Advertisement

Estimates of residential building energy consumption using a multi-verse optimizer-based support vector machine with k-fold cross-validation

  • Hamed Tabrizchi
  • Mohammad Masoud JavidiEmail author
  • Vahid Amirzadeh
Original Paper
  • 23 Downloads

Abstract

The ever-increasing human population, building constructions, and technology usages have currently caused electric consumption to grow significantly. Accordingly, some of the efficient tools for more and more energy saving and development are efficient energy management and forecasting energy consumption for buildings. Additionally, efficient energy management and smart restructuring can improve energy performance in different areas. Given that electricity is the main form of energy that is consumed in residential buildings, forecasting the electrical energy consumption in a building will bring significant benefits to the building and business owners. All these means call for precise energy forecast to make the best decisions. In recent years, artificial intelligence, generally, and machine learning methods, in some areas, have been employed to forecast building energy consumption and efficiency. The present study aims to predict energy consumption with higher accuracy and lower run time. We optimize the parameters of a support vector machine (SVM) using a multi-verse optimizer (MVO) without the grid search algorithm, due to the development consequence of residential energy predicting models. This paper presented the MVO-SVM approach for predicting energy consumption in residential buildings. The proposed approach examined a UCI repository dataset. Based on the experimental results MVO can effectively decrease the number of features while preserving a great predicting precision.

Keywords

Support vector machine Energy consumption forecast Multi-verse optimizer Cross-validation Data science 

Notes

References

  1. Alobaidi MH, Chebana F, Meguid MA (2018) Robust ensemble learning framework for day-ahead forecasting of household based energy consumption. Appl Energy 212:997–1012CrossRefGoogle Scholar
  2. Amasyali K, El-Gohary NM (2018) A review of data-driven building energy consumption prediction studies. Renew Sustain Energy Rev 81:1192–1205CrossRefGoogle Scholar
  3. Andonovski G, Angelov P, Blažič S, Škrjanc I (2016) A practical implementation of Robust Evolving Cloud-based Controller with normalized data space for heat-exchanger plant. Appl Soft Comput 48:29–38CrossRefGoogle Scholar
  4. Angelov P (2014) Outside the box: an alternative data analytics framework. J Autom Mobile Robot Intell Syst 8:29–35Google Scholar
  5. Angelov P, Kasabov N (2005) Evolving computational intelligence systems. In: Proceedings of the 1st international workshop on genetic fuzzy systems, pp 76–82Google Scholar
  6. Angelov P, Victor J, Dourado A, Filev D (2004) On-line evolution of Takagi–Sugeno fuzzy models. IFAC Proc 37:67–72CrossRefGoogle Scholar
  7. Bai Y, Sun Z, Zeng B, Long J, Li L, de Oliveira JV, Li C (2018) A comparison of dimension reduction techniques for support vector machine modeling of multi-parameter manufacturing quality prediction. J Intell Manuf, pp 1–12Google Scholar
  8. Cameron AC, Windmeijer FAJ (1997) An R-squared measure of goodness of fit for some common nonlinear regression models. J Econom 77:329–342MathSciNetCrossRefzbMATHGoogle Scholar
  9. Candanedo LM, Feldheim V, Deramaix D (2017) Data driven prediction models of energy use of appliances in a low-energy house. Appl Energy Predict 140:81–97Google Scholar
  10. Cheng M-Y, Prayogo D, Wu Y-W (2018) Prediction of permanent deformation in asphalt pavements using a novel symbiotic organisms search–least squares support vector regression. Neural Comput Appl, 1–13Google Scholar
  11. de Jesús Rubio J (2009) SOFMLS: online self-organizing fuzzy modified least-squares network. IEEE Trans Fuzzy Syst 17:1296–1309CrossRefGoogle Scholar
  12. de Jesús Rubio J (2017) Interpolation neural network model of a manufactured wind turbine. Neural Comput Appl 28:2017–2028CrossRefGoogle Scholar
  13. de Jesús Rubio J, Lughofer E, Meda-Campaña JA, Páramo LA, Novoa JF, Pacheco J (2018) Neural network updating via argument Kalman filter for modeling of Takagi–Sugeno fuzzy models. J Intell Fuzzy Syst 35:2585–2596CrossRefGoogle Scholar
  14. Edwards RE, New J, Parker LE (2012) Predicting future hourly residential electrical consumption: a machine learning case study. Energy Build 49:591–603CrossRefGoogle Scholar
  15. Faris H, Hassonah MA, Ala’M A-Z, Mirjalili S, Aljarah I (2018) A multi-verse optimizer approach for feature selection and optimizing SVM parameters based on a robust system architecture. Neural Comput Appl 30:2355–2369CrossRefGoogle Scholar
  16. Fushiki T (2011) Estimation of prediction error by using K-fold cross-validation. Stat Comput 21:137–146MathSciNetCrossRefzbMATHGoogle Scholar
  17. Gandomi AH, Yang X-S, Talatahari S, Alavi AH (2013) Metaheuristic algorithms in modeling and optimization. In: Metaheuristic applications in structures and infrastructures. Elsevier, Amsterdam, pp 1–24Google Scholar
  18. Gong Y, Yang S, Ma H, Ge M (2018) Fuzzy regression model based on geometric coordinate points distance and application to performance evaluation. J Intell Fuzzy Syst 34:395–404CrossRefGoogle Scholar
  19. Guo Y et al (2018) Machine learning-based thermal response time ahead energy demand prediction for building heating systems. Appl Energy 221:16–27CrossRefGoogle Scholar
  20. Han B, Bian XJP (2018) A hybrid PSO-SVM-based model for determination of oil recovery factor in the low-permeability reservoir. Petroleum 4:43–49CrossRefGoogle Scholar
  21. Iglesias JA, Angelov P, Ledezma A, Sanchis A (2012) Creating evolving user behavior profiles automatically. Trans Knowl Data Eng 24:854–867CrossRefGoogle Scholar
  22. Jain RK, Smith KM, Culligan PJ, Taylor JE (2014) Forecasting energy consumption of multi-family residential buildings using support vector regression: investigating the impact of temporal and spatial monitoring granularity on performance accuracy. Appl Energy 123:168–178CrossRefGoogle Scholar
  23. Limanond T, Jomnonkwao S, Srikaew A (2011) Projection of future transport energy demand of Thailand. Energy Policy 39:2754–2763CrossRefGoogle Scholar
  24. Mirjalili S, Mirjalili SM, Hatamlou A (2016) Multi-verse optimizer: a nature-inspired algorithm for global optimization. Neural Comput Appl 27:495–513CrossRefGoogle Scholar
  25. Moon J, Park J, Hwang E, Jun S (2017) Forecasting power consumption for higher educational institutions based on machine learning, pp 1–23Google Scholar
  26. Muralitharan K, Sakthivel R, Vishnuvarthan R (2018) Neural network based optimization approach for energy demand prediction in smart grid. Neurocomputing 273:199–208CrossRefGoogle Scholar
  27. Nikolaou T, Kolokotsa D, Stavrakakis G, Apostolou A, Munteanu C (2015) Managing indoor environments and energy in buildings with integrated intelligent systems. Springer, BerlinCrossRefGoogle Scholar
  28. Nowotarski J, Weron RJR, Reviews SE (2018) Recent advances in electricity price forecasting: a review of probabilistic forecasting. Renew Sustain Energy Rev 81:1548–1568CrossRefGoogle Scholar
  29. Paudel S et al (2017) A relevant data selection method for energy consumption prediction of low energy building based on support vector machine. Electr Energy Syst 138:240–256Google Scholar
  30. Poli AA, Cirillo C (1993) On the use of the normalized mean square error in evaluating dispersion model performance. Atmos Environ 27:2427–2434CrossRefGoogle Scholar
  31. Pratama M, Anavatti SG, Angelov PP, Lughofer E (2014) PANFIS: a novel incremental learning machine. IEEE Trans Neural Netw 25:55–68CrossRefGoogle Scholar
  32. Qiu B, Zhang Y, Yang Z (2018) New discrete-time ZNN models for least-squares solution of dynamic linear equation system with time-varying rank-deficient coefficient. IEEE Trans Neural Netw Learn Syst 29:5767–5776MathSciNetCrossRefGoogle Scholar
  33. Rohani A, Taki M, Abdollahpour MR (2018) A novel soft computing model (Gaussian process regression with K-fold cross validation) for daily and monthly solar radiation forecasting (Part: I). Renew Energy 115:411–422CrossRefGoogle Scholar
  34. Seyedzadeh S, Rahimian FP, Glesk I, Roper M (2018) Machine learning for estimation of building energy consumption and performance: a review. Vis Eng 6:5CrossRefGoogle Scholar
  35. Shi J, Yang Y, Wang P, Liu Y, Han S (2010) Genetic algorithm-piecewise support vector machine model for short term wind power prediction. In: 2010 8th World congress on intelligent control and automation (WCICA). IEEE, pp 2254–2258Google Scholar
  36. Song H, Qin AK, Salim FD (2017) Multi-resolution selective ensemble extreme learning machine for electricity consumption prediction. In: International conference on neural information processing. Springer, Berlin, pp 600–609Google Scholar
  37. Szoplik J (2015) Forecasting of natural gas consumption with artificial neural networks. Energy 85:208–220CrossRefGoogle Scholar
  38. Troy AR, Grove JM, O’Neil-Dunne JP, Pickett ST, Cadenasso ML (2007) Predicting opportunities for greening and patterns of vegetation on private urban lands. Environ Manag 40:394–412CrossRefGoogle Scholar
  39. UCI Machine Learning Repository: appliances energy prediction data set. https://archive.ics.uci.edu/ml/datasets/Appliances+energy+prediction. Accessed 3 Jan 2019
  40. Vapnik V (1992) Principles of risk minimization for learning theory. In: Advances in neural information processing systems, pp 831–838Google Scholar
  41. Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10:988–999CrossRefGoogle Scholar
  42. Vapnik V (2013) The nature of statistical learning theory. Springer Science and Business Media, New YorkzbMATHGoogle Scholar
  43. Wang X, Pardalos PM (2014) A survey of support vector machines with uncertainties. Ann Data Sci 1:293–309CrossRefGoogle Scholar
  44. Wang Z, Wang Y, Srinivasan RSJE (2018) A novel ensemble learning approach to support building energy use prediction. Energy Build 159:109–122CrossRefGoogle Scholar
  45. Wei Y et al (2018) A review of data-driven approaches for prediction and classification of building energy consumption. Renew Sustain Energy Rev 82:1027–1047CrossRefGoogle Scholar
  46. Wong T-T (2015) Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognit 48:2839–2846CrossRefzbMATHGoogle Scholar
  47. World Energy Trilemma Index 2018. https://www.worldenergy.org/publications/2018/trilemma-report-2018/. Accessed 2 Jan 2019
  48. World Power Consumption | Electricity Consumption. https://yearbook.enerdata.net/electricity/electricity-domestic-consumption-data.html. Accessed 2 Jan 2019
  49. Yang Z, Ce L, Lian L (2017a) Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods. Appl Energy 190:291–305CrossRefGoogle Scholar
  50. Yang J et al (2017b) k-Shape clustering algorithm for building energy usage patterns analysis and forecasting model accuracy improvement. Energy Build 146:27–37CrossRefGoogle Scholar
  51. Zhang Y, Zhang X, Tang L (2012) Energy consumption prediction in ironmaking process using hybrid algorithm of SVM and PSO. In: International symposium on neural networks. Springer, pp 594–600Google Scholar
  52. Zhang F, Deb C, Lee SE, Yang J, Shah KW (2016) Time series forecasting for building energy consumption using weighted support vector regression with differential evolution optimization technique. Energy Build 126:94–103CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceShahid Bahonar University of KermanKermanIran
  2. 2.Department of StatisticsShahid Bahonar University of KermanKermanIran

Personalised recommendations