A Comparison of the Forecasting Methods of the Electric Consumption of Ubon Ratchathani Rajabhat University

Main Article Content

ธนกร สุทธิสนธ์

Abstract

Forecasting electric consumption if accurate can be useful information to the administrators and those concerned to set the policy for saving the electric consumption. As a consequence, the cost of electric consumption could be reduced. The research aimed to forecast the electric consumption of Ubon Ratchathani Rajabhat University. Three methods were employed: Holt-Winters Method, SARIMA and combined method.  Data used in the work were the time series of a monthly electric consumption. Data were collected from the Ministry of Energy from January 2005 to 2017 totaling 149 value sets. Data were categorized into two sets: one from January 2005 to December 2016 (144 value sets) and the other from January to December, 2017. Data gained in set one were used as the forecasting model by using R language. Then, data gained in set two were used to compare the accuracy of the three methods. Based on the experiment, it was found that SARIMA was the one with the lowest Mean Absolute Percentage Error (MAPE). Therefore, SARIMA was the most suitable model to be used to forecast the electric consumption of Ubon Ratchathani Rajabhat University.

Keywords

Article Details

How to Cite
สุทธิสนธ์ธ. (2018). A Comparison of the Forecasting Methods of the Electric Consumption of Ubon Ratchathani Rajabhat University. Journal of Industrial Technology Ubon Ratchathani Rajabhat University, 8(1), 151-163. Retrieved from https://www.tci-thaijo.org/index.php/jitubru/article/view/131396
Section
Research Article

References

[1] Ministry of Energy. Government energy reduction program [Internet]. 2017 [cited 2017 August 20]. Available from: http://www.e-report.energy.go.th/data/index.php (in Thai)
[2] Jeong K, Koo C, Hong T. An estimation model for determining the annual energy cost budget in educational facilities using SARIMA (seasonal autoregressive integrated moving average) and ANN (artificial neural network). Energy. 2014; 71: 71–9.
[3] Dong B, Li Z, Rahman S. M, Vega R. A hybrid model approach for forecasting future residential electricity consumption. Energy and Buildings. 2016; 117: 341–51.
[4] Riansut W. Forecasting model for the export values of rubber wood and furniture of Thailand. Naresuan University Journal: Science and Technology. 2016; 24(3): 108–22.
[5] Panichkitkosolkul W. Comparison of forecasting method of daily jewellery gold prices: Holt,s forecast method, Box–Jenkins method and combined forecast method. Naresuan University Journal: Science and Technology. 2006; 14(2): 9-16.
[6] Ungpansattawong S. Statistical forecasting techniques. Khon Kaen: Khon Kaen University Press; 2012. (in Thai)
[7] Abraham B, Ledolter J. Statistical methods for forecasting. New York: John Wiley & Sons; 2005.
[8] Swanson NR, Zeng T. Choosing among competing econometric forecast: Regression–based forecast combination using model selection. Journal of Forecasting. 2001; 20: 425–40.
[9] Bluman AG. Elementary Statistics (A step by step approach). 7th ed. New York: McGraw–Hill; 2015.
[10] Kongkapet P. Nonparametric statistics. Bangkok: daenext; 2011 (in Thai)

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.