Applying Smart Meter and Data Mining Techniques to Predict Refrigeration System Performance

Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 209)

Abstract

This study presents six data mining techniques for prediction of coefficient of performance (COP) for refrigeration equipment. These techniques include artificial neural networks (ANNs), support vector machines (SVMs), classification and regression tree (CART), multiple regression (MR), generalized linear regression (GLR), and chi-squared automatic interaction detector (CHAID). Based on COP values, abnormal situation of equipment can be evaluated for refrigerant leakage. Experimental results from cross-fold validation are compared to determine the best models. The study shows that data mining techniques can be used for accurately and efficiently predicting COP. In the liquid leakage phase, ANNs provide the best performance. In the vapor leakage phase, the best model is the GLR model. The models built in this study are effective for evaluating refrigeration equipment performance.

Keywords

Refrigeration management smart meter monitoring experiment data mining performance diagnosis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Liao, S.-H., Chu, P.-H., Hsiao, P.-Y.: Data mining techniques applications. A decade review from 2000 to 2011. Expert Systems with Applications 39(12), 11303–11311 (2012)CrossRefGoogle Scholar
  2. 2.
    Lee, H.I.: Energy report. lower the price of electricity. Bureau of Energy Ministry of Economics Affairs (2011)Google Scholar
  3. 3.
    Ozgoren, M., Bilgili, M., Babayigit, O.: Hourly performance prediction of ammoniaewater solar absorption refrigeration. Applied Thermal Engineering 40, 80–90 (2012)CrossRefGoogle Scholar
  4. 4.
    Şahin, A.T.: Performance analysis of single-stage refrigeration system with internal heat exchanger using neural network and neuro-fuzzy. Renewable Energy 36(10), 2747–2752 (2011)CrossRefGoogle Scholar
  5. 5.
    Ahmed, A., Korres, N.E., Ploennigs, J., Elhadi, H., Menzel, K.: Mining building performance data for energy-efficient operation. Advanced Engineering Informatics 25(2), 341–354 (2011)CrossRefGoogle Scholar
  6. 6.
    Chou, J., Chiu, C., Farfoura, M., Al-Taharwa, I.: Optimizing the Prediction Accuracy of Concrete Compressive Strength Based on a Comparison of Data-Mining Techniques. Journal of Computing in Civil Engineering 25(3), 242–253 (2011)CrossRefGoogle Scholar
  7. 7.
    Taylor, J.W., Buizza, R.: Using weather ensemble predictions in electricity demand forecasting. International Journal of Forecasting 19(1), 57–70 (2003)CrossRefGoogle Scholar
  8. 8.
    Saab, S., Badr, E., Nasr, G.: Univariate modeling and forecasting of energy consumption. The case of electricity in Lebanon. Energy 26(1), 1–14 (2001)CrossRefGoogle Scholar
  9. 9.
    Chen, C.S., Tzeng, Y.M., Hwang, J.C.: The application of artificial neural networks to substation load forecasting. Electric Power Systems Research 38(2), 153–160 (1996)CrossRefGoogle Scholar
  10. 10.
    Ye, B., Guo, C., Cao, Y.: Short-term load forecasting using a new fuzzy modeling strategy, Hangzhou, P.R. China, pp. 5045–5049 (2004)Google Scholar
  11. 11.
    Pao, H.T.: Comparing linear and nonlinear forecasts for Taiwan’s electricity consumption. Energy 31(12), 1793–1805 (2006)CrossRefGoogle Scholar
  12. 12.
    Şencan, A., Köse, S.L., Selbaş, R.: Prediction of thermophysical properties of mixed refrigerants using artificial neural network. Energy Conversion and Management 52(2), 958–974 (2011)CrossRefGoogle Scholar
  13. 13.
    Orenstein, T., Kohavi, Z., Pomeranz, I.: An optimal algorithm for cycle breaking in directed graphs. Journal of Electronic Testing 7(1-2), 71–81 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Department of Construction EngineeringNational Taiwan University of Science and TechnologyTaipei CityTaiwan

Personalised recommendations