Advertisement

Electrical Energy Prediction with Regression-Oriented Models

  • Tao Zhang
  • Lyuchao Liao
  • Hongtu Lai
  • Jierui Liu
  • Fumin Zou
  • Qiqin Cai
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 891)

Abstract

Electrical energy consumption analysis is critical to saving energy, and therefore more and more attention has been paid to make a consumption prediction. However, there are so many factors in the building that affect the energy consumption of electrical appliances that it’s hard to get an efficient method. To address these problems, the traditional linear regression model, SVM-based model, Random Forest (RF) and XGBoost algorithm were employed to explore the relationship between factors and consumption. The experimental results show that XGBoost is an efficient method to explore correlation pattern and to make a consumption prediction; removal of lighting factor show a more reasonable result to the prediction accuracy; and factor of temperature shows a more significant for consumption prediction than of humidity. This finding would be benefit to energy consumption modelling and improving prediction accuracy.

Keywords

Electrical energy consumption Electrical data mining Regression prediction model Electric quantity prediction 

Notes

Acknowledgment

This work was supported in part by Projects of National Science Foundation of China (No.41471333); project NGII20170625 of CERNET Innovation Project; project 2017A13025 of Science and Technology Development Center, Ministry of Education, China; project 2018Y3001 of Fujian Provincial Department of Science and Technology; projects of Fujian Provincial Department of Education (JA14209, JA15325).

References

  1. 1.
    Barbato, A., Capone, A., Rodolfi, M., et al.: Forecasting the usage of household appliances through power meter sensors for demand management in the smart grid. In: 2011 IEEE International Conference on Smart Grid Communications (SmartGridComm), pp. 404–409. IEEE (2011)Google Scholar
  2. 2.
    Firth, S., Lomas, K., Wright, A., et al.: Identifying trends in the use of domestic appliances from household electricity consumption measurements. Energy Build. 40(5), 926–936 (2008)CrossRefGoogle Scholar
  3. 3.
    Fan, L.J.: Energy consumption forecasting and energy saving analysis of urban buildings based on multiple linear regression model. Nat. Sci. J. Xiangtan Univ., 123–126 (2016)Google Scholar
  4. 4.
    Zhou, Y.P., Yu, Z., Li, J., Huang, Y.J., Zhang, G.Q.: Review of measuring methods and prediction models of building occupant behavior. HV & AC, pp. 11–18 (2017)Google Scholar
  5. 5.
    Candanedo, L.M., Feldheim, V., Deramaix, D.: Data driven prediction models of energy use of appliances in a low-energy house. Energy Build. 140, 81–97 (2017)CrossRefGoogle Scholar
  6. 6.
    Li, A.Q., Bai, X.L.: Study on predication of energy consumption in residential buildings. Build. Sci. 8, 006 (2007)Google Scholar
  7. 7.
    Chao, Z., Siming, L., Qiaoling, X.: College building energy consumption prediction based on GM-RBF neural network. J. Nanjing Univ. Sci. Technol. 38, 48–53 (2014)Google Scholar
  8. 8.
    Yoon, Y.R., Moon, H.J.: Energy consumption model with energy use factors of tenants in commercial buildings using Gaussian process regression. Energy Build. 168, 215–224 (2018)CrossRefGoogle Scholar
  9. 9.
  10. 10.
    Zhou, F., Zhang, L.M., Qin, W.W., Wu, X.G., Lin, J.Y.: Energy consumption forecasting model and abnormal diagnosis of large public buildings based on support vector machine. J. Civ. Eng. Manag. 6, 014 (2017)Google Scholar
  11. 11.
    James, G., Witten, D., Hastie, T., Tibshirani, R.: An Introduction to Statistical Learning, vol. 112. Springer, New York (2013)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Tao Zhang
    • 1
    • 2
  • Lyuchao Liao
    • 1
    • 2
  • Hongtu Lai
    • 1
  • Jierui Liu
    • 1
    • 2
  • Fumin Zou
    • 1
    • 2
  • Qiqin Cai
    • 1
    • 2
  1. 1.Fujian Key Lab for Automotive Electronics and Electric DriveFujian University of TechnologyFuzhouChina
  2. 2.Fujian Provincial Big Data Research Institute of Intelligent TransportationFujian University of TechnologyFuzhouChina

Personalised recommendations