, A., Rajagopal, R.: Smart meter driven segmentation: what your consumption says about you. IEEE Trans. Power Syst. 28, 4019–4030 (2013). https://doi.org/10.1109/TPWRS.2013.2266122
Beckel, C., Sadamori, L., Staake, T., Santini, S.: Revealing household characteristics from smart meter data. Energy 78, 397–410 (2014). https://doi.org/10.1016/j.energy.2014.10.025
Dent, I., Aickelin, U., Rodden, T., Craig, T.: Finding the creatures of habit; clustering households based on their flexibility in using electricity. SSRN Electron. J. (2012). https://doi.org/10.2139/ssrn.2828585
Cao, H.A., Beckel, C., Staake, T.: Are domestic load profiles stable over time? An attempt to identify target households for demand side management campaigns. In: IECON Proceedings (Industrial Electronics Conference), pp. 4733–4738. IEEE (2013). https://doi.org/10.1109/iecon.2013.6699900
Magoulès, F., Zhao, H., Elizondo, D.: Development of an RDP neural network for building energy consumption fault detection and diagnosis. Energy Build. 62, 133–138 (2013). https://doi.org/10.1016/j.enbuild.2013.02.050
Yu, Y., Woradechjumroen, D., Yu, D.: A review of fault detection and diagnosis methodologies on air-handling units. Energy Build. 82, 550–562 (2014). https://doi.org/10.1016/j.enbuild.2014.06.042
Li, S., Wen, J.: A model-based fault detection and diagnostic methodology based on PCA method and wavelet transform. Energy Build. 68, 63–71 (2014). https://doi.org/10.1016/j.enbuild.2013.08.044
Liang, J., Du, R.: Model-based fault detection and diagnosis of HVAC systems using support vector machine method. Int. J. Refrig. 30, 1104–1114 (2007). https://doi.org/10.1016/j.ijrefrig.2006.12.012
Du, Z., Fan, B., Jin, X., Chi, J.: Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis. Build. Environ. 73, 1–11 (2014). https://doi.org/10.1016/j.buildenv.2013.11.021
Capozzoli, A., Lauro, F., Khan, I.: Fault detection analysis using data mining techniques for a cluster of smart office buildings. Expert Syst. Appl. 42, 4324–4338 (2015). https://doi.org/10.1016/j.eswa.2015.01.010
Bynum, J.D., Claridge, D.E., Curtin, J.M.: Development and testing of an automated building commissioning analysis tool (ABCAT). Energy Build. 55, 607–617 (2012). https://doi.org/10.1016/j.enbuild.2012.08.038
Wang, H., Xu, P., Lu, X., Yuan, D.: Methodology of comprehensive building energy performance diagnosis for large commercial buildings at multiple levels. Appl. Energy 169, 14–27 (2016). https://doi.org/10.1016/j.apenergy.2016.01.054
Grueneich, D., Jacot, D.: Scale, Speed, and persistence in an analytics age of efficiency: how deep data meets big savings to deliver comprehensive efficiency. Electr. J. 27, 77–86 (2014). https://doi.org/10.1016/j.tej.2014.03.001
Larsen, P.H., Carvallo, J.P., Goldman, C.A., Murphy, S., Stuart, E., Rockwell, K., Schell, S., Nicholls, L.: Updated Estimates of the Remaining Market Potential of the U.S. ESCO Industry (2017). https://emp.lbl.gov/sites/default/files/revised_market_potential_final_25apr2017.pdf. Accessed 8 May 2017
International Performance Measurement and Verification Protocol Concepts and Options for Determining Energy and Water Savings, Toronto, CA, vol. 1 (2012). http://www.eeperformance.org/uploads/8/6/5/0/8650231/ipmvp_volume_i__2012.pdf. Accessed 1 Oct 2017
FEMP, M&V Guidelines: Measurement and Verification for Performance-Based Contracts - Version 4.0 (2015). http://www1.eere.energy.gov/. Accessed 27 Dec 2017
Ke, M.T., Yeh, C.H., Jian, J.T.: Analysis of building energy consumption parameters and energy savings measurement and verification by applying eQUEST software. Energy Build. 61, 100–107 (2013). https://doi.org/10.1016/j.enbuild.2013.02.012
Granderson, J., Touzani, S., Fernandes, S., Taylor, C.: Application of automated measurement and verification to utility energy efficiency program data. Energy Build. 142, 191–199 (2017). https://doi.org/10.1016/j.enbuild.2017.02.040
Heo, Y., Zavala, V.M.: Gaussian process modeling for measurement and verification of building energy savings. Energy Build. 53, 7–18 (2012). https://doi.org/10.1016/j.enbuild.2012.06.024
Burkhart, M.C., Heo, Y., Zavala, V.M.: Measurement and verification of building systems under uncertain data: a Gaussian process modeling approach. Energy Build. 75, 189–198 (2014). https://doi.org/10.1016/j.enbuild.2014.01.048
Roth, J., Rajagopal, R.: Benchmarking building energy efficiency using quantile regression. Energy (2018). https://doi.org/10.1016/j.energy.2018.02.108
Koenker, R., Bassett, G.: Regression quantile (1978). https://doi.org/10.1257/jep.15.4.143
Chen, C.: An introduction to quantile regression and the QUANTREG Procedure. Sugi 30, 1–24 (2001)
White, H.: A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity. Econometrica 48, 817–838 (1980). https://doi.org/10.2307/1912934
Ürge-Vorsatz, D., Cabeza, L.F., Serrano, S., Barreneche, C., Petrichenko, K.: Heating and cooling energy trends and drivers in buildings. Renew. Sustain. Energy Rev. 41, 85–98 (2015). https://doi.org/10.1016/j.rser.2014.08.039
Landerman, L.R., Land, K.C., Pieper, C.F.: An empirical evaluation of the predictive mean matching method for imputing missing values. Sociol. Methods Res. 26, 3–33 (1997). https://doi.org/10.1177/0049124197026001001
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix A
Appendix A
Variable name | Characteristic and Explanation |
---|---|
District type | District Ownership Type Description |
Educational type | Educational Option Type Description |
Charter School | A “Y” or “N” value indicating whether a school is a charter school in the current academic year. |
High grade | Highest grade offered |
Enrollment | A total count of K-12 students enrolled (primary or short-term) on Census Day (the first Wednesday in October). These data were submitted to CALPADS as part of the annual Fall 1 submission |
Total free meal count | Of the Enrollment (K-12), a total unduplicated count of students who meet household income or categorical eligibility criteria for free meals based on one or more of the following reasons: (1) applying for the National School Lunch Program (NSLP); (2) submitting alternative household income forms; (3) student homeless or migrant statuses in CALPADS; (4) being “directly certified” through CALPADS as participating in California’s food stamp or CalWORKs programs during July - November; or (5) being identified through the weekly CALPADS Foster Matching process or matched by the LEA through the CALPADS online match process as being in Foster Placement or Foster Family Maintenance on Census day. The Free Meal Count (K-12) is not displayed on any CALPADS report; however, this count represents the official Free Meal Count (K-12) for the academic year. |
Percent eligible free | The percent of students eligible for free meals. [Free Meal Count (K-12) divided by Enrollment (K-12)] |
FRPM count | Of the Enrollment (K-12), a total unduplicated count of students who meet household income or categorical eligibility criteria for free or reduced meals (FRPM) based on one or more of the following reasons: (1) applying for the National School Lunch Program (NSLP); (2) submitting alternative household income forms; (3) student homeless or migrant statuses in CALPADS; (4) being “directly certified” through CALPADS as participating in California’s food stamp or CalWORKs programs during July - November; or (5) being identified through the weekly CALPADS Foster Matching process or matched by the LEA through the CALPADS online match process as being in Foster Placement or Foster Family Maintenance on Census day |
Percent eligble FRPM | The percent of students eligible for free or reduced price meals (FRPM). [FRPM Count (K-12) divided by Enrollment (K-12)] |
EDP 365 | The total cost for the current expense of education |
Current expense ADA | Total ADA (average daily attendance) is defined as the total days of student attendance divided by the total days of instruction. This is the total cost of the ADA |
Current expense per ADA | The total cost per ADA or the EDP_365 divided by the Current Expense ADA |
School type | The type of school as either “High School”, “Unified”, or “Elementary” |
Area (sf) | Total area of the school building(s) in square feet |
Median Household Income | The median household income for the zip code taken from the US Census Bureau |
Temperature max | The maximum temperature recorded during the day in Fahrenheit |
Temperature min | The minimum temperature recorded during the day in Fahrenheit |
Temperature mean | The average daily temperature for the day in Fahrenheit |
Dewpoint | The average daily dewpoint temperature for the day in Fahrenheit |
Temperature wetbulb | The average daily wetbulb temperature for the day |
Heating degree day (HDD) | Number of degrees that the day’s average temperature was below 65° Fahrenheit |
Cooling degree day (CDD) | The number of degrees that the day’s average temperature was above 65° Fahrenheit |
Total precipitation | The total amount of precipitation (water equivalent) in inches |
Standard pressure | The total standard pressure for the day in Hg |
Result speed | The resulting wind speed for the day |
Average wind speed | The daily average wind speed in miles per hour |
Max5speed | The max speed of wind with a duration of 5 min |
Max2speed | The max speed of wind with a duration of 2 min |
Temperature mean squared | The average daily temperature squared |
Heating degree day squared (HDD_2) | The heating degree day (HDD) squared |
Cooling degree day squared (CDD_2) | The cooling degree day (CDD) squared |
Temperature mean natural log | The natural log transformation of the average daily temperature |
Weekend | Dummy variable where “1” is a weekend and “0” is a weekday |
Enrollment per area | The total enrollment per unit area (Students per square foot) |
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Roth, J., Jain, R.K. (2018). Data-Driven, Multi-metric, and Time-Varying (DMT) Building Energy Benchmarking Using Smart Meter Data. In: Smith, I., Domer, B. (eds) Advanced Computing Strategies for Engineering. EG-ICE 2018. Lecture Notes in Computer Science(), vol 10863. Springer, Cham. https://doi.org/10.1007/978-3-319-91635-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-319-91635-4_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-91634-7
Online ISBN: 978-3-319-91635-4
eBook Packages: Computer ScienceComputer Science (R0)