Forecasting Electricity Consumption Under the Responsibility of the Provincial Electricity Authority (PEA): A Sectoral Approach

  • Saran Kumjinda Faculty of Economics, Kasetsart University
  • Sumalee Santipolvut Faculty of Economics, Kasetsart University
  • Rewat Thamma-Apiroam Faculty of Economics, Kasetsart University
Keywords: sectoral, forecasting electricity consumption, Provincial Electricity Authority (PEA)

Abstract

The Forecasting electricity consumption under the responsibility of the Provincial Electricity Authority (PEA) for seven years from 2017 to 2023 is examined by exploring all five sectors, namely residential, commercial, industrial, agricultural, and non-profit, and comparing the effectiveness of each forecast model. The four models under study are the Holt-Winters’ two parameters linear exponential smoothing non-seasonal (Holt-Winters’ non-seasonal), Autoregressive Integrated Moving Average (ARIMA), Artificial Neural Network (ANN), and Support Vector Machine-Regression (SVM-R). The Mean Absolute Percentage Error (MAPE) was used to determine the most suitable and effective model. MAPE was the first to be considered, and the comparative results of the lowest MAPE values indicate that the Holt-Winters’ non-seasonal model was the most suitable for forecasting electricity demand in the residential, industrial, and non-profit sectors, with ARIMA(3,1,0) and ANN being most appropriate for the commercial and agricultural sectors. Total electricity demand from 2017 to 2023 for five sectors is projected to continuously increase. The annual electricity capacity of the PEA shows a continuous decrease when compared to total electricity demand from 2017 to 2023. The distributed volume was 369.86, 335.35, 292.18, 270.93, 246.03, 223.60, and 207.42 million kWh respectively, due to the continuous decrease in electricity sales significantly impacting on the management of electricity production and distribution. Consequently, in the future, there may be a shortfall in electricity production and distribution under the responsibility of the PEA.

Downloads

Download data is not yet available.

References

Shakibai, A. R., & Koochekzadeh, S. (2009). Modeling and Predicting Agricultural Energy Consumption in Iran, American-Eurasian J. Agric. & Environ. Sci, 5(3), 308-312.

Erol, A. H., Ozcelikkan, N., Tokgoz, A. Ozel, S., Zaim, S., & Demirel, O.F. (2012). Forecasting Electricity Consumption of Turkey Using Time Series Methods and Neural Networks. Proceedings of the International Conference in Mathematics 2012, Al Ain, United Arab Emirates University, 11-14 March, 117-127.

Rahman, A. & Ahmar, A. S. (2017). Forecasting of Primary Energy Consumption Data in the United States: A comparison between ARIMA and Holter-Winters models. AIP Conference Proceedings, 1885(1), doi: 10.1063/1.5002357.

Nichiforov, C., Stamatescu, I., Fagarasan, I., & Stamatescu, G. (2017). Energy Consumption Forecasting Using ARIMA and Neural Network Models. 2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE), 2017, 1-4. Doi: 10.1109/ISEEE.2017.8170657.

Unakitan, G. & Turkekul, B. (2014). Univariate Modelling of Energy Consumption in Turkish Agriculture. Energy Sources Part B Economics Planning and Policy, 9(3), 284-290.

Sabir, S. (2018). Predictive Modeling of Household Energy Demand. Project Report of the Department of Computer Science Database and Programming Technologies, Aalborg University, Aalborg, Denmark.

Shao, Y. E. & Tsai, Y. S. (2018). Predictions of Industrial and Commercial Electricity Sales in Taiwan Using ARIMA and Artificial Neural Networks (ANN) Techniques. International Journal of e-Education, e-Business, e-Management and e-Learning, 8(2), 74-81.

Official Information Commission (OIC). (2016). Definition of the EGAT, MEA, and PEA. Retrieved from https://www.oic.go.th/Ginfo

Suttichaimethee, P. (2010). Exponential smoothing, Applied Econometrics for Research. Bangkok, Thailand: Saha Dhammik Co., Ltd.

Suttichaimethee, P. (2010). Autoregressive integrated moving average, Applied Econometrics for Research. Bangkok, Thailand: Saha Dhammik Co., Ltd.

Haykin, S. (2009). Artificial Neural Network. Neural Networks and Learning Machines (3rd ed.). New Jersey, USA: Pearson Education, Inc., Upper Saddle River.

Haykin, S. (2009). Support Vector Machine. Neural Networks and Learning Machines (3rd ed.). New Jersey, USA: Pearson Education, Inc., Upper Saddle River.

Phupha, V., Rungreunganun, V., & Pimapunsri, P. (2010). Forecast a Shortage of Power in Thailand . The 2nd RMUTP International Conference Green Technology and Productivity, 62, 215-221.

Klimberg, R. K., Sillup, G. P., Boyle, K. J., & Tavva, V. (2010). Forecasting Performance Measures-What are their practical meaning?. Advances in Business and Management Forecasting, 7, 137-147.

Chujai, P., Kerdprasop, N., & Kerdprasop, K. (2013). Time Series Analysis of Household Electric Consumption with ARIMA and ARMA Models. Proceedings of the International MultiConference of Engineers and Computer Scientists 2013, 1, 295-300.

Adhikari, R. & Agrawal, R. K. (2013). Time Series Forecasting Using Support Vector Machines, An Introductory Study on Time Series Modeling and Forecasting. Germany, LAP LAMBERT Academic Publishing, arXiv:1302.6613v1.

Public Relations Department. (2016). Analysis of Electricity Distribution Situation of the PEA. Bangkok, Thailand: Printing Division, Provincial Electricity Authority (PEA), Main Office.

International Energy Agency (IEA). (2014). World Outlook Energy 2014. Retrieved from www.iea.org

Power Economic Division, PEA. (2017). Historical Electricity Consumption Time Series Data (kWh) Between 1992 and 2016 of the PEA. Bangkok, Thailand: Provincial Electricity Authority (PEA), Main Office.

Project Planning Division, PEA. (2017). Time Frame for the Electrical Power Station Construction of the PEA. Bangkok, Thailand: The Provincial Electricity Authority (PEA), Main Office.

Power Economic Division, PEA. (2017). Electricity loss of the PEA (Calculation by Using Technical Loss Method). Bangkok, Thailand: The Provincial Electricity Authority (PEA), Main Office.

Power Economic Division, PEA. (2017). Electricity capacity of the PEA. Bangkok, Thailand: Provincial Electricity Authority (PEA), Main Office.

Power Economic Division, PEA. (2017). Definition of Electricity Loss. Bangkok, Thailand: The Provincial Electricity Authority (PEA), Main Office.

Katara, S., Faisal, A., & Engmann, G. M. (2014). A Time Series Analysis of Electricity Demand in Tamale, Ghana. International Journal of Statistics and Applications, 4(6), 269-275.

Usha, T. M., Appavu Alias Balamurugan, S. (2016). Seasonal Based Electricity Demand Forecasting Using Time Series Analysis. Circuits and Systems, 7(10), 3320-3328.

Bunchongsilp, A. (2007). Forecasting of Electric Energy Usage in Larg Industry. Master of Engineering, Department of Industrial Engineering and Management, Silpakorn University, Thailand.

As’ad, M. (2012). Finding the Best ARIMA model to forecast Daily Peak Electricity Demand. Proceedings of the Fifth Annual ASEARC Conference-Looking to the future-Programme and Proceedings, 2-3 February 2012, University of Wollongong, Australia.

Sujjaviriyasup, T. (2017). Hybrid Model of Support Vector Machine and Genetic Algorithm for Forecasting the Annual Peak Electricity Demand of Thailand. The Journal of KMUTNB, 27(3), 453-465.

Singchai, P. & Keeratiwintakorn, P. (2014). Electricity Demand Forecast for Thailand Demand Side Management Center. Information Technology Journal, 10(2), 32-42.

Salahat, S. & Awad, M. (2017). Short-Term Forecasting of Electricity Consumption in Palestine Using Artificial Neural Networks. International Journal of Artificial Intelligence and Applications (IJAIA), 8(2), 11-21.

Ogcu, G., Demirel, O. F., & Zaim, S. (2012). Forecasting Electricity Consumption with Neural Networks and Support Vector Regression. Procedia-Social and Behavior Sciences, 58(2012), 1576-1585.

Newinpun, J., Chomtee, B., & Payakkapong, P. (2012). A Comparison of the Four Forecasting Methods for Peak Electricity Energy Demand in the Center Region of Thailand. Graduate Research Conference (GRC), Khon Kaen University, 281-290.

Sarkodie, S. A. (2017). Estimating Ghana’s Electricity Consumption by 2030: An ARIMA Forecast. Energy Sources, Part B: Economics, Planning, and Policy, 12(10), 936-944.

Kaewhawong, N. (2015). Forecasting Consumption of Thailand by Using SARIMA and Regression Models with ARMA Errors. Thai Journal of Science and Technology, 4(1), 24-36.

Sutthison, T. (2019). Application of the Forecasting Technique by Hybrid Model for Forecasting the Electricity Demands of Rajabhat University. Naresuan University Journal: Science and Technology (NUJST), 27(1), 18-31.

Kornkrua, N. & Boonlha, K. (2016). Forecasting Power Units Quantity Distributed Phitsanulok Province. Journal of Science Ladkrabang, 25(2), 54-64.

Kandananond, K. (2011). Forecasting Electricity Demand in Thailand with an Artificial Neural Network Approach. Energies, 4(12), 1246-1257.

Panklib, K., Prakasvudhisarn, C., Khummongkol, D. (2015). Electricity Consumption Forecasting in Thailand Using an Artificial Neural Network and Multiple Linear Regression. Energy Sources Part B Economics Planning and Policy, 10(4), 427-434.

Srivastava, U. K., Shenoy, G V. & Sharma, S.C. (1989). Time Series Analysis, Quantitative Techniques for Managerial Decisions (2nd ed.). New Delhi, India: New Age International (P) Limited.

Wikiljungbox. (2010). Ljung–Box Test, Wikipedia, the Free Encyclopedia. Retrieved from https://en.wikipedia.org
Published
2019-06-30
How to Cite
Kumjinda, S., Santipolvut, S., & Thamma-Apiroam, R. (2019). Forecasting Electricity Consumption Under the Responsibility of the Provincial Electricity Authority (PEA): A Sectoral Approach. Thai Journal of East Asian Studies, 23(1), 84-115. Retrieved from https://so02.tci-thaijo.org/index.php/easttu/article/view/213414
Section
Research Article