Mediumterm Electricity Load Demand Forecasting using HoltWinter Exponential Smoothing and SARIMA in University Campus

Medium-term Electricity Load Demand Forecasting using Holt-Winter Exponential Smoothing and SARIMA in University Campus

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2021 by IJETT Journal
Volume-69 Issue-3
Year of Publication : 2021
Authors : Rosnalini Mansor, Bahtiar Jamili Zaini, Catherine Chan May May
DOI :  10.14445/22315381/IJETT-V69I3P225

Citation 

MLA Style: Rosnalini Mansor, Bahtiar Jamili Zaini, Catherine Chan May May "Medium-term Electricity Load Demand Forecasting using Holt-Winter Exponential Smoothing and SARIMA in University Campus" International Journal of Engineering Trends and Technology 69.3(2021):165-171. 

APA Style:Rosnalini Mansor, Bahtiar Jamili Zaini, Catherine Chan May May. Medium-term Electricity Load Demand Forecasting using Holt-Winter Exponential Smoothing and SARIMA in University Campus  International Journal of Engineering Trends and Technology, 69(3),165-171.

Abstract
This study was conducted to determine the best model in forecasting the electricity load demand for the next 1, 2, and 3 months in a university in Malaysia by comparing 4 error measures, such as Mean Squared Error, Root Mean Squared Error, Mean Absolute Percentage Error, and Geometric Root Mean Squared Error. Two forecasting methods were compared in this study to obtain the best forecasting results. The methods are Holt-Winter’s Exponential Smoothing (HWES) method and Seasonal Autoregressive Integrated Moving Average (SARIMA). This study used 68 secondary data from January 2010 until August 2015. Microsoft Excel and JMP were used to determine the type of time series components, model estimation, and model evaluation. The results showed that seasonal and trend components exist in the dataset. The best model was SARIMA (0,0,1) (1,0,0), 12 models since it denoted the lowest error measurement compared to HWES. Then, this model is used for forecasting the next 1, 2, and 3 months in load demand of electricity.

Reference
[1] Y. Brunet., Energy Storage, in Solar Engineering of Thermal Processes, (2013) 373–408.
[2] P. Mandal, A. K. Srivastava, M. Negnevitsky, and J. Park., Sensitivity analysis of neural network parameters to improve the performance of electricity price forecasting, Int. J. Energy Res., 33 (2009) 38–51.
[3] S. Hassan, A. Khosravi, J. Jaafar, and M. A. Khanesar., A systematic design of interval type-2 fuzzy logic system using extreme learning machine for electricity load demand forecasting, Int. J. Electr. Power Energy Syst., 82 (2016) 1–10.
[4] L. Suganthi and A. A. Samuel, Energy models for demand forecasting - A review, Renew. Sustain. Energy Rev., 16(2) (2012) 1223–1240.
[5] Y. Ren, P. N. Suganthan, N. Srikanth, and G. Amaratunga., Random vector functional link network for short-term electricity load demand forecasting, Inf. Sci. (Ny)., (2016) 367–368,1078–1093.
[6] S. A. A. Karim and S. A. Alwi., Electricity Load Forecasting in UTP Using Moving Averages and Exponential Smoothing Techniques, Appl. Math. Sci., 7(80) 4003–4014, 2013.
[7] Y. Kim, H.-G. Son, and S. Kim., Short term electricity load forecasting for institutional buildings, Energy Reports, 5 (2019) 1270–1280.
[8] A. Vaghefi, M. A. Jafari, E. Bisse, Y. Lu, and J. Brouwer., Modeling and forecasting of cooling and electricity load demand, Appl. Energy, 136 (2015) 186–196.
[9] R. Mansor, B. J. Zaini, and C. S. Yee., Forecasting of electricity consumption and supply for campus university using time series models, Int. J. Supply Chain Manag., 8(5) (2019) 467–472.
[10] Y. W. Lee, K. G. Tay, and Y. Y. Choy., Forecasting Electricity Consumption Using Time Series Model, Int. J. Eng. Technol., 7(4.30) (2018) 218.
[11] E. Akarslan and F. O. Hocaoglu., A novel short-term load forecasting approach using Adaptive Neuro-Fuzzy Inference System, in Proceedings-6th International Istanbul Smart Grids and Cities Congress and Fair, ICSG (2018) 160–163.
[12] R. Koen and J. Holloway., Application of multiple regression analysis to forecasting South Africa`s electricity demand, J. Energy South. Africa, 25(4) (2014) 48–58.
[13] I. A. Samuel, C. Felly-Njoku, A. A. A. Covenant, and A. Awelewe., Medium-Term Load Forecasting Of Covenant University Using The Regression Analysis Methods, J. Energy Technol. Policy, 4(4) (2014) 10–17.
[14] M. H. Jifri, E. E. Hassan, N. H. Miswan, and N. Bahaman., Macro-Factor Affecting the Electricity Load Demand in Power System, Int. J. Adv. Sci. Enggineering Inf. Technol., 7(5) (2017) 1818–1824.
[15] N. Jalil, M. H. Ahmad, and N. Mohamed., Electricity load demand forecasting using exponential smoothing methods, 22(11) (2013) 1540–1543.
[16] H. He, T. Liu, R. Chen, Y. Xiao, and J. Yang., High frequency short-term demand forecasting model for distribution power grid based on ARIMA, in IEEE International Conference on Computer Science and Automation Engineering (CSAE), (3) (2012) 293–297.
[17] E. Almeshaiei and H. Soltan., A methodology for Electric Power Load Forecasting, Alexandria Eng. J., 50(2) (2011) 137–144.
[18] J. M. Vilar, R. Cao, and G. Aneiros., Forecasting next-day electricity demand and price using nonparametric functional methods, Int. J. Electr. Power Energy Syst., 39(1) (2012) 48–55.
[19] N. H. Miswan, R. M. Said, and S. H. H. Anuar., ARIMA with regression model in modelling electricity load demand, J. Telecommun. Electron. Comput. Eng., 8(12) (2016) 113–116.
[20] J. R. Dong, C. Y. Zheng, G. Y. Kan, M. Zhao, J. Wen, and J. Yu., Applying the ensemble artificial neural network-based hybrid data- driven model to daily total load forecasting, Neural Comput. Appl., 26(3) (2015) 603–611.
[21] S. Hassan, A. Khosravi, and J. Jaafar., Examining performance of aggregation algorithms for neural network-based electricity demand forecasting, Int. J. Electr. Power Energy Syst., 64 (2015) 1098–1105.
[22] W. Sulandari and H. Utami., Forecasting electricity load demand using hybrid exponential smoothing-artificial neural network model, Int. J. Adv. Intell. Informatics, 2(3) (2016) 131–139.
[23] Z. Ismail and R. Mansor., Fuzzy logic approach for forecasting half-hourly Malaysia electricity load demand, Int. Inst. Forecast. Proc.,(2011) 1–17.
[24] R. Efendi, M. M. Deris, and Z. Ismail., Implementation of fuzzy time series in forecasting of the non-stationary data, Int. J. Comput. Intell. Appl.,15(2) (2016) 1–10.
[25] R. Mansor, M. M. Kasim, and M. Othman., Weighted Subsethood Segmented Fuzzy Time Series for Moving Holiday Electricity Load Demand Forecasting, J. Adv. Res. Dyn. Control Syst., 12(2) (2020) 686–700.
[26] R. Mansor, M. Zulkifli, M. M. Yusof, and M. I. Ismail., Performance of fuzzy approach in Malaysia short-term electricity load forecasting, in AIP Conference Proceedings, 1635 (2014) 817–824.
[27] R. Mansor, M. M. Kasim, and M. Othman., A weighted subsethood mamdani fuzzy rules based system rule extraction (MFRBS-WSBA) for forecasting electricity load demand - A framework, J. Telecommun. Electron. Comput. Eng., 8(8) (2016) 97–102.
[28] R. Mansor, M. M. Kasim, and M. Othman., The Framework of Weighted Subset-hood Mamdani Fuzzy Rule Based System Rule Extraction ( MFRBS-WSBA ) for Forecasting Electricity Load Demand, AIP Conf. Proceeding, 1761(020061) (2016) 1–7.
[29] A. Setiawan, I. Koprinska, and V. G. Agelidis., Very short-term electricity load demand forecasting using support vector regression, in International Joint Conference on Neural Networks, (2009) 2888–2894.
[30] X. Qiu, L. Zhang, Y. Ren, P. Suganthan, and G. Amaratunga., Ensemble deep learning for regression and time series forecasting, in IEEE, (2014).
[31] 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, Meas. J. Int. Meas. Confed., 103 (2017) 52–61.
[32] N. Akrom and Z. Ismail., EMD-DR Models for Forecasting Electricity Load Demand, Contemp. Eng. Sci., 9(16) (2016) 763–780.
[33] W. Sulandari, M. Hisyam, and P. Canas., Indonesian Electricity Load Forecasting using Singular Spectrum Analysis , Fuzzy Systems and Neural Networks, Energy, 190 (2020) 116408.
[34] R. Mansor, B. J. Zaini, and S. Othman., Moving Holiday Effects on Forecasting Electricity Load Demand, Product. Manag., 26(1) (2021) 29–45.
[35] N. H. Miswan, N. H. Hussin, R. M. Said, and K. Hamzah., ARAR Algorithm in Forecasting Electricity Load Demand in Malaysia, Glob. J. Pure Appl. Math., 12(1) (2016) 361–367.
[36] M. H. Jifri, E. E. Hassan, and N. H. Miswan., Forecasting performance of time series and regression in modeling electricity load demand, 7th IEEE Int. Conf. Syst. Eng. Technol. ICSET - Proc., (2017) 12–16.
[37] H. K. Alfares and M. Nazeeruddin., Electric load forecasting: Literature survey and classification of methods, Int. J. Syst. Sci., 33(1) (2002) 23–34.
[38] R. Efendi, Z. Ismail, and M. M. Deris., A new linguistic out-sample approach of fuzzy time series for daily forecasting of Malaysian electricity load demand, Appl. Soft Comput. J., 28 (2015) 422–430.
[39] O. Samuel et al., Towards modified entropy mutual information feature selection to forecast medium-term load using a deep learning model in smart homes, Entropy, 22(1) (2020) 68.
[40] F. Riva, F. D. Sanvito, F. T. Tonini, E. Colombo, and F. Colombelli., Modelling Long-term Electricity Load Demand for Rural Electrification Planning, IEEE Milan PowerTech, PowerTech (2019).
[41] S. R. Khuntia, J. L. Rueda, and M. A. M. M. Van der Meijden., Long-term electricity load forecasting considering volatility using multiplicative error model, Energies, 11(12) (2018).
[42] F. Riva, F. D. Sanvito, F. T. Tonini, E. Colombo, and F. Colombelli., Modelling long-term electricity load demand for rural electrification planning, (2019).
[43] M. A. Lazim., Introductory Business Forecasting- a practical approach, 3rd Editio, Kuala Lumpur: UiTM Press, (2014).
[44] E. P. Clement., Using Normalized Bayesian Information Criterion (Bic) to Improve Box - Jenkins Model Building, Am. J. Math. Stat., 4(5) (2014) 214–221.

Keywords
Electricity load demand, Holt-Winter exponential smoothing, Medium-term forecasting, Seasonal autoregressive integrated moving average