International Conference on Case-Based Reasoning

Case-Based Reasoning Research and Development pp 306-319 | Cite as

CBR Model for Predicting a Building’s Electricity Use: On-Line Implementation in the Absence of Historical Data

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9343)

Abstract

This paper presents the development and on-line implementation of a case-based reasoning (CBR) model that predicts the hourly electricity consumption of an institutional building. Building operation measurements and measured and forecast weather information are used to predict the electricity use for the next 6 h. The model’s ability to efficiently deal with an initial absence of historical data and continuously learn as more data becomes available was tested by emptying the database holding historical data prior to the on-line implementation. The prediction accuracy was monitored for almost 4 months. The results show significant improvement as more data becomes available: the initial error, 1 h following the on-line implementation is close to 44 %, it decreases by almost half after 16 h, and reaches 12.8 % at the end of the monitored period. This shows the applicability of a CBR predictive model for new and retrofit buildings where historical data is not available.

Keywords

Case-based reasoning Building Electricity consumption Prediction Historical data Continuous learning 

References

  1. 1.
    Transition to Sustainable Buildings. International Energy Agency, Paris (2013)Google Scholar
  2. 2.
    North American Intelligent Buildings Roadmap. Continental Automated Buildings Association, Ottawa (2011)Google Scholar
  3. 3.
    Kreider, J.F., Haberl, J.S: Predicting hourly building energy use: the great energy predictor shootout – overview and discussion of results. In: Proceedings of the ASHRAE Annual Meeting, June 25–29 1994, pp. 1104–1118, Florida (1994)Google Scholar
  4. 4.
    Haberl, J.S., Thamilseran, S.: Great energy predictor shootout II measuring retrofit savings. ASHRAE J. 40, 49–56 (1998)Google Scholar
  5. 5.
    Zhao, H.-X., Magoules, F.: A review on the prediction of building energy consumption. Renew. Sustain. Energy Rev. 16, 3586–3592 (2012)CrossRefGoogle Scholar
  6. 6.
    Ekici, B.B., Aksoy, U.T.: Prediction of building energy consumption by using artificial neural networks. Adv. Eng. Softw. 40, 356–362 (2009)CrossRefMATHGoogle Scholar
  7. 7.
    Gonzalez, P.A., Zamarreno, J.M.: Prediction of hourly energy consumption in buildings based on a feedback artificial neural network. Energy Build. 37, 595–601 (2005)CrossRefGoogle Scholar
  8. 8.
    Karatasou, S., Santamouris, M., Geros, V.: Modeling and predicting building’s energy use with artificial neural networks: methods and results. Energy Build. 38, 949–958 (2006)CrossRefGoogle Scholar
  9. 9.
    Ucenic, C., Atsalakis, G.: A neuro-fuzzy approach to forecast the electricity demand. In: Proceedings of the 2006 IASME/WSEAS International Conference on Energy & Environmental Systems, pp. 299–304, Chalkida, Greece (2006)Google Scholar
  10. 10.
    Escrivá-Escrivá, G., Roldán-Blay, C., Álvarez-Bel, C.: Electrical consumption forecast using actual data of building end-use decomposition. Energy Build. 82, 73–81 (2014)CrossRefGoogle Scholar
  11. 11.
    Escrivá-Escrivá, G., Álvarez-Bel, C., Roldán-Blay, C., Alcázar-Ortega, M.: New artificial neural network prediction method for electrical consumption forecasting based on building end-uses. Energy Build. 43, 3112–3119 (2011)CrossRefGoogle Scholar
  12. 12.
    Yang, J., Rivard, H., Zmeureanu, R.: On-line building energy prediction using adaptive artificial neural networks. Energy Build. 37, 1250–1259 (2005)CrossRefGoogle Scholar
  13. 13.
    Neto, A.H., Fiorelli, F.A.S.: Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption. Energy Build. 40, 2169–2176 (2008)CrossRefGoogle Scholar
  14. 14.
    Hong, T., Koo, C., Jeong, K.: A decision support model for reducing electric energy consumption in elementary school facilities. Appl. Energy 95, 253–266 (2012)CrossRefGoogle Scholar
  15. 15.
    Breekweg, M.R.B., Gruber, P., Ahmed, O.: Development of a generalized neural network model to detect faults in building energy performance – Part I. In: ASHRAE Transactions, Atlanta (2000)Google Scholar
  16. 16.
    Kumar, S., Mahdavib, A.: Integrating thermal comfort field data analysis in a case-based building simulation environment. Build. Environ. 36, 711–720 (2001)CrossRefGoogle Scholar
  17. 17.
    Monfet, D., Corsi, M., Choiniere, D., Arkhipova, E.: Development of an energy prediction tool for commercial buildings using case-based reasoning. Energy Build. 81, 152–160 (2014)CrossRefGoogle Scholar
  18. 18.
    Platon, R., Dehkordi, V.R., Martel, J.: Hourly prediction of a building’s electricity consumption using case-based reasoning, artificial neural networks and principal component analysis. Energy Build. 92, 10–18 (2015)CrossRefGoogle Scholar
  19. 19.
    Ndiayea, D., Gabriel, K.: Principal component analysis of the electricity consumption in residential dwellings. Energy Build. 43, 446–453 (2011)CrossRefGoogle Scholar
  20. 20.
    Lam, J.C., Wan, K.W., Cheung, K.L., Yang, L.: Principal component analysis of electricity use in office buildings. Energy Build. 40, 828–836 (2008)CrossRefGoogle Scholar
  21. 21.
    ASHRAE Guideline 14: Measurement of energy and demand savings. In: ASHRAE, Atlanta (2002)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Natural Resources Canada, CanmetENERGYVarennesCanada

Personalised recommendations