i-manager Publications

AI-Optimized Multilevel Power Converter for High Efficiency Electric Vehicle Traction Drives under Dynamic Road and Grid Conditions

Rajesh Kumar Singh*, Khadim Moin Siddaqui**

S. R. Institute of Management and Technology, Lucknow, Uttar Pradesh, India.

Periodicity:October - December'2025
DOI : https://doi.org/10.26634/jee.19.2.22922

Abstract

The transition toward electric mobility demands traction inverters that deliver high efficiency, thermal stability, and robust performance under diverse real-world driving conditions. This study introduces an AI-optimized three-level T-type Silicon Carbide (SiC) traction inverter designed for intelligent, energy-efficient electric vehicle (EV) propulsion. A Proximal Policy Optimization (PPO)-based controller is developed to dynamically regulate modulation index, switching frequency, and switching sequence, enabling coordinated loss-thermal optimization. The controller is trained on WLTP and UDDS drive cycles using a physics-based inverter, motor, and thermal model derived from SiC MOSFET datasheets. High-fidelity figures were produced using scientific plotting rather than simulation screenshots to ensure journal-standard reproducibility. The proposed inverter achieves significant improvements: switching losses are reduced by up to 52%, peak junction temperature is lowered by approximately 23%, and average drive-cycle efficiency is increased from 92.1% to 96.8%. These gains translate to an increase of 20-24 km in WLTP driving range for a 75-kWh battery EV. The results demonstrate that AI-assisted modulation can substantially enhance converter performance, reduce thermal stress, and support sustainable green-energy transportation systems.

Keywords

Electric Vehicles, Traction Inverters, Silicon Carbide, Multilevel Converters, Reinforcement Learning, Thermal Optimization.

How to Cite this Article?

Singh, R. K., and Siddaqui, K. M. (2025). AI-Optimized Multilevel Power Converter for High Efficiency Electric Vehicle Traction Drives under Dynamic Road and Grid Conditions. i-manager’s Journal on Electrical Engineering , 19(2), 23-32. https://doi.org/10.26634/jee.19.2.22922

References

[1]. Burkart, R. M., & Kolar, J. W. (2013). Comparative evaluation of SiC and Si PV inverter systems based on power density and efficiency as indicators of initial cost and operating revenue. In 2013 IEEE 14th Workshop on Control and Modeling for Power Electronics (COMPEL) (pp. 1-6). IEEE.

[2]. Dusmez, S., & Khaligh, A. (2013). A charge-nonlinear-carrier-controlled reduced-part single-stage integrated power electronics interface for automotive applications. IEEE Transactions on Vehicular Technology, 63(3), 1091-1103.

[3]. Ehsani, M., Gao, Y., Longo, S., & Ebrahimi, K. (2018). Modern Electric, Hybrid Electric, and Fuel Cell Vehicles. CRC press.

[4]. Englberger, S., Hesse, H., Kucevic, D., & Jossen, A. (2019). A techno-economic analysis of vehicle-to-building: Battery degradation and efficiency analysis in the context of coordinated electric vehicle charging. Energies, 12(5), 955.

[5]. Hua, H., Qin, Y., Hao, C., & Cao, J. (2019). Optimal energy management strategies for energy Internet via deep reinforcement learning approach. Applied Energy, 239, 598-609.

[6]. Ioinovici, A. (2013). Power Electronics and Energy Conversion Systems: Fundamentals and Hard-Switching Converters. John Wiley & Sons.

[7]. Kazimierczuk, M. K. (2015). Pulse-Width Modulated DC-DC Power Converters. John Wiley & Sons.

[8]. Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2016). Continuous control with deep reinforcement learning. In Proceedings of the 4th International Conference on Learning Representations (ICLR 2016).

[9]. Millan, J., Godignon, P., Perpiñà, X., Pérez-Tomás, A., & Rebollo, J. (2013). A survey of wide bandgap power semiconductor devices. IEEE Transactions on Power Electronics, 29(5), 2155-2163.

[10]. Mohan, N., Undeland, T. M., & Robbins, W. P. (2003). Power Electronics: Converters, Applications, and Design. John wiley & sons.

[11]. Ozpineci, B. (2004). Comparison of Wide-Bandgap Semiconductors for Power Electronics Applications. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States).

[12]. Pandey, S., & Sharma, D. (2015). Multilevel inverter topologies or photovoltaic grid connections: a review. International Journal of Engineering and Technical Research (IJETR), 3(5), 93-95.

[13]. Peng, F. Z. (2003). Z-source inverter. IEEE Transactions on Industry Applications, 39(2), 504-510.

[14]. Pinto, C., De Castro, R., Barreras, J. V., Araujo, R. E., & Howey, D. A. (2018). Smart balancing control of a hybrid energy storage system based on a cell-to-cell shared energy transfer configuration. In 2018 IEEE Vehicle Power and Propulsion Conference (VPPC) (pp. 1-6). IEEE.

[15]. Prathaban, A. V., Dhandapani, K., & Soni Abubakar, A. I. (2022). Compact Thirteen-Level Inverter for PV Applications. Energies, 15(8), 2808.

[16]. Qu, X., Song, Y., Liu, D., Cui, X., & Peng, Y. (2020). Lithium-ion battery performance degradation evaluation in dynamic operating conditions based on a digital twin model. Microelectronics Reliability, 114, 113857.

[17]. Rashid, M. H. (Ed.). (2017). Power Electronics Handbook. Butterworth-heinemann.

[18]. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347.

[19]. Teodorescu, R., Liserre, M., & Rodriguez, P. (2011). Grid Converters for Photovoltaic and Wind Power Systems. John Wiley & Sons.

[20]. Tu, H., Feng, H., Srdic, S., & Lukic, S. (2019). Extreme fast charging of electric vehicles: A technology overview. IEEE Transactions on Transportation Electrification, 5(4), 861-878.

[21]. U.S. Environmental Protection Agency. (1999). Urban Dynamometer Driving Schedule (UDDS) Specification (EPA-420-R-99-011). U.S. Environmental Protection Agency.

[22]. United Nations Economic Commission for Europe. (2017). UN Global Technical Regulation No. 15: Worldwide Harmonized Light vehicles Test Procedure (WLTP). UNECE.

[23]. Wan, Y., Xu, Q., & Dragičević, T. (2024). Reinforcement learning-based predictive control for power electronic converters. IEEE Transactions on Industrial Electronics, 72(5), 5353–5364.

[24]. Wang, Y., Poorfakhraei, A., Mehdi, N., & Emadi, A. (2021). Comparative analysis of 2-level and 3-level voltage source inverters in traction applications. In 2021 IEEE Transportation Electrification Conference & Expo (ITEC) (pp. 614-619). IEEE.

[25]. Weiss, M., Winbush, T., Newman, A., & Helmers, E. (2024). Energy consumption of electric vehicles in Europe. Sustainability, 16(17), 7529.

[26]. Wolfspeed, Inc. (2019). C2M0080120D Silicon Carbide Power MOSFET Datasheet. Wolfspeed Technical Documentation.

[27]. Zhao, S., Blaabjerg, F., & Wang, H. (2020). An overview of artificial intelligence applications for power electronics. IEEE Transactions on Power Electronics, 36(4), 4633-4658.

[28]. Zhong, Q. C., & Hornik, T. (2012). Control of Power Inverters in Renewable Energy and Smart Grid Integration. John Wiley & Sons.

AI-Optimized Multilevel Power Converter for High Efficiency Electric Vehicle Traction Drives under Dynamic Road and Grid Conditions

Abstract

Keywords

How to Cite this Article?

References

If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Options for accessing this content:

	North Americas,UK, Middle East,Europe		India	Rest of world
	USD	EUR	INR	USD-ROW
Pdf	35	35	200	20
Online	15	15	200	15
Pdf & Online	35	35	400	25