Advertisement

Using Machine Learning to Optimize Energy Consumption of HVAC Systems in Vehicles

  • Martin BöhmeEmail author
  • Andreas Lauber
  • Marco Stang
  • Luyi Pan
  • Eric Sax
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1018)

Abstract

The detachment and calculation of functionalities from a vehicle into a cloud creates new chances. By linking different data sources with the in-vehicle data in the cloud, an optimization of these functionalities in terms of energy efficiency can be applied. For example, the Heating, Ventilation and Air Conditioning (HVAC) consumes up to 30% of total energy in a vehicle. Electric vehicles in particular lead to these high values because they are not able to recover the waste heat from combustion engines for interior heating. Therefore, the optimization of energy efficient strategies with respect to the vehicle energy management system becomes more relevant. Forecasts of the interior vehicle temperature are directly related to the HVAC energy consumption. This work focuses on the implementation and accuracy evaluation of Recurrent Neural Networks (RNN) for interior vehicle temperature forecasting.

Keywords

Heating Ventilation and Air Conditioning (HVAC) Energy efficiency Internet of Things Machine learning 

References

  1. 1.
    Traub, M., Vögel, H.J., Sax, E., Streichert, T., Härri, J.: Digitalization in automotive and industrial systems. In: Proceedings of 2018 Design Automation Test in Europe Conference and Exhibition DATE 2018, January 2018, pp. 1203–1204 (2018).  https://doi.org/10.23919/DATE.2018.8342198
  2. 2.
    Zamora-Martínez, F., Romeu, P., Botella-Rocamora, P., Pardo, J.: Towards energy efficiency: forecasting indoor temperature via multivariate analysis. Energies 6, 4639–4659 (2013).  https://doi.org/10.3390/en6094639CrossRefGoogle Scholar
  3. 3.
    Kurdikeri, R.B., Raju, A.B.: Comparative study of short-term wind speed forecasting techniques using artificial neural networks. In: Proceedings of 2018 International Conference on Current Trends Towards Converging Technologies, ICCTCT 2018, pp. 1–5 (2018).  https://doi.org/10.1109/ICCTCT.2018.8550849
  4. 4.
    Sak, H., Senior, A., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: INTERSPEECH 2014 (2014).  https://doi.org/10.1016/j.edumed.2017.01.001CrossRefGoogle Scholar
  5. 5.
    Greff, K., Srivastava, R.K., Koutnik, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: Search Space Odyssey. CoRR. abs/1503.0, pp. 2222–2232 (2015)Google Scholar
  6. 6.
    Massaro, E., Ahn, C., Ratti, C., Santi, P., Stahlmann, R., Lamprecht, A., Roehder, M., Huber, M.: The car as an ambient sensing platform. Proc. IEEE 105, 3–7 (2017).  https://doi.org/10.1109/JPROC.2016.2634938CrossRefGoogle Scholar
  7. 7.
    Chai, T., Draxler, R.R.: Root mean square error (RMSE) or mean absolute error (MAE)? - Arguments against avoiding RMSE in the literature. Geosci. Model Dev. 7, 1247–1250 (2014).  https://doi.org/10.5194/gmd-7-1247-2014CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Martin Böhme
    • 1
    Email author
  • Andreas Lauber
    • 1
  • Marco Stang
    • 1
  • Luyi Pan
    • 1
  • Eric Sax
    • 1
  1. 1.Karlsruhe Institute of Technology, Institute for Information Processing Technologies (ITIV)KarlsruheGermany

Personalised recommendations