The Impact of Driver Behavior on Electric Bus Energy Consumption: Optimizing Driver Performance with Bio-Inspired WUTP Algorithm with Real-Time Big Data

Year 2025, Volume: 9 Issue: 4, 602 - 617, 31.12.2025

Yunus Emre Ekici , Ozan Akdağ , Nisanur Yildiran , Teoman Karadag

https://doi.org/10.30939/ijastech..1789079

Abstract

The transition toward sustainable urban mobility requires not only technological innovations in electric buses (E-Buses) but also optimization of operational factors such as driver behavior, which significantly influences energy consumption and driving range. This study develops a novel artificial intelligence framework, integrating real-time big data with a bio-inspired Water Uptake and Transport in Plants (WUTP) algorithm, to optimize E-Bus driver performance under real-world conditions. Data were collected from trolleybus-type hybrid electric buses operating in Malatya, Turkey, encompassing nearly 50 million observations across diverse seasonal, topographical, and operational contexts. Through preprocessing and correlation-based feature selection, 14 key parameters—including regenerative braking, auxiliary loads (HVAC and static converters), acceleration, and road slope—were identified as critical determinants of energy consumption. The WUTP algorithm, implemented with 60,000 representative data rows, generated optimized driving profiles and weighting coefficients, enabling precise estimation of optimal operational thresholds. Results reveal that maintaining regenerative braking above 77%, moderating accelerator pedal use at approximately 44%, and stabilizing average vehicle speed significantly extend range and reduce energy demand. Comparative evaluation of six drivers demonstrated efficiency disparities exceeding 30%, underscoring the importance of training and monitoring systems. The proposed model is distinguished by its dynamic treatment of auxiliary loads, scalability across routes and climates, and applicability for fleet planning, battery sizing, and eco-driving assessment. Overall, this research contributes a robust, adaptable, and scalable framework that enhances operational efficiency, reduces environmental impact, and supports the broader deployment of sustainable E-Bus systems in global transit networks.

Keywords

Big data , Electric bus , Energy Consumption , Optimization

Thanks

We would like to thank Malatya Metropolitan Municipali-ty Transportation Services (MOTAŞ) for sharing trolley-bus data with us under the protocol, thereby enabling aca-demic research to be conducted.

References

• [1] Holland SP, Mansur ET, Muller NZ, Yates AJ. The environmental benefits of transportation electrification: Urban buses. Energy Policy 2021;148:111921. https://doi.org/10.1016/J.ENPOL.2020.111921.
• [2] Zhou B, Wu Y, Zhou B, Wang R, Ke W, Zhang S, et al. Real-world performance of battery electric buses and their life-cycle benefits with respect to energy consumption and carbon dioxide emissions. Energy 2016;96:603–13. https://doi.org/10.1016/J.ENERGY.2015.12.041.
• [3] Belloni M, Tarsitano D, Sabbioni E. A Comprehensive Analysis of Energy Consumption in Battery-Electric Buses Using Experimental Data: Impact of Driver Behavior, Route Characteristics, and Environmental Conditions. ELECTRONICS 2025;14. https://doi.org/10.3390/electronics14040735.
• [4] Manzolli JA, Trovão JP, Antunes CH. A review of electric bus vehicles research topics – Methods and trends. Renew Sustain Energy Rev 2022;159:112211. https://doi.org/10.1016/J.RSER.2022.112211.
• [5] Lyu A, Zhang H, Shen Y, Zhang Y. Eco-Driving Level Evaluation Model for Electric Buses Entering and Leaving Stops. IEEE ACCESS 2025;13:71792–805. https://doi.org/10.1109/access.2025.3561469; 10.1109/ACCESS.2025.3561469.
• [6] Yan Y, Fan Y-C. Influence of the Driver Style difference in the Acceleration Process on the Energy Consumption of the EV Bus 2016:186–90. https://doi.org/10.2991/ICEAT-16.2017.39.
• [7] Ramanujam Y, Malhotra I, Thimmalapura S. A Study of Parameters Influencing Energy Consumption of an Electric Vehicle. 2019 IEEE Transp Electrif Conf ITEC-India 2019 2019. https://doi.org/10.1109/ITEC-INDIA48457.2019.ITECINDIA2019-45.
• [8] Szurke SK, Saly G, Lakatos I. Analyzing Energy Efficiency and Battery Supervision in Electric Bus Integration for Improved Urban Transport Sustainability. SUSTAINABILITY 2024;16. https://doi.org/10.3390/su16188182.
• [9] Dong C, Xiong Z, Zhang C, Li N, Li Y, Xie N, et al. A transformer-based approach for deep feature extraction and energy consumption prediction of electric buses based on driving distances. Appl Energy 2025;380. https://doi.org/10.1016/j.apenergy.2024.123941.
• [10] Kang Y, Wei J, Liu Z, Xiao K. An energy consumption prediction model for electric buses based on extreme gradient boosting fusion algorithm. Int J GREEN ENERGY 2025;22:2504–17. https://doi.org/10.1080/15435075.2025.2464155.
• [11] Jamadar NM, Jadhav HT. A review on braking control and optimization techniques for electric vehicle. Proc Inst Mech Eng Part D J Automob Eng 2021;235:2371–82. https://doi.org/10.1177/0954407021996906.
• [12] Jamadar NM, Jadhav HT. Rule-based assistive hybrid electric brake system with energy generation for electric vehicle. Energy Sources, Part A Recover Util Environ Eff 2025;47. https://doi.org/10.1080/15567036.2021.2015485.
• [13] Ekici YE, Aydin AA, Karadağ T, Akdağ O, Ateş A. Energy consumption model with real-time data for driving range extension of electric buses. Sustain Futur 2025;9:100603. https://doi.org/10.1016/j.sftr.2025.100603.
• [14] Ekıcı YE, Akdağ O, Aydin AA, Karadağ T. A novel energy consumption prediction model of electric buses using real-time big data from route, environment, and vehicle parameters. IEEE Access 2023;2:1–1. https://doi.org/10.1109/access.2023.3316362.
• [15] Bozankaya. Bozankaya Elektrikli Otobüs n.d.
• [16] Ekici YE, Karadag T, Akdag O, Aydin AA, Tekin HO. Tailoring Energy Efficiency for Urban Electric Buses: The GTECM Model for Enhanced Range and Sustainable Operation Using Real-Time Big Data. IEEE Trans Intell Transp Syst 2025;26:12600–14. https://doi.org/10.1109/TITS.2025.3558147.
• [17] Ekici YE, Karadağ T, Akdağ O, Aydin AA, Tekin HO. Enhancing Electric Vehicle Range through Real-Time Failure Prediction and Optimization: Introduction to DHBA-FPM Model with an Artificial Intelligence Approach. ICT Express 2025. https://doi.org/10.1016/j.icte.2025.03.009.
• [18] Ekici YE, Karadag T, Aydin AA, Akdag O. Impact of Outside Temperature on Driving Range and Energy Consumption Using Real-Time Big Data for Electric Buses. 8th Int. Artif. Intell. Data Process. Symp. IDAP 2024, 2024, p. 1–9. https://doi.org/10.1109/IDAP64064.2024.10710801.
• [19] Ekici YE, Ka T, Aydın AA, Akdağ O. Driving Range Problem in Electric Vehicles and Methods to Increase. Artic. Rev. Eng., 2024, p. 253–86. https://doi.org/10.5281/zenodo.13950544.
• [20] Evin E, Aydin MB, Kardas G. Design and Implementation of a CANBus-Based Eco-Driving System for Public Transport Bus Services. IEEE Access 2020;8:8114–28. https://doi.org/10.1109/ACCESS.2020.2964119.
• [21] Enclosure O, Filter AIR, Test E. Vehicle Recommended. Hum Factors 1993;4970:1–9.
• [22] Aydin AA. A Comparative Perspective on Technologies of Big Data Value Chain. IEEE Access 2023;11:112133–46. https://doi.org/10.1109/ACCESS.2023.3323160.
• [23] EKİCİ YE, DİKMEN İC, NURMUHAMMED M, KARADAĞ T. A Review on Electric Vehicle Charging Systems and Current Status in Turkey. Int J Automot Sci Technol 2021;5:316–30. https://doi.org/10.30939/ijastech..958368.
• [24] Ekici YE, Tan N. Investigation Of Charging And Discharging Characteristics Of Different Type Batteries Using Trambus Accelerator Pedal Data On Hybrid Electric Vehicle Model. Int J Energy Eng Sci 2018;3:55–67.
• [25] Agarwal P, Jain S, Candan M. Some Characteristics of Matrix Operators on Generalized Fibonacci Weighted Difference Sequence Space. Symmetry 2022, Vol 14, Page 1283 2022;14:1283. https://doi.org/10.3390/SYM14071283.
• [26] Roberts DM, Kunst RE. A Case against Continuing Use of the Spearman Formula for Rank-Order Correlation. Psychol Rep 1990;66:339–49. https://doi.org/10.2466/PR0.1990.66.1.339.
• [27] Laerd Statistics, “Spearman’s rank-order correlation: A guide to when to use it, what it does and what the assumptions are,” Laerd Statistics, n.d. [Online]. Available: https://statistics.laerd.com/statistical-guides/spearmans-rank-order-correlation-statistical-guide.php. [Accessed: Sep. 22, 2025].
• [28] Braik M, Al-Hiary H. A novel meta-heuristic optimization algorithm inspired by water uptake and transport in plants. Neural Comput Appl 2025;37:13643–724. https://doi.org/10.1007/s00521-025-11228-z.
• [29] Zimmermann U, Steudle E. Physical Aspects of Water Relations of Plant Cells. Adv Bot Res 1979;6:45–117. https://doi.org/https://doi.org/10.1016/S0065-2296(08)60329-8.
• [30] Knipfer T, Fricke W. Root pressure and a solute reflection coefficient close to unity exclude a purely apoplastic pathway of radial water transport in barley (Hordeum vulgare). New Phytol 2010;187:159–70. https://doi.org/10.1111/j.1469-8137.2010.03240.x.