The Development of a Hybrid Model for Forecasting Time Series Data of Monthly Household Electrical Distribution Units of People in the Northeast, Thailand

Main Article Content

Thanakon Sutthison
Surat Haruay

Abstract

The objective of this research was to develop a suitable model for forecasting time series data of monthly household electrical distribution units of people in the Northeast, Thailand. Data were collected from the Provincial Electricity Authority from January 2009 – May 2019, a total of 127 values, consisting of 3 data sets, namely EGAT 1, EGAT 2, and EGAT 3. For the development of the model, the researcher applied empirical mode decomposition to reduce Fast Oscillation of the data before being forecasted by two univariate time series models, including Holt –Winters Exponential Smoothing Method and Seasonal Auto-regressive integrated moving average. After that, a hybrid forecasting model was created using combined forecasting method. In addition, the forecasting efficiency was compared by 5 performance measurement criteria, 1) namely Mean Absolute Error, 2) Root Mean Square Error, 3) Mean Absolute Percentage Error, 4) Median Absolute Percentage Error and 5) Symmetric Mean Absolute Percentage Error. The findings indicated that the forecasting efficiency of the developed model was better than two univariate time series models in all criteria. Therefore, it can be concluded that the hybrid model is the suitable model for forecasting time series data of monthly household electrical distribution units of people in the Northeast, Thailand.

Article Details

Section
Applied Science Research Articles

References

[1] P. Du, J. Wang, W. Yang, and T. Niu, “A novel hybrid model for short-term wind power forecasting,” Applied Soft Computing, no. 80, pp. 93–106, 2019.

[2] J. Zhang, Y.M. Wei, D. Li, Z. Tan, and J. Zhou, “Short term electricity load forecasting using a hybrid model,” Energy, no. 158, pp. 774–781, 2018.

[3] W. Yang, J. Wang, T. Niu, and P. Du, “A hybrid forecasting system based on a dual decomposition strategy and multi-objective optimization for electricity price forecasting,” Applied Energy, vol. 235, pp. 1205–1225, 2019.

[4] H. Luo, D. Wang, C. Yue, Y. Liu, and H. Guo. “Research and application of a novel hybrid decomposition-ensemble learning paradigm with error correction for daily PM 10 forecasting,” Atmospheric Research, vol. 201, pp. 34–45, 2018.

[5] Y. Cheng, H. Zhang, Z. Liu, L. Chen, and P. Wang, “Hybrid algorithm for short-term forecasting of PM2.5 in China,” Atmospheric Environment, vol. 200, pp. 264–279, 2019.

[6] M. Manmin, Time Series and Forecasting. Bangkok : Four Printing, 2006 (in Thai).

[7] N. Papukdee, N. Senawong, and P. Busababodhin, “A comparative forecasting model of monthly rainfall in Northeast of Thailand,” The Journal of KMUTNB, vol. 29, no. 2, pp. 302–313, 2019 (in Thai).

[8] Z. Yang and J.Wang, “A hybrid forecasting approach applied in wind speed forecasting based on a data processing strategy and an optimized artificial intelligence algorithm,” Energy, vol. 160, pp. 87–100, 2018.

[9] M. Santhosh, C. Venkaiah, and D. M. Vinod Kumar, “Ensemble empirical mode decomposition based adaptive wavelet neural network method for wind speed prediction,” Energy Conversion and Management, vol. 168, pp. 482–493, 2018.

[10] Y. Yaslan and B. Bican, “Empirical mode decomposition based denoising method with support vector regression for time series prediction: A case study for electricity load forecasting,” Measurement, vol. 103, pp. 52–61, 2017.

[11] J. F. Rendon-Sanchez and L. M. de Menezes, “Structural combination of seasonal exponential smoothing forecasts applied to load forecasting,” European Journal of Operational Research, vol. 275, no. 3, pp. 916–924, 2019.

[12] Power Economics Division, “Electricity Sales Report” Provincial Electricity Authority, Bangkok, Thailand. Accessed: March, 2019. [Online]. Available: http://peaoc.pea.co.th/ped/

[13] N. Huang, Z. Shen, S. Long, M. Wu, H. Shih, Q. Zheng, N. Yen, C. Tung, and H. Liu, “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” in Proceedings of The Royal Society a Mathematical Physical and Engineering Sciences, 1998, no. 454, pp. 903–995, 1998.

[14] G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 4th ed., New Jersey: John Wiley and Sons, Inc., 2008.

[15] R Core Team. forecast: Forecasting Functions for Time Series and Linear Models. R Foundation for Statistical Computing, Vienna, Austria. Accessed: March 2019. [Online]. Available: https://cran.rproject.org/web/packages/forecast/