Primary supervisor

Hao Wang

The rapid growth of electric vehicles (EVs) is transforming both transportation and energy systems. Private EVs, commercial fleets, autonomous vehicles and shared-mobility services can contribute to cleaner urban transport, but their charging demand also creates new challenges for electricity networks, transport systems and charging-service providers.

Effective EV charging requires coordinated decisions across multiple timescales. Long-term planning decisions determine where charging stations should be located, how much capacity should be installed, and when infrastructure should be expanded. Operational decisions determine when and where individual EVs should charge, how vehicles should be routed or scheduled, and how charging stations, renewable generation, batteries and electricity networks should be coordinated in real time.

This project investigates how artificial intelligence and optimisation can support the integrated planning and operation of EV charging systems. Students may work with mobility, charging, traffic, electricity-network, weather, renewable-energy, geographic or socioeconomic data. Depending on their interests, they may apply predictive AI, deep learning, reinforcement learning, generative AI, large language models, agentic AI or mathematical optimisation to a selected problem.

Potential topics include:

  • forecasting spatial and temporal EV charging demand from mobility and charging data;
  • planning the locations, capacities and expansion pathways of public, residential or fleet charging infrastructure;
  • jointly planning charging infrastructure across coupled transportation and electricity networks;
  • optimising EV charging, routing and fleet schedules under uncertain demand, travel and electricity conditions;
  • coordinating bidirectional charging, vehicle-to-grid, vehicle-to-building or vehicle-to-vehicle energy exchange;
  • operating charging stations with solar generation, battery storage and dynamic electricity prices;
  • developing safe, robust and explainable reinforcement-learning methods for real-time charging control;
  • creating multi-agent systems in which EVs, charging stations, fleets and network operators coordinate or negotiate;
  • developing agentic AI systems that use data, models and optimisation tools to plan, reason and adapt across changing operating conditions;
  • using large language models to interpret planning requirements, policies, user preferences or operational information;
  • building digital twins or simulation environments for evaluating charging plans and control strategies; and
  • examining charging accessibility, fairness, resilience and the needs of different communities and users.

Each student will focus on a clearly defined research question within this broader area. The project can be primarily data-driven, AI-focused or optimisation-focused, depending on the student’s skills and interests.

    #sustainability

    Aim/outline

    This project aims to develop AI and optimisation methods for planning and operating reliable, efficient, resilient and user-centred EV charging systems.

    The project will typically involve:

    • Problem selection and formulation: Select a planning or operational challenge involving EV charging infrastructure, charging stations, fleets, mobility or electricity networks.
    • Data analysis and modelling: Analyse relevant mobility, charging, geographic, traffic, energy or user data and model the interactions between EVs, charging facilities and the wider system.
    • Method development: Develop a suitable method using machine learning, deep learning, reinforcement learning, generative or agentic AI, mathematical optimisation, or a combination of these tools.
    • Evaluation: Compare the proposed approach with appropriate benchmarks using realistic datasets, simulations or case studies.
    • System-level analysis: Assess performance in terms of cost, charging accessibility, travel convenience, grid impacts, renewable-energy use, robustness, fairness or emissions.
    • Practical recommendations: Translate the results into insights for charging-network planners, fleet operators, energy companies, policymakers or EV users.

    URLs/references

    Recent papers from the team (updated in Sep 2026).

    1) J. Li^, Yu Hui Yuan*, Q. Cui, Hao Wang, Cross-Entropy-Based Approach to Multi-Objective Electric Vehicle Charging Infrastructure Planning, 2023 IEEE IAS Industrial and Commercial Power System Asia Conference (IEEE I&CPS Asia), 2023.

    2) Aditya Khele*, C. Jiang^, Hao Wang, Fairness-Aware Optimization of Vehicle-to-Vehicle Interaction for Smart EV Charging Coordination, The 59th annual IEEE Industrial and Commercial Power System Technical Conference (IEEE I&CPS), 2023.

    3) C. Jiang^, A. Liebman, Hao Wang, Network-Aware Electric Vehicle Coordination for Vehicle-to-Anything Value Stacking Considering Uncertainties, The 59th annual IEEE Industrial and Commercial Power System Technical Conference (IEEE I&CPS), 2023.

    4) J. Fan^, Hao Wang, A. Liebman, MARL for Decentralized Electric Vehicle Charging Coordination with V2V Energy Exchange, The 49th Annual Conference of the IEEE Industrial Electronics Society (IEEE IECON), 2023.

    5) J. Fan^, A. Liebman, Hao Wang, Safety-Aware Reinforcement Learning for Electric Vehicle Charging Station Management in Distribution Network, 2024 IEEE Power & Energy Society General Meeting (IEEE PESGM), 2024.

    6) Y. Wang#, Hao Wang, R. Razzaghi, M. Jalili, A. Liebman, Multi-Objective Coordinated EV Charging Strategy in Distribution Networks Using An Improved Augmented Epsilon-Constrained Method, Applied Energy, 2024.

    7) J. Li^, A. Chew*, Hao Wang, Investigating State-of-the-Art Planning Strategies for Electric Vehicle Charging Infrastructures in Coupled Transport and Power Networks: A Comprehensive Review, Progress in Energy, 2024.

    8) J. Fan^, C. Huang^, Hao Wang, Agent-Based Decentralized Energy Management of EV Charging Station with Solar Photovoltaics via Multi-Agent Reinforcement Learning, The 10th IEEE International Smart Cities Conference (IEEE ISC2), 2024.

    9) C. Jiang^, A. Liebman, B, Jie, Hao Wang, Dynamic rolling horizon optimization for network-constrained V2X value stacking of electric vehicles under uncertainties, Renewable Energy, 2025.

    10) X.L. Lee^, A,N. Toosi, P. Pudney, I. McLeod, A. Cheema, Hao Wang, Impact Analysis of Optimal EV Bi-directional Charging with Spatial-temporal Constraints, 2025 IEEE Power & Energy Society General Meeting (PESGM), 2025.

    11) J.K. Yap^, V.M. Baskaran, W.S. Tan, Hao Wang, D. Dowe, Joint Optimisation of Electric Vehicle Routing and Scheduling: A Deep Learning-Driven Approach for Dynamic Fleet Sizes, International Joint Conference on Neural Networks (IJCNN), 2025.

    12) X Zheng*, C Jiang^, Hao Wang, Large Language Model-Assisted Planning of Electric Vehicle Charging Infrastructure with Real-World Case Study, Sustainable Energy Technologies and Assessments, 2025.

    13) J Li^, Hao Wang, A Multi-View Multi-Timescale Hypergraph-Empowered Spatiotemporal Framework for EV Charging Forecasting, IEEE Transactions on Smart Grid, 17 (2), 1430-1443, 2026.

    14) J Li^, Hao Wang, A Unified Variational Imputation Framework for Electric Vehicle Charging Data Using Retrieval-Augmented Language Model, IEEE Transactions on Smart Grid, 17 (4), 3531-3545, 2026.

    15) E Kheirkhah-Rad^, PL Bodic, Hao Wang, M Wallace, Degradation-Aware Charger Deployment, Battery Sizing, and Charge Scheduling for Electric Bus Fleets, IEEE Transactions on Transportation Electrification 12 (2), 2149-2161, 2026.

    16) S Zhao#, AN Toosi, MA Cheema, M Goudarzi, Hao Wang, Efficient bidirectional charge scheduling for electric vehicles: Optimizing cost and carbon emissions, Sustainable Energy, Grids and Networks 46, 1-14, 2026.

    17) JK Yap^, VM Baskaran, WS Tan, ZY Ding, Hao Wang, D Dowe, Fleet-Size-Agnostic Transformer Model for Electric Vehicle Routing and Scheduling, IEEE Transactions on Industry Applications, 2026.

    18) C Huang^, Y Yang, Hao Wang, Physics-Informed Graph-Based Safe RL with Constraint-Specific Critics for Community Battery Coordination in Distribution Network, IEEE Transactions on Smart Grid, 2026.

    (*Thesis students; ^HDR students; #Research Fellow)

    Required knowledge

    Required: Python programming and an interest in artificial intelligence, optimisation, transportation or energy systems.

    Preferred: Experience in one or more of machine learning, deep learning, reinforcement learning, data analytics, mathematical optimisation or operations research. Prior knowledge of EVs, transportation or power systems is helpful but not essential.