This paper use ML approaches to optimize electric vehicle (EV) charging schedules, decrease wait times, and increase energy efficiency, all while balancing driver satisfaction and charging efficiency. In order to provide intelligent charging recommendations, the proposed architecture analyzes real-time data, such as battery status, charging station availability, traffic, electricity consumption, and user preferences. Advanced machine learning techniques, such as predictive analytics, reinforcement learning, and optimization models, are designed to reduce costs, extend battery life, and optimize the distribution of charging infrastructure load. The system also considers driver comfort criteria, such as preferable charging times, route distance, and charging speed, to improve overall customer satisfaction. This paper’s integration of smart energy management and personalized charging strategies can enable modern smart cities to experience enhanced power consumption, more environmentally favorable mobility, and the development of a smart electric vehicle (EV) ecosystem.