Preliminary Evaluation of Symbolic Regression Methods for Energy Consumption Modelling

R. Rueda, M. P. Cuéllar, M. Delgado, M. C. Pegalajar


In the last few years, energy efficiency has become a research field of high interest for governments and industry. In order to understand consumption data and provide useful information for high-level decision making processes in energy efficiency, there is the problem of information modelling and knowledge discovery coming from a set of energy consumption sensors. This paper focuses in this problem, and explores the use of symbolic regression techniques able to find out patterns in data that can be used to extract an analytical formula that explains the behaviour of energy consumption in a set of public buildings. More specifically, we test the feasibility of different representations such as trees and straight line programs for the implementation of genetic programming algorithms, to find out if a building consumption data can be suitably explained from the energy consumption data from other similar buildings. Our experimental study suggests that the Straight Line Programs representation may overcome the limitations of traditional tree-based representations and provides accurate patterns of energy consumption models.


  1. Alcazar, A. I. E. and Sharman, K. C. (1996). Some applications of genetic programming in digital signal processing.
  2. Alonso, C. L., Montan˜a, J. L., Puente, J., and Borges, C. E. (2009). A new linear genetic programming approach based on straight line programs: Some theoretical and experimental aspects. International Journal on Artificial Intelligence Tools, 18(5):757-781.
  3. Benz, F. and Kötzing, T. (2013). An effective heuristic for the smallest grammar problem. In Proc. of GECCO (Genetic and evolutionary computation), pages 487- 494.
  4. Berkowitz, S. J. (1984). On computing the determinant in small parallel time using a small number of processors. Inf. Process. Lett., 18(3):147-150.
  5. Davidson, J. W., Savic, D. A., and Walters, G. A. (2001). Symbolic and numerical regression: experiments and applications. In John, R. and Birkenhead, R., editors, Developments in Soft Computing, pages 175-182, De Montfort University, Leicester, UK. Physica Verlag.
  6. Duffy, J. and Engle-Warnick, J. (2002). Using Symbolic Regression to Infer Strategies from Experimental Data, pages 61-82. Physica-Verlag HD, Heidelberg.
  7. Giusti, M., Heintz, J., Morais, J., Morgenstem, J., and Pardo, L. (1998). Straight-line programs in geometric elimination theory. Journal of Pure and Applied Algebra, 124(1):101 - 146.
  8. K., M. and K., K. (1989). Nonlinear least-squares regression analysis by a simplex method using differential equations containing michaelis-menten type rate constants. pages 25-34.
  9. Koza, J. R. (1994). Genetic programming ii: Automatic discovery of reusable subprograms. Cambridge, MA, USA.
  10. Krick, T. (2002). Straight-line programs in polynomial equation solving.
  11. Langdon, W. B. (1998). Genetic Programming - Computers Using “Natural Selection” to Generate Programs, pages 9-42. Springer US, Boston, MA.
  12. Lankhorst, M. M. (1994). Breeding grammars: Grammatical inference with a genetic algorithm. In Proceedings of the 1994 Eurosim Conference on Massively Parallel Processing Applications and Development, pages 423-430. Elsevier.
  13. Lazarus, C. and Hu, H. (2001). Using genetic programming to evolve robot behaviours.
  14. M., R. A. (2007). Programacin gentica: La regresin simblica. Entramado, 3:76-85.
  15. Maros, S., Arias Caete, M., and Dominique, R. (2016). Energy efficiency .saving energy, saving money.
  16. McKay, B., Willis, M., and Barton, G. (1997). Steady-state modelling of chemical process systems using genetic programming. Computers & Chemical Engineering, 21(9):981 - 996.
  17. McKay, B., Willis, M. J., and Barton, G. W. (1995). Using a tree structured genetic algorithm to perform symbolic regression. pages 487-492.
  18. Molina-Solana, M. (2014). Data mining for building energy management. In Proceedings of Sustainable Places 2014.
  19. Molina-Solana, M., Ros, M., Martn-Bautista, M. J., and Vila, A. (2014). Minera de datos y gestin energtica: tendencias actuales. In Proc. XVII Congreso Espaol sobre Tecnologas y Lgica Fuzzy (ESTYLF2014), pages 627-632.
  20. Naoki, M., McKay, B., Xuan, N., Daryl, E., and Takeuchi, S. (2009). A New Method for Simplifying Algebraic Expressions in Genetic Programming Called Equivalent Decision Simplification, pages 171-178. Springer Berlin Heidelberg, Berlin, Heidelberg.
  21. Neves, S. and Araujo, F. (2015). Straight-line programs for fast sparse matrix-vector multiplication. Concurrency and Computation: Practice and Experience, 27(13):3245-3261.
  22. Pan, J., Jain, R., and Paul, S. (2014). A survey of energy efficiency in buildings and microgrids using networking technologies. IEEE Communications Surveys Tutorials, 16(3):1709-1731.
  23. Pandey, H. M. (2016). Performance evaluation of selection methods of genetic algorithm and network security concerns. Procedia Computer Science, 78:13 - 18.
  24. Patil, N. S. and Patil, P. P. R. (2010). Data aggregation in wireless sensor network.
  25. Rhudy, M. (2014). Time alignment techniques for experimental sensor data. volume 5.
  26. Royston, P. (2004). Multiple imputation of missing values. volume 4.
  27. Schmidt, M. and Lipson, H. (2010). Symbolic Regression of Implicit Equations, pages 73-85. Springer US, Boston, MA.
  28. Sequera, J., del Castillo Diez, J., and Sotos, L. (2012). Document clustering with evolutionary systems through straight-line programs slp. Intelligent Learning Systems and Applications, 4(4):303-318.
  29. Tsoulos, I. G. and Lagaris, I. E. (2006). Solving differential equations with genetic programming. Genetic Programming and Evolvable Machines, 7(1):33-54.
  30. Yu, Z., Haghighat, F., Fung, B. C., and Yoshino, H. (2010). A decision tree method for building energy demand modeling. Energy and Buildings, 42(10):1637 - 1646.

Paper Citation

in Harvard Style

Rueda R., P. Cuéllar M., Delgado M. and C. Pegalajar M. (2017). Preliminary Evaluation of Symbolic Regression Methods for Energy Consumption Modelling . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 39-49. DOI: 10.5220/0006108100390049

in Bibtex Style

author={R. Rueda and M. P. Cuéllar and M. Delgado and M. C. Pegalajar},
title={Preliminary Evaluation of Symbolic Regression Methods for Energy Consumption Modelling},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},

in EndNote Style

JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Preliminary Evaluation of Symbolic Regression Methods for Energy Consumption Modelling
SN - 978-989-758-222-6
AU - Rueda R.
AU - P. Cuéllar M.
AU - Delgado M.
AU - C. Pegalajar M.
PY - 2017
SP - 39
EP - 49
DO - 10.5220/0006108100390049