EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Performance comparison of PI and AI-based controllers for solar PV-fed fast electric vehicle battery charging systems

Apoorva Srivastava, Vikas Yadav, Vinit Yadav, Tarun Nayyar, Shailesh Kumar Yadav, Ayush Asthana

Energy Storage and Conversion · 17.04.2026

DOI: 10.59400/esc4074 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energy Storage and Conversion, online erschienen am 17.04.2026. Verfasst von Apoorva Srivastava und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of electric vehicles (EVs) has created a strong demand for efficient and fast charging solutions. However, conventional charging methods are time-consuming and place significant stress on the power grid when deployed on large scale. To address these challenges, this study proposes a standalone solar photovoltaic (PV)-based DC microgrid for fast EV charging. The system is designed to regulate charging using a DC-DC boost converter controlled by two strategies: a conventional Proportional-Integral (PI) controller and an Artificial Neural Network (ANN)-based controller. A detailed simulation model is developed in MATLAB/Simulink, including PV system parameters, converter specifications, and a lithium-ion battery modeled using a Thevenin equivalent circuit. The ANN controller is trained using real-time operating conditions such as irradiance, temperature, and state of charge (SoC). Performance is evaluated based on transient response, overshoot, settling time, steady-state error, and total harmonic distortion (THD). Results show that the ANN controller significantly improves system performance. Voltage overshoot is reduced from 10% to 2%, current overshoot from 20% to 4%, and THD from 6.8% to 2.1%. Additionally, the settling time is improved by approximately 57% compared to the PI controller. These findings demonstrate that AI-based control strategies provide a more efficient, stable, and reliable solution for renewable energy-based EV charging systems. The ANN controller reduced voltage overshoot from 10% to 2%, current overshoot from 20% to 4%, and THD from 6.8% to 2.1%, while improving settling time by up to 57%.

Zitieren

APA

Srivastava, A., Yadav, V., Yadav, V., Nayyar, T., Yadav, S. K., & Asthana, A. (2026). Performance comparison of PI and AI-based controllers for solar PV-fed fast electric vehicle battery charging systems. Energy Storage and Conversion. https://doi.org/10.59400/esc4074

Vancouver

Srivastava A, Yadav V, Yadav V, Nayyar T, Yadav SK, Asthana A. Performance comparison of PI and AI-based controllers for solar PV-fed fast electric vehicle battery charging systems. Energy Storage and Conversion. 2026. doi:10.59400/esc4074

BibTeX
@article{Srivastava2026,
  author = {Srivastava, Apoorva and Yadav, Vikas and Yadav, Vinit and Nayyar, Tarun and Yadav, Shailesh Kumar and Asthana, Ayush},
  title = {Performance comparison of PI and AI-based controllers for solar PV-fed fast electric vehicle battery charging systems},
  journal = {Energy Storage and Conversion},
  year = {2026},
  doi = {10.59400/esc4074}
}
Kostenlos starten →