5G-Powered Intelligent Data-Driven Electric Vehicle Charging Management for Maximised Economic Benefits and Sustainability​

This project leverages 5G technology to transform EV charging infrastructure into intelligent, data-driven systems. Through real-time data acquisition, edge-cloud computing, and AI-based forecasting, the system aims to optimise charging operations for cost, efficiency, and sustainability. 

The forecasting and EV charging scheduling modules have been developed and tested using high-resolution datasets. This research supports Singapore’s transition towards a smarter and greener mobility ecosystem.

Project Deliverables/Outcomes/Impact:

• Developed AI models for forecasting electricity price, EV charging demand, and PV power generation.
• Developed optimisation algorithm for intelligent EV charging scheduling
• Published 1 top journal paper and a few conference papers
• Strong commercialisation potential with industry for real-world deployment
• Contributions to sustainable urban mobility and energy efficiency

Publications

Hanwen Zhang, Dusit Niyato, Wei Zhang (corresponding author), et al. “The Roles of Generative Artificial Intelligence in Internet of Electric Vehicles." IEEE Internet of Things Journal (IoT-J), vol. 12, no. 6, pp. 6208-6232. March 2025.

B. Sivaneasan, Kuan Tak Tan, Wei Zhang (corresponding author). “Cognitive Digital Twin for Microgrid: A Real-World Study for Intelligent Energy Management and Optimization.” IEEE Internet Computing, vol. 29, no. 1, pp. 39-47. January 2025.

Wei Zhang (corresponding author) and Sakshi Bansal. “Towards Industrial Artificial Intelligence: A Discussion of Management, Technology and Human." IEEE Systems, Man, and Cybernetics Magazine, vol. 12, no. 1, pp. 4-16. January 2026.

 Sara Sameer, Wei Zhang (corresponding author), Xin Lou, et al. "GiNet: Integrating Sequential and Context-Aware Learning for Battery Capacity Prediction." IEEE Vehicular Technology Conference (VTC), pp. 1-6. IEEE. Oslo, Norway. June 17-20, 2025.

Lei Wang, Wei Zhang (corresponding author), Wei Li, et al. “DGAT: Dynamic Graph Attention-Transformer Network for Battery State of Health Multi-Step Prediction." Energy, vol. 330, pp. 136876. September 2025.