Multivariate Forecasting of Electricity Consumption for Sustainable Energy Planning
Main Article Content
Abstract
Forecasting accurate consumption of electricity is crucial for energy security of a rapidly grown region. Prior study proves that there is a positive relationship between electricity consumption, population and economic growth. Nevertheless, only a few have applied the multivariate model within a regional context for the long-term electricity forecasting. This study tries to bridge the gap in forecast reliability by using machine learning to support regional sustainable energy planning in the Lampung Province. The methodology includes data preprocessing, integration, and cleaning, and model training and validation using time-series data. The Vector Autoregressive (VAR) was employed to predict electricity consumption from 2024 to 2030 based on historical data from 2010 to 2023. The model demonstrated a robust predictive performance, with a low MAPE of 0.57%, RMSE of 37.74, and a high R² value of 0.998. This instills confidence in the findings of the research and the future use of the VAR for electricity forecasting. The model suggests that the trend of energy consumption in Lampung Province is continuously increasing. The study also stresses the need for renewables to meet future electricity needs, ensuring energy infrastructure tackles socio-economic growth and the energy transition agenda with regard to the development of Lampung Province.
Article Details
Articles published in International Journal of Sustainable Energy Planning and Management are following the license Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License: Attribution - NonCommercial - NoDerivs (by-nc-nd). Further information about Creative Commons
Authors can archive post-print (final draft post-refereering) on personal websites or institutional repositories under these conditions:
- Publishers version cannot be stored elsewhere but on publishers homepage
- Published source must be acknowledged
- Must link to publisher version
References
[1] Muyasyaroh AP. ‘Just’ access to electricity: Energy justice in Indonesia’s rural electrification (LISDES) program. IOP Conf Ser Earth Environ Sci 2023;1199:012015. https://doi.org/10.1088/1755-1315/1199/1/012015.
[2] Cuce E, Riffat SB. A comprehensive assessment of sectoral energy consumption in the UK: past, present and future. Int J Low-Carbon Technol 2016;11:424–30. https://doi.org/10.1093/ijlct/ctv013.
[3] Beraldi P, Violi A, Bruni M, Carrozzino G. A Probabilistically Constrained Approach for the Energy Procurement Problem. Energies 2017;10:2179. https://doi.org/10.3390/en10122179.
[4] Schuler RE. Planning, Markets and Investment in the Electric Supply Industry. 2012 45th Hawaii Int. Conf. Syst. Sci., Maui, HI, USA: IEEE; 2012, p. 1923–30. https://doi.org/10.1109/HICSS.2012.472.
[5] Jaksic B, Dzodan J, Tomsic Z. Overview of foresight techniques in energy supply. 2014 IEEE Int. Energy Conf. ENERGYCON, Cavtat, Croatia: IEEE; 2014, p. 473–8. https://doi.org/10.1109/ENERGYCON.2014.6850469.
[6] Zhang Q, Ishihara KN, Mclellan BC, Tezuka T. Scenario analysis on future electricity supply and demand in Japan. Energy 2012;38:376–85. https://doi.org/10.1016/j.energy.2011.11.046.
[7] Kabeyi MJB, Olanrewaju OA. Sustainable Energy Transition for Renewable and Low Carbon Grid Electricity Generation and Supply. Front Energy Res 2022;9:743114. https://doi.org/10.3389/fenrg.2021.743114.
[8] Siregar YI. Ranking of energy sources for sustainable electricity generation in Indonesia: A participatory multi-criteria analysis. Int J Sustain Energy Plan Manag 2022;35:45–64. https://doi.org/10.54337/ijsepm.7241.
[9] Sani K, Siallagan M, Putro US, Mangkusubroto K. Indonesia Energy Mix Modelling Using System Dynamics. Int J Sustain Energy Plan Manag 2018:29-51 Pages. https://doi.org/10.5278/IJSEPM.2018.18.3.
[10] Czisch G. Scenarios for a Future Electricity Supply: Cost-optimized variations on supplying Europe and its neighbours with electricity from renewable energies. Institution of Engineering and Technology; 2011. https://doi.org/10.1049/PBRN010E.
[11] MEMR. Electricity Supply Business Plan (Rencana Usaha penyediaan Tenaga Listrik/ RUPTL) 2021-2030. Jakarta: MEMR; 2021.
[12] Rodríguez-Caballero CV. Energy consumption and GDP: a panel data analysis with multi-level cross-sectional dependence. Econom Stat 2022;23:128–46. https://doi.org/10.1016/j.ecosta.2020.11.002.
[13] Wu C-F, Huang S-C, Chiou C-C, Chang T, Chen Y-C. The Relationship Between Economic Growth and Electricity Consumption: Bootstrap ARDL Test with a Fourier Function and Machine Learning Approach. Comput Econ 2022;60:1197–220. https://doi.org/10.1007/s10614-021-10097-7.
[14] Al-Mulali U, Che Sab CNB. Electricity consumption, CO2 emission, and economic growth in the Middle East. Energy Sources Part B Econ Plan Policy 2018;13:257–63. https://doi.org/10.1080/15567249.2012.658958.
[15] Chirwa TG, Odhiambo NM. Electricity consumption and economic growth: New evidence from advanced, emerging and developing economies. Int J Energy Sect Manag 2020;14:1–19. https://doi.org/10.1108/IJESM-11-2018-0014.
[16] Emirmahmutoglu F, Denaux Z, Omay T, Tiwari AK. Regime dependent causality relationship between energy consumption and GDP growth: evidence from OECD countries. Appl Econ 2021;53:2230–41. https://doi.org/10.1080/00036846.2020.1857330.
[17] Topolewski Ł. Relationship between Energy Consumption and Economic Growth in European Countries: Evidence from Dynamic Panel Data Analysis. Energies 2021;14:3565. https://doi.org/10.3390/en14123565.
[18] Zhu D, Wang J, Cheng R, Liu D. Relationship Between Electricity Consumption and Economic Growth: An Empirical Analysis based on VAR Model. 2024 IEEE 13th Int. Conf. Commun. Syst. Netw. Technol. CSNT, Jabalpur, India: IEEE; 2024, p. 1324–9. https://doi.org/10.1109/CSNT60213.2024.10546061.
[19] Nguyen HT. Economic growth and electricity consumption. J Int Econ Manag 2021;21:1–23. https://doi.org/10.38203/jiem.021.2.0026.
[20] Jo H-H, Jang M, Kim J. How Population Age Distribution Affects Future Electricity Demand in Korea: Applying Population Polynomial Function. Energies 2020;13:5360. https://doi.org/10.3390/en13205360.
[21] Mazur A. How does population growth contribute to rising energy consumption in America? Popul Environ 1994;15:371–8. https://doi.org/10.1007/BF02208318.
[22] Wilkinson WL. Environmental impact of electricity generation. Trans R Soc South Afr 2001;56:131–3. https://doi.org/10.1080/00359190109520511.
[23] Gaur K, Kumar H, Agarwal RPK, Baba KVS, Soonee SK. Analysing the electricity demand pattern. 2016 Natl. Power Syst. Conf. NPSC, Bhubaneswar, India: IEEE; 2016, p. 1–6. https://doi.org/10.1109/NPSC.2016.7858969.
[24] Mugisha J, Ratemo MA, Bunani Keza BC, Kahveci H. Assessing the opportunities and challenges facing the development of off-grid solar systems in Eastern Africa: The cases of Kenya, Ethiopia, and Rwanda. Energy Policy 2021;150:112131. https://doi.org/10.1016/j.enpol.2020.112131.
[25] Raghutla C, Chittedi KR. Energy poverty and economic development: evidence from BRICS economies. Environ Sci Pollut Res 2022;29:9707–21. https://doi.org/10.1007/s11356-021-16174-6.
[26] Castrejon-Campos O, Aye L, Hui FKP. Making policy mixes more robust: An integrative and interdisciplinary approach for clean energy transitions. Energy Res Soc Sci 2020;64:101425. https://doi.org/10.1016/j.erss.2020.101425.
[27] AbuBaker M. Household Electricity Load Forecasting Toward Demand Response Program using Data Mining Techniques in a Traditional Power Grid. Int J Energy Econ Policy 2021;11:132–48. https://doi.org/10.32479/ijeep.11192.
[28] Wahid F, Ullah H, Ali S, Jan SA, Ali A, Khan A, et al. The Determinants and Forecasting of Electricity Consumption in Pakistan. Int J Energy Econ Policy 2020;11:241–8. https://doi.org/10.32479/ijeep.10646.
[29] Wani TA, Shiraz M. Electricity Demand Forecasting Using Regression Techniques. In: Zhang G, Kaushika ND, Kaushik SC, Tomar RK, editors. Adv. Energy Built Environ., vol. 36, Singapore: Springer Singapore; 2020, p. 111–21. https://doi.org/10.1007/978-981-13-7557-6_9.
[30] Román-Portabales A, López-Nores M, Pazos-Arias JJ. Systematic Review of Electricity Demand Forecast Using ANN-Based Machine Learning Algorithms. Sensors 2021;21:4544. https://doi.org/10.3390/s21134544.
[31] Pallonetto F, Jin C, Mangina E. Forecast electricity demand in commercial building with machine learning models to enable demand response programs. Energy AI 2022;7:100121. https://doi.org/10.1016/j.egyai.2021.100121.
[32] Md. N, Most Sifat Muntaha S, Md. Shohel R, Md. Sazzad H, Md. Matiur Rahman M. Forecasting Climatic Variables using Vector Autoregression (VAR) Model. Eur J Stat Probab 2023;11:20–38. https://doi.org/10.37745/ejsp.2013/vol11n12038.
[33] Gao J, Peng B, Yan Y. Estimation, Inference, and Empirical Analysis for Time-Varying VAR Models. J Bus Econ Stat 2024;42:310–21. https://doi.org/10.1080/07350015.2023.2191673.
[34] Taiebnia A, Mohammadi S. Forecast accuracy of the linear and nonlinear autoregressive models in macroeconomic modeling. J Forecast 2023;42:2045–62. https://doi.org/10.1002/for.3002.
[35] Guefano S, Tamba JG, Azong TEW, Monkam L. Methodology for forecasting electricity consumption by Grey and Vector autoregressive models. MethodsX 2021;8:101296. https://doi.org/10.1016/j.mex.2021.101296.
[36] Kim Y, Kim S. Electricity Load and Internet Traffic Forecasting Using Vector Autoregressive Models. Mathematics 2021;9:2347. https://doi.org/10.3390/math9182347.
[37] Zivot E, Wang J. Vector Autoregressive Models for Multivariate Time Series. Model. Financ. Time Ser. -Plus®, New York, NY: Springer New York; 2003, p. 369–413. https://doi.org/10.1007/978-0-387-21763-5_11.
[38] Kumar M, Pal N. Machine Learning-based Electric Load Forecasting for Peak Demand Control in Smart Grid. Comput Mater Contin 2023;74:4785–99. https://doi.org/10.32604/cmc.2022.032971.
[39] Liu Y, Roberts MC, Sioshansi R. A vector autoregression weather model for electricity supply and demand modeling. J Mod Power Syst Clean Energy 2018;6:763–76. https://doi.org/10.1007/s40565-017-0365-1.
[40] Chevalier J-M, Ouédraogo NS. Energy Poverty and Economic Development. In: Chevalier J-M, editor. New Energy Crisis, London: Palgrave Macmillan UK; 2009, p. 115–44. https://doi.org/10.1057/9780230242234_5.
[41] Davis RA, Zang P, Zheng T. Sparse Vector Autoregressive Modeling. J Comput Graph Stat 2016;25:1077–96. https://doi.org/10.1080/10618600.2015.1092978.
[42] Scott Hacker R, Hatemi-J A. Optimal lag-length choice in stable and unstable VAR models under situations of homoscedasticity and ARCH. J Appl Stat 2008;35:601–15. https://doi.org/10.1080/02664760801920473.
[43] Cubadda G, Grassi S, Guardabascio B. The time-varying Multivariate Autoregressive Index model. Int J Forecast 2025;41:175–90. https://doi.org/10.1016/j.ijforecast.2024.04.007.
[44] Lampung Statistics n.d. https://lampung.bps.go.id/ (accessed May 23, 2024).
[45] Lütkepohl H. Vector autoregressive models. In: Hashimzade N, Thornton MA, editors. Handb. Res. Methods Appl. Empir. Macroecon., Edward Elgar Publishing; 2013. https://doi.org/10.4337/9780857931023.00012.
[46] Qin D. Rise of VAR Modelling Approach. J Econ Surv 2011;25:156–74. https://doi.org/10.1111/j.1467-6419.2010.00637.x.
[47] Botchkarev A. A New Typology Design of Performance Metrics to Measure Errors in Machine Learning Regression Algorithms. Interdiscip J Inf Knowl Manag 2019;14:045–76. https://doi.org/10.28945/4184.
[48] Murphy AH, Ehrendorfer M. Evaluation of Forecasts. In: Grasman J, Van Straten G, editors. Predict. Nonlinear Model. Nat. Sci. Econ., Dordrecht: Springer Netherlands; 1994, p. 11–28. https://doi.org/10.1007/978-94-011-0962-8_3.
[49] Al Hasibi RA, Bawan EK. An Analysis of the Impact of the Covid-19 Pandemic on the Implementation of Renewable Energy in the Supply of Electricity. Int J Sustain Energy Plan Manag 2023;39:3–21. https://doi.org/10.54337/ijsepm.7659.
[50] Fitriana I, Hadiyanto, Warsito B, Himawan E, Santosa J. The Optimization of Power Generation Mix To Achieve Net Zero Emission Pathway in Indonesia Without Specific Time Target. Int J Sustain Energy Plan Manag 2024;41:5–19. https://doi.org/10.54337/ijsepm.8263.
[51] Al Irsyad MI, Quist J, Rahayu H, Blok K. A Strategic Plan for Renewable Energy Transition in a Coal Dependent Region using Participatory Backcasting: The Case of South Kalimantan Province in Indonesia. Int J Sustain Energy Plan Manag 2025;45:23–39. https://doi.org/10.54337/ijsepm.9826.