Advertisement

A Multi-component Chiller Status Prediction Method Using E-LSTM

  • Chenrui Xu
  • Kebin JiaEmail author
  • Zhuozheng Wang
  • Ye Yuan
Conference paper
  • 23 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1107)

Abstract

With the development of intelligent information technology, chiller system composed by different interrelated components has been widely used in industry to cool products and machinery. Predicting the status of chiller system can effectively monitor energy consumption and reduce accident rate. In this paper, we propose an improved LSTM (E-LSTM) method to predict multi-component chiller status. Firstly, a mean filter method is used to preprocess the original multi-component time series data. Secondly, we adopt E-LSTM to extract hidden features from seven component-wise inputs, consisting of outdoor temperature, wet bulb temperature, outdoor enthalpy, L1 & L2 differential pressures, total power, and IT load. Finally, the learned hidden features are fed into a regression layer to predict three future chiller statuses, including PUE, cold source power, and refrigeration secondary pump power, respectively. Experimental results show that the proposed method outperforms the baselines, such as linear regression, SVR, RNN, GRU and LSTM, and hence demonstrate the effectiveness of our proposed method in the task of chiller status prediction.

Notes

Acknowledgement

This paper is supported by the Project for the National Natural Science Foundation of China under Grants No. 61672064, Advanced Information Network Beijing Laboratory (040000546618017).

References

  1. 1.
    The Science Behind Refrigeration. Berg Chilling Systems Inc. Accessed 2016Google Scholar
  2. 2.
    Jie, Z.: Research on regression analysis model and its dynamic optimization mechanism for data prediction (2018)Google Scholar
  3. 3.
    Shunlai, R., Caiwu, L.: Optimal scheduling method of global energy consumption for virtualized data center. Comput. Eng. 39(12) (2013)Google Scholar
  4. 4.
    Ming, W., Dingli, Z., Qian, F., Jun, Q.I., Huangcheng, F., Wenbo, C.: Non-linear auto-regressive time series prediction method for tunnel surrounding rock deformation. J. Beijing Jiaotong Univ. 41(4) (2017)Google Scholar
  5. 5.
    Binnan, L., Guishing, K.: Prediction model of soil moisture characteristic curve based on grey theory-BP neural network method. Resour. Environ. Arid Areas (7) (2018)Google Scholar
  6. 6.
    Nanyi, Z.: Study on the extraction and prediction of data features based on deep learning (2017)Google Scholar
  7. 7.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  8. 8.
    TechTarget Data Center: “Power usage effectiveness”. https://searchdatacenter.techtarget.com.cn/whatis/9-21989/
  9. 9.
    Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Chao, D., Jinwei, S.: Visual analysis system of cigarette market data based on thermal attempt. Tobacco Technol. (12) (2016)Google Scholar
  11. 11.
    Metz, C.: Google just open sourced tensorflow, its artificial intelligence engine. Wired. Accessed 10 Nov 2015Google Scholar
  12. 12.
    Zeiler, M.D.: Adadelta: an adaptive learning rate method (2012). arXiv preprint arXiv:1212.5701

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Chenrui Xu
    • 1
    • 2
    • 3
  • Kebin Jia
    • 1
    • 2
    • 3
    Email author
  • Zhuozheng Wang
    • 1
    • 2
    • 3
  • Ye Yuan
    • 1
    • 2
    • 3
  1. 1.Faculty of Information TechnologyBeijing University of TechnologyBeijingChina
  2. 2.Beijing Laboratory of Advanced Information NetworksBeijingChina
  3. 3.Beijing Key Laboratory of Computational Intelligence and Intelligent SystemBeijing University of TechnologyBeijingChina

Personalised recommendations