Uncertainty reduction in measuring and verification of energy savings by statistical learning in manufacturing environments

  • Noelia Oses
  • Aritz Legarretaetxebarria
  • Marco Quartulli
  • Igor García
  • Mikel Serrano
Short Original Paper


Industry 4.0 methodological advancements based on continuous analytics and on the sensorization of manufacturing lines make it possible to design and develop integrated systems for measurement and verification of the impact of implemented energy conservation measures (ECM) in industrial plants. The pilot study presented here has focused on developing a model of the energy consumption of the injection machines in a manufacturing facility. The energy savings are calculated by comparing energy consumption of the post- and pre-ECM periods, adjusted so that the comparison is made in the pre-ECM operating conditions. The contribution of the model is to reduce the uncertainty, i.e. to provide narrower limits for the possible values of the estimate of consumed energy, by taking advantage of the fact that the period in which the energy savings are to be measured is usually quite larger than the time intervals in which the energy performance measurements are taken. This better approximation of the range of possible values for the estimate is achieved by combining traditional statistics and machine learning methods.


Measurement and verification Adjusted baseline calculation Energy savings Statistical learning 


  1. 1.
    Khouri, I., et al.: Towards an optimization methodology of a rough forged part taking into account ductile damage. Int. J. Interact. Des. Manuf. 5, 213–225 (2011)CrossRefGoogle Scholar
  2. 2.
    Adam, L., et al.: Application of high-performance computing to a blot static tensile test. Int. J. Interact. Des. Manuf. 6, 195–203 (2012)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Amaya, A.F.D., Torres, A.G.D., Maya, D.A.A.: First and second thermodynamic law analyses applied to ignition engines modeling and emission prediction. Int. J. Interact. Des. Manuf. (2014). doi:10.1007/s12008-014-0247-y
  4. 4.
    Cherifi, A., et al.: Methodology for innovative eco-design based on TRIZ. Int. J. Interact. Des. Manuf. 9, 167–175 (2015)CrossRefGoogle Scholar
  5. 5.
    Cascini, G., et al.: Systematic design through the integration of TRIZ and optimization tools. In: Procedia Engineering 9 (2011). Proceeding of the ETRIA World TRIZ Future Conference, pp. 674–679. ISSN: 1877-7058. doi:10.1016/j.proeng.2011.03.154. http://www.sciencedirect.com/science/article/pii/S1877705811001718
  6. 6.
    Efficiency Valuation Organisation: International performance measurement and verification protocol-core concepts. EVO 10000-1, 2014 (2014)Google Scholar
  7. 7.
    CEATI International: Energy savings measurement guide. http://www.ceati.com/freepublications/7031_Guide_Web.pdf. Accessed 11 May 2015
  8. 8.
    American Society of Heating: Refrigerating and Air-conditioning Engineers, Inc. ASHRAE Guide-line 14-2002 Measurement of Energy and Demand Savings (2002). ISSN: 1049-894XGoogle Scholar
  9. 9.
    Efficiency Valuation Organisation: International Performance Measurement and Verification Protocol—Concepts and Options for Determining Energy and Water Savings, vol. I. US Department of Energy (2002). (DOE/GO-102002-1554)Google Scholar
  10. 10.
    Haberl, J.S., et al.: ASHRAE’s proposed guideline 14P for measurement of energy and demand savings: how to determine what was really saved by the retrofit. In: First International Conference for Enhanced Building Operations, Austin (2001)Google Scholar
  11. 11.
    International Organization for Standardization. ISO 50015:2014: Energy management systems—measurement and verification of energy performance of organizations-general principles and guidance. https://www.iso.org/obp/ui/#iso:std:iso:50015:ed-1:v1:en. Accessed 11 May 2015
  12. 12.
    International Organization for Standardization. ISO 50001—energy management system (2011). https://www.iso.org/obp/ui/#iso:std:iso:50001:ed-1:v1:en. Accessed 11 May 2015
  13. 13.
    Heo, Y., et al.: Cost-effective measurement and verification method for determining energy savings under uncertainty. In: Proceedings of ASHRAE Annual Conference (2013)Google Scholar
  14. 14.
    Higgins, J.A.: Energy modeling basics. ASHRAE J. 54.12, 26–30 (2012). ISSN:00012491Google Scholar
  15. 15.
    Heo, Yeonsook: Zavala, Victor M: Gaussian process modeling for measurement and verification of building energy savings. Energy Build. 53, 7–18 (2012). ISSN: 0378-7788. doi:10.1016/j.enbuild.2012.06.024
  16. 16.
    Tutterow, V., Schultz, S., Yigdall, J.: Making the case for energy metering and monitoring at industrial facilities. In: 2011 ACEEE Summer Study on Energy Efficiency in Industry, Niagara Falls (2011)Google Scholar
  17. 17.
    US Department of Energy: Superior energy performance measurement and verification protocol for industry (2012)Google Scholar
  18. 18.
    Gontarz, A., Weiss, L., Wegener, K.: Energy consumptionmeasurement with a multichannel measurement system on a machinetool. In: International Conference on Innovative Technologies IN-TECH. Inspire AG, IWF, ETH Zürich (2010). doi:10.3929/ethz-a-007577653
  19. 19.
    Kleinbaum, D.G., et al.: Applied Regression Analysis and other Multivariable Methods, 3rd edn. Duxbury, NY (1998)MATHGoogle Scholar
  20. 20.
    Efficiency Valuation Organisation: International performance measurement and verification protocol—statistics and uncertainty for IPMVP. EVO 10100–1, 2014 (2014)Google Scholar
  21. 21.
    Duda, R.O., Hart, P.E.: Pattern Classification, 2nd edn. Wiley-Interscience, New York (2000). ISBN: 0471056693MATHGoogle Scholar
  22. 22.
    Mitchell, T.M.: Machine Learning, 1st edn. McGraw-Hill Inc, New York (1997). ISBN: 0070428077, 9780070428072MATHGoogle Scholar
  23. 23.
    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence (IJCAI’95), vol. 2, pp. 1137–1143. Morgan Kaufmann Publishers Inc., Montreal (1995). ISBN: 1-55860-363-8Google Scholar
  24. 24.
    James, G., et al.: An introduction to statistical learning—with applications in R. In: Casella, G., Fienberg, S., Olkin, I. (eds.) 6th edn. Springer, New York (2013). ISBN: 978-1461471370Google Scholar

Copyright information

© Springer-Verlag France 2016

Authors and Affiliations

  1. 1.Vicomtech-IK4, Parque Científico y Tecnológico de GipuzkoaDonostia/San SebastiánSpain
  2. 2.Dominion SolutionsBilbaoSpain

Personalised recommendations