Citation

Hossen, Md Sabbir (2025) Integration of AI-driven systems with open charge point protocol for enhanced electric vehicle charging management. Masters thesis, Multimedia University.

Full text not available from this repository.

Abstract

The rapid adoption of electric vehicles (EVs) introduces significant challenges for power distribution networks, particularly in managing peak demand and ensuring efficient resource allocation. While the Open Charge Point Protocol (OCPP) enables interoperability in EV charging systems, it lacks predictive intelligence for demand forecasting and optimized scheduling. This thesis proposes an AI–OCPP framework that integrates short-term demand forecasting with intelligent scheduling to improve charging efficiency, reduce operational cost, and enhance user fairness. The forecasting component evaluates Prophet, XGBoost, LSTM, and GRU models using real-world OCPP datasets collected from a Malaysian charging station. The scheduling component investigates Genetic Algorithm (GA), Reinforcement Learning (Q-Learning), and a hybrid GA+Q approach under realistic grid and tariff constraints. Experimental results demonstrate that the proposed framework effectively reduces peak load, improves cost efficiency, and ensures fair allocation of charging resources. The hybrid GA+Q strategy achieves the best overall performance by combining global optimization with adaptive learning. The integration of forecasting and scheduling further enhances system responsiveness and enables proactive decisionmaking. Overall, this work provides a practical and scalable AI-driven solution for OCPP-based EV charging systems, contributing to the development of intelligent and sustainable charging infrastructures.

Item Type:	Thesis (Masters)
Additional Information:	Call No.: TL220.5 .M37 2025
Uncontrolled Keywords:	Battery charging stations (Electric vehicles)
Subjects:	T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL1-484 Motor vehicles. Cycles
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	22 May 2026 05:10
Last Modified:	22 May 2026 05:10
URII:	http://shdl.mmu.edu.my/id/eprint/15900

Downloads

Edit (login required)