Abstract
Buildings consume over 40% of the total energy in modern societies, and improving their energy efficiency can significantly reduce our energy footprint. In this article, we present WattScale, a data-driven approach to identify the least energy-efficient buildings from a large population of buildings in a city or a region. Unlike previous methods such as least-squares that use point estimates, WattScale uses Bayesian inference to capture the stochasticity in the daily energy usage by estimating the distribution of parameters that affect a building. Further, it compares them with similar homes in a given population. WattScale also incorporates a fault detection algorithm to identify the underlying causes of energy inefficiency. We validate our approach using ground truth data from different geographical locations, which showcases its applicability in various settings. WattScale has two execution modes—(i) individual and (ii) region-based, which we highlight using two case studies. For the individual execution mode, we present results from a city containing >10,000 buildings and show that more than half of the buildings are inefficient in one way or another indicating a significant potential from energy improvement measures. Additionally, we provide probable cause of inefficiency and find that 41%, 23.73%, and 0.51% homes have poor building envelope, heating, and cooling system faults, respectively. For the region-based execution mode, we show that WattScale can be extended to millions of homes in the U.S. due to the recent availability of representative energy datasets.
- Alliance to Save Energy. 2020. Energy Use in Buildings. (visited on December 2020). Retrieved from https://www.ase.org/initiatives/buildings.Google Scholar
- ENGIE Resources. 2017. Whitepaper: Advanced Metering Infrastructure - AMI - is a fundamental part of the grid's evolution. Retrieved from https://tinyurl.com/y9sn8r9s.Google Scholar
- Pecan Street. 2017. Dataport dataset. Retrieved from https://dataport.cloud/.Google Scholar
- Green Button Alliance. 2017. Green Button Data. Retrieved from http://www.greenbuttondata.org/.Google Scholar
- Baltimore Gas and Electric. 2019. Load Profiles. Retrieved from https://supplier.bge.com/electric/load/profiles.asp.Google Scholar
- Lawrence Berkeley National Lab. 2019. Building Performance Database. Retrieved from https://bpd.lbl.gov/.Google Scholar
- Energy Upgrade California. 2019. California: Rebates and Incentives. Retrieved from https://www.energyupgradeca.org/home-energy-efficiency/rebates-incentives/.Google Scholar
- US Department of Energy. 2019. Energy Saver: Incentives and Financing for Energy Efficient Homes. Retrieved from https://www.energy.gov/energysaver/services/incentives-and-financing-energy-efficient-homes.Google Scholar
- NorthWestern Energy. 2019. Customer Load Profiles. Retrieved from http://www.northwesternenergy.com/for-suppliers/customer-load-profiles.Google Scholar
- San Diego Gas and Electric. 2019. Customer Load Profiles. Retrieved from https://www.sdge.com/more-information/doing-business-with-us/energy-service-providers/customer-load-profiles.Google Scholar
- Efficiency Vermont. 2019. Find Your Rebates. Retrieved from https://www.efficiencyvermont.com/rebates.Google Scholar
- M. Aftab, C. K. Chau, and M. Khonji. 2017. Real-time appliance identification using smart plugs: Demo abstract. In Proceedings of the 8th International Conference on Future Energy Systems.Google Scholar
- J. C. Allen. 1976. A modified sine wave method for calculating degree days. Environ. Entomol. 5, 3 (1976).Google Scholar
- FUNIP ASHRAE. 2013. Fundamentals handbook. IP Edit. (2013).Google Scholar
- N. Batra, O. Parson, M. Berges, A. Singh, and A. Rogers. 2014. A comparison of non-intrusive load monitoring methods for commercial and residential buildings. arXiv preprint arXiv:1408.6595.Google Scholar
- G. Bellala, M. Marwah, M. Arlitt, G. Lyon, and C. Bash. 2012. Following the electrons: Methods for power management in commercial buildings. In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Datac Mining.Google Scholar
- M. A. Brown, M. Cox, B. Staver, and P. Baer. 2014. Climate change and energy demand in buildings. Proceedings of the American Council for an Energy Efficient Economy (ACEEE’14).Google Scholar
- William Chung, Y. V. Hui, and Y. Miu Lam. 2006. Benchmarking the energy efficiency of commercial buildings. Appl. Energy 83, 1 (2006), 1--14.Google Scholar
- S. De Wit. 1997. Influence of modeling uncertainties on the simulation of building thermal comfort performance. In Building Simulation, Vol. 5.Google Scholar
- C. Fan, F. Xiao, and S. Wang. 2014. Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques. Appl. Energy (2014).Google Scholar
- H. Fei, Y. Kim, S. Sahu, M. Naphade, S. K. Mamidipalli, and J. Hutchinson. 2013. Heat pump detection from coarse grained smart meter data with positive and unlabeled learning. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Google Scholar
- M. Fels. 1986. PRISM: An Introduction. Energy Build. (1986).Google Scholar
- R. Fontugne, J. Ortiz, N. Tremblay, P. Borgnat, P. Flandrin, K. Fukuda, D. Culler, and H. Esaki. 2013. Strip, bind, and search: A method for identifying abnormal energy consumption in buildings. In Proceedings of the 12th International Conference on Information Processing in Sensor Networks.Google Scholar
- Andrew Gelman et al. 2006. Prior distributions for variance parameters in hierarchical models (comment on article by browne and draper). Bayesian Anal. 1, 3 (2006), 515--534.Google Scholar
- ASHRAE Guideline. 2014. Guideline 14-2014. Measure. Energy Demand Water Sav. (2014).Google Scholar
- G. Hart. 1992. Nonintrusive appliance load monitoring. Proc. IEEE (1992).Google Scholar
- J. S. Hygh, J. F. DeCarolis, D. B. Hill, and S. R. Ranjithan. 2012. Multivariate regression as an energy assessment tool in early building design. Build. Environ. (2012).Google Scholar
- S. Iyengar, S. Lee, D. Irwin, and P. Shenoy. 2016. Analyzing energy usage on a city-scale using utility smart meters. In Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments.Google Scholar
- P. Jacobs and H. Henderson. 2002. State-of-the-art review of whole building, building envelope, and HVAC component and system simulation and design tools. Architect. Energy Corp. (2002).Google Scholar
- H. Janetzko, F. Stoffel, S. Mittelstädt, and D. A. Keim. 2014. Anomaly detection for visual analytics of power consumption data. Comput. Graphics (2014).Google Scholar
- S. Katipamula and M. Brambley. 2005. Review article: Methods for fault detection, diagnostics, and prognostics for building systems—A review, Part I. HVAC8R Research.Google Scholar
- J. Kelso (Ed.). 2012. Buildings Energy Data Book. Department of Energy.Google Scholar
- J. Kissock, J. Haberl, and D. Claridge. 2002. Development of a Toolkit for Calculating Linear, Change-Point Linear and Multiple-Linear Inverse Building Energy Analysis Models. Technical Report. Texas A8M University.Google Scholar
- H. Levy. 2015. Stochastic Dominance: Investment Decision Making Under Uncertainty. Springer.Google Scholar
- J. E. Seem. 2007. Using intelligent data analysis to detect abnormal energy consumption in buildings. Energy Build. (2007).Google Scholar
- HCS Thom. 1954. The rational relationship between heating degree days and temperature. Monthly Weather Rev. (1954).Google Scholar
- S. Wang, C. Yan, and F. Xiao. 2012. Quantitative energy performance assessment methods for existing buildings. Energy Build. (2012).Google Scholar
- Zeyu Wang and Ravi S. Srinivasan. 2017. A review of artificial intelligence-based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models. Renew. Sustain. Energy Rev. 75 (2017), 796--808.Google Scholar
Cross Ref
- C. Yan, S. Wang, and F. Xiao. 2012. A simplified energy performance assessment method for existing buildings based on energy bill disaggregation. Energy Build. (2012).Google Scholar
- H. Zhao and F. Magoulès. 2012. A review on the prediction of building energy consumption. Renew. Sustain. Energy Rev. (2012).Google Scholar
- Q. Zhou, S. Wang, and Z. Ma. 2009. A model-based fault detection and diagnosis strategy for HVAC systems. Int. J. Energy Res. (2009).Google Scholar
Index Terms
WattScale: A Data-driven Approach for Energy Efficiency Analytics of Buildings at Scale
Recommendations
WattHome: A Data-driven Approach for Energy Efficiency Analytics at City-scale
KDD '18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningBuildings consume over 40% of the total energy in modern societies and improving their energy efficiency can significantly reduce our energy footprint. In this paper, we present WattHome, a data-driven approach to identify the least energy efficient ...
Modelling energy efficiency performance of residential building stocks based on Bayesian statistical inference
This paper provides a model based on Integrated Nested Laplace Approximation to predict the energy performance of existing residential building stocks. The energy demand and the discomfort hours for heating and cooling were taken as response variables ...
Design of a New Automated Fault Detector based on artificial intelligence and Big Data Techniques
AbstractConcerns over energy and environmental issues around the world have led to the worldwide focus on energy use reduction. Studies in each area of energy have shown that residential and commercial construction sectors consume more power than other ...






Comments