Neural network based projection of electricity demand in Indonesia using repetitive training method

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Indonesia Energy Outlook (IEO) 2016 published by BPPT projected the electricity demand in 2025 significantly will increase more than twice to 513 TWh from 203 TWh in 2015. This projection is based on the target of 100% electrification ratio in 2025. Assuming an average population growth of 1.2% in 2025 and a nominal GDP growth of 5.02% in 2014 which are expected to increase to 8% in 2025.This study projected the total electricity demand for the period 2016-2025 based on GDP, population, and electricity sales per sector (household, commercial, and industry) from the period of 2000-2015. Time series data modeling using Auto Regressive (AR) model and Autoregressive model with exogenous input (ARX) implemented using Artificial Neural Network Back-Propagation (ANN-BP). The repetitive training method is used to achieve the specified target error.



  • Keywords

    total electricity demand, electricity sales, AR/ARX models, repetitive NNBP

  • References

      [1] AAAT/BPPT. ((2016)). Indonesai Energy Outlook (IEO) 2016 - Energy Development in Supporting Green Industry.

      [2] A. Ahmed, O. Duran, Y. Zweiri, and M. Smith, "Hybrid Spectral Unmixing: Using Artificial Neural Networks for Linear/Non-Linear Switching," Remote Sensing, vol. 9, p. 775, (2017).

      [3] A. M. Al-saadi, S. Kh. Zamiem, L. A. A. Al-Jumaili, M. JameelJubair, and H. Abdalla Al- Hashemi, "Estimating the Optimum Duration of Road Projects Using Neural Network Model," International Journal of Engineering and Technology (IJET), vol. 9, pp. 3458-3469, (2017).

      [4] A. Dingli and K. S. Fournier, "Financial Time Series Forecasting - A Machine Learning Approach," Machine Learning and Applications: An International Journal, vol. 4, pp. 11-27, (2017).

      [5] E. U. A. Gaffar, "Prediction of Regional Economic Growth in East Kalimantan using Genetic Algorithm," International Journal of Computing and Informatics (IJCANDI), vol. 1, pp. 58-67, May, (2016).

      [6] S. M. Karthik and P. Arumugam, "Stochastic modelling based monthly rainfall prediction using seasonal Artificial Neural Networks," Journal on Soft Computing, vol. 7, pp. 1421-1426, January, (2017).

      [7] M. B. Patel and S. R. Yalamalle, "Stock Price Prediction Using Artificial Neural Network," International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), vol. 3, pp. 13755-13762, June, (2014).

      [8] J. Vrbka, "Predicting Future GDP Development by Means of Artificial Intelligence," Littera Scripta, vol. 9, (2016).

      [9] Haviluddin and R. Alfred, "A Genetic-Based Backpropagation Neural Network for Forecasting in Time-Series Data," in The 2015 International Conference on Science in Information Technology (ICSITech 2015), Yogyakarta, Indonesia, 2015.

      [10] B. Al-hnaity and M. Abbod, "Predicting Financial Time Series Data Using Hybrid Model," vol. 650, pp. 19-41, (2016).

      [11] O. O. Bozkurt, G. Biricik, and Z. C. Tayşi, "Artificial neural network and SARIMA based models for power load forecasting in Turkish electricity market," PLOS ONE 20 April (2017).

      [12] M. Khairalla, X. Ning, and N. T. AL-Jallad, "Hybrid Forecasting Scheme for Financial Time-Series Data using Neural Network and Statistical Methods," (IJACSA) International Journal of Advanced Computer Science and Applications, vol. 8, pp. 319-327, (2017).

      [13] A. Malav, K. Kadam, and P. Kamat, "Prediction of heart disease using K-Means and Artificial Neural Network as Hybrid Approach to improve accuracy," International Journal of Engineering and Technology, vol. 9, pp. 3081-3085, (2017).

      [14] A. Sapronova, C. Meissner, and M. Mana, "Short time ahead wind power production forecast," Journal of Physics: Conference Series, vol. 749, p. 012006, (2016).

      [15] S. Rachad, B. Nsiri, and B. Bensassi, "System Identification of Inventory System Using ARX and ARMAX Models," International Journal of Control and Automation, vol. 8, pp. 283-294, (2015).

      [16] Ahmar, A. S. (2018). A Comparison of α-Sutte Indicator and ARIMA Methods in Renewable Energy Forecasting in Indonesia. International Journal of Engineering & Technology, 7(1.6), 9–11.

      [17] Ahmar, A. S., Guritno, S., Abdurakhman, Rahman, A., Awi, Alimuddin, … Arifin, A. N. M. (2018). Modeling Data Containing Outliers using ARIMA Additive Outlier (ARIMA-AO). Journal of Physics: Conference Series, 954(1), 01010.

      [18] Ahmar, A. S., Rahman, A., & Mulbar, U. (2018). A New Method for Time Series Forecasting: α- Sutte Indicator. Journal of Physics: Conference Series.

      [19] Rahman, A., & Ahmar, A. S. (2017). Forecasting of primary energy consumption data in the United States: A comparison between ARIMA and Holter-Winters models. In AIP Conference Proceedings (Vol. 1885).

      [20] CDI-EMR. ((2010)). Handbook of Energy & Economic Statistics of Indonesia 2010.

      [21] CDI-EMR. ((2011)). Handbook of Energy & Economic Statistics of Indonesia 2011.

      [22] CDI-EMR. ((2012)). Handbook of Energy & Economic Statistics of Indonesia 2012.

      [23] CDI-EMR. ((2013)). Handbook of Energy & Economic Statistics of Indonesia 2013.

      [24] CDI-EMR. ((2016)). Handbook of Energy & Economic Statistics of Indonesia 2016.

      [25] M. H. Beale, M. T. Hagan, and H. B. Demuth. ((2015)). Neural Network Toolbox™User's Guide.

      [26] Mislan, Haviluddin, S. Hardwinarto, Sumaryono, and M. Aipassa, "Rainfall Monthly Prediction Based on Artificial Neural Network: A Case Study in Tenggarong Station, East Kalimantan - Indonesia," in International Conference on Computer Science and Computational Intelligence (ICCSCI 2015), Binus, Jakarta, 2015, pp. 142 – 151.

      [27] P. N. E. Company). ((2014)). Business Plan for Electrical Power Supply Period 2015-2024.




Article ID: 12733
DOI: 10.14419/ijet.v7i2.2.12733

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.