IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v336y2025ics036054422503837x.html

Machine learning for subnational residential electricity demand forecasting to 2050 under shared socioeconomic pathways: Comparing tree-based, neural and kernel methods

Author

Listed:
  • Gulaydin, Oguzhan
  • Mourshed, Monjur

Abstract

A scenario-based machine learning framework is presented for long-term, subnational electricity demand forecasting, integrating Shared Socioeconomic Pathways (SSPs) with spatially downscaled demographic, economic, and climatic variables. Using Turkey as a case study, the framework projects residential electricity demand to 2050 across all 81 provinces. The subnational approach enables the use of data-intensive machine learning algorithms by expanding the training dataset through the multiplicative effect of combining spatial and temporal dimensions. Six machine learning models: tree-based (Random Forest, XGBoost), neural networks (Feed-forward Neural Network, Long Short-Term Memory), and kernel-based methods (Support Vector Regression, Gaussian Process Regression), are systematically compared against a traditional linear regression benchmark. Random Forest achieves the highest accuracy (R2= 0.9359, MAE= 0.04 TWh), outperforming neural and kernel-based models and substantially improving on the linear baseline. Socioeconomic variables, especially family households, population, and GDP, have a greater influence on electricity demand than climatic indicators such as heating and cooling degree days. Turkey’s residential electricity demand is projected to increase by 78% from 65.5 TWh in 2023 to 116.7±2.9 TWh by 2050, with substantial variation across provinces. The spatial variation in demand forecasts highlights the value of subnational modelling for energy planning and the limitations of national-level projections. The use of SSPs enables a consistent and policy-relevant exploration of plausible long-term demand trajectories. By combining subnational resolution, scenario-based inputs, and a structured comparison of algorithm families, the study offers a transferable framework for electricity demand forecasting in regionally diverse or data-scarce contexts, supporting infrastructure planning and decarbonisation strategies.

Suggested Citation

  • Gulaydin, Oguzhan & Mourshed, Monjur, 2025. "Machine learning for subnational residential electricity demand forecasting to 2050 under shared socioeconomic pathways: Comparing tree-based, neural and kernel methods," Energy, Elsevier, vol. 336(C).
    • Handle: RePEc:eee:energy:v:336:y:2025:i:c:s036054422503837x
    DOI: 10.1016/j.energy.2025.138195
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S036054422503837X
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.energy.2025.138195?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Hamzacebi, Coskun & Es, Huseyin Avni, 2014. "Forecasting the annual electricity consumption of Turkey using an optimized grey model," Energy, Elsevier, vol. 70(C), pages 165-171.
    2. Aneeque A. Mir & Mohammed Alghassab & Kafait Ullah & Zafar A. Khan & Yuehong Lu & Muhammad Imran, 2020. "A Review of Electricity Demand Forecasting in Low and Middle Income Countries: The Demand Determinants and Horizons," Sustainability, MDPI, vol. 12(15), pages 1-35, July.
    3. repec:eco:journ2:2017-04-33 is not listed on IDEAS
    4. Yarbaşı, İkram Yusuf & Çelik, Ali Kemal, 2023. "The determinants of household electricity demand in Turkey: An implementation of the Heckman Sample Selection model," Energy, Elsevier, vol. 283(C).
    5. Kaytez, Fazil, 2020. "A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption," Energy, Elsevier, vol. 197(C).
    6. Dalton, Michael & O'Neill, Brian & Prskawetz, Alexia & Jiang, Leiwen & Pitkin, John, 2008. "Population aging and future carbon emissions in the United States," Energy Economics, Elsevier, vol. 30(2), pages 642-675, March.
    7. Gianluca Bontempi & Souhaib Ben Taieb & Yann-Aël Le Borgne, 2013. "Machine learning strategies for time series forecasting," ULB Institutional Repository 2013/167761, ULB -- Universite Libre de Bruxelles.
    8. Evelina Trutnevyte & Céline Guivarch & Robert Lempert & Neil Strachan, 2016. "Reinvigorating the scenario technique to expand uncertainty consideration," Climatic Change, Springer, vol. 135(3), pages 373-379, April.
    9. Brian C. O’Neill & Timothy R. Carter & Kristie Ebi & Paula A. Harrison & Eric Kemp-Benedict & Kasper Kok & Elmar Kriegler & Benjamin L. Preston & Keywan Riahi & Jana Sillmann & Bas J. Ruijven & Detlef, 2021. "Publisher Correction: Achievements and needs for the climate change scenario framework," Nature Climate Change, Nature, vol. 11(3), pages 274-274, March.
    10. Hussain, Anwar & Rahman, Muhammad & Memon, Junaid Alam, 2016. "Forecasting electricity consumption in Pakistan: the way forward," Energy Policy, Elsevier, vol. 90(C), pages 73-80.
    11. Mustafa Saglam & Catalina Spataru & Omer Ali Karaman, 2022. "Electricity Demand Forecasting with Use of Artificial Intelligence: The Case of Gokceada Island," Energies, MDPI, vol. 15(16), pages 1-22, August.
    12. Hong, Tao & Pinson, Pierre & Fan, Shu & Zareipour, Hamidreza & Troccoli, Alberto & Hyndman, Rob J., 2016. "Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond," International Journal of Forecasting, Elsevier, vol. 32(3), pages 896-913.
    13. Amin, Amin & Mourshed, Monjur, 2024. "Community stochastic domestic electricity forecasting," Applied Energy, Elsevier, vol. 355(C).
    14. Spyros Makridakis & Evangelos Spiliotis & Vassilios Assimakopoulos, 2018. "Statistical and Machine Learning forecasting methods: Concerns and ways forward," PLOS ONE, Public Library of Science, vol. 13(3), pages 1-26, March.
    15. Mustafa Saglam & Catalina Spataru & Omer Ali Karaman, 2023. "Forecasting Electricity Demand in Turkey Using Optimization and Machine Learning Algorithms," Energies, MDPI, vol. 16(11), pages 1-23, June.
    16. Yukseltan, Ergun & Yucekaya, Ahmet & Bilge, Ayse Humeyra, 2017. "Forecasting electricity demand for Turkey: Modeling periodic variations and demand segregation," Applied Energy, Elsevier, vol. 193(C), pages 287-296.
    17. Detlef Vuuren & Elmar Kriegler & Brian O’Neill & Kristie Ebi & Keywan Riahi & Timothy Carter & Jae Edmonds & Stephane Hallegatte & Tom Kram & Ritu Mathur & Harald Winkler, 2014. "A new scenario framework for Climate Change Research: scenario matrix architecture," Climatic Change, Springer, vol. 122(3), pages 373-386, February.
    18. Tashman, Leonard J., 2000. "Out-of-sample tests of forecasting accuracy: an analysis and review," International Journal of Forecasting, Elsevier, vol. 16(4), pages 437-450.
    19. Dilaver, Zafer & Hunt, Lester C., 2011. "Turkish aggregate electricity demand: An outlook to 2020," Energy, Elsevier, vol. 36(11), pages 6686-6696.
    20. Waite, Michael & Cohen, Elliot & Torbey, Henri & Piccirilli, Michael & Tian, Yu & Modi, Vijay, 2017. "Global trends in urban electricity demands for cooling and heating," Energy, Elsevier, vol. 127(C), pages 786-802.
    21. Bilgili, Mehmet & Pinar, Engin, 2023. "Gross electricity consumption forecasting using LSTM and SARIMA approaches: A case study of Türkiye," Energy, Elsevier, vol. 284(C).
    22. Melissa R. Allen & Steven J. Fernandez & Joshua S. Fu & Mohammed M. Olama, 2016. "Impacts of climate change on sub-regional electricity demand and distribution in the southern United States," Nature Energy, Nature, vol. 1(8), pages 1-9, August.
    23. Kumar Biswajit Debnath & Monjur Mourshed, 2018. "Author Correction: Challenges and gaps for energy planning models in the developing-world context," Nature Energy, Nature, vol. 3(6), pages 528-528, June.
    24. Tutun, Salih & Chou, Chun-An & Canıyılmaz, Erdal, 2015. "A new forecasting framework for volatile behavior in net electricity consumption: A case study in Turkey," Energy, Elsevier, vol. 93(P2), pages 2406-2422.
    25. Hahn, Heiko & Meyer-Nieberg, Silja & Pickl, Stefan, 2009. "Electric load forecasting methods: Tools for decision making," European Journal of Operational Research, Elsevier, vol. 199(3), pages 902-907, December.
    26. Yuchen Guo & Ze Zhang, 2024. "Reducing carbon emissions through green renewal: insights from residential energy consumption in Chinese urban inventory districts from an evidence-based decision-making perspective," Humanities and Social Sciences Communications, Palgrave Macmillan, vol. 11(1), pages 1-13, December.
    27. Huang, Bwo-Nung & Hwang, M.J. & Yang, C.W., 2008. "Causal relationship between energy consumption and GDP growth revisited: A dynamic panel data approach," Ecological Economics, Elsevier, vol. 67(1), pages 41-54, August.
    28. Brian O’Neill & Elmar Kriegler & Keywan Riahi & Kristie Ebi & Stephane Hallegatte & Timothy Carter & Ritu Mathur & Detlef Vuuren, 2014. "A new scenario framework for climate change research: the concept of shared socioeconomic pathways," Climatic Change, Springer, vol. 122(3), pages 387-400, February.
    29. Auffhammer, Maximilian & Mansur, Erin T., 2014. "Measuring climatic impacts on energy consumption: A review of the empirical literature," Energy Economics, Elsevier, vol. 46(C), pages 522-530.
    30. Hong, Tao & Fan, Shu, 2016. "Probabilistic electric load forecasting: A tutorial review," International Journal of Forecasting, Elsevier, vol. 32(3), pages 914-938.
    31. Martinez, A. & Iglesias, G., 2024. "Global wind energy resources decline under climate change," Energy, Elsevier, vol. 288(C).
    32. Kumar Biswajit Debnath & Monjur Mourshed, 2018. "Challenges and gaps for energy planning models in the developing-world context," Nature Energy, Nature, vol. 3(3), pages 172-184, March.
    33. Hyndman, Rob J. & Koehler, Anne B., 2006. "Another look at measures of forecast accuracy," International Journal of Forecasting, Elsevier, vol. 22(4), pages 679-688.
    34. Pesantez, Jorge E. & Li, Binbin & Lee, Christopher & Zhao, Zhizhen & Butala, Mark & Stillwell, Ashlynn S., 2023. "A Comparison Study of Predictive Models for Electricity Demand in a Diverse Urban Environment," Energy, Elsevier, vol. 283(C).
    35. Kavaklioglu, Kadir, 2011. "Modeling and prediction of Turkey's electricity consumption using Support Vector Regression," Applied Energy, Elsevier, vol. 88(1), pages 368-375, January.
    36. Elisha R. Frederiks & Karen Stenner & Elizabeth V. Hobman, 2015. "The Socio-Demographic and Psychological Predictors of Residential Energy Consumption: A Comprehensive Review," Energies, MDPI, vol. 8(1), pages 1-37, January.
    37. Zheng, Shuguang & Huang, Guohe & Zhou, Xiong & Zhu, Xiaohang, 2020. "Climate-change impacts on electricity demands at a metropolitan scale: A case study of Guangzhou, China," Applied Energy, Elsevier, vol. 261(C).
    38. Gang Chen & Qingchang Hu & Jin Wang & Xu Wang & Yuyu Zhu, 2023. "Machine-Learning-Based Electric Power Forecasting," Sustainability, MDPI, vol. 15(14), pages 1-21, July.
    39. Kristie Ebi & Stephane Hallegatte & Tom Kram & Nigel Arnell & Timothy Carter & Jae Edmonds & Elmar Kriegler & Ritu Mathur & Brian O’Neill & Keywan Riahi & Harald Winkler & Detlef Vuuren & Timm Zwickel, 2014. "A new scenario framework for climate change research: background, process, and future directions," Climatic Change, Springer, vol. 122(3), pages 363-372, February.
    40. Dilaver, Zafer & Hunt, Lester C, 2011. "Modelling and forecasting Turkish residential electricity demand," Energy Policy, Elsevier, vol. 39(6), pages 3117-3127, June.
    41. Weron, Rafał, 2014. "Electricity price forecasting: A review of the state-of-the-art with a look into the future," International Journal of Forecasting, Elsevier, vol. 30(4), pages 1030-1081.
    42. Li, Chuan & Tao, Ying & Ao, Wengang & Yang, Shuai & Bai, Yun, 2018. "Improving forecasting accuracy of daily enterprise electricity consumption using a random forest based on ensemble empirical mode decomposition," Energy, Elsevier, vol. 165(PB), pages 1220-1227.
    43. Hoxha, Julian & Çodur, Muhammed Yasin & Mustafaraj, Enea & Kanj, Hassan & El Masri, Ali, 2023. "Prediction of transportation energy demand in Türkiye using stacking ensemble models: Methodology and comparative analysis," Applied Energy, Elsevier, vol. 350(C).
    44. Debnath, Kumar Biswajit & Mourshed, Monjur, 2018. "Forecasting methods in energy planning models," Renewable and Sustainable Energy Reviews, Elsevier, vol. 88(C), pages 297-325.
    45. Maria Pempetzoglou, 2014. "Electricity Consumption and Economic Growth: A Linear and Nonlinear Causality Investigation for Turkey," International Journal of Energy Economics and Policy, Econjournals, vol. 4(2), pages 263-273.
    46. Elmar Kriegler & Jae Edmonds & Stéphane Hallegatte & Kristie Ebi & Tom Kram & Keywan Riahi & Harald Winkler & Detlef Vuuren, 2014. "A new scenario framework for climate change research: the concept of shared climate policy assumptions," Climatic Change, Springer, vol. 122(3), pages 401-414, February.
    47. Pedro J. Zarco-Periñán & Irene M. Zarco-Soto & Fco. Javier Zarco-Soto, 2021. "Influence of the Population Density of Cities on Energy Consumption of Their Households," Sustainability, MDPI, vol. 13(14), pages 1-15, July.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Skea, Jim & van Diemen, Renée & Portugal-Pereira, Joana & Khourdajie, Alaa Al, 2021. "Outlooks, explorations and normative scenarios: Approaches to global energy futures compared," Technological Forecasting and Social Change, Elsevier, vol. 168(C).
    2. Thangjam Aditya & Sanjita Jaipuria & Pradeep Kumar Dadabada, 2025. "A Review of Methods for Long‐Term Electric Load Forecasting," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 44(4), pages 1403-1423, July.
    3. Ludwig Weh, 2025. "A Participatory Scenario Framework Advances Ecosystem Scenarios as Environmental Futures Approach," Futures & Foresight Science, John Wiley & Sons, vol. 7(2), August.
    4. De Cian, Enrica & Wing, Ian Sue, "undated". "Global Energy Demand in a Warming Climate," EIA: Climate Change: Economic Impacts and Adaptation 232222, Fondazione Eni Enrico Mattei (FEEM).
    5. Tom Wilson & Irina Grossman & Monica Alexander & Phil Rees & Jeromey Temple, 2022. "Methods for Small Area Population Forecasts: State-of-the-Art and Research Needs," Population Research and Policy Review, Springer;Southern Demographic Association (SDA), vol. 41(3), pages 865-898, June.
    6. Hongliang Zhang & Jianhong E. Mu & Bruce A. McCarl & Jialing Yu, 2022. "The impact of climate change on global energy use," Mitigation and Adaptation Strategies for Global Change, Springer, vol. 27(1), pages 1-19, January.
    7. Simona Pedde & Kasper Kok & Eric Kemp-Benedict & Oliver Johnson & Henrik Carlsen & Carole Green & Sara Talebian & Stefan Fagerström & Xiaoshi Xing, 2025. "Emerging regional perspectives of global climate change scenarios: a systematic review," Climatic Change, Springer, vol. 178(6), pages 1-19, June.
    8. Nicholas A. Cradock-Henry & Bob Frame & Benjamin L. Preston & Andy Reisinger & Dale S. Rothman, 2018. "Dynamic adaptive pathways in downscaled climate change scenarios," Climatic Change, Springer, vol. 150(3), pages 333-341, October.
    9. N. B. Melnikov & A. P. Gruzdev & M. G. Dalton & M. Weitzel & B. C. O’Neill, 2021. "Parallel Extended Path Method for Solving Perfect Foresight Models," Computational Economics, Springer;Society for Computational Economics, vol. 58(2), pages 517-534, August.
    10. Kılkış, Şiir, 2022. "Urban emissions and land use efficiency scenarios towards effective climate mitigation in urban systems," Renewable and Sustainable Energy Reviews, Elsevier, vol. 167(C).
    11. van Sluisveld, Mariësse A.E. & Hof, Andries F. & Carrara, Samuel & Geels, Frank W. & Nilsson, Måns & Rogge, Karoline & Turnheim, Bruno & van Vuuren, Detlef P., 2020. "Aligning integrated assessment modelling with socio-technical transition insights: An application to low-carbon energy scenario analysis in Europe," Technological Forecasting and Social Change, Elsevier, vol. 151(C).
    12. Koch, Johannes & Leimbach, Marian, 2023. "SSP economic growth projections: Major changes of key drivers in integrated assessment modelling," Ecological Economics, Elsevier, vol. 206(C).
    13. Petropoulos, Fotios & Apiletti, Daniele & Assimakopoulos, Vassilios & Babai, Mohamed Zied & Barrow, Devon K. & Ben Taieb, Souhaib & Bergmeir, Christoph & Bessa, Ricardo J. & Bijak, Jakub & Boylan, Joh, 2022. "Forecasting: theory and practice," International Journal of Forecasting, Elsevier, vol. 38(3), pages 705-871.
      • Fotios Petropoulos & Daniele Apiletti & Vassilios Assimakopoulos & Mohamed Zied Babai & Devon K. Barrow & Souhaib Ben Taieb & Christoph Bergmeir & Ricardo J. Bessa & Jakub Bijak & John E. Boylan & Jet, 2020. "Forecasting: theory and practice," Papers 2012.03854, arXiv.org, revised Jan 2022.
    14. Dale S. Rothman & Paul Raskin & Kasper Kok & John Robinson & Jill Jäger & Barry Hughes & Paul C. Sutton, 2023. "Global Discontinuity: Time for a Paradigm Shift in Global Scenario Analysis," Sustainability, MDPI, vol. 15(17), pages 1-12, August.
    15. Enrica Cian & Ian Sue Wing, 2019. "Global Energy Consumption in a Warming Climate," Environmental & Resource Economics, Springer;European Association of Environmental and Resource Economists, vol. 72(2), pages 365-410, February.
    16. Cotterman, Turner, 2019. "Why Rapid and Deep Decarbonization isn’t Simple: Linking Bottom-up Socio-technical Decision-making Insights with Top-down Macroeconomic Analyses," Conference papers 333088, Purdue University, Center for Global Trade Analysis, Global Trade Analysis Project.
    17. Kılkış, Şiir, 2023. "Integrated urban scenarios of emissions, land use efficiency and benchmarking for climate neutrality and sustainability," Energy, Elsevier, vol. 285(C).
    18. Small, Mitchell J. & Wong-Parodi, Gabrielle & Kefford, Benjamin M. & Stringer, Martin & Schmeda-Lopez, Diego R. & Greig, Chris & Ballinger, Benjamin & Wilson, Stephen & Smart, Simon, 2019. "Generating linked technology-socioeconomic scenarios for emerging energy transitions," Applied Energy, Elsevier, vol. 239(C), pages 1402-1423.
    19. Zhao, Jianheng & Daigneault, Adam & Weiskittel, Aaron & Wei, Xinyuan, 2023. "Climate and socioeconomic impacts on Maine's forests under alternative future pathways," Ecological Economics, Elsevier, vol. 214(C).
    20. Kalkuhl, Matthias & Wenz, Leonie, 2020. "The impact of climate conditions on economic production. Evidence from a global panel of regions," Journal of Environmental Economics and Management, Elsevier, vol. 103(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:energy:v:336:y:2025:i:c:s036054422503837x. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/energy .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.