SavedAdd your journal

Journals / Karaelmas Fen ve Mühendislik Dergisi / 2026 / Cilt: 16 Sayı: 2

Modeling and Prediction Methods for Energy Consumption of Electric Vehicles

Elektrikli Araçların Enerji Tüketimi için Modelleme ve Tahmin Yöntemleri

Pınar Kıramanlıoğlu(BEYKENT ÜNİVERSİTESİ)0000-0001-5768-6400
Begüm Erol(Kahramanmaraş İstiklal Üniversitesi)0000-0001-9131-3317
Mehmet Mutlu Yenisey(İSTANBUL ÜNİVERSİTESİ-CERRAHPAŞA)0000-0002-4532-344X
Pages
61–77
Publication Date
2026-07-24
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results demonstrate that integrating physically meaningful parameters with data-driven methods enhances prediction accuracy and supports sustainable energy use.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In recent years, growing environmental issues and concerns over energy sustainability have driven major changes in the transportation sector.
📊
Key Findings & Data:For instance, vehicle weight and aerodynamics influence energy use, while driver acceleration and braking patterns can substantially increase it.
💡
Conclusion & Impact:The results demonstrate that integrating physically meaningful parameters with data-driven methods enhances prediction accuracy and supports sustainable energy use.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Elektrikli araçlar · enerji tüketimi · genişletilmiş elektrikli araç enerji veri seti(E-VED)

Abstract

In recent years, growing environmental issues and concerns over energy sustainability have driven major changes in the transportation sector. Electric vehicles (EVs) have appeared as a key solution to reduce the environmental impact of fossil fuel use. Their increasing adoption makes understanding energy consumption and its determinants crucial, as it directly affects range anxiety, charging infrastructure, and ownership costs. EV energy consumption depends on vehicle characteristics, driving behavior, environmental conditions, and auxiliary systems. For instance, vehicle weight and aerodynamics influence energy use, while driver acceleration and braking patterns can substantially increase it. Declining battery performance and intensive use of heating or air conditioning also raise consumption. This study examines the factors influencing EV energy use and predicts consumption using both an analytical model and machine learning (ML) techniques. Comparative evaluation showed that the Random Forest (RF) method achieved the highest prediction accuracy, while the analytical model performed competitively. According to the RF feature importance analysis, Acceleration, Timestamp, and Elevation Smoothed were the most influential variables, emphasizing the dominant role of driving dynamics and road topography. The results demonstrate that integrating physically meaningful parameters with data-driven methods enhances prediction accuracy and supports sustainable energy use.

Özet

Son yıllarda, artan çevre sorunları ve enerji sürdürülebilirliği konusundaki endişeler ulaşım sektöründe büyük değişikliklere neden olmuştur. Elektrikli araçlar (EV'ler), fosil yakıt kullanımının çevresel etkisini azaltmak için kilit bir çözüm olarak ortaya çıkmıştır. Artan benimsenmeleri, enerji tüketimini ve belirleyicilerini anlamayı çok önemli hale getiriyor, çünkü menzil kaygısını, şarj altyapısını ve mülkiyet maliyetlerini doğrudan etkiliyor. EV enerji tüketimi araç özelliklerine, sürüş davranışına, çevre koşullarına ve yardımcı sistemlere bağlıdır. Örneğin, araç ağırlığı ve aerodinamik enerji kullanımını etkilerken, sürücü hızlanması ve frenleme modelleri bunu önemli ölçüde artırabilir. Azalan pil performansı ve yoğun ısıtma veya klima kullanımı da tüketimi artırır. Bu çalışma EV enerji kullanımını etkileyen faktörleri inceler ve hem analitik bir model hem de makine öğrenimi (ML) tekniklerini kullanarak tüketimi öngörür. Karşılaştırmalı değerlendirme, Rastgele Orman (RF) yönteminin en yüksek tahmin doğruluğunu elde ettiğini, analitik modelin ise rekabetçi bir şekilde performans gösterdiğini gösterdi. RF özellik önem analizine göre, Hızlanma, Zaman Damgası ve Yükseklik Dumanlı, sürüş dinamiklerinin ve yol topografyasının baskın rolünü vurgulayan en etkili değişkenlerdi. Sonuçlar, fiziksel olarak anlamlı parametrelerin veri odaklı yöntemlerle entegre edilmesinin tahmin doğruluğunu artırdığını ve sürdürülebilir enerji kullanımını desteklediğini göstermektedir.

🔖

Cite This Article

Kıramanlıoğlu, P., Erol, B., Yenisey, M. M. (2026). Modeling and Prediction Methods for Energy Consumption of Electric Vehicles. Karaelmas Fen ve Mühendislik Dergisi, Cilt: 16 Sayı: 2, 61–77. https://doi.org/10.7212/karaelmasfen.1849045

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. Abd El-Latif, E. I., & El-dosuky, M. (2025). Explainable energy consumption and speed prediction in sustainable cities using deep learning. Neural Computing and Applications, 37(8), 6233-6249. https://doi.org/10.1007/s00521-024-10850-7
  2. Aslan, E. (2024). Elektrikli araçların enerji tüketimini tahmin etmede makine öğrenimi algoritmalarının performanslarının karşılaştırılması. Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 14(2), 518–530. https://doi.org/10.21597/jist.1448216
  3. De Cauwer, C., van Mierlo, J., & Coosemans, T. (2015). Energy consumption prediction for electric vehicles based on real-world data. Energies, 8(8), 8573–8593. https://doi.org/10.3390/en8088573
  4. Huang, Y.-W., Prehofer, C., Lindskog, W., Puts, R., Mosca, P., & Kauermann, G. (2024). Predictive energy management for battery electric vehicles with hybrid models. arXiv preprint. https://doi.org/10.48550/arXiv.2405.10984
  5. Hussain, I., Ching, K. B., Uttraphan, C., Tay, K. G., & Noor, A. (2025). Evaluating machine learning algorithms for energy consumption prediction in electric vehicles: A comparative study. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-94946-7
  6. Janpoom, K., Suttakul, P., Achariyaviriya, W., Fongsamootr, T., Katongtung, T., & Tippayawong, N. (2023). Investigating the influential factors in real-world energy consumption of battery electric vehicles. Energy Reports, 9, 316–320. https://doi.org/10.1016/j.egyr.2023.10.012
  7. Kilic, S. (2013). Linear regression analysis. Journal of Mood Disorders, 3(2), 90. https://doi.org/10.5455/jmood.20130624120840
  8. Ramoliya, F., Trivedi, C., Darji, K., Kakkar, R., Gupta, R., Tanwar, S., Polkowski, Z., Alqahtani, F., & Tolba, A. (2024). ML-based energy consumption and distribution framework analysis for EVs and charging stations in smart grid environment. IEEE Access, 12, 23319–23337. https://doi.org/10.1109/ACCESS.2024.3365080
  9. Rathore, H., Meena, H. K., & Jain, P. (2023). Prediction of EV energy consumption using random forest and XGBoost. Proceedings of the 2nd International Conference on Power Electronics and Energy (ICPEE 2023). IEEE. pp. 1-6, India. https://doi.org/10.1109/ICPEE54198.2023.10060798
  10. Polymeni, S., Spanos, G., Pitsiavas, V., Lalas, A., Votis, K., & Tzovaras, D. (2026). Analyzing energy consumption in battery electric vehicles: A statistical-based approach. IEEE Transactions on Transportation Electrification, 12(1), 529-541 https://doi.org/10.1109/TTE.2025.3618308
  11. Şahin, D. Ö., Çandırlı, M., Erşen, A., & Akar, M. H. (2025). Elektrikli araba veri kümesi üzerinde makine öğrenmesi ve derin öğrenme algoritmaları kullanarak şarj durumu tahmini. Mühendis ve Makina, 66(719), 361–387. https://doi.org/10.46399/muhendismakina.1728570
  12. Shen, H., Zhou, X., Yu, A., Lamantia, M., Chen, P., & Wang, J. (2023). An experimental comparison of physics-based and machine-learning-based electric vehicle energy consumption estimation methods. IFAC-PapersOnLine, 56, 8672–8677. https://doi.org/10.1016/j.ifacol.2023.10.045
  13. Teimoori, Z., Yassine, A., & Lu, C. (2024). Deep transfer learning for detecting electric vehicles highly correlated energy consumption parameters. IEEE Transactions on Artificial Intelligence, 5(8), 4087–4100. https://doi.org/10.1109/TAI.2024.3358796
  14. The Engineering Toolbox. (2013). Rolling friction resistance. Available at: http://www.engineeringtoolbox.com/rolling-friction-resistance-d_1303.html (Accessed: 15 November 2013).
  15. Wu, X., Freese, D., Cabrera, A., & Kitch, W. A. (2015). Electric vehicles’ energy consumption measurement and estimation. Transportation Research Part D: Transport and Environment, 34, 52–67. https://doi.org/10.1016/j.trd.2014.10.007 Yılmaz, H., & Yagmahan, B. (2024). Electric vehicle energy consumption prediction for unknown route types using deep neural networks by combining static and dynamic data. Applied Soft Computing, 167. https://doi.org/10.1016/j.asoc.2024.112336
  16. Zhang, S., Fatih, D., Abdulqadir, F., Schwarz, T., & Ma, X. (2022). Extended vehicle energy dataset (eVED): An enhanced large-scale dataset for deep learning on vehicle trip energy consumption. arXiv preprint. https://doi.org/10.48550/arXiv.2203.08630
  17. Zhang, T., Peng, Q., & Zeng, S. (2025). Predicting EV charging demand in renewable-energy-powered grids using explainable machine learning. Sustainability (Switzerland), 17(9). https://doi.org/10.3390/su17094158
  18. Zhu, Q., Huang, Y., Lee, C. F., Liu, P., Zhang, J., & Wik, T. (2025). Predicting electric vehicle energy consumption from field data using machine learning. IEEE Transactions on Transportation Electrification, 11(1), 2120–2132. https://doi.org/10.1109/TTE.2024.3416532