Citation

Hossen, Md Sabbir and Ramasamy, Gobbi and Eng Eng, Ngu and Sarker, Md Tanjil (2026) Smarter electric vehicle charging from Open Charge Point Protocol data: Reducing grid peaks and energy costs with tariff-aware scheduling. Smart Energy, 23. p. 100267. ISSN 2666-9552

Text 1-s2.0-S2666955226000420-main.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

The increasing adoption of electric vehicles (EVs) presents significant operational challenges for charging infrastructure, particularly in managing charging demand under feeder capacity and electricity tariff constraints. This paper proposes a practical data-driven framework that integrates short-term charging load forecasting, anomaly detection, and tariff-aware scheduling using real Open Charge Point Protocol (OCPP) telemetry collected from a multi-station residential charging network. The forecasting module employs lightweight statistical models with Fourier seasonality, while an Isolation Forest identifies abnormal charging behavior and a heuristic scheduling strategy coordinates charging according to feeder limits and time-of-use electricity prices. Experimental results demonstrate that the proposed framework achieves up to 35.0% peak demand reduction and 28.0% electricity cost savings while maintaining 100% energy delivery. The forecasting component requires only 0.0247 s for model training and 0.0008 s for prediction, demonstrating its suitability for real-time deployment. The results show that practical and computationally efficient methods, when integrated using real OCPP operational data, can effectively improve EV charging management under realistic operating conditions.

Item Type:	Article
Uncontrolled Keywords:	Electric vehicle charging, Open Charge Point Protocol, Tariff-aware scheduling, Grid-constrained energy management, Load forecasting, Ridge regression with seasonality, Proportional fairness, Real-world OCPP data
Subjects:	T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL1-484 Motor vehicles. Cycles
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	02 Oct 2026 00:30
Last Modified:	02 Oct 2026 00:30
URII:	http://shdl.mmu.edu.my/id/eprint/16806

Downloads

Edit (login required)