Journal of Korean Society of Industrial and Systems Engineering (산업경영시스템학회지)

Society of Korea Industrial and System Engineering (한국산업경영시스템학회)
권호 표지
DOI QR코드

DOI QR Code

The Prediction and Analysis of the Power Energy Time Series by Using the Elman Recurrent Neural Network

엘만 순환 신경망을 사용한 전력 에너지 시계열의 예측 및 분석

  • Lee, Chang-Yong (Dept. of Industrial and Systems Engineering, Kongju National University) ;
  • Kim, Jinho (Dept. of Industrial and Systems Engineering, Kongju National University)
  • 이창용 (공주대학교 산업시스템공학과) ;
  • 김진호 (공주대학교 산업시스템공학과)
  • Received : 2018.02.06
  • Accepted : 2018.03.14
  • Published : 2018.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose an Elman recurrent neural network to predict and analyze a time series of power energy consumption. To this end, we consider the volatility of the time series and apply the sample variance and the detrended fluctuation analyses to the volatilities. We demonstrate that there exists a correlation in the time series of the volatilities, which suggests that the power consumption time series contain a non-negligible amount of the non-linear correlation. Based on this finding, we adopt the Elman recurrent neural network as the model for the prediction of the power consumption. As the simplest form of the recurrent network, the Elman network is designed to learn sequential or time-varying pattern and could predict learned series of values. The Elman network has a layer of "context units" in addition to a standard feedforward network. By adjusting two parameters in the model and performing the cross validation, we demonstrated that the proposed model predicts the power consumption with the relative errors and the average errors in the range of 2%~5% and 3kWh~8kWh, respectively. To further confirm the experimental results, we performed two types of the cross validations designed for the time series data. We also support the validity of the model by analyzing the multi-step forecasting. We found that the prediction errors tend to be saturated although they increase as the prediction time step increases. The results of this study can be used to the energy management system in terms of the effective control of the cross usage of the electric and the gas energies.

Keywords

References

  1. Ahn, B., Choi, H., and Lee, H., Regional Long-term/ Mid-term Load Forecasting using SARIMA in South Korea, Journal of the Korea Academia-Industrial cooperation Society, 2015, Vol. 16, No. 12, pp. 8576-8584. https://doi.org/10.5762/KAIS.2015.16.12.8576
  2. Bergmeir, C., Hyndman, R., and Koo, B., A note on the validity of cross-validation for evaluating autoregressive time series prediction, Computational Statistics and Data Analysis, 2018, Vol. 120, No. C, pp. 70-83. https://doi.org/10.1016/j.csda.2017.11.003
  3. Black, F. and Scholes, M., The Pricing of Options and Corporate Liabilities, J. Polit. Econ, 1973, Vol. 81, No. 3, pp. 637-654. https://doi.org/10.1086/260062
  4. Bontempi, G., Ben Taieb, S., and Le Borgne, Y., Machine Learning Strategies for Time Series Forecasting. In : Aufaure MA., Zimanyi E. (eds) Business Intelligence, eBISS 2012. Lecture Notes in Business Information Processing, Vol, 138, Springer, Berlin, Heidelberg.
  5. Box, G., Jenkins, G., and Reinsel, G., Time Series Analysis : Forecasting and Control, 4th Edition, Wiley, Hoboken, New Jersey, 2008.
  6. Cox, J., Ross, S., and Rubinstein, M., Option pricing : A simplified approach, J. Financial Econ., 1979, Vol. 7, pp. 229-263. https://doi.org/10.1016/0304-405X(79)90015-1
  7. Elman, J., Finding Structure in Time, Cognitive Science, 1990, Vol. 14, pp. 179-211. https://doi.org/10.1207/s15516709cog1402_1
  8. Hochreiter, S. and Schmidhuber, J., Long short-term memory, Neural Computation, 1997, Vol. 9, No. 8, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  9. https://cran.r-project.org/web/packages/RSNNS/RSNNS.pdf.
  10. Jung, H. and Song, K., Daily Maximum Electric Load Forecasting for the Next 4 Weeks for Power System Maintenance and Operation, The Transactions of The Korean Institute of Electrical Engineers, 2014, Vol. 63, No. 11, pp. 1497-1502. https://doi.org/10.5370/KIEE.2014.63.11.1497
  11. Kim et al., Weekly Maximum Electric Load Forecasting for 104 Weeks by Seasonal ARIMA Model, Journal of the Korean Institute of IIIuminating and Electrical Installation Engineer, 2014, Vol. 28, No. 1, pp. 50-56. https://doi.org/10.5207/JIEIE.2014.28.1.050
  12. Lee, C., Song, G., and Kim, J., Correlation Analyses of the Temperature Time Series Data from the Heat Box for Energy Modeling in the Automobile Drying Process, Journal of Society of Korea Industrial and Systems Engineering, 2014, Vol. 37, No. 2, pp. 27-34. https://doi.org/10.11627/jkise.2014.37.2.27
  13. Lee, H. and Shin, H., Electricity Demand Forecasting based on Support Vector Regression, IE Interfaces, 2011, Vol. 24, No. 4, pp. 351-361. https://doi.org/10.7232/IEIF.2011.24.4.351
  14. Nam, B., Song, K., Kim, K., and Cha, J., The Spatial Electric Load Forecasting Algorithm using the Multiple Regression Analysis Method, Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, 2008, Vol. 22, No. 2, pp. 63-70. https://doi.org/10.5207/JIEIE.2008.22.2.063
  15. Pagan, A., The econometrics of financial markets, J. Empirical Finance, 1996, Vol. 3, No. 1, pp. 15-102. https://doi.org/10.1016/0927-5398(95)00020-8
  16. Park, Y. and Wang, B., Neuro-Fuzzy Model based Electrical Load Forecasting System : Hourly, Daily, and Weekly Forecasting, Journal of Korean Institute of Intelligent Systems, 2004, Vol. 14, No. 5, pp. 533-538. https://doi.org/10.5391/JKIIS.2004.14.5.533
  17. Peng, C., Havlin, S., Stanley, H., and Goldberger A. Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series, Chaos, 1994, Vol. 49, No. 1, pp. 82-87.
  18. Schmidhuber, J., Deep Learning in Neural Networks : An Overview, Neural Networks, 2015, Vol. 61, pp. 85-117. https://doi.org/10.1016/j.neunet.2014.09.003
  19. Shim et al., A Model on Price Forecasting of Natural Resources with Restricted Market, Journal of Society of Korea Industrial and Systems Engineering, 2014, Vol. 37, No. 4, pp. 82-89. https://doi.org/10.11627/jkise.2014.37.4.82
  20. Sohn, K., Kim, S., and Shon, E., Fuzzy Time Series Models with Triangular Fuzzy Numbers as Parameters, Journal of Korean Data Analysis Society, 2001, Vol. 3, No. 2, pp. 149-162.
  21. Various methods for detecting long-range dependence can be found, for example, in J. Beran, Statistics for Long- Memory Processes (Chapman & Hall/CRC, 1994) Ch. 4.4.

Cited by

  1. RNN모델에서 하이퍼파라미터 변화에 따른 정확도와 손실 성능 분석 vol.11, pp.7, 2021, https://doi.org/10.22156/cs4smb.2021.11.07.031