AI-Driven Framework for Renewable Green Energy Management of Electric Vehicle Charging Networks

The rapid global adoption of electric vehicles (EVs) presents both an opportunity and a challenge for modern power systems. While EVs promise to reduce greenhouse gas emissions and dependency on fossil fuels, their large-scale integration introduces significant stress on electricity grids, especially during peak demand periods. At the same time, the push towards decarbonised energy systems has accelerated the deployment of renewable energy sources such as solar and wind. However, the intermittency and unpredictability of these green energy sources create complexity in matching supply with dynamic EV charging demands. This dual transformation — of transport and energy — necessitates intelligent, adaptive systems that can effectively manage and optimise the coordination between EV charging infrastructure and renewable energy supply.;;Despite advancements in EV technology and grid integration, current energy management approaches often overlook the synergy between predictive modelling and optimisation grounded in real-time renewable generation data. A critical research gap exists in developing scalable, AI-enabled frameworks that jointly forecast renewable energy availability and EV charging demand and translate these forecasts into actionable infrastructure planning and operational strategies.;;This research aims to develop an AI-driven framework that enables predictive and optimised green energy management of EV charging networks. By leveraging open-source datasets — including traffic flow data, weather patterns, solar/wind generation profiles, and existing charging infrastructure — the framework will integrate advanced machine learning and generative AI techniques to forecast both renewable energy supply and spatial-temporal EV charging demand. It will also employ optimisation algorithms to determine the ideal placement and sizing of EV charging stations based on these forecasts, with the goal of improving energy efficiency, grid stability, and cost-effectiveness.;;The specific objectives include: (1) developing accurate AI-based models for forecasting EV charging demand; (2) creating renewable energy prediction models tailored to short-term energy scheduling; (3) designing optimization algorithms to align EV infrastructure with forecasted demand and renewable supply; and (4) evaluating the impact of integrated planning on grid performance, cost, and carbon emissions through simulation studies.;;Expected outcomes include a prototype AI-enabled framework for green energy management in EV networks, validated optimisation models, simulation-based evidence of operational benefits, and scholarly outputs in smart energy systems and AI-based infrastructure planning. Moreover, the project lays the foundation for future enhancements such as dynamic pricing models, peer-to-peer energy trading, and adaptive energy policies, supporting a sustainable energy transition.