Intelligent Demand Aware Smart Charging Scheduling Framework for Large Scale Electric Vehicle Integration

The rapid adoption of electric vehicles (EVs) is placing unprecedented demands on power grids, necessitating intelligent and scalable charging management systems. This paper presents IDASC-Net, an Intelligent Demand-Aware Smart Charging Scheduling Framework designed to optimize EV charging in large-scale environments. The paradigm incorporates unsupervised data preprocessing, time behavior modelling, graph-enhanced spatio-temporal forecasting, federated learning, reinforcement-based time scheduling, and quantum-enhanced optimization. Large-scale simulations with grid and EV real data show that IDASC-Net can substantially enhance the key performance parameters. It realizes a 53.2 % decrease in the average wait time, as much as 49.7 % of the decrease in grid load deviation and 28.2 % growth in the use of renewable energy. The framework can be said to have the strength of aligning technical performance with user experience as it results in an improvement of user satisfaction scores by 24 27 points. Furthermore, edge-deployed version is real-time responsive and its scheduling runtime is approximately 2.5 seconds, which is a practical feasibility. The findings affirm that IDASC-Net can be used to integrate EV in a reliable, energy saving, and user-friendly mode. The area of future work will be the introduction of integration with vehicle-to-grid (V2G) models and city-scale mobility prediction to develop greater adaptability and resilience. This paper defines a new and successful framework of next-generation energy orchestration of EVs on the smart grids and urban infrastructures.