Electric vehicles keep gaining ground fast these days. That quick adoption creates real headaches for charging infrastructure management. Things like pricing efficiency and grid stability stand out as major issues. This study puts forward a single framework to handle them. It blends AI-based dynamic pricing right in with energy estimates tied to different scenarios. The setup tweaks charging rates on the fly. It pulls in live data on electricity needs, renewable sources available, and shifts in grid status. They produce an hourly forecast for prices through a Random Forest Regressor. That lets the model pick up on patterns that play out day by day or week by week. In the end, drivers get to shift their charging plans around. They weigh economic perks against environmental effects. The framework goes beyond just pricing though. It adds a solid piece for calculating energy needs. This part figures out the exact kWh required based on trip length, how efficient the vehicle runs, and a bit of extra buffer for safety. Overcharging gets avoided that way. Station backups and lines ease up too. Developers built the application in Python with Flask. That delivers an interactive view in real time. Backup rules cover cases where vehicle details come up missing or unclear. To check how well it works, they stacked the AI pricing results against standard flat rates from typical stations. Outcomes point to more flexible options overall. Cost forecasts turn out sharper. Users adapt easier to changes. On top of that, the whole idea opens doors for distributing grid loads in smarter ways. Energy use in EV charging setups leans more toward sustainability.